Diagnosis of the Failures of a Complex Industrial System by Neuro-Fuzzy Networks Optimized by a Genetic Algorithm (ANFIS-GA): A Case of the Franceville Brewery

Diagnosis of the Failures of a Complex Industrial System by Neuro-Fuzzy Networks Optimized by a Genetic Algorithm (ANFIS-GA): A Case of the Franceville Brewery

© 2023 by IJETT Journal
Volume-71 Issue-2
Year of Publication : 2023
Author : Ondo Boniface, Nyatte Steyve, Kombé Thimotée, Elé Perre
DOI : 10.14445/22315381/IJETT-V71I2P227

How to Cite?

Ondo Boniface, Nyatte Steyve, Kombé Thimotée, Elé Perre, "Diagnosis of the Failures of a Complex Industrial System by Neuro-Fuzzy Networks Optimized by a Genetic Algorithm (ANFIS-GA): A Case of the Franceville Brewery," International Journal of Engineering Trends and Technology, vol. 71, no. 2, pp. 236-248, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I2P227

Fault diagnosis in intricate industrial operations is a difficult task, especially in the African context, due to the stochastic interaction between symptoms and faults, a lot of inputs and outputs, and the difficulty of acquiring characteristic data (spectral study, sound, vibration, electrical quantities, etc.) of the operating state through specialized sensors. Furthermore, if this diagnosis is performed online, a fast time algorithm is required to account for the system's instantaneous changes. With the objective of reducing maintenance costs, improving productivity, and increasing machine availability, we develop an online fault diagnosis model for a dynamic process based on an adaptive neuro-fuzzy inference system (ANFIS) based on the production history and associated faults. This algorithm is optimized by the algorithm based on gene (GA) to learn the defect-production correlation of a brewery from historical production and process failure data. This method, based on the data, such as the format of bottles produced, daily production hours, number of manufactured bottles without defects per day, number of manufactured bottles with defects per day, and downtime of production subsystems, allows us to extract the data-driven defect-symptom correlation. Optimizing an ANFIS classifier for fault diagnosis reduces the computation time and increases accuracy, thus allowing the integration of newly identified faults in the process. In conclusion, the proposed model, based on GA-ANFIS, is tested on the process of the Franceville brewery in Gabon. The results on our dataset are better than other types of data from some studies according to their accuracy (88.97%), precision (89.23%), sensitivity (73.20%), and specificity (96.27%).

ANFIS, Complex industrial system, Diagnosis of the failures, Reliability, Optimization.

