Chapter Introduction CHAPTER Introduction 1.1 Research background One of the most important trends in modern manufacturing systems has been the relentless efforts towards minimizing the cost, maximizing productivity and improving product quality. Tool condition sensing greatly contributes towards the optimization of the cutting process, efficient tool change policies, improvement on product quality, and reducing tool cost (Kumar et al., 1997). Thus tool condition monitoring (TCM) is critical in manufacturing systems. The major objective of a sensor-based TCM system is to determine the cutting tool conditions (such as tool wear, breakage etc.) from the sensor data. Much research (Elbestawi et al., 1991; Dornfeld, 1990; Tansel and McLauglin, 1993; Wong et al., 1997) has been undertaken in these fields, since cutting tools are both an important factor in manufacturing costs and the quality of the workpiece (Pfeifer and Wiegers, 2000). Despite intensive research during the past two decades, successful and effective TCM in automated machining systems remains an engineering challenge (Li and Mathew, 1990). The developed systems often have narrow ranges of performance, require substantial training or setup time to function correctly (Byrne and Dornfeld, 1995). Therefore further research is needed. In the following section, the basic architecture of sensor-based TCM systems is Chapter Introduction presented, which includes sensing method, feature extraction and selection, and decision-making techniques. 1.2 Architecture of TCM system TCM System is basically an information flow and processing system (as shown in Figure 1.1), in which the information source selection and acquisition (sensing data collection), information processing and refinement (feature extraction and selection) and decision making based on the refined information (condition identification) are fully integrated. Signal Selection and Acquisition Information Processing and Refinement Decision Making Tool Condition Figure 1.1 Information flow and processing scheme in TCM 1.2.1 Signal acquisition by sensing methods Sensing is the first part of the information-driven TCM system, which provides the primary information inputs. The basic requirements in the selection of sensing signals are: 1. The signals should directly or indirectly provide information that is closely related to the changes in the tool conditions. 2. The signals should have high signal to noise ratio (SNR), and not interfere with the machining process. 3. The acquired sensing information should indicate or detect all significant events in the cutting process. 1.2.2 Signal processing Signal processing is the core function of the information-driven TCM system, Chapter Introduction which includes feature extraction and feature selection. It basically performs a transformation process in which a large flow of sensor signals is streamlined to a compact tool-condition-informative feature vector in time and frequency domain. The key challenge in this technique is to derive features, which contain not only as much tool condition information as possible, but also compact in nature. Feature extraction Since sensed signals are typically noisy, these signals have to be further processed i.e. feature extraction, to yield useful features that are highly sensitive to tool conditions. The widely used feature extraction approaches include: 1. Time domain analysis such as derivative of signal (Li and Mathew, 1990), statistical value of waveform (Kannatey-Asibu and Dornfeld, 1982). 2. Advanced signal processing techniques such as neural network (Tansel and McLauglin, 1993), wavelet analysis (Tansel and McLauglin, 1993, Wu and Du, 1995). 3. Power spectrum analysis such as FFT, cross spectrum (Emel and KannateyAsibul, 1988). 4. Time series analysis, such as autoregressive (AR) and autoregressive moving average (ARMA) (Liang and Dornfeld, 1989). Feature selection Feature selection is to select an optimum subset of features from potentially useful features which are available in a given problem domain (Gose et al., 1996). It is a challenging task to select the characteristic features that not only represent the characteristics of the process (information), but also contains less noise. This method outputs a subset of all available features, therefore, the dimensionality of the final input feature set may be reduced. Its intention is not only to discover all the features Chapter Introduction relevant to the concept and determine how relevant they are, but also to find a minimum feature subset for effective classification with good generalization performance. In addition, feature selection may also speed up the classifier for time critical applications, and make feature discovery possible. The optimum feature subset has been defined as the subset that performs the best under a classification system (Jain and Zongker, 1997). "Performs the best" here may be explained in two slightly different ways: 1. The subset of features which gives the lowest classification error (an unconstrained combinatorial optimization problem); or 2. The smallest subset of features for which the classification error proportion is below a set threshold (constrained combinatorial optimization) (Siedlecki and Sklansky, 1988). The latter is widely employed in many practical applications including this research. 1.2.3 Decision making The decision-making strategy is to map the signal features to a proper class (machining tool conditions) i.e. pattern recognition (Li and Mathew, 1990). The output of the decision-making process includes one or more of the following: 1. Identification of tool conditions (such as tool wear/breakage etc.). 2. Evaluation of the severity of certain abnormal tool conditions. 3. Prediction of tool conditions and control of machining process. This research focuses on the first item, i.e. binary tool conditions identification (fresh or worn) and multiclassification of tool conditions (sharp, workable and worn). The robustness of decision-making depends not only on the identification techniques, Chapter Introduction but also on the features’ quality. The better the inter-class separation capability of the features, the more robust the identification results will be. 1.3 Literature review Tool wear in the metal cutting process results in a loss in dimensional accuracy of the finished product and some possible damage to the work-piece. With the increasing use of machining centers and flexible manufacturing systems, on-line tool wear monitoring has become a challenging research field. The following session provides a comprehensive review about every component of the above mentioned scheme. 