A knowledge-based system for numerical design of experiments processes in mechanical engineering

Abstract This paper describes a specific knowledge-based system (KBS) to assist designers in configuring numerical design of experiments (NDoE) processes efficiently. NDoE processes are applied in product design to improve the quality of product, by taking into account variabilities and uncertainties. NDoE processes are defined by various and complex methodologies to achieve several objectives, as optimization, surrogate modeling or sensitivity analysis. On the other hand, NDoE processes may demand huge computing resources to execute hundreds simulations, and also advanced expert knowledge to set the best configuration amongst numerous possibilities. Designers aim to obtain most useful results with a minimal computational cost as soon as possible. Thus, the configuration step must be as fast as possible, and it must lead to an efficient combination of complex methods, algorithms and hyper-parameters, to obtain valuable information on the product. The proposed KBS and its inference engine, a bayesian network, is detailed and applied to a product developed by automotive industry. The KBS propose new efficient configurations to achieve designers' goal. This application shorten the configuration step of the NDoE process, and enables designers to use more complex methods. It also allows designers to capitalize knowledge and learn from each past NDoE process.

[1]  Martin Davies,et al.  Knowledge (Explicit, Implicit and Tacit): Philosophical Aspects , 2015 .

[2]  N. R. Sakthivel,et al.  Vibration based fault diagnosis of monoblock centrifugal pump using decision tree , 2010, Expert Syst. Appl..

[3]  Joaquin Vanschoren,et al.  Exposé: An ontology for data mining experiments , 2010 .

[4]  Concha Bielza,et al.  Comparison of Bayesian networks and artificial neural networks for quality detection in a machining process , 2009, Expert Syst. Appl..

[5]  Dimitris Kiritsis,et al.  A review of knowledge-based expert systems for process planning. Methods and problems , 1995 .

[6]  Hadi Salehi,et al.  Emerging artificial intelligence methods in structural engineering , 2018, Engineering Structures.

[7]  Novruz Allahverdi,et al.  Artificial neural network and fuzzy expert system comparison for prediction of performance and emission parameters on a gasoline engine , 2011, Expert Syst. Appl..

[8]  M. Sergent,et al.  Constructing space-filling designs using an adaptive WSP algorithm for spaces with constraints , 2014 .

[9]  H. Akaike.  Statistical predictor identification , 1970 .

[10]  Michal Tkác,et al.  Artificial neural networks in business: Two decades of research , 2016, Appl. Soft Comput..

[11]  P. Spirtes,et al.  Causation, prediction, and search , 1993 .

[12]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[13]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[14]  Julien Le Duigou,et al.  Simulation Data Management for Adaptive Design Of Experiment , 2015 .

[15]  Hong Wan,et al.  Work smarter, not harder: A tutorial on designing and conducting simulation experiments , 2012, 2015 Winter Simulation Conference (WSC).

[16]  Alain Bernard,et al.  Product Lifecycle Management Model for Design Information Management in Mechanical Field , 2011 .

[17]  Eusebio Valero,et al.  A review on design of experiments and surrogate models in aircraft real-time and many-query aerodynamic analyses , 2018 .

[18]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[19]  Barry Smyth,et al.  Retrieval, reuse, revision and retention in case-based reasoning , 2005, The Knowledge Engineering Review.

[20]  Bojan Dolsak,et al.  Finite element mesh design expert system , 2002, Knowl. Based Syst..

[21]  G. V. Kass.  An Exploratory Technique for Investigating Large Quantities of Categorical Data , 1980 .

[22]  Ross D King,et al.  An ontology of scientific experiments , 2006, Journal of The Royal Society Interface.

[23]  William P. Wagner.  Trends in expert system development: A longitudinal content analysis of over thirty years of expert system case studies , 2017, Expert Syst. Appl..

[24]  Lian Ding,et al.  A contemporary study into the application of neural network techniques employed to automate CAD/CAM integration for die manufacture , 2009, Comput. Ind. Eng..

[25]  David J. Weiner.  Expert systems to aid in the formulation of hypotheses and design of experiments in biomedical research , 1992 .

