A deep reinforcement learning based multi-criteria decision support system for optimizing textile chemical process

Abstract Textile manufacturing is a typical traditional industry involving high complexity in interconnected processes with limited capacity on the application of modern technologies. Decision-making in this domain generally takes multiple criteria into consideration, which usually arouses more complexity. To address this issue, the present paper proposes a decision support system that combines the intelligent data-based models of random forest (RF) and a human knowledge-based multi-criteria structure of analytical hierarchical process (AHP) in accordance with the objective and the subjective factors of the textile manufacturing process. More importantly, the textile chemical manufacturing process is described as the Markov decision process (MDP) paradigm, and a deep reinforcement learning scheme, the Deep Q-networks (DQN), is employed to optimize it. The effectiveness of this system has been validated in a case study of optimizing a textile ozonation process, showing that it can better master the challenging decision-making tasks in textile chemical manufacturing processes.

[1]  Xianyi Zeng,et al.  Modeling color fading ozonation of reactive-dyed cotton using the Extreme Learning Machine, Support Vector Regression and Random Forest , 2020, Textile Research Journal.

[2]  Ceyhun Araz,et al.  A Multicriteria Decision Aid Approach on Navel Selection Problem for Rotor Spinning , 2006 .

[3]  Kenji Suzuki,et al.  Artificial Neural Networks - Industrial and Control Engineering Applications , 2011 .

[4]  Ludovic Koehl,et al.  Integration of human knowledge and measured data for optimization of fabric hand , 2004, Int. J. Gen. Syst..

[5]  J. Dyer.  Remarks on the analytic hierarchy process , 1990 .

[6]  Abhijit Majumdar,et al.  Determination of quality value of cotton fibre using hybrid AHP-TOPSIS method of multi-criteria decision-making , 2005 .

[7]  L. Boullart,et al.  Optimizing the Fiber-to-Yarn Production Process with a Combined Neural Network/Genetic Algorithm Approach , 1997 .

[8]  Xianyi Zeng,et al.  AI for Apparel Manufacturing in Big Data Era: A Focus on Cutting and Sewing , 2018 .

[9]  Daniel J. Power,et al.  Decision Support Systems: A Historical Overview , 2008 .

[10]  Enrico Zio,et al.  Reinforcement learning for microgrid energy management , 2013 .

[11]  Mohsen Shanbeh,et al.  An Intelligent Model to Predict Breaking Strength of Rotor Spun Yarns Using Gene Expression Programming , 2012 .

[12]  Enrico Zio,et al.  A reinforcement learning framework for optimal operation and maintenance of power grids , 2019, Applied Energy.

[13]  Morched Cheikhrouhou,et al.  Multi-criteria decision making in workforce choice using AHP, WSM and WPM , 2018, The Journal of The Textile Institute.

[14]  Cenk Sahin,et al.  The prediction of quality characteristics of cotton/elastane core yarn using artificial neural networks and support vector machines , 2020 .

[15]  Abhijit Majumdar,et al.  Navel selection for rotor spinning denim fabrics using a multi-criteria decision-making process , 2010 .

[16]  Lenz Belzner,et al.  Optimization of global production scheduling with deep reinforcement learning , 2018 .

[17]  Anindya Ghosh,et al.  Selection of Handloom Fabrics for Summer Clothing Using Multi-Criteria Decision Making Techniques , 2015 .

[18]  T. Saaty.  How to Make a Decision: The Analytic Hierarchy Process , 1990 .

[19]  B. Alsberg,et al.  A quantitative structure-property relationship study of the photovoltaic performance of phenothiazine dyes , 2015 .

[20]  M. Bohanec,et al.  The Analytic Hierarchy Process , 2004 .

[21]  Laijiu Zheng,et al.  Bio‐degumming optimization parameters of kenaf based on a neural network model , 2010 .

[22]  Anindya Ghosh,et al.  Forecasting of Cotton Yarn Properties Using Intelligent Machines , 2010 .

[23]  T. P. Imthias Ahamed,et al.  Reinforcement Learning Solution for Unit Commitment Problem through Pursuit Method , 2009 .

[24]  J. Mwasiagi,et al.  The use of hybrid algorithms to improve the performance of yarn parameters prediction models , 2012, Fibers and Polymers.

