Multiprocessor systems for connectionist diagnosis of technical processes

Abstract The paper summarizes the requirements for a new family of monitoring and diagnostic systems, characterized among others by networking capability, high computing speed and adaptive learning ability. The diagnostic process is regarded as a pattern recognition procedure. Artificial neural networks (ANNs) or connectionist models and their pattern recognition abilities are illustrated. The back propagation technique as the most frequently used learning algorithm for multi-layered ANNs is outlined together with some acceleration methods. Neural network forms of traditional pattern recognition approaches are described, which usually mean a direct determination of the networks' parameters. The paper gives the first results of investigations comparing the learning and recognition performance of frequently used traditional pattern recognition techniques, back propagation networks and a network based on the condensed nearest-neighbour concept, developed at the University of Paderborn. Two “neuro monitoring and diagnostic systems” based on parallel processor structures and incorporating neural network techniques for learning and classification, being developed at the Institute for Electrical Measurement, University of Paderborn, are presented and compared in the paper.

[1]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[2]  G. Mirchandani,et al.  On hidden nodes for neural nets , 1989 .

[3]  Michael T. Manry,et al.  Iterative improvement of a Gaussian classifier , 1990, Neural Networks.

[4]  Gail A. Carpenter,et al.  Neural network models for pattern recognition and associative memory , 1989, Neural Networks.

[5]  D. Barschdorff,et al.  Heart sound analysis using neural and statistical classifiers: a comparison , 1989, [1989] Proceedings. Computers in Cardiology.

[6]  Rolf Isermann,et al.  Process fault detection based on modeling and estimation methods - A survey , 1984, Autom..

[7]  D Barschdorff,et al.  Real-time failure detection on complex mechanical structures via parallel data processing , 1986 .

[8]  Richard L. Kegg,et al.  One-Line Machine and Process Diagnostics , 1984 .

[9]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[10]  L. Monostori.  Computer-aided generation of monitoring strategy for complex machine tool monitoring systems , 1987 .

[11]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[12]  J. Makhoul,et al.  Formation of disconnected decision regions with a single hidden layer , 1989, International 1989 Joint Conference on Neural Networks.

[13]  Stephen Grossberg,et al.  Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns , 1988, Other Conferences.

[14]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[15]  Richard Lippmann,et al.  Neural Net and Traditional Classifiers , 1987, NIPS.

[16]  L. Monostori.  SIGNAL PROCESSING AND DECISION MAKING IN MACHINE TOOL MONITORING SYSTEMS. , 1988 .

[17]  Christopher Rose,et al.  Minimum distance automata in parallel networks for optimum classification , 1989, Neural Networks.

[18]  Dennis J. Volper,et al.  Quadratic function nodes: Use, structure and training , 1990, Neural Networks.

[19]  László Monostori,et al.  A pattern recognition based vibration monitoring module for machine tools , 1988 .

[20]  Hironori Kasahara,et al.  Practical Multiprocessor Scheduling Algorithms for Efficient Parallel Processing , 1984, IEEE Transactions on Computers.

[21]  G. Gates,et al.  The reduced nearest neighbor rule (Corresp.) , 1972, IEEE Trans. Inf. Theory.

[22]  László Monostori.  Learning procedures in machine tool monitoring , 1986 .

[23]  László Monostori,et al.  Neural networks—Their applications and perspectives in intelligent machining , 1991 .