1.3.1 Overview of sensing method To achieve greater reliability and robustness in turning operation, both single and multiple sensing, coupled with various signal processing and pattern recognition techniques, have been investigated for single or multiple tool condition identification. As aforementioned, the potentially most economical scheme for TCM is to employ a single-sensor approach for multiple tool conditions identification from the viewpoint of information utilization. The sensing methods in TCM can be categorized into direct or indirect methods according to the signal obtained (Micheletti et al., 1976). The direct sensing method estimates tool conditions through the measurement of tool geometry directly, such as shape or position of cutting edge, optical scanning of the tool tip, electrical measurement of the contact resistance between the tool and workpiece, and radioactive analysis of the chip, analyzing the vision of the tool, measuring the volume of wear particles or the distance between workpiece and tool or tool holder. The limitation of these methods lies in that it is difficult to collect the relevant Chapter Introduction information under actual cutting process. The indirect methods are those concerned with detecting some process-borne signals about tool wear and establishing the relationship between these signals and tool wear (Elbestawi et al., 1991). Indirect methods include measurement of cutting force (Elbestawi et al., 1991; Hong et al., 1996; Santanu et al., 1996; Bao and Tansel, 2000), acoustic emission (Diei and Dornfield, 1987; Sampath and Vajpayee, 1987; Liu and Liang, 1991; Zizka, 1996; Wilcox et al., 1997; Niu et al., 1998; Xu, 2001), vibration of tool or tool post (Lee et al., 1987; Elwardany et al., 1996; Moore and Kiss, 1996; Li and Dong, 2000), ultrasonic vibration (Ultrasonic Energy) (Hayashi et al., 1988; Coker and Shin, 1996; Abuzahra and Yu, 2000), acoustic wave (sound) (Takata et al., 1986), current of spindle or feed motor (power input) (Matsushima et al., 1982; Rangwala and Dornfeld, 1987; Altintas, 1992; Lee et al., 1995) and optical signal (Cuppini et al., 1986; Oguamanam et al., 1994; Wong et al., 1997). These indirect methods have the advantages of less complexity and suitability for practical application (Byrne and Dornfeld, 1995), thus they have been used by many researchers. Of all the signals, acoustic emission (AE), and cutting force are most commonly used. An introduction about them is provided as follows. AE sensing AE signals reflect the microscopic activities (friction, fracture etc.) of the cutting process. It naturally contains multiple tool condition information such as tool wear, fracture etc. Through proper processing, it can be more economically (compared with multi-sensing approach) used for multiple tool condition identification. The merit of using AE to detect tool wear lies in its frequency range is much higher than that of the machine vibrations and environment noises (Sata et al., 1973). Hence, relatively precise signal can easily be obtained by applying high-pass filter. Moreover, AE can Chapter Introduction be obtained by using a piezoelectric transducer mounted on the tool holder which does not interfere with the cutting operation, thereby makes continuous monitoring tool condition possible. However, other researchers held a different idea. They believed that AE signals cannot be independently used to provide reliable tool wear detection in TCM. Blum and Inasaki (1990) performed experiments to determine the relationship between flank wear and AE signals. They were particularly interested in the use of the AE mode, a parameter describing the ‘whole’ characteristics of the cutting process, and then concluded that extracting tool wear information from the AE signal was difficult. The reason causing the two opposing views did not lay on the sensing technology, but on the ensuing analysis (Lister, 1993). Based on this opinion, this thesis first discusses the application of AE signals in TCM system when steel is used as workpiece. Cutting force sensing Measuring cutting forces is one of the most common techniques to monitor tool condition, since they are more sensitive to tool wear than vibration or power measurements (Lee et al., 1989). The reliability of force measurements is another factor for their popularity in tool wear monitoring applications. As a cutting tool shears the workpiece, high stresses and strain rates give rise to forces with dynamic behavior across a broad spectrum of frequencies. The relationship between tool wear (e.g. flank wear and crater wear) and increasing cutting force is well known for a long time (Dornfeld, 1990; Oraby and Hayhurst, 1991; Lee et al, 1992; Ravindra et al., 1993b; Tarng et al., 1994). Although many investigators agreed that the change of cutting forces represents an accurate and reliable approach to estimate tool condition, they still argued which component is the most sensitive; dynamic component, static component, or both of Chapter Introduction them. Cutting condition is also an argued issue. Cuppini et al. (1990) implemented a continuous monitoring method and established relationships between wear and cutting power without cutting conditions. While, Choudhury and Kishore (2000) believed that cutting speed, feed and depth of cut should be taken into account in tool condition recognition. This work has tried to clear up the above arguments according to cutting force from titanium machining. 1.3.2 Overview of signal processing AE signal processing Due to AE signals’ high frequency nature and sensitivity to the micro-structural behavior of material, it is widely employed to extract the useful information in TCM. Iwata and Moriwaki (1977) pioneered the method of using AE signals to monitor tool wear condition in a cutting process, and they found that the power of spectrum of AE signals up to 350kHz increased with tool wear and then it reached saturation. Since the AE signal associated with the tool flank wear is stationary in nature, fast fourier transform (FFT) is still the best tool for the analysis of this type of signals. The spectral density of AE signals has been found to be the most informative feature for TCM in turning (Emel and Kannatey-Asibu, 1988). Naerheim and Arora (1984) used continuous and discontinuous AE in turning operations to test gradual wear and intermittent degradation of cutting tools, respectively. Roget et al (1988) concluded that AE parameters such as root mean square (RMS), mean, and peak values and their corresponding variance, kurtosis and skew could provide sufficient warning information of tool breakage and tool wear in various cutting condition. Jemielniak and Otman (1988) considered that the skew and kurtosis to be better indicators of tool Chapter Introduction failure than RMS values. Another approach for improving the reliability of the wear related AE signal was proposed by Blum and Suzuki (1988). A feature called “AE mode” has been observed to be quite sensitive to tool wear condition. Time series analysis focuses on the stochastic nature in the dynamics process of AE generation. Liang and Dornfeld (1989) employed time series modeling techniques to extract AE features such as autoregressive (AR) parameters and AR residual signals for testing and monitoring tool wear. Moriwaki and Tobito (1990) proposed statistical features (mean, variance and the coefficient of RMS) as inputs of a pattern recognition system to identify and predict the ensuing tool life for coated tool life estimation. Zheng et al. (1992) used an optic fiber sensor and a commercially available PZT AE sensor to conduct drilling and milling operations. Results from the two experiments showed a reasonable degree of agreement. Using AE features, König et al. (1992) performed tests to monitor small drillings and detect tool fracture, and reported that AE features were sensitive to tool chipping. Dornfeld (1992) presented compelling reviews on the application of AE sensing techniques in tool wear detection in machining. He observed that the changes in skew and kurtosis of AE RMS signals could effectively indicate tool wear. Kakade et al. (1994) reported that AE parameters (ring-down count, rise time, event duration, event rate and frequency) could distinguish clearly the cutting action of a sharp and worn or broken tool. Kannatey-Asibu and Dornfeld (1982) found that the changes in skew, kurtosis and of the AE RMS signal effectively indicate the tool wear in machining. Kamarthi et al. (1995) considered that AE features extracted by the wavelet transform were very sensitive to gradually increasing flank wear. The magnitude of the AE in the