[25]  Seung Ho Hong,et al.  A Dynamic pricing demand response algorithm for smart grid: Reinforcement learning approach , 2018, Applied Energy.

[26]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[27]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[28]  Heeyoung Kim,et al.  A new metric of absolute percentage error for intermittent demand forecasts , 2016 .

[29]  Kenneth O. Stanley,et al.  Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning , 2017, ArXiv.

[30]  Danying Zuo,et al.  The effect of denim color fading ozonation on yarns , 2018 .

[31]  Evangelos Triantaphyllou,et al.  A computational evaluation of the original and revised analytic hierarchy process , 1994 .

[32]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[33]  Rupal Rana,et al.  Dynamic pricing policies for interdependent perishable products or services using reinforcement learning , 2015, Expert Syst. Appl..

[34]  Ali Hamzeh,et al.  Using reinforcement learning to find an optimal set of features , 2013, Comput. Math. Appl..

[35]  Javier García,et al.  Reinforcement learning for pricing strategy optimization in the insurance industry , 2019, Eng. Appl. Artif. Intell..

[36]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[37]  Danying Zuo,et al.  Color fading of reactive-dyed cotton using UV-assisted ozonation , 2018, Ozone: Science & Engineering.

[38]  T. Das,et al.  A Reinforcement Learning Model to Assess Market Power Under Auction-Based Energy Pricing , 2007, IEEE Transactions on Power Systems.

[39]  Mehmet Dayik,et al.  Prediction of Yarn Properties Using Evaluation Programing , 2009 .

[40]  Anindya Ghosh,et al.  Prediction of cotton yarn properties using support vector machine , 2010 .

[41]  Jianguo Yang,et al.  Quality Prediction in Complex Industrial Process with Support Vector Machine and Genetic Algorithm Optimization: A Case Study , 2012 .

[42]  Kikuo Fujimura,et al.  Tactical Decision Making for Lane Changing with Deep Reinforcement Learning , 2017 .

[43]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[44]  Anindya Ghosh,et al.  Yarn engineering using hybrid artificial neural network-genetic algorithm model , 2013, Fibers and Polymers.

[45]  Anindya Ghosh,et al.  Optimization of woven fabric parameters for ultraviolet radiation protection and comfort using artificial neural network and genetic algorithm , 2016, Neural Computing and Applications.

[46]  Xi Chen,et al.  Evolution Strategies as a Scalable Alternative to Reinforcement Learning , 2017, ArXiv.

[47]  Xianyi Zeng,et al.  Study the effect of operating parameters and intrinsic features of yarn and fabric on thermal conductivity of stretch knitted fabrics using artificial intelligence system , 2014, Fibers and Polymers.

[48]  Dong-Joong Kang,et al.  Fast defect detection for various types of surfaces using random forest with VOV features , 2015 .

[49]  Zhenglei He,et al.  Production cost optimization of enzyme washing for indigo dyed cotton denim by combining Kriging surrogate with differential evolution algorithm , 2020 .

[50]  Anindya Ghosh,et al.  Modelling, optimization and decision making techniques in designing of functional clothing , 2011 .

[51]  Danying Zuo,et al.  Effects of color fading ozonation on the color yield of reactive-dyed cotton , 2019, Dyes and Pigments.

[52]  Nolan Etters,et al.  Advances In Indigo Dyeing: Implications for the Dyer, Apparel Manufacturer and Environment , 1995 .

[53]  Carl-Johan Hoel,et al.  Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[54]  Prasenjit Chatterjee,et al.  Cotton Fabric Selection Using a Grey Fuzzy Relational Analysis Approach , 2018, Journal of The Institution of Engineers (India): Series E.

[55]  Long-Ji Lin,et al.  Reinforcement learning for robots using neural networks , 1992 .

[56]  Arkady Borisov,et al.  Markov decision process in the problem of dynamic pricing policy , 2011, Automatic Control and Computer Sciences.

[57]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[58]  Ali Hasanbeigi,et al.  A Review of Energy Use and Energy Efficiency Technologies for the Textile Industry , 2012 .

[59]  Anindya Ghosh,et al.  Advanced Optimization and Decision-Making Techniques in Textile Manufacturing , 2019 .

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

[61]  Abhijit Majumdar,et al.  Modelling and prediction of antibacterial activity of knitted fabrics made from silver nanocomposite fibres using soft computing approaches , 2019, Neural Computing and Applications.