Model-Based Intelligent Fault Detection and Diagnosis for Mating Electric Connectors in Robotic Wiring Harness Assembly Systems

Mating a pair of electric connectors is one of the most important steps in a robotic wiring harness assembly system. A class of piecewise linear force models is proposed to describe both the successful and the faulty mating processes of connectors via an elaborate analysis of forces during different phases. The corresponding parameter estimation method of this model is also presented by adapting regular least-square estimation methods. A hierarchical fuzzy pattern matching multidensity classifier is proposed to realize fault detection and diagnosis for the mating process. This classifier shows good performance in diagnosis. A typical type of connectors is investigated in this paper. The results can easily be extended to other types. The effectiveness of proposed methods is finally confirmed through experiments.

[1]  Christopher G. Atkeson,et al.  Constructive Incremental Learning from Only Local Information , 1998, Neural Computation.

[2]  Arnaud Devillez,et al.  Four fuzzy supervised classification methods for discriminating classes of non-convex shape , 2004, Fuzzy Sets Syst..

[3]  Heikki N. Koivo,et al.  Application of artificial neural networks in process fault diagnosis , 1991, Autom..

[4]  Moamar Sayed Mouchaweh,et al.  Incremental learning in Fuzzy Pattern Matching , 2002, Fuzzy Sets Syst..

[5]  Helge-Björn Kuntze,et al.  A neuro-fuzzy supervisory control system for industrial batch processes , 2001, IEEE Trans. Fuzzy Syst..

[6]  Chu Kiong Loo,et al.  Extrapolation detection and novelty-based node insertion for sequential growing multi-experts network , 2003, Appl. Soft Comput..

[7]  Rolf Isermann,et al.  Hierarchical motor diagnosis utilizing structural knowledge and a self-learning neuro-fuzzy scheme , 2000, IEEE Trans. Ind. Electron..

[8]  Patrice Billaudel,et al.  Performance evaluation of fuzzy classification methods designed for real time application , 1999, Int. J. Approx. Reason..

[9]  Heinz Wörn,et al.  Robot Manipulation of Deformable Objects: Advanced Manufacturing , 2000 .

[10]  T. Fukuda,et al.  Manipulation of deformable linear objects using knot invariants to classify the object condition based on image sensor information , 2006, IEEE/ASME Transactions on Mechatronics.

[11]  Rolf Isermann,et al.  Preface to the special section of papers on supervision, fault detection and diagnosis of technical systems , 1997 .

[12]  Rolf Isermann,et al.  Model-based fault-detection and diagnosis - status and applications , 2004, Annu. Rev. Control..

[13]  Rolf Isermann,et al.  Closed Loop Fault Diagnosis Based on a Nonlinear Process Model and Automatic Fuzzy Rule Generation , 1997 .

[14]  Heinz Wörn,et al.  Robot Manipulation of Deformable Objects: Advanced Manufacturing , 2000 .

[15]  Peter Loborg.  Error Recovery in Automation - An Overview , 1994 .

[16]  Gwi-Tae Park,et al.  A design scheme for a hierarchical fuzzy pattern matching classifier and its application to the tire tread pattern recognition , 1994, CVPR 1994.