frequency domain was employed by Li and Yuan (1998) to monitor the change of tool states. Choi et al. (1999) fused AE and cutting forces to develop a real-time TCM for turning operations. Chapter Introduction The recorded data were analyzed through a fast block-averaging algorithm for features and patterns indicative of tool fracture. Similar work was conducted by Jemielniak and Otman (1998), who used a statistical signal-processing algorithm to identify RMS, skew and kurtosis of the AE signals and detect catastrophic tool failure. Inspection of the results indicated that the skew and kurtosis were better indicators of catastrophic tool failure than the RMS values. Cutting force processing Shi and Ramalingam (1990) investigated the feasibility of different force components, and observed that the feed force to cutting force ratio was sensitive to flank wear but insensitive to process changes (cutting speed and depth of cut). Dornfeld (1990) and Ko and Cho (1994) focused on the dynamic characteristic of the cutting force, due to the friction variation between tool and workpiece in tool wear process. Oraby and Hayhurst (1991) developed a model to build the relationship between the feed force, radial force and flank wear in a turning operation. Elbestawi et al. (1991) employed FFT to compute the sensitivity of cutting harmonics (cutting force signals) to flank wear. Lee et al. (1992) found that the components of feed and tangential dynamic force bore a good relationship to flank wear trend. Lister (1993) analyzed the power spectra of dynamic cutting forces and found that the power level of certain frequency band increases with tool wear. In the orthogonal milling, Caprino et al. (1996) concluded that both the horizontal and vertical forces undergo large variations with tool wear. Lee et al. (1989) analyzed the dynamic force signals of a coated grooved tool by FFT, and found that the percentage increase of dynamic tangential force could give a promising threshold for the prediction of tool failure. Choudhury and Kishore (2000) observed that the ratio between the feed force and cutting force provided a practical method to quantify tool wear in turning. Dimla and 10 Chapter Conclusions and Recommendations scheme can be illustrated as shown Figure 8.1. Firstly an SOM or some clustering tool can be used to partition the feature input space into several disjoint regions. Then for each particular region, different SVMs (or other neural networks) compete until the most adequate one is used to tackle partitioned regions. Since the partitioned regions have more uniform distributions than that of the entire input space, it is easier for an SVM to capture a more stationary input-output relationship. Moreover, less number of training data points in each region makes the system more efficient for both training and classifying. SVMs Feature Input Signal Extraction Self-Organizing Feature Map Region SVMs Output SVMs n SVMs Region SVMs Output SVMs n SVMs Region SVMs Output SVMs n Figure 8.1 Proposed hybrid system with SVM and SOM 132 References Author’s Publications List Journal Papers 1. Sun, J., Hong, G. S., Rahman, M., Wong, Y.S. Identification of Feature Set for Effective Tool Condition Monitoring by Acoustic Emission Sensing, International Journal of Production Research, Vol.42, No.5, pp.901–918, 2004. 2. Sun, J., Rahman, M., Wong, Y.S., Hong, G.S. Multi-classification of Tool Wear with Support Vector Machine by Manufacturing Loss Consideration, International Journal of Machine Tools and Manufacture, Vol. 44, No.11, pp.1179–1187, 2004. 3. Sun, J., Hong, G. S., Rahman, M., Wong, Y. S. Improved Performance Evaluation of Tool Condition Identification by Manufacturing Loss Consideration, International Journal of Production Research, Vol. 43, No. pp. 1185 – 1204, 2005 4. Sun, J., Hong, G. S., Wong, Y. S., Rahman, M. and Z.G. Wang Effective Training data selection in Tool Condition Monitoring System, appear in International Journal of Machine Tools and Manufacture 5. Sun, J., Wong, Y. S., Rahman, M., Hong, G. S. and Z.G. Wang Tool Condition Identification Framework in Titanium Machining, submit to Journal of Engineering Manufacture, Proceedings of the Institution of Mechanical Engineers, Part B 6. Z.G. Wang, M. Rahman, Y.S. Wong and J. Sun Optimization of multi-pass milling using parallel genetic algorithm and parallel genetic simulated annealing, submit to International Journal of Machine Tools and Manufacture 7. Z.G. Wang, Y.S. Wong, M. Rahman and J. Sun Multi-objective optimization of high-speed milling of titanium alloys, submit to International Journal of Advanced Manufacturing Technology. Conference Papers 1.Wang Z.G., Rahman M., Wong Y.S., Sun J., Modeling of cutting forces during machining of titanium alloys with different coolant strategies, 8th CIRP International Workshop on Modeling in Machining Operations, Chemnitz, Germany, May 2005. 2. Wong, Y.S., Rahman, M., Hong, G.S., Sun, J. Tool Condition Identification in Titanium Machining. In The 3nd International Symposium on Instrumentation Science and Technology Proceedings, Xi'an , China, 2004 3. Sun, J., Hong, G. S., Rahman, M., Wong, Y.S. Feature Extraction and Selection in Tool Condition Monitoring System, AI2002, Advances in Artificial Intelligence, 487-498, Australia, 2002 4. Sun, J., Rahman, M., Wong, Y. S., Hong, G.S. Feature Selection in Tool Condition Monitoring System, 6th International Conference on Mechatronics Technology, Japan, September 2002 5. Sun, J., Gao, X.Y. An Intelligent Algorithm for Engine Transient State Working Condition Test-Stand, 2002 IEEE International Conference on Fuzzy Systems, Honolulu, May 2002 6. Sun, J., Gao, X.Y., Sun, Y. Predictive Decoupling Fuzzy Control Algorithm for Internal combustion Engine Transient State Working Condition Test-Stand,4th Asian Conference on Robotics and its Applications, Singapore, June 2001 133 References References Abuzahra, N.H. and Yu, G. Analytical Model for Tool Wear Monitoring in Turning Operations Using Ultrasound Waves, International Journal of Machine Tools and Manufacture, Vol. 40, No.11, pp.1619-1635, 2000. Altintas, Y. Prediction of Cutting Force And Tool Breakage in Milling from Feed Drive Current Measurements, ASME Trans., Journal of Engineering for Industry, Vol. 114, No.4, pp.386-392, 1992 Amo, P., Ferreras, F.L., Cruz, F. and Rosa, M. Smoothing Functions for Automatic Relevance Feedback in Information Retrieval. In Proceedings of the 11th International Workshop on Database and Expert Systems Applications (DEXA'00), 2000 Anelia Angelova Data pruning. M.Sc. Thesis, California Institute of Technology. 2004. Arsie Ivan, Fabrizio Marotta, Cesare Pianese, Gianfranco Rizzo Information Based Selection of Neural Networks Training Data for S.I. Engine Mapping, Society of Automotive Engineers (SAE) Paper, 2001-01-0561, in SP-1585, ISBN 0-76800732-1, pp. 173-184, 2001. Balakrishnan, P., Trabelsi, H., Kannatey-Asibu, E. and Emel, E. A Sensor Fusion Approach to Cutting Tool Monitoring, in Proceedings of ASME Winter Annual Meeting, Sensors and Controls for Manufacturing, 33, PED, pp.101- 108, 1988. Bao, W.Y. and Tansel, I.N. Modeling Micro-End-Milling Operations, Part III: Influence of Tool Wear, International Journal of Machine Tools and Manufacture, Vol. 40, No. 5, pp.2193-2211, 2000. Barker, R.W., Klutke, G. and Hinich, M.J. Monitoring Rotating Tool Wear Using Higher Order Spectral Features, ASME Trans., Journal of Engineering for Industry, Vol. 115, No.1, pp.23-29, 1993. and Brailovsky, V.L. On Domain Knowledge and Feature Selection Using a Support Vector Machine, Pattern Recognition Letters, Vol. 20, No.5, pp.475484, 1999. Barzilay, O. Bellman, R.E. Adaptive Control Processes: A Guided Tour. Princeton University Press, New Jersey, 1961. Bi, L.L. Tool Condition Monitoring for Turning by Acoustic Emission. M.Eng. Thesis, National University of Singapore. 