[1] David Satterthwaite, “The Links between Poverty and The Environment in Urban Areas of Africa, Asia, and Latin America,” The Annals of the American Academy of Political and Social Science, vol. 590, pp. 73-92, 2003.
[2] Syed A. Taqvi et al., “Multiple Fault Diagnosis in Distillation Column Using Multikernel Support Vector Machine,” Industrial & Engineering Chemistry Research, vol. 57, no. 43, pp. 14689-14706, 2018. Crossref, https://doi.org/10.1021/acs.iecr.8b03360
[3] Venkat Venkatasubramanian et al., “A Review of Process Fault Detection and Diagnosis: Part I: Quantitative Model-based Methods,” Computers & chemical engineering, vol. 27, no. 3, pp. 293-311, 2003. Crossref, https://doi.org/10.1016/S0098-1354(02)00160-6
[4] R. Isermann, and P. Balle, “Trends in the Application of Model-based Fault Detection and Diagnosis of Technical Processes,” Control engineering practice, vol. 5, no. 5, pp. 709-719, 1997. Crossref, https://doi.org/10.1016/S0967-0661(97)00053-1
[5] Jianhui Luo et al., “Model-based Prognostic Techniques [Maintenance Applications],” Proceedings AUTOTESTCON 2003. IEEE Systems Readiness Technology Conference, pp. 330-340, 2003. Crossref, https://doi.org/10.1109/AUTEST.2003.1243596
[6] L. Travé-Massuyès, and R. Milne, “Gas-turbine Condition Monitoring Using Qualitative Model-based Diagnosis,” IEEE Expert, vol. 12, no. 3, pp. 22-31, 1997. Crossref, https://doi.org/10.1109/64.590070
[7] P.M. Frank, “Analytical and Qualitative Model-based Fault Diagnosis – A Survey and Some New Results,” European Journal of control, vol. 2, no. 1, pp. 6-28, 1996. Crossref, https://doi.org/10.1016/S0947-3580(96)70024-9
[8] Cliff Joslyn, “A Possibilistic Approach to Qualitative Model-based Diagnosis,” Telematics and Informatics, vol. 11, no. 4, pp. 365-384, 1994. Crossref, https://doi.org/10.1016/0736-5853(94)90026-4
[9] Miao Mou, and Xiaoqiang Zhao, “Incipient Fault Detection and Diagnosis of Nonlinear Industrial Process with Missing Data,” Journal of the Taiwan Institute of Chemical Engineers, vol. 132, p. 104115, 2022. Crossref, https://doi.org/10.1016/j.jtice.2021.10.015
[10] Peng Xu et al., “Industrial Process Fault Detection and Diagnosis Framework Based on Enhanced Supervised Kernel Entropy Component Analysis,” Measurement, vol. 196, p. 111181, 2022. Crossref, https://doi.org/10.1016/j.measurement.2022.111181
[11] Alaa M. Morsy, Abd Elmoaty M. Abd Elmoaty, and Abdelrhman B. Harraz, “Predicting Mechanical Properties of Engineering Cementitious Composite Reinforced with PVA Using Artificial Neural Network,” Case Studies in Construction Materials, vol. 16, p. e00998, 2022. Crossref, https://doi.org/10.1016/j.cscm.2022.e00998
[12] Fredrick Mumali, “Artificial Neural Network-based Decision Support Systems in Manufacturing Processes: A Systematic Literature Review,” Computers & Industrial Engineering, vol. 165, p. 107964, 2022. Crossref, https://doi.org/10.1016/j.cie.2022.107964
[13] Nima Amini, and Qinqin Zhu, “Fault Detection and Diagnosis with a Novel Source-Aware Autoencoder and Deep Residual Neural Network,” Neurocomputing, vol. 488, pp. 618-633, 2022. Crossref, https://doi.org/10.1016/j.neucom.2021.11.067
[14] Ronny Francis Ribeiro Junior et al., “Fault Detection and Diagnosis in Electric Motors Using 1d Convolutional Neural Networks with Multi-channel Vibration Signals,” Measurement, vol. 190, p. 110759, 2022. Crossref, https://doi.org/10.1016/j.measurement.2022.110759
[15] Zhe Yang, Piero Baraldi, and Enrico Zio, “A Method for Fault Detection in Multi-component Systems Based on Sparse Autoencoderbased Deep Neural Networks,” Reliability Engineering & System Safety, vol. 220, p. 108278, 2022. Crossref, https://doi.org/10.1016/j.ress.2021.108278
[16] Hongtian Chen et al., “Fault Detection for Nonlinear Dynamic Systems with Consideration of Modeling Errors: A Data-driven Approach,” IEEE Transactions on Cybernetics, pp. 1-11, 2022. Crossref, https://doi.org/10.1109/TCYB.2022.3163301
[17] Shumei Chen, Jianbo Yu, and Shijin Wang, “One-dimensional Convolutional Neural Network-based Active Feature Extraction for Fault Detection and Diagnosis of Industrial Processes and its Understanding via Visualization,” ISA Transactions, vol. 122, pp. 424-443, 2022. Crossref, https://doi.org/10.1016/j.isatra.2021.04.042
[18] Alibek Kopbayev et al., “Fault Detection and Diagnosis to Enhance Safety in Digitalized Process System,” Computers & Chemical Engineering, vol. 158, p. 107609, 2022. Crossref, https://doi.org/10.1016/j.compchemeng.2021.107609
[19] Felix Ghislain Yem Souhe et al., “Fault Detection, Classification and Location in Power Distribution Smart Grid using Smart Meters Data,” Journal of Applied Science and Engineering, vol. 26, no. 1, pp. 23-34, 2023. Crossref, https://doi.org/10.6180/jase.202301_26(1).0003
