Virtual In-line Inspection for Function Verification in Serial Production by means of Artificial Intelligence

In high-tech production, companies often deal with the manufacture of assemblies with quality requirements close to the technological limits of manufacturing processes. The article shows an approach of a virtual in-line inspection, predicting the products functionality. An artificial neural network (ANN) fed with product characteristics and process data as well as the resulting functional fulfillment of the product is trained for virtual function prognosis. Through the preventive identification of defective products before the final assembly step, components can be recovered and returned to serial production. By optimizing the parameters of the ANN, incorrect classifications are reduced and the practical applicability is ensured. The approach is demonstrated in an industrial application in the automotive industry.

[1]  Kadir Aydin,et al.  Comparison of linear regression and artificial neural network model of a diesel engine fueled with biodiesel-alcohol mixtures , 2016 .

[2]  Robert Schmitt,et al.  Cognition-based self-optimisation of an automotive rear-axle-drive production process , 2010 .

[3]  Benjamin Haefner,et al.  Function-oriented measurements and uncertainty evaluation of micro-gears for lifetime prognosis , 2017 .

[4]  Yue-Shi Lee,et al.  Cluster-based under-sampling approaches for imbalanced data distributions , 2009, Expert Syst. Appl..

[5]  Benjamin Haefner,et al.  Optimization of selective assembly and adaptive manufacturing by means of cyber-physical system based matching , 2015 .

[6]  Benjamin Haefner,et al.  In-line Measurement Technology and Quality Control , 2019, Precision Manufacturing.

[7]  Benjamin Haefner,et al.  Meta-Model Based on Artificial Neural Networks for Tooth Root Stress Analysis of Micro-Gears , 2018 .

[8]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[9]  Benjamin Haefner,et al.  Function-Oriented Quality Control Strategies for High Precision Products , 2018 .

[10]  Stefano Petrò,et al.  Early cost estimation for tolerance verification , 2011 .

[11]  Giovanni Moroni,et al.  Inspection Strategies and Multiple Geometric Tolerances , 2013 .

[12]  Brett A. Lidbury,et al.  Enhancement of hepatitis virus immunoassay outcome predictions in imbalanced routine pathology data by data balancing and feature selection before the application of support vector machines , 2017, BMC Medical Informatics and Decision Making.

[13]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery in Databases , 1996, AI Mag..

[14]  Albert Weckenmann,et al.  Function-oriented method for the definition and verification of microstructured surfaces , 2013 .

[15]  Mehmet Çunkas,et al.  Modeling and prediction of surface roughness in turning operations using artificial neural network and multiple regression method , 2011, Expert Syst. Appl..

[16]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[17]  M. Mostafizur Rahman,et al.  Cluster Based Under-Sampling for Unbalanced Cardiovascular Data , 2013 .

[18]  Chih-Fong Tsai,et al.  Clustering-based undersampling in class-imbalanced data , 2017, Inf. Sci..

[19]  Nathalie Japkowicz,et al.  The class imbalance problem: A systematic study , 2002, Intell. Data Anal..

[20]  Aman Jantan,et al.  State-of-the-art in artificial neural network applications: A survey , 2018, Heliyon.