INTELLIGENT ON-LINE MONITORING AND DIAGNOSIS FOR MANUFACTURING

To comply with the global market demands on both quality and efficiency in the manufacturing industry, this book presents the work on developing an intelligent on-line monitoring system for sheet metal stamping processes. It focuses on solving three major questions: (1)how to effectively measure and select the features from the appropriate sensor signals; (2)how to define an effective and efficient learning algorithm to acquire the knowledge from the limited training samples; and (3) how to generate an accurate and simple criterion of the decision making for on-line application. Support vector machine (SVM) technique has been well developed and applied in the work. Through studying the noise density using support vector regression technique, a new approach to measure similarity of the signals is proposed. It helps us to construct a mathematical model to describe the strain signals, which is able to compare the dynamic and real-time data. More important to engineering practice is the new measure similarity technique overcomes the effect of signal sifting, which exists in most of signal acquisition and causes related techniques invalidate sometimes.