[20] J.-S.R. Jang, “ANFIS: Adaptive-network-based Fuzzy Inference System,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 3, pp. 665-685, 1993. Crossref, https://doi.org/10.1109/21.256541
[21] Saeed Rajabi et al., “Fault Diagnosis in Industrial Rotating Equipment Based on Permutation Entropy, Signal Processing and Multi-output Neuro-fuzzy Classifier,” Expert systems with applications, vol. 206, p. 117754, 2022. Crossref, https://doi.org/10.1016/j.eswa.2022.117754
[22] Norazwan Md Nor, Mohd Azlan Hussain, and Che Rosmani Che Hassan, “Multi-scale Kernel Fisher Discriminant Analysis with Adaptive Neuro-fuzzy Inference System (ANFIS) in Fault Detection and Diagnosis Framework for Chemical Process Systems,” Neural Computing and Applications, vol. 32, pp. 9283-9297, 2020. Crossref, https://doi.org/10.1007/s00521-019-04438-9
[23] Choug Abdelkrim et al., “Detection and Classification of Bearing Faults in Industrial Geared Motors using Temporal Features and Adaptive Neuro-fuzzy Inference System,” Heliyon, vol. 5, no. 8, pe02046, 2019. Crossref, https://doi.org/10.1016/j.heliyon.2019.e02046
[24] Amar Kumar Verma, Aakruti Jain, and Radhika Sudha, “Neuro-fuzzy Classifier for Identification of Stator Winding Inter-turn Fault for Industrial Machine,” International conference on Modelling, Simulation and Intelligent Computing, pp. 101-110, 2020. Crossref, http://dx.doi.org/10.1007/978-981-15-4775-1_12
[25] Timothee Kombe, and Sandra Nzeneu, “Graphical Interfaces for Dynamic Supervision for Failures Prognosis using the AI-PLC Combinatorial Approach: The Case Study of Cameroon Breweries Mill,” International Journal of Advances in Scientific Research and Engineering, vol. 5, no. 10, pp. 7-16, 2019. Crossref, https://doi.org/10.31695/IJASRE.2019.33491
[26] Nyatte Steyve et al., “Optimized Real-time Diagnosis of Neglected Tropical Diseases by Automatic Recognition of Skin Lesions,” Informatics in Medicine Unlocked, vol. 33, p. 101078, 2022. Crossref, https://doi.org/10.1016/j.imu.2022.101078
[27] Mahdi Panahi et al., “Spatial Prediction of Landslide Susceptibility using Hybrid Support Vector Regression (SVR) and the Adaptive Neuro-fuzzy Inference System (ANFIS) with Various Metaheuristic Algorithms,” Science of the Total Environment, vol. 741, p. 139937, 2020. Crossref, https://doi.org/10.1016/j.scitotenv.2020.139937
[28] Aman Arora et al., “Optimization of State-of-the-art fuzzy-metaheuristic ANFIS-based Machine Learning Models for Flood Susceptibility Prediction Mapping in the Middle Ganga Plain, India,” Science of the Total Environment, vol. 750, p. 141565, 2021. Crossref, https://doi.org/10.1016/j.scitotenv.2020.141565
[29] Ibrahim M. El-Hasnony, Sherif I. Barakat, and Reham R. Mostafa, “Optimized ANFIS Model using Hybrid Metaheuristic Algorithms for Parkinson’s Disease Prediction in IoT Environment,” IEEE Access, vol. 8, pp. 119252-119270, 2020. Crossref, https://doi.org/10.1109/ACCESS.2020.3005614
[30] Hossein Moayedi et al., “Novel Hybrids of Adaptive Neuro-fuzzy Inference System (ANFIS) with Several Metaheuristic Algorithms for Spatial Susceptibility Assessment of Seismic-induced Landslide,” Geomatics, Natural Hazards and Risk, vol. 10, no. 1, pp. 1879-1911, 2019. Crossref, https://doi.org/10.1080/19475705.2019.1650126
[31] Sorin Nădăban, “Fuzzy Logic and Soft Computing-Dedicated to the Centenary of the Birth of Lotfi A. Zadeh (1921–2017),” Mathematics, vol. 10, no. 17, p. 3216, 2022. Crossref, https://doi.org/10.3390/math10173216
[32] Boris Brinzer, Amardeep Banerjee, and Michael Hauth, “Complexity Thinking and Cyber-Physical Systems,” SSRG International Journal of Industrial Engineering, vol. 4, no. 1, pp. 14-21, 2017. Crossref, https://doi.org/10.14445/23499362/IJIE-V4I1P103
[33] Panli Zhang et al., “A Genetic Algorithm with Jumping Gene and Heuristic Operators for Traveling Salesman Problem,” Applied Soft Computing, VOL. 127, P. 109339, 2022. Crossref, https://doi.org/10.1016/j.asoc.2022.109339
[34] Andrea Di Placido, Claudia Archetti, and Carmine Cerrone, “A Genetic Algorithm for the Close-enough Traveling Salesman Problem with Application to Solar Panels Diagnostic Reconnaissance,” Computers & Operations Research, vol. 145, p. 105831, 2022. Crossref, https://doi.org/10.1016/j.cor.2022.105831
[35] Vladimir Ilin et al., “A Hybrid Genetic Algorithm, List-based Simulated Annealing Algorithm, and Different Heuristic Algorithms for Travelling Salesman Problem,” Logic Journal of the IGPL, 2022. Crossref, https://doi.org/10.1093/jigpal/jzac028