1997. Bishop, C.M. Neural Networks for Pattern Recognition. Oxford University Press, 1995. Blum, T., Suzuki, I., and Inasaki, I. Development of a Condition Monitoring System for Cutting Tool Using a Sensor, Bulletin Japan Society of Precision Engineering, Vol. 22, No. 4, pp.304-311, 1988. 134 References Blum, T. and Inasaki, I. A Study on Acoustic Emission from the Orthogonal Cutting Process, ASME Trans., Journal of Engineering for Industry, Vol.112, No.3, pp.203211, 1990. Boothroyd, G. and Knight, W.A. Fundamentals of Machining and Machine tools (2nd edition), Marcel Dekker Inc., New York, 1989. Bradley, P.S. and Mangasarian, O.L. Feature Selection via Concave Minimization and Support Vector Machines. In ICML-98: Proc. of the 15th International Conference on Machine Learning, Madison, WI, USA, pp.82-90, 1998. Brown, M.P.S., Grundy, W.N., Lin, D., Cristiani, N., Sugnet, C.W., Furey, T.S., Ares, M., and Haussler, D. Knowledge-based Analysis of Microarray Gene Expression Data by Using Support Vector Machines. In Proceedings of the National Academy of Sciences, Vol. 97, No.1, pp.262–267, 2000. Burges, C.J.C. A Tutorial on Support Vector Machines for Pattern Recognition, Data Mining Knowledge Discovery, Vol. 2, No. 2, pp.955-975, 1998 Byrne, G. and Dornfeld, D.A. Tool Condition Monitoring – The Status of Research and Industrial Application, Annals of CIRP, Vol. 44, pp.541-567,1995 Calado, J. M. F., Korbicz, J., Patan, K., Patton, R. J. and Sáda Costa, J. M.G. Soft Computing Approaches to Fault Diagnosis for Dynamic Systems, European Journal of Control, Vol. 7, pp.2-3, 2001 Caprino, G., Lorio, I. De, Nele, L. and Santo, L. Effect of Tool Wear on Cutting Forces in Orthogonal Cutting of Unidirectional Glass Fiber Reinforced Plastics, Composites Part A 27A, pp.409–415, 1996. Chenoweth, T. and Obradovic, Z. An Explicit Feature Selection Strategy for Predictive Models of the S&P 500 Index, Neurovest Journal, Vol. 3, No. 6, pp.14-21, 1995. Che-haron, C.H. Tool Life and Surface Integrity in Turning Titanium Alloy, Journal of Materials Processing Technology, 118, pp.231-237, 2001 Jiaa, C.L. and Dornfeld, D.A. A Self-organizing Approach to the Prediction and Detection of Tool Wear, ISA Transactions, Vol. 37, No. 4, pp.239-255, 1998 Choi, D., Kwon, W.T. and Chu, C.N. Real-time Monitoring of Tool Fracture in Turning using Sensor Fusion, International Journal of Advanced Manufacturing Technology, Vol.15, No.5, pp305–310, 1999 Choudhury, S.K. and Kishore, K.K. Tool Wear Measurement in Turning Using Force Ratio, International Journal of Machine Tools and Manufacture, Vol. 40, No. 6, pp.899–909, 2000 Chryssolouris, G. and Domroese, M. Sensor Integration for Tool Wear Estimation in Machining. In Proceedings of the Winter Annual Meeting of ASME, Symposium on Sensors and Controls for Manufacturing, pp.115-123, 1988. Chryssoloursis, G. Sensor Synthesis for Control of Manufacturing Process, ASME Trans., Journal of Engineering for Industry, Vol. 114, pp.158-174, 1992. 135 References Chu, W., Keerthi, S.S. and Ong, C.J., Bayesian Trigonometric Support Vector Classifier, Neural Computation, 15(9), pp.2227-2254, 2003. Coker, S.A. and Shin, Y.C. In Process Control of Surface Roughness due to Tool Wear Using Ultrasonic System, International Journal of Machine Tools and Manufacture, Vol. 36, No. 3, pp.411-422, 1996. Colgan, J., Chin, H., Danai, K. and Hayashi, S.R. On-Line Tool Breakage Detection in Turning: A Multi-Sensor Method, ASME Trans., Journal of Engineering for Industry, Vol. 116, pp.117-123, 1994 Cook, R. and Weisberg, S. Residuals and Influence in Regression, Chapman and Hall, New York, 1982. Cortes, C. and Vapnik, V.N. Support Vector Networks, Machine Learning, Vol. 20, No. 3, pp.273- 297, 1995. Cristianini, N. and Taylor, J.S. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods, New York, Cambridge University Press, 2000. Cuppini, D., D’Enrrico, G. and Rutelli, G. Tool Image Processing with Application to Unmanned Metal-cutting, A Computer Vision System for Wear Sensing and Failure Detection, SPIE 701, pp.416-422, 1986. Cuppini, D., D’Errico, G. and Rutelli, G. Tool Wear Monitoring Based on Cutting Power Measurement, Wear, 139, pp.303–311, 1990. Damodarasamy, S. and Raman, S. An Inexpensive System for Classifying Tool Wear States Using Pattern Recognition, Wear, 170, pp.149-160, 1993. Dan, L. and Mathew, J. Tool Wear and Failure Monitoring Techniques for Turning—A Review, International Journal of Machine Tools and Manufacture, Vol.30, No.4, pp.579–598, 1990 Danai, K. and Ulsoy, A.G. A Dynamic State Model for On-Line Tool Wear Estimation in Turning, ASME Trans., Journal of Engineering for Industry, 109, pp.396–399,1987. Darenfed, S. and Wu, S. Polynomial Learning Networks For Cutting Tool Diagnosis in Machining Operations, Transcation Canadian Society of Mechanical Engineers, Vol.16, No.2, pp.147–163, 1992. Das, S., Roy, R. and Chattopadhyay, A.B. Evaluation of Wear of Turning Carbide Inserts Using Neural Networks, International Journal of Machine Tools and Manufacture, Vol. 36, No. 7, pp.789-797,1996 Diei, E.N. and Dornfield, D.A. Acoustic Emission Sensing of Tool Wear in Face Milling, ASME Trans., Journal of Engineering for Industry, 109, pp.234-240, 1987. Dimla, D.E.Snr. and Lister P.M. On-line Metal Cutting Tool Condition Monitoring. I: Force and Vibration Analyses, International Journal of Machine Tools and Manufacture, Vol. 40, No.5, pp.739–768, 2000a 136 References Dimla, D.E.Snr. and Lister P.M. On-line Metal Cutting Tool Condition Monitoring Part II: Multi-Layer Perception Neural Networks Analysis, International Journal of Machine Tools and Manufacture, Vol. 40, No.5, pp.769-781, 2000b Dimla, D.E.Snr. Sensor Signals for Tool-Wear Monitoring in Metal Cutting Operations—a Review of Methods, International Journal of Machine Tools and Manufacture, Vol. 40, No.8, pp.1073–1098, 2000c Diniz, A.E., Liu, J.J. and Dornfeld, D.A. Correlating Tool Life, Tool Wear and Surface Roughness through Acoustic Emission in Finishing Turning, Wear, Vol. 152, No.2, pp.395-407, 1992 Dornfeld, D.A. Neural Network Sensor Fusion for Tool Condition Monitoring, Annals of CIRP, Vol. 39, No.1, pp.101–105, 1990. Dornfeld, D.A. Application of Acoustic Emission Techniques in Manufacturing, NDT and International, Vol. 25, No. pp.259–269, 1992. Dornfeld, D.A. In Process Recognition of Cutting States, Japan Society of Mechanical Engineers International Journal, Series C: Dynamics Control, Vol. 37, No.4, pp.638–650, 1994. Du, R., Elbestawi, M.A., and Wu, S.M. Automated Monitoring of Manufacturing Processes: Part 1, Monitoring Decision-Making Methods, ASME Trans., Journal of Engineering for Industry, Vol. 117, No. 2, pp.121-132, 1995a. Du, R., Elbestawi, M.A. and Wu, S.M. Automated Monitoring of Manufacturing Processes: Part 2, Applications, ASME Trans., Journal of Engineering for Industry, Vol. 117, No. 2, pp.133-141, 1995b. Duan, K., Keerthi, S.S. and Poo, A.N. Evaluation of Simple Performance Measures for Tuning SVM Hyperparameters, Neurocomputing, Vol. 51, pp.41-59, 2003. Duan, K., Keerthi, S.S., Shevade, S.K., Chu, W. and Poo, A.N. Multi-category Classification by Soft-Max Combination of Binary Classifiers. In Proceedings of Fourth International Workshop on Multiple Classifier Systems, Surrey, UK, 2003. Elanayar, S. and Shin, Y.C. Robust Tool Wear Estimation with Radial Basis Function Neural Networks, ASME Trans., Journal of Dynamic Systems, Measurement, and Control, Vol. 117, pp.459-467, 1995. Elbestawi, M.A., Papazafiriou, T.A. and Du, R.X. In-process Monitoring of Tool Wear in Milling Using Cutting Force Signature, International Journal of Machine Tools and Manufacture, Vol. 31, No. 1, pp.55-73, 1991. Elwardany, T.I., Gao, D. and Elbestawi, M.A. Tool Condition Monitoring in Drilling Using Vibration Signal Analysis, International Journal of Machine Tools and Manufacture, Vol. 36, No. 6, pp.687-711, 1996. Emel, E. and Kannatey-Asibu, E. Tool Failure Monitoring in Turning by Pattern Recognition Analysis of AE Signals, ASME Trans., Journal of Engineering for Industry, Vol.110, pp.137-145, 1988. 