Optimal sensor distribution in multi-station assembly processes for maximal variance detection capability

Recent advances in sensor technology now allow manufacturers to distribute multiple sensors in multi-station assembly processes. A distributed sensor system enables the continual monitoring of manufactured products and greatly facilitates the determination of the underlying process variation sources that cause product quality defects. This paper addresses the problem of optimally distributing sensors in a multi-station assembly process to achieve a maximal variance detection capability. A sensitivity index is proposed for characterizing the detection ability of process variance components and the optimization problem for sensor distribution is formulated for a multi-station assembly process. A data-mining-guided evolutionary method is devised to solve this non-linear optimization problem. The data-mining-guided method demonstrates a considerable improvement compared to the existing alternatives. Guidance on practical issues such as the interpretation of the rules generated by the data mining method and how many sensors are required are also provided.

[1]  Darek Ceglarek,et al.  Sensor optimization for fault diagnosis in single fixture systems : A methodology , 1999 .

[2]  Yu Ding,et al.  A survey of inspection strategy and sensor distribution studies in discrete-part manufacturing processes , 2006 .

[3]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[4]  Darek Ceglarek,et al.  Sensor location optimization for fault diagnosis in multi-fixture assembly systems , 1998 .

[5]  Feng Niu,et al.  Distributed Sensing for Quality and Productivity Improvements , 2006, IEEE Transactions on Automation Science and Engineering.

[6]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[7]  Yu Ding,et al.  MODELING AND DIAGNOSIS OF MULTISTAGE MANUFACTURING PROCESSES: PART I - STATE SPACE MODEL , 2000 .

[8]  Darek Ceglarek,et al.  Sensor Optimization for Fault Diagnosis in Multi-Fixture Assembly Systems With Distributed Sensing , 2000 .

[9]  Olvi L. Mangasarian,et al.  Mathematical Programming in Neural Networks , 1993, INFORMS J. Comput..

[10]  Jionghua Jin,et al.  State Space Modeling of Sheet Metal Assembly for Dimensional Control , 1999 .

[11]  Jaime A. Camelio,et al.  Modeling Variation Propagation of Multi-Station Assembly Systems With Compliant Parts , 2003 .

[12]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[13]  Jaime A. Camelio,et al.  Sensor Placement for Effective Diagnosis of Multiple Faults in Fixturing of Compliant Parts , 2005 .

[14]  Darek Ceglarek,et al.  Dimensional variation reduction for automotive body assembly , 1995 .

[15]  Haym Hirsh,et al.  Learning to set up numerical optimizations of engineering designs , 1998 .

[16]  Abhyuday Mandal,et al.  SELC: Sequential Elimination of Level Combinations by Means of Modified Genetic Algorithms , 2006, Technometrics.

[17]  Michael Jackson,et al.  Optimal Design of Experiments , 1994 .

[18]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[19]  Andreas Karlsson,et al.  Matrix Analysis for Statistics , 2007, Technometrics.

[20]  Jun Ni,et al.  Measurement Scheme Synthesis in Multi-Station Machining Systems , 2004 .

[21]  Jun Ni,et al.  Dimensional Errors of Fixtures, Locating and Measurement Datum Features in the Stream of Variation Modeling in Machining , 2003 .

[22]  Haym Hirsh,et al.  Learning to set up numerical optimizations of engineering designs , 1998, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[23]  Qiang Huang,et al.  Part Dimensional Error and Its Propagation Modeling in Multi-Operational Machining , 2003 .

[24]  Yu Ding,et al.  Optimal Engineering System Design Guided by Data-Mining Methods , 2005, Technometrics.

[25]  Arnold J. Stromberg,et al.  Number-theoretic Methods in Statistics , 1996 .

[26]  Anne-Lise Huyet,et al.  Optimization and analysis aid via data-mining for simulated production systems , 2006, Eur. J. Oper. Res..

[27]  Ryszard S. Michalski,et al.  LEARNABLE EVOLUTION MODEL: Evolutionary Processes Guided by Machine Learning , 2004, Machine Learning.

[28]  Michael Yu Wang,et al.  Locator and Sensor Placement for Automated Coordinate Checking Fixtures , 1998, Manufacturing Science and Engineering.

[29]  David E. Goldberg,et al.  The parameter-less genetic algorithm in practice , 2004, Inf. Sci..

[30]  Qiang Huang,et al.  State space modeling of dimensional variation propagation in multistage machining process using differential motion vectors , 2003, IEEE Trans. Robotics Autom..

[31]  Darek Ceglarek,et al.  Fixture Failure Diagnosis for Autobody Assembly Using Pattern Recognition , 1996 .

[32]  Dariusz Ceglarek,et al.  Diagnosability Analysis of Multi-Station Manufacturing Processes , 2002 .

[33]  Yu Ding,et al.  Optimal sensor distribution for variation diagnosis in multistation assembly processes , 2003, IEEE Trans. Robotics Autom..

[34]  Yu Ding,et al.  Optimal coordinate sensor placements for estimating mean and variance components of variation sources , 2005 .