Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems |
| |
| Affiliation: | 1. Department of Chemical & Biomolecular Engineering, University of Connecticut, 159 Discovery Dr., Storrs, CT 06269, USA;2. Connecticut Center for Advanced Technology, Inc. 222 Pitkin St., Suite 101, East Hartford, CT 06108, USA;3. Gerber Technology, Inc. 24 Industrial Park Rd., Tolland, CT 06084, USA;4. Department of Electrical & Computer Engineering, University of Connecticut, 371 Fairfield Way, Storrs, CT 06269, USA;1. Department of Industrial Engineering and Management, National Taipei University of Technology, Taipei 10608, Taiwan;2. ChipMOS TECHNOLOGIES INC., Hsinchu Science Park, Hsinchu City 300, Taiwan;1. Polytech’Tours, Université de Tours, Laboratoire de Mécanique et Rhéologie EA 2640, 7 avenue Marcel Dassault, 37200 Tours, France;2. Polytech’Tours, Université de Tours, Signal & Image Group, 7 avenue Marcel Dassault, 37200 Tours, France;3. INSA Centre Val de Loire, Laboratoire de Mécanique et Rhéologie EA 2640, 3 rue de la chocolaterie, CS 23410, 41034 Blois, France;1. Department of Automation, University of Science and Technology of China, Hefei 230026, Anhui, China;2. School of Mechanical and Electric Engineering, Soochow University, Suzhou 215021, Jiangsu, China;1. Department of Industrial & Management Engineering, Pohang University of Science and Technology (POSTECH), 77 Cheongam-ro, Nam-gu, Pohang, Gyeongbuk, 37673, Republic of Korea;2. Department of Industrial Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon, 16419, Republic of Korea;1. University of Novi Sad, Faculty of Technical Sciences, Department of Production Engineering, Trg Dositeja Obradovi?a 6, 21000 Novi Sad, Serbia;2. University of Novi Sad, Faculty of Technical Sciences, Department of Power, Electronic and Telecommunication Engineering, Trg Dositeja Obradovi?a 6, 21000 Novi Sad, Serbia;3. University of Novi Sad, Faculty of Technical Sciences, Chair for Computer Graphics, Trg Dositeja Obradovi?a 6, 21000 Novi Sad, Serbia |
| |
| Abstract: | We present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models. |
| |
| Keywords: | Machining Machine learning Signal processing Fault detection Machine state monitoring |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