[26]  Dimitris Kiritsis,et al.  Ontologies in the context of product lifecycle management: state of the art literature review , 2015 .

[27]  Agnar Aamodt,et al.  Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches , 1994, AI Commun..

[28]  Nassim Boudaoud,et al.  Modeling Pollutant Emissions of Diesel Engine based on Kriging Models: a Comparison between Geostatistic and Gaussian Process Approach , 2012 .

[29]  Abid Ali Khan,et al.  Case Based Reasoning Support for Adaptive Finite Element Analysis: Mesh Selection for an Integrated System , 2014 .

[30]  Genki Yagawa,et al.  Computational mechanics enhanced by deep learning , 2017 .

[31]  Wang Hu,et al.  Optimization of sheet metal forming processes by adaptive response surface based on intelligent sampling method , 2008 .

[32]  Can Cui,et al.  A recommendation system for meta-modeling: A meta-learning based approach , 2016, Expert Syst. Appl..

[33]  Thomas Bauernhansl,et al.  Expert Systems in Special Machinery: Increasing the Productivity of Processes in Commissioning☆ , 2017 .

[34]  Kimiz Dalkir,et al.  Knowledge Management in Theory and Practice , 2005 .

[35]  Edoardo Patelli,et al.  General purpose software for efficient uncertainty management of large finite element models , 2012, Finite elements in analysis and design : the international journal of applied finite elements and computer aided engineering.

[36]  Juan Alfonso Lara,et al.  Data preparation for KDD through automatic reasoning based on description logic , 2014, Inf. Syst..

[37]  Marco Scutari,et al.  Learning Bayesian Networks with the bnlearn R Package , 2009, 0908.3817.

[38]  Frederick T. Chen.  A personal computer based expert system framework for the design of experiments , 1991 .

[39]  Bill Martin,et al.  LIS professionals and knowledge management: some recent perspectives , 2006 .

[40]  Mohmmad Hanafy,et al.  Co-design of Products and Systems Using a Bayesian Network☆ , 2014 .

[41]  Shailendra Kumar,et al.  A knowledge based system for automated design of deep drawing die for axisymmetric parts , 2014, Expert Syst. Appl..

[42]  Debora Slanzi,et al.  Evolutionary Bayesian Network design for high dimensional experiments , 2014 .

[43]  W. Scott Spangler,et al.  DEXPERT: an expert system for the design of experiments , 1992 .

[44]  Benoît Eynard,et al.  An ontology for numerical design of experiments processes , 2018, Comput. Ind..

[45]  Andy J. Keane,et al.  Recent advances in surrogate-based optimization , 2009 .

[46]  Anders L. Madsen,et al.  Parallelisation of the PC Algorithm , 2015, CAEPIA.

[47]  Seda Sahin,et al.  Hybrid expert systems: A survey of current approaches and applications , 2012, Expert Syst. Appl..

[48]  Sahar Bayat,et al.  Comparison of Bayesian Network and Decision Tree Methods for Predicting Access to the Renal Transplant Waiting List , 2009, MIE.

[49]  Claudio Urrea,et al.  Development of an expert system to select materials for the main structure of a transfer crane designed for disabled people , 2015, Expert Syst. Appl..

[50]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[51]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[52]  Filip De Turck,et al.  Evolutionary Model Type Selection for Global Surrogate Modeling , 2009, J. Mach. Learn. Res..

[53]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[54]  J. Ross Quinlan,et al.  Improved Use of Continuous Attributes in C4.5 , 1996, J. Artif. Intell. Res..

[55]  Iftekhar A. Karimi,et al.  Design of computer experiments: A review , 2017, Comput. Chem. Eng..

[56]  Fabrice Gaudier.  URANIE: The CEA/DEN Uncertainty and Sensitivity platform , 2010 .

[57]  Hui Liu,et al.  A new hybrid method for learning bayesian networks: Separation and reunion , 2017, Knowl. Based Syst..

[58]  B. Iooss,et al.  A Review on Global Sensitivity Analysis Methods , 2014, 1404.2405.