A simulation-based quality variance control system for the environment-sensitive process manufacturing industry

Optimizing the process parameters with respect to the future environmental conditions is an immediate challenge for environment-sensitive process manufacturing industry to achieve more consistent production quality. In this paper, we propose a simulation-based quality variance control system consisted of three core components: an indoor environment calibration module, a quality prediction module and a simulation engine. We then demonstrate the use of this system by analyzing a typical manufacturing process consisted of four sub-processes. The studies show that the proposed system can achieve better performances by integrating a future indoor environment calibration module than that of without such module. In addition, the simulation-based method can provide more acceptable outcome which outperforms the collaborative filtering algorithm. Such system is feasible to be applied in real industry scenarios which are sensitive to environmental changes to precisely control the quality variances.

[1]  Fred Spiring,et al.  Introduction to Statistical Quality Control , 2007, Technometrics.

[2]  Cliff T. Ragsdale,et al.  Combining a neural network with a genetic algorithm for process parameter optimization , 2000 .

[3]  Miao He,et al.  A collaborative filtering algorithm to control the quality variance in an environment-sensitive process manufacturing industry , 2017, 2017 IEEE 2nd International Conference on Cloud Computing and Big Data Analysis (ICCCBDA).

[4]  Bertil Thomas,et al.  Artificial neural network models for indoor temperature prediction: investigations in two buildings , 2006, Neural Computing and Applications.

[5]  Young Whan Park,et al.  Parameter optimization using a regression model and fitness function in laser welding of aluminum alloys for car bodies , 2011 .

[6]  C. Willmott,et al.  Ambiguities inherent in sums-of-squares-based error statistics , 2009 .

[7]  E. H. Mathews,et al.  Building and environment—The way forward , 1996 .

[8]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[9]  Bahram Moshfegh,et al.  Numerical predictions of indoor climate in large industrial premises. A comparison between different k–ε models supported by field measurements , 2007 .

[10]  Jeffrey S. Smith,et al.  Simulation for manufacturing system design and operation: Literature review and analysis , 2014 .

[11]  Li Shun-ying Literature Review and Analysis of Bilingual Teaching , 2006 .