[36] Monique Simplicio Viana, Rodrigo Colnago Contreras, and Orides Morandin Junior, “A New Frequency Analysis Operator for Population Improvement in Genetic Algorithms to Solve the Job Shop Scheduling Problem,” Sensors, vol. 22, no. 12, p. 4561, 2022. Crossref, https://doi.org/10.3390/s22124561
[37] Rui Li et al., “Two-stage Knowledge-driven Evolutionary Algorithm for Distributed Green Flexible Job Shop Scheduling with Type-2 Fuzzy Processing Time,” Swarm and Evolutionary Computation, vol. 74, p. 101139, 2022. Crossref, https://doi.org/10.1016/j.swevo.2022.101139
[38] Rui Li, Wenyin Gong, and Chao Lu, “Self-adaptive Multi-objective Evolutionary Algorithm for Flexible Job Shop Scheduling with Fuzzy Processing Time,” Computers & Industrial Engineering, vol. 168, p. 108099, 2022. Crossref, https://doi.org/10.1016/j.cie.2022.108099
[39] Bahman Arasteh, Mohammad Abdi, and Asgarali Bouyer, “Program Source Code Comprehension by Module Clustering using Combination of Discretized Gray Wolf and Genetic Algorithms,” Advances in Engineering Software, vol. 173, p. 103252, 2022. Crossref, https://doi.org/10.1016/j.advengsoft.2022.103252
[40] Selcuk Demir, and Emrehan Kutlug Şahin, “Liquefaction Prediction with Robust Machine Learning Algorithms (SVM, RF, and XGBoost) Supported by Genetic Algorithm-based Feature Selection and Parameter Optimization from the Perspective of Data Processing,” Environmental Earth Sciences, vol. 81, 2022. Crossref, https://doi.org/10.1007/s12665-022-10578-4
[41] Jose Brito, and Augusto Fadel, and Gustavo Semaan, “A Genetic Algorithm Applied to Optimal Allocation in Stratified Sampling,” Communications in Statistics-Simulation and Computation, vol. 51, no. 7, pp. 3714-3732, 2022. Crossref, https://doi.org/10.1080/03610918.2020.1722832
[42] Ying Lai et al., “Development of ANFIS Technique for Estimation of CO2 Solubility in Amino Acids and Study on Impact of Input Parameters,” Arabian Journal of Chemistry, vol. 15, no. 11, p. 104284, 2022. Crossref, https://doi.org/10.1016/j.arabjc.2022.104284
[43] Rana Muhammad Adnan et al., “Development of New Machine Learning Model for Streamflow Prediction: Case Studies in Pakistan,” Stochastic Environmental Research and Risk Assessment, vol. 36, pp. 999-1033, 2022. Crossref, https://doi.org/10.1007/s00477-021- 02111-z
[44] Samad Emamgholizadeh et al., “Prediction of Soil Cation Exchange Capacity using Enhanced Machine Learning Approaches in the Southern Region of the Caspian Sea,” Ain Shams Engineering Journal, vol. 14, no. 2, p. 101876, 2023. Crossref, https://doi.org/10.1016/j.asej.2022.101876
[45] Hossein Dehghanisanij et al., “A Hybrid Machine Learning Approach for Estimating the Water-use efficiency and Yield in Agriculture,” Scientific Reports, vol. 12, 2022. Crossref, https://doi.org/10.1038/s41598-022-10844-2
[46] VeenaKumari Adil, and Sanjay Kumar Singhai, “A Status Review of Different Industrial Drives,” SSRG International Journal of Electrical and Electronics Engineering, vol. 3, no. 3, pp. 1-9, 2016. Crossref, https://doi.org/10.14445/23488379/IJEEE-V3I3P101
[47] M. Akif Kunt, and Haluk Gunes, “Experimental Investigation of the Performance of Different Heat Exchanger Profiles in the Waste Heat Recovery System with Thermoelectric Generator for Automobile Exhaust Systems,” SSRG International Journal of Mechanical Engineering, vol. 4, no. 8, pp. 1-5, 2017. Crossref, https://doi.org/10.14445/23488360/IJME-V4I8P101
[48] G. Anitha et al., “A Survey of Security Issues in IIoT and Fault Identification using Predictive Analysis in Industry 4.0,” International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 99-108, 2022. Crossref, https://doi.org/10.14445/22315381/IJETTV70I12P211
[49] Nishant Jakhar, and Rainu Nandal, “Load and Delay Effective based Resource Allocation And Scheduling Model to Optimize Power Distribution in Smart Grid Network,” International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 67-75, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I12P208
[50] Techatat Buranaaudsawakul et al., “The Impact of Oversized Electrical Equipments on Energy Management of Thailand Department Stores,” International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 35-41, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I12P205
[51] Maamar Ali Saud AL Tobi et al.,“Machinery Faults Diagnosis using Support Vector Machine (SVM) and Naïve Bayes Classifiers,” International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 26-34, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I12P204
[52] Jian Zhou et al., “Performance Evaluation of Hybrid FFA-ANFIS and GA-ANFIS Models to Predict Particle Size Distribution of a Muck-pile After Blasting,” Engineering with computers, vol. 37, pp. 265-274, 2021. Crossref, https://doi.org/10.1007/s00366-019-00822-0