137 References Ertunc, H.M., Loparo, KA, and Ocak, H. Tool Wear Condition Monitoring in Drilling Operations Using Hidden Marko Modes (HMMs), International Journal of Machine Tools and Manufacture, Vol. 41, No. 9, pp.1363-1384, 2001. Ezugwu, E.O., Bonney, J. and Yamane, Y. An Overview of the Machinability of Aeroengine Alloys, Journal of Materials Processing Technology, 134, pp.233-253, 2003. Fassois, S.D., Eman, K.f. and Wu, S.M. A Fast Algorithm for On-line Machining Process Modeling and Adaptive Control, ASME Trans., Journal of Engineering for Industry, Vol.111, pp133-139, 1989. Fisher, R. A. The Design of Experiments (9th ed.). Hafner Publishing Company, New York, 1971 Gabriel, V. and Mastusky, J. Study of Machining Process by Acoustic Emission Method. Proceedings of the IV International Conference on Monitoring and Automatic Supervision in Manufacturing, Annals of CIRP, pp.143-148, 1995. Geoffrey Boothroyd and Winston Knight Fundamentals of Metal Machining and Machine Tools. McGraw-Hill International Book Co., 1981, Auckland, New Zealand. Giardini, C., Ceretti, E. and Maccarini, G. A Neural Network Architecture for Tool Wear Detection through Digital Camera Observations, Advanced Manufacturing Systems and Technology, 1996. Gose, E., Johnsonbaugh, R. and Jost, S. Pattern Recognition and Image Analysis, Prentice-Hall, 1996. Gould, L. Sensing Tool and Drive Element Conditions in Machine Tools, Sensor, pp.5–13, 1988. Grbec, P. and Leskovar, P. Acoustic Emission of a Cutting Process, Ultrasonics, Vol. 15, No.1, pp.17–20, 1977 Hand, D.J. Construction and Assessment of Classification Rules. Chichester, England, JohnWiley & Sons, 1997. Haykin, S. Neural Networks-A Comprehensive Foundation. Prentice Hall, New Jersey, 1999. Hayashi, S.R., Thomas, C.E. and Wildes, D.G. Tool Breakage Detection by Monitoring Ultrasonic Vibrations, Annals of CIRP, No. 37, pp.61-64, 1988. Helmut A. Mayer and Roland Schwaiger Evolutionary and Coevolutionary Approaches to Time Series Prediction Using Generalized Multi-Layer Perceptrons, Congress on Evolutionary Computation, Washington DC, 1999. Hong, G.S., Rahman, M. and Zhou, Q. Using Neural Network for Tool Condition Monitoring Based on Wavelet Decomposition, International Journal of Machine Tools and Manufacture, Vol. 36, No. 5, pp.551-566, 1996. Houshmand, A.A., Herrin, G.D. and Kannatey-asibu, E. A Dynamic Model for Tool-wear Detection Using Acoustic Emission, Control of Manufacturing Processes, PED 52, pp.13-22, 1991. 138 References Hsu, C.W. and Lin, C.J. A Comparison of Methods for Multi-Class Support Vector Machines, IEEE Transactions on Neural Networks, 13, pp.415-425, 2002 International Standard (ISO 3685, second edition): Tool Life Testing with Singlepoint Turning Tools, pp.23, 1993. Iwata, K. and Moriwaki, T. Application of Acoustic Emission Measurement to InProcess Sensing of Tool Wear, Annals of CIRP, Vol. 26, No.1-2, pp.19–23, 1977 Jain, A. K. and Zongker, D. Feature-selection: Evaluation, Application, and Small Sample Performance, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 19, No.2, pp.152-157, 1997. Jebara, T. and Jaakkola, T. Feature Selection and Dualities in Maximum Entropy Discrimination. In UAI-2000: Proc. of the 16th Conference on Uncertainty in Artificial Intelligence, Stanford University, CA, USA, 2000. Jemielniak, K. and Otman, O. Tool Failure Detection Based on Analysis of Acoustic Emission Signals, Journal of Material Processing Technology, 76, pp.192–197, 1998 Jiaa, C.L. and Dornfeld, D.A. Self-organizing Approach to the Prediction and Detection of Tool Wear, ISA Transaction, Vol. 37, No.4, pp.239-255, 1998 Jiang, Y.C. and Xu, J.H. In-process Monitoring of Tool Wear Stage by the Frequency Band Energy Method. Annals of CIRP, Vol. 36, No.1, pp.45-48, 1987 Joachims, T. The Maximum-Margin Approach to Learning Text Classifiers: Method, Theory and Algorithms. PhD Thesis, University of Dortmund, 2000. Kakade, S., Vijayaraghavan, L. and Krishnamurthy, R. In-process Tool Wear and Chip-form Monitoring in Face Milling Operation Using Acoustic Emission, Journal of Material Processing Technology, Vol. 44, pp.207–214, 1994. Kamarthi, S., Kumara, S. and Cohen, P. Wavelet Representation of Acoustic Emission in Turning Process, Intelligent Engineering Systems through Artificial Neural Networks, Vol. 5, pp.861–866, 1995. Kannatey-Asibu, E. and Dornfeld, D.A. A Study of Tool Wear Using Statistical Analysis of Metal Cutting Acoustic Emission, Wear, Vol.76, pp.247-254, 1982. Karakoulas, G. and Shawe-Taylor, J. Optimizing Classifiers for Imbalanced Training Sets. In M. S. Kearns, S.A. Solla, D.A. Cohn (Eds.), Advances in Neural Information Processing Systems, Vol. 11, Cambridge, MA: MIT Press, 1999. Keerthi, S.S. and Gilbert, E.G. Convergence of a Generalized SMO Algorithm for SVM Classifier Design, Machine Learning, Vol. 46, 2002, pp. 351-360. Kim, J.S. Development of an on-Line Tool-Life Monitoring System Using Acoustic Emission Signal in Gear Shaping, International Journal of Machine Tools and Manufacture, Vol. 39, No.11, pp.1761-1777, 1999. Ko, T.J. and Cho, D.W. Cutting State Monitoring in Milling by a Neural Network, International Journal of Machine Tools and Manufacture, Vol. 34, No.5, pp.659–676, 1994. 139 References Koren, Y. and Lenz, E. Mathematical Model for The Flank Wear While Turning Steel with Carbide Tools. In Proceedings of the CIRP Seminars on Manufacturing Systems, Vol.1, No.2, 1972. Koren, Y. Flank Wear Model of Cutting Tools Using Control Theory, ASME Trans., Journal of Engineering for Industry, Vol. 100, pp.103-109, 1978. König, W., Kutzner, K. and Schehl, U. Tool Monitoring of Small Drills with Acoustic Emission, International Journal of Machine Tools and Manufacture, Vol. 32, No.4, pp.487–493, 1992. Kramer, B.M. Tool Wear by Solution: A Quantitative Understanding, ASME Trans., Journal of Engineering for Industry, Vol. 102, pp.303-309, 1980. Kumar, S.A., Ravindra, H.V. and Srinivasa, Y.G. In-process Tool Wear Monitoring through Time Series Modeling and Pattern Recognition, International Journal of Production Research, Vol. 35, No. 3, pp.739-751, 1997. Kwok, J.T. Integrating the Evidence Framework and the Support Vector Machine. In Proceedings of the European Symposium on Artificial Neural Networks, Bruges, Belgium, pp.177-182, 1999. Lee, J.M., Choi, D.K. and Chu, C.N. Real Time Tool Breakage Monitoring for NC Milling Process, Annals of CIRP, Vol. 44, No.1, pp.59-62, 1995. Lee, K.S., Lee, L.C. and Teo, S.C. On-line Tool Wear Monitoring Using a PC, Journal of Material Processing Technology, Vol. 29, pp.3–13, 1992. Lee, L.C., Lee, K.S. and Gan, C.S. On the Correlation Between Dynamic Cutting Force and Tool Wear, International Journal of Machine Tools and Manufacture, Vol. 29, No.3, pp.295–303, 1989 Lee, M.Y., Thomas, C.E. and Wildes, G. Review – Prospects for In-Process Diagnosis of Metal Cutting by Monitoring Vibration Signals, Journal of Material. Science, Vol. 22, pp.3821-3890, 1987. Leem, C.S. and Dornfeld, D.A. A Customised Neural Network for Sensor Fusion in Online Monitoring of Cutting Tool Wear, ASME Trans., Journal of Engineering for Industry, Vol. 117, pp.152-159,1995. Li, D. and Mathew, J. Tool Wear and Failure Monitoring Techniques for Turning A Review, International Journal of Machine Tools and Manufacture, Vol. 30, No.4, pp579-598, 1990. Li, S. and Elbestawi, M.A. Tool Condition Monitoring in Machining by Fuzzy Neural Networks, Journal of Dynamic Systems, Measurement and Control, Vol. 118, pp.665-672, 1996a. Li, S. and Elbestawi, M.A. Fuzzy Clustering for Automated Tool Condition Monitoring in Machining, Mechanical Systems and Signal Processing, Vol. 10, No.5, pp.533-550, 1996b. Li, X. and Yuan, Z. Tool Wear Monitoring with Wavelet Packet Transform-Fuzzy Clustering Method, Wear, 219, pp.145-154, 1998. 