kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университет10.55452/1998-6688-2024-21-3-90-115kaz29-1372Research ArticleКОМПЬЮТЕРНЫЕ НАУКИCOMPUTER SCIENCEВЛИЯНИЕ ВЫБОРКИ ДАННЫХ НА РЕШЕНИЕ ЗАДАЧИ РАСПОЗНАВАНИЯ ОБРАЗОВ ДЛЯ ДИАГНОСТИКИ ПРОМЫШЛЕННОГО ОБОРУДОВАНИЯTHE INFLUENCE OF DATA SAMPLING ON SOLVING THE PROBLEM OF PATTERN RECOGNITION FOR DIAGNOSTICS OF INDUSTRIAL EQUIPMENThttps://orcid.org/0000-0002-5862-6415СамигулинаЗ. И.SamigulinaZ. I.

PhD, профессор 

050000, г. Алматы

PhD, Professor 

050000, Almaty

z.samigulina@kbtu.kzhttps://orcid.org/0009-0003-1734-8548БайкадамоваС. С.BaikadamovaS. S.

магистр 

050000, г. Алматы

Master student 

050000, Almaty

tassbulatova@gmail.comКазахстанско-Британский технический университетКазахстанKazakh-British Technical UniversityKazakhstan20240110202421390115Copyright © Самигулина З.И., Байкадамова С.С., 20242024Самигулина З.И., Байкадамова С.С.Samigulina Z.I., Baikadamova S.S.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/1372

Статья посвящена исследованию влияния выборки данных на прогностическую способность классификатора при диагностике промышленного оборудования. Рассматривались различные типы выборок данных, такие как простая случайная выборка, кластерная и систематизированная выборка. По результатам различных выборок данных были построены классификаторы на основе методов роя частиц и ансамблевых моделей (бэггинг и тип с голосованием). Наилучшие результаты показала стратегия ансамблевого моделирования с голосованием, которая сочетает в себе прогнозирование на основе нейронной сети, деревьев с градиентным усилением и наивных Байесовских моделей. Наилучшие результаты были достигнуты с использованием систематического метода выборки данных и стратегии ансамблевого моделирования с голосованием, которая сочетает в себе прогнозирование на основе нейронной сети, деревьев с градиентным усилением и наивных моделей Байеса: accuracy 93,6%; classification error 8%; recall 94,32%; precision 93,87%. Полученная лучшая стратегия диагностики оборудования на основе выборки данных и ансамблевой модели была использована для реализации в технологии FMEA (Failure Mode and Effects Analysis) с целью получения улучшенной и адаптированной версии для работы с большими данными.

With the sophisticated technology that modern industrial organizations are equipped with, state prediction and diagnostics are essential duties. The current research aims to develop a more accurate modified artificial intelligence system for industrial equipment diagnostics in the oil and gas industry. Researching faulty signals and processing methods utilized by equipment in the oil and gas industry, as well as assessing the advantages and disadvantages of different signal extraction strategies, are the first steps in the process. The second is the application of artificial intelligence to decision-making and equipment defect detection. This method widely used by the oil and gas sectors to lower equipment failure rates. The recommended diagnostic system helps organizations reduce the financial risks associated with equipment defects by increasing production dependability, enabling for maintenance planning, predicting probable failures, and expediting equipment repairs. The article is devoted to the study of the data sampling influence on the classifier’s predictive ability in diagnosing of the industrial equipment. Various types of data samples were considered, such as: simple random sample, cluster sample, systematic sample. According to the results of listed data samples were built classifiers based on particle swarm optimization and ensemble models (bagging and voting type). The best results were achieved using the systematic sampled dataset and an ensemble modeling strategy with voting, which combines forecasting based on a neural net, gradient boosted trees and naive Bayes models: accuracy 93.6%; classification error 8%; recall 94.32%; precision 93.87%. The resulting best strategy for diagnosing equipment based on data sampling and an ensemble model was used for implementation in FMEA (Failure Mode and Effects Analysis) technology in order to obtain an improved version, which is adapted for working with big data.

диагностика промышленного оборудованиявыборка данныхпростая случайная выборкакластерная выборкасистематическая выборкаоптимизация роя частицансамблевые методыулучшенная модель FMEAindustrial equipment diagnosticsdata samplingsimple random samplecluster samplesystematic sampleparticle swarm optimizationensemble methodsFMEA improved modelThis research has been funded by the Science Committee of the Ministry of Education and Science of the Republic Kazakhstan (Grant No. AP23486386).ReferencesSamigulina G., Samigulina Z. Diagnostics of industrial equipment and faults prediction based on modified algorithms of artificial immune systems. Journal of Intelligent Manufacturing, Springer, 2022, vol. 33, pp.1433–1450.Samigulina G., Samigulina Z. Diagnostics of industrial equipment and faults prediction based on modified algorithms of artificial immune systems. Journal of Intelligent Manufacturing, Springer, 2022, vol. 33, pp.1433–1450.Samigulina G., Samigulina Z. Biologically Inspired Unified Artificial Immune System for Industrial Equipment Diagnostic. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, 2023, vol 13811. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_7.Samigulina G., Samigulina Z. Biologically Inspired Unified Artificial Immune System for Industrial Equipment Diagnostic. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2022. Lecture Notes in Computer Science, 2023, vol 13811. Springer, Cham. https://doi.org/10.1007/978-3-031-25891-6_7.Elton P De Souza, Lis Moura, Thiago Barroso Costa, João Lucas Lobato Soares. Convolutional neural networks for pattern-based fault diagnosis in low-rotation equipment. International congress of mechanical engineering, 2023.Elton P De Souza, Lis Moura, Thiago Barroso Costa, João Lucas Lobato Soares. Convolutional neural networks for pattern-based fault diagnosis in low-rotation equipment. International congress of mechanical engineering, 2023.Leandro Ventricci, Ronny Francis Ribeiro Junior, Guilherme Ferreira Gomes. Motor fault classification using hybrid short-time Fourier transform and wavelet transform with vibration signal and convolutional neural network. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2024, vol. 6, p. 46.Leandro Ventricci, Ronny Francis Ribeiro Junior, Guilherme Ferreira Gomes. Motor fault classification using hybrid short-time Fourier transform and wavelet transform with vibration signal and convolutional neural network. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2024, vol. 6, p. 46.Qiushi Wang, Zhicheng Sun, Yueming Zhu, Chunhe Song. Intelligent fault diagnosis