Creation of Digital Twins by Combining Fuzzy Rules with Artificial Neural Networks

The rise of digital twins in the manufacturing industry is accompanied by new possibilities, like process automation and condition monitoring, real time simulations and quality and maintenance prediction are just a few advantages which can be realized. This paper takes a novel approach by extracting the fundamental knowledge of a data set from a production process and mapping it to an expert fuzzy rule set. Afterwards, new fundamental augmented data is generated by exploring the feature space of the previously generated fuzzy rule set. At the same time, a high number of artificial neural network (ANN) models with different hyperparameter configurations are created. The best models are chosen, in line with the idea of survival of the fittest, and improved with the additional training data sets, generated by the fuzzy rule simulation. It is shown that ANN models can be improved by adding fundamental knowledge represented by the discovered fuzzy rules. Those models can represent digitized machines as digital twins. The architecture and effectiveness of the digital twin is evaluated within an industry 4.0 use case.

[1]  A. T. Abbas,et al.  Prediction of Cutting Conditions in Turning AZ61 and Parameters Optimization Using Regression Analysis and Artificial Neural Network , 2018 .

[2]  A. Asuncion,et al.  UCI Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences , 2007 .

[3]  Marco Sepulveda,et al.  A Review and Methodology Development for Remaining Useful Life Prediction of Offshore Fixed and Floating Wind turbine Power Converter with Digital Twin Technology Perspective , 2018, 2018 2nd International Conference on Green Energy and Applications (ICGEA).

[4]  George Percivall,et al.  Using big data analytics and IoT principles to keep an eye on underground infrastructure , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[5]  Katharina Morik,et al.  Stability prediction in milling processes using a simulation-based Machine Learning approach , 2018 .

[6]  Haibin Chen,et al.  Deep neural network for manufacturing quality prediction , 2017, 2017 Prognostics and System Health Management Conference (PHM-Harbin).

[7]  Michael R. Berthold,et al.  Mixed fuzzy rule formation , 2003, Int. J. Approx. Reason..

[8]  Huizhong Yang,et al.  Iterative learning fault diagnosis algorithm for non-uniform sampling hybrid system , 2017, IEEE/CAA Journal of Automatica Sinica.

[9]  Luis Alberto Rodríguez-Picón,et al.  Using regression models for predicting the product quality in a tubing extrusion process , 2018, Journal of Intelligent Manufacturing.

[10]  Abdulmotaleb El Saddik,et al.  Digital Twins: The Convergence of Multimedia Technologies , 2018, IEEE MultiMedia.

[11]  Seokho Kang,et al.  Joint modeling of classification and regression for improving faulty wafer detection in semiconductor manufacturing , 2018, J. Intell. Manuf..

[12]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[13]  Marc Priggemeyer,et al.  Experimentable Digital Twins—Streamlining Simulation-Based Systems Engineering for Industry 4.0 , 2018, IEEE Transactions on Industrial Informatics.

[14]  Jiujun Cheng,et al.  Dendritic Neuron Model With Effective Learning Algorithms for Classification, Approximation, and Prediction , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[15]  Miran Brezocnik,et al.  A comparison of machine learning methods for cutting parameters prediction in high speed turning process , 2016, Journal of Intelligent Manufacturing.

[16]  He Zhang,et al.  Digital Twin in Industry: State-of-the-Art , 2019, IEEE Transactions on Industrial Informatics.

[17]  Yan Xu,et al.  A Digital-Twin-Assisted Fault Diagnosis Using Deep Transfer Learning , 2019, IEEE Access.

[18]  Fei Tao,et al.  Digital Twin and Big Data Towards Smart Manufacturing and Industry 4.0: 360 Degree Comparison , 2018, IEEE Access.

[19]  Fei-Yue Wang,et al.  From parallel plants to smart plants: intelligent control and management for plant growth , 2017, IEEE/CAA Journal of Automatica Sinica.

[20]  A. A. Malozemov,et al.  Digital Twins Technology for Internal Combustion Engines Development , 2018, 2018 Global Smart Industry Conference (GloSIC).

[21]  Yuan He,et al.  From Surveillance to Digital Twin: Challenges and Recent Advances of Signal Processing for Industrial Internet of Things , 2018, IEEE Signal Processing Magazine.

[22]  Meng Zhang,et al.  Digital Twin Shop-Floor: A New Shop-Floor Paradigm Towards Smart Manufacturing , 2017, IEEE Access.

[23]  Emilia Sipos,et al.  Failure analysis and prediction using neural networks in the chip manufacturing process , 2017, 2017 40th International Spring Seminar on Electronics Technology (ISSE).

[24]  George Panoutsos,et al.  An ensemble data-driven fuzzy network for laser welding quality prediction , 2017, 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[25]  Wilfried Sihn,et al.  Digital Twin in manufacturing: A categorical literature review and classification , 2018 .

[26]  Guan Tianyi,et al.  Research on the Predicting Model of Convenience Store Model Based on Digital Twins , 2018, 2018 International Conference on Smart Grid and Electrical Automation (ICSGEA).

[27]  Fei Tao,et al.  Digital twin modeling method for CNC machine tool , 2018, 2018 IEEE 15th International Conference on Networking, Sensing and Control (ICNSC).

[28]  Pan Su,et al.  Aberystwyth University Induction of accurate and interpretable fuzzy rules from preliminary crisp representation , 2018 .

[29]  Xiaochao Li,et al.  A Genetic Algorithm Based Fuzzy Inference System for Pattern Classification and Rule Extraction , 2018, International Journal of Engineering & Technology.

[30]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[31]  Jiajun Wang,et al.  Parameter optimization of interval Type-2 fuzzy neural networks based on PSO and BBBC methods , 2019, IEEE/CAA Journal of Automatica Sinica.

[32]  Manuel Paul,et al.  Keeping the digital twin up-to-date — Process monitoring to identify changes in a plant , 2018, 2018 IEEE International Conference on Industrial Technology (ICIT).

[33]  Valeriy Vyatkin,et al.  Automatic Generation of a Simulation-Based Digital Twin of an Industrial Process Plant , 2018, IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society.