140 References Li, X., Dong, S. and Yuan, Z. Discrete Wavelet Transform for Tool Breakage Monitoring, International Journal of Machine Tools and Manufacture, Vol. 39, No.12, pp.1935-1944, 1999. Li, X., Dong, S. and Venuvinod, P.K. Hybrid Learning for Tool Wear Monitoring, International Journal of Advance Manufacturing Technology, Vol. 16, pp.303-307, 2000. Li, X.Q., Wong Y.S. and Nee, A.Y.C. A Comprehensive Identification of Tool Failure and Chatter Using a Parallel Multi-Art2 Neural Network, ASME Trans., Journal of Manufacturing Science and Engineering, Vol. 120, pp.433-442, 1998. Liang, S.Y. and Dornfeld, D.A. Tool Wear Detection Using Time Series Analysis of Acoustic Emission, ASME Trans., Journal of Engineering for Industry, Vol.111, pp.199-204, 1989 Liao, T.W. and Chen, L.J. A Neural Network Approach for Grinding Processes: Modeling and Optimization, International Journal of Machine Tools and Manufacture, Vol. 34, No. 7, pp.919-937, 1994 Liao, T.W. Online PCBN Tool Failure Monitoring System Based on Acoustic Emission Signature, IEE Proceedings. Science, Measurement and Technology, Vol. 142, No. 5, pp.404-409, 1995 Lin, S.C. and Lin, R.J. Tool Wear Monitoring in Face Milling using Force Signals, Wear, Vol. 198, pp.136-142, 1996. Lister, P.M. On-line Measurement of Tool Wear. Ph.D. thesis, Manufacturing and Machine Tools Division, UMIST. Manchester, UK, 1993. Liu, M. and Liang, S.Y. Analytical Modeling of Acoustic Emission for Monitoring of Peripheral Milling Process, International Journal of Machine Tools and Manufacture, Vol. 31, No. 4, pp.589-606, 1991. MacKay, D.J.C. Information-Based Objective Functions for Active Data Selection, Neural Computing, Vol. 44, pp.589-603, 1991 Mackay, D.J.C. A Practical Bayesian Framework for Back Propagation Networks. Neural Computing, Vol. 4, No.3, pp.448-472, 1992a. MacKay D.J.C. Bayesian Methods for Adaptive Models. PhD Thesis, California Institute of Technology. 1992b. Mackay, D.J.C. Bayesian Methods for Backpropagation Networks, Models of Neural Networks II, Springer, 1993 Mackay, D.J.C. Bayesian Non-linear Modeling for the Prediction Competition. ASHRAE Transactions, Vol.100, No.2, pp.1053-1062, 1994 Marques, M.J.M. and Mesquita, R.M.D. Monitoring the Wear of Sintered Highspeed Steel Tools, Journal of Material Processing Technology, Vol. 25, pp.195-213, 1991. 141 References Matsushima, K., Bertok, P. and Sata, T. In Process Detection of Tool Breakage by Monitoring the Spindle Current of a Machine Tool, ASME J. of Measurement and Control for Batch Manufacturing, pp.145-154, 1982. Mercer, J. Functions of Positive and Negative Type and Their Connection with the Theory of Integral Equations, Philos. Trans. Roy. Soc. London A, Vol. 209, pp.415446, 1909. Micheletti, G.F., Koenig, W. and Victor, H.R. In-Process Tool Wear Sensors for Cutting Operations, Annals of CIRP, Vol. 25, pp. 483-496, 1976. Molinari, A. and Nouari, M. Modeling of Tool Wear by Diffusion in Metal Cutting, Wear, Vol. 252, pp.135-149, 2002. Montgomery, D.C. and Peck, E.A. Introduction to Linear Regression Analysis (2nd edition). John Wiley & Sons, 1982, New York. Moore, T.N. and Kiss, R. Detection of Tool Failure Using Vibration Data. In Condition Monitoring and Diagnostic Engineering Management COMADEM 96 Conference Proceedings, pp.325-334, 1996. Morgan, N. and Boulard, H. Generalization and Parameter Estimation in Feedforward Neural Nets: Some Experiments, in Touretzky, D.S.(Ed.), Advances in neural information processing systems (Margan Kaufmann, San Mateo), 1990, pp.630-637. Moriwaki, T. and Tobito, M. A New Approach to Automatic Detection of Life of Coated Tool Based on Acoustic Emission Measurement, ASME Trans., Journal of Engineering for Industry, Vol. 112, pp.212–218, 1990. Naerheim,Y. and Arora, A. In-process Monitoring of Machining Using Acoustic Emission, Review of Progress in Quantitative Nondestructive Evaluation, Vol. (B), pp.753–762, 1984, Plenum Press, USA Neal, R.M. Bayesian Learning for Neural Networks. Lecture Notes in Statistics, No. 118, Springer-Verlag, 1996, New York Neal, R.M. Regression and Classification using Gaussian Process Priors (with discussion). in J. M. Bernardo, et al. (editors) Bayesian Statistics 6, Oxford University Press, pp. 475-501, 1997 Niu, Y.M., Wong, Y.S. and Hong, G.S. An Intelligent Sensor System Approach for Reliable Tool Flank Wear Recognition, International Journal of Advance Manufacturing Technology, Vol. 14, pp.77-84, 1998a. Niu, Y.M., Wong, Y.S., Hong, G.S. and Liu, T.I. Multi-category Classification of Tool Conditions Using Wavelet Packets and ART2 Network, Journal of Manufacturing Science and Engineering, Vol. 120, pp.807-815, 1998b. Oguamanam, D.C.D., Raafat, H. and Taboun, S.M. A Machine Vision System for Wear Monitoring and Breakage Detection of Single-point Cutting Tools, Computers in Industrial Engineering, Vol. 26, No. 3, pp.575-598, 1994. 142 References Oraby, S.E. and Hayhurst, D.R. Development of Models for Tool Wear Force Relationships in Metal Cutting, International Journal of Machine Tools and Manufacture, Vol. 33, No.2, pp.125–138, 1991 Ostendorf, M. and Atlas, L. Joint Use of Dynamical Classifiers and Ambiguity Plane Features. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Vol. VI, pp.3589-3592, 2001. Ou Yu-Yen, Chen Chien-Yu, Hwang Shien-Ching and Oyang Yen-Jen Expediting Model Selection for Support Vector Machines Based on Data Reduction. In Proceedings of IEEE International Conference on Systems, Man and Cybernetics, 2003 Penny, W. and Roberts, S. J. Bayesian Classification Using Neural Networks - How Useful Is the Evidence Framework, Neural Networks, Vol.12, pp.877 - 892, 1999. Pfeifer, T. and Wiegers, L. Reliable Tool Wear Monitoring by Optimized Image and Illumination Control in Machine Vision, Journal of International Measurement Confederation, Vol. 28, pp.209-218. 2000. Platt, J.C. Fast Training of Support Vector Machines Using Sequential Minimal Optimization. In B. Schölkopf, C. Burgus and A. J. Smola, editors, Advances in Kernel Methods: Support vector Machines, MIT Press, Cambridge, MA, 1998 Platt, J.C. Sequential Minimal Optimization: A Fast Algorithm for Training Support Vector Machines. Technical Report MSR-TR-98-14, Microsoft Research, 1998. Plutowski, M. Selecting Training Exemplars for Neural Network Learning. PhD Dissertation, University of California, San Diego, 1994. Purushothaman, S. and Srinivasa, Y.G. A Procedure for Training an Artificial Neural Network with Application to Tool Wear Monitoring, International Journal of Production Research, Vol. 36, pp.635-651, 1998. Ragg, T. and Gutjahr, S. Automatic Determination of Optimal Network Topologies Based on Information Theory and Evolution. In Proceedings of the 23rd EUROMICRO Conference '97 New Frontiers of Information Technology, 1997. Randall Fish, R.K., Ostendorf, M., Bernard, G.D. and Castanon, D.A. Multilevel Classification of Milling Tool Wear with Confidence Estimation, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No.1, pp.75-85, 2003. Rangwala, S. and Dornfeld, D.A. Integration of Sensors via Neural Networks for Detection of Tool Wear States. In Proceedings of Winter Annual Meetings of the ASME, PED, Vol. 25, pp.109-120, 1987. Rangwala, S. and Dornfeld, D.A. Sensor Integration Using Neural Networks for Intelligent Tool Condition Monitoring, ASME Trans., Journal of Engineering for Industry, Vol. 112, pp.219-228, 1990 Rao, S.B. Tool Wear Monitoring through the Dynamics of Stable Turning, ASME Trans., Journal of Engineering for Industry Vol.108, No.1, pp.183-190, 1986 143 References Ravindra, H.V., Srinivasa, Y.G. and Krishnamurthy, R. Tool Wear Monitoring in Turning Using a Pattern Recognition Technique, Journal of Material Processing Technology, Vol. 37, pp.731-740, 1993a. Ravindra, H.V., Srinivasa, Y.G. and Krishnamurthy, R. Modeling of Tool Wear Based on Cutting Forces in Turning, Wear, Vol.169, pp.25–32,1993b. Ravindra, H.V., Srinivasa, Y.G. and Krishnamurthy, R. Acoustic Emission for Tool Condition Monitoring in Metal Cutting, Wear, Vol. 212, No.1, pp.78–84,1997. Reeves, C. Training Set Selection in Neural Network Applications. In Proc. of 2nd International Conference on Artificial Neural Nets and Genetic Algorithms, SpringerVerlag, Vienna, pp.476-478, 1995 Reeves, C. and Stewart, J.T. Selection of Training Data for Neural Networks by a Genetic Algorithm. In Proc. of 5th International Conference on Parallel Problem Solving from Nature, Springer-Verlag, Berlin, pp.633-642, 1998 Rioul, O. and Flandrin, P. Time-scale Energy Distributions: A General Class Extending Wavelet Transforms, IEEE Transactions on Signal Processing, Vol. 40 pp.1746-1757, 1992. Roget, J., Souquet, P. and Gsib, N. Application of Acoustic Emission to the Automatic Monitoring of Tool Condition during Machining, ASNDT Materials Evaluation, Vol. 46, pp.225–229, 1988 Ruck, D.W., Rogers, S.K. and Kabrisky, M. Feature Selection Using a Multilayer Perceptron, Journal of Neural Network Computing, Vol. 2, pp.40-48. 1990. Shi, T. and Ramalingam, S. Real-time Flank Wear Sensing, Winter Annual Meeting of ASME, PED, Vol.43, pp.157–170, 1990. Slater, J. D., Wu, F. Y., Honig, L. S., Ramsay, R. E., and Morgan, R. Neural Network Analysis of the P300 Event-Related Potential in Multiple Sclerosis, Electroencephalography and Clinical Neurophysiology, 1993. Sampath, A. and Vajpayee, S. Tool Health Monitoring Using Acoustic Emission, International Journal of Production Research, Vol. 25, No. 5, pp.703-719, 1987. Santanu D., Chattopadhyay, A.B. and Murthy, A.S.R. Force Parameters for Online Tool Wear Estimation: A Neural Network Approach, Neural Networks, Vol. 9, No. 9, pp.1639-1645. 1996. Santanu, D. and Chattopadhyay, A.B. Application of the Analytic Hierarchy Process for Estimating the State of Tool Wear, International Journal of Machine Tools and Manufacture, Vol. 43, No.1, pp.1–6, 2003. Sata, T., Matsushima, K. and Nagakura, T. Learning and Recognition of the Cutting States by Spectrum Analysis, Annals of CIRP, Vol. 22, pp.41-45, 1973. Scott, D.W. Multivariate Density Estimation: Theory, Practice and Visualization. John Wiley & Sons, New York, 1992. Sen, A. and Serivastava, M. Regression Analysis: Theory, Methods, and Applications. New York: Springer-Verlagm, 1990. 144 References Sethu Vijayakumar, Masashi Sugiyama and Hidemitsu Ogawa, Training Data Selection for Optimal Generalization with Noise Variance Reduction in Neural Networks, In: Marinaro & Tagliaferri(ed.), Neural Nets WIRN Vietri-98, SpringerVerlag, 1998, pp.153-166. Shevade, S.K., Keerthi, S.S., Bhattacharyya, C. and Murthy, K.R.K. Improvements to the SMO Algorithm for SVM Regression, IEEE Transactions on Neural Networks, Vol. 11, pp.1188-1194, 2000. Shi, T. and Ramalingam, S. Real-time Flank Wear Sensing. In Proceeding of Winter Annual Meeting of the ASME, PED 43, pp157–170, 1990 Sick, B. Tool Wear Monitoring in Turning: A Neural Network Application, Measurement + Control, Vol. 34, No. 7, pp.207- 222, The Institute of Measurement and Control, London, 2001 Siedlecki, W. and Sklansky, J. On Automatic Feature Selection, International Journal of Pattern Recognition and Artificial Intelligence, Vol. 2, No.2, pp.197-220, 1988. Siedlechi, W. and Sklansky, J. A Note on Genetic Algorithms for Large-Scale Feature Selection, Pattern Recognition Letters, Vol. 10, pp.335-347, 1989. Silva, R.G. Cutting Tool Wear Monitoring of the Turning Process Using Artificial Intelligence. Ph.D. Thesis, British Library, 1997. Silva, R. G., Rruben, R. L., Baker, K.J. and Wilcox, S. J. Tool Wear Monitoring of Turning Operations by Neural Network Classification of a Feature Set Generated from Multiple Sensors, Mechanical Systems and Signal Processing, 12, pp.319-332, 1998. Sollich, P. and Saad., D. Learning from Queries for Maximum Information Gain in Imperfectly Learnable Problems, Advances in Neural Information Processing System, Vol. 7, pp.287–294, MIT Press, 1995. Steppe, J.M. and Bauer, Jr.K.W. Improved Feature Screening in Feed-Forward Neural Networks, Neurocomputing, Vol. 13, pp.47-58, 1996. Sun, J., Hong, G.S., Rahman, M. and Wong, Y.S. Identification of Feature Set for Effective Tool Condition Monitoring by Acoustic Emission Sensing, International Journal of Production Research, Vol. 42, No.5, pp.901–918, 2004. Sun, J., Wong, Y.S., Rahman, M. and Hong, G.S. Multi-classification of Tool Wear with Support Vector Machine by Manufacturing Loss Consideration, International Journal of Machine Tools and Manufacture, Vol. 44, No.11, pp.1179– 1187, 2004. Sun, J., Hong, G.S., Rahman, M. and Wong, Y.S. Improved Performance Evaluation of Tool Condition Identification by Manufacturing Loss Consideration, International Journal of Production Research, Vol. 43, No. pp.1185 – 1204, 2005. Sun, J., Hong, G. S., Wong, Y. S., Rahman, M. and Z.G. Wang Effective Training data selection in Tool Condition Monitoring System, appear in International Journal of Machine Tools and Manufacture 145 References Takata, S., Ahn, J. H., Miki, M., Miyao, Y., and Sata, T. A Sound Monitoring System for Fault Detection of Machine and Machining States, Annals of CIRP, Vol. 35, No. 1, pp.289-292, 1986. Tansel, I.N., Mekdeci, C., Rodriguez, O., and Uragun, B. Monitoring Drill Conditions With Wavelet Based Encoding and Neural Networks, International Journal of Machine Tools and Manufacture, Vol. 33, No. 4, pp.559-575, 1992. Tansel, I.N. and McLauglin, C. Monitoring Drill Conditions with Wavelet Based Encoding and Neural Networks, International Journal of Machine Tools and Manufacture, Vol. 33, No.4, pp.559-575, 1993. Tansel, I.N. Detection of Tool Breakage in Milling Operations: I. The Time Series Analysis Approach; II. The Neural Network Approach, International Journal of Machine Tools and Manufacture, Vol. 33, No.4, pp.531-558, 1993. Tarng, Y.S., Hseih, Y.W. and Hwang, S.T. Sensing Tool Breakage in Face Milling with a Neural Network, International Journal of Machine Tools and Manufacture, Vol. 34, No. 3, pp.341-350. 1994. Tay, F.E.H. and Cao, L.J. Saliency Analysis of Support Vector Machines for Feature Selection, Neural Network World, Vol. 2, No. 1, pp.153-166. 2001a. Tay, F.E.H. and Cao, L.J. Improved Financial Time Series Forecasting by Combining Support Vector Machines with Self-Organizing Feature Map, Intelligent Data Analysis, Vol. 5, pp.1-16, 2001b. Vafaie Haleh and DeJong Kenneth Robust Feature Selection Algorithms. In Fifth International Conference on Tools with Artificial Intelligence (ICTAI '93), USA, pp.356-363, 1993 Van Gestel T., Suykens, J.A.K., De Moor, B. and Vandewalle, J. Automatic Relevance Determination for Least Squares Support Vector Machine Classifiers. In Proceedings of the 9th European Symposium on Artificial Neural Networks. pp.1318, 2001. Vapnik, V.N. The Nature of Statistical Learning Theory, Springer, 1995 Vapnik, V.N. Statistical Learning Theory, Wiley, New York, 1998 Vapnik, V.N. and Chapelle, O. Bounds on Error Expectation for Support Vector Machine, ed. by Peter J. Bartlett, Bernhard Schölkopf, Dale Schuurmans and Alex J. Smola, Advances in Large Margin Classifiers, MIT Press, 1999. Wang, L.T., Mostafa G. Mehrabi and Jr. Elijah Kannatey-Asibu Hidden Markov Model-Based Tool Wear Monitoring in Turning, ASME, Journal of Manufacturing Science and Engineering, Vol.124, pp. 651- 658, 2002. Weston, J. and Watkins, C. Multi-class Support Vector Machines, Technical Report CSD-TR-98-04, Royal Holloway, University of London, UK, 1998 Weston, J. and Mukherjee, S. Feature Selection for SVMs. In NIPS-13: Advances in Neural Information Processing Systems 13, Denver, Colorado, 2001. 146 References Wilcox, S.J., Reuben, R.L. and Souquet, P. The Use of Cutting Force and Acoustic Emission Signals for the Monitoring of Tool Insert Geometry during Rough Face Milling, International Journal of Machine Tools and Manufacture , Vol. 37, No. 4, pp.481-494, 1997. Williams, C.K.I. and Barber, D. Bayesian Classification with Gaussian Processes, IEEE Trans, Pattern Analysis and Machine Intelligence, Vol. 20, No.12, pp.13421351, 1998 Wilson, D. R. and Martinez, T. R. Instance Pruning Techniques. In International Conference Machine Learning, pp. 403–411, 1997. 14th Wong, Y.S., Nee, A.Y.C., Li, X.Q. and Reisdorf, C. Tool Condition Monitoring using Laser Scatter Pattern, Journal of Material Processing Technology, Vol. 63, pp.205-210, 1997. Wu, Y. and Du, R. Feature Extraction and Assessment Using Wavelet Packages for Monitoring Machining Processes, Mechanical Systems and Signal Processing, Vol. 10, pp.29-53, 1995 Xu, X. Development of an Online Tool Wear Monitoring System. M.Eng. Thesis. National University of Singapore, 2001. Yang, J. and Havaldar, R. Feature Subset Selection Using a Genetic Algorithm, IEEE Intelligent Systems, Vol. 13, No.2, pp.44-49, 1998 Yao, Y.X., Li, X. and Yuan, Z.J. Tool Wear Detection with Fuzzy Classification and Wavelet Fuzzy Neural Network, International Journal of Machine Tools and Manufacture, Vol. 39, No.10, pp.1525–1538, 1999. Yi, L., Lee, Y.K. and Grace Wahba Support Vector Machines for Classification in Nonstandard Situations, Machine Learning, Vol. 46, pp.191-202, 2002 Zhang, B.T. Accelerated Learning by Active Example Selection, International Journal of Neural Systems, Vol. 5, No.1, pp.67–75, 1994 Zheng, S.X. Intrinsic Optical Fiber Sensor for Monitoring Acoustic Emission, Sensors and Actuators, A: Physical, 31, pp.110–114, 1992 Zhang, Z. A Tool Condition Monitoring Approach Based on SVM. M.Eng. Thesis, National University of Singapore, 2002. Zizka, J. Tool Wear and Chatter Monitoring. In Condition Monitoring and Diagnostic Engineering Management COMADEM 96 Conference Proceedings, pp.377-387, 1996. 147 [...]... different category of tool wear conditions Therefore this tool condition identification method is extended to multiclassifying tool conditions Finally, a framework which generalizes sensing signal selection, feature analysis, performance evaluation and decision making is proposed in this study Two case studies are provided to demonstrate the above proposed methods: one based on AE signal from machining... naturally contain multiple tool condition information (tool wear, fracture), have been proven to effective in TCM Compared with multi-sensing approach, AE sensing can be more economically Thus, it is used as references for developing tool condition identification system During metal cutting the workpiece undergoes considerable plastic deformation as the tool pushes through it Within the deformation zones,... effective feature set to identify tool conditions From the analyzed results, cutting force sensing is considered as a suitable monitoring signal, and its effective feature set is used as input for tool condition identification in titanium machining Then, a performance evaluation function with manufacturing loss consideration is introduced to determine whether a tool is due for replacement other than merely... learning and prediction is the most popular method to perform decision making on tool conditions These issues are further discussed in great details in the following chapters The value of this research is to improve the application of NNs -based methods in TCM so as to realize reliable tool condition identification over a range of cutting conditions 1.4 Research objective and contributions The objective... Chapter 1 Introduction an effective training data set with reliable recognition performance in tool condition identification The benefits of multiclassification of tool wear are described in chapter 6 The problems that existed in the application of NNs in TCM are analyzed, and the performance evaluation function introduced in chapter 5 is extended to multilevel classification of tool condition Finally three... other based on cutting force from machining titanium In short, the major contributions of this thesis include: (1) Develop a method to identify feature set from various extracted features 17 Chapter 1 Introduction (2) Propose a new performance evaluation function by manufacturing loss consideration (3) Propose an effective decision making method in tool condition identification (4) Improve the performances... number of neurons, and can be retrieved almost instantaneously in practical application NNs can also perform decision making based on incomplete and noisy information, which makes it suitable for the diagnostic function in a manufacturing system (Rangwala and Dornfeld, 1990) Rangwala and Dornfeld (1987) pioneered the use of Back-propagation (BP) to classify AE and force signal for tool wear monitoring. .. algorithms impose a great challenge for feature extraction techniques (Niu et al., 1998) However, extracting compact tool- wear-sensitive but condition- 15 Chapter 1 Introduction independent features is still an ongoing research issue In this thesis, support vector machine (SVM) is proposed to learn the correct tool wear information in the extensive cutting conditions Compared with other learning algorithms,... signals Generally, the AE signals from machining process may contain both types because of the co-existence of different tool conditions 2.4 Cutting forces and tool wear Understanding the basic force trend in the metal-cutting process that is related to tool wear or failure will enable one to know tool conditions The variation of cutting forces to tool wear has been widely established (Oraby and Hayhurst,... the cutting tool When a tool is used under normal cutting conditions, flank wear is usually the primary factor that determines the life of an insert, while crater formation is more important under high-temperature and high speed cutting conditions (Boothroyd and Knight, 1989) In this experiment, due to cutting conditions within the normal range, only flank wear is considered to determine tool life This . of tool wear conditions. Therefore this tool condition identification method is extended to multiclassifying tool conditions. Finally, a framework which generalizes sensing signal selection,. tool conditions identification (fresh or worn) and multiclassification of tool conditions (sharp, workable and worn). The robustness of decision-making depends not only on the identification. refinement (feature extraction and selection) and decision making based on the refined information (condition identification) are fully integrated. Figure 1.1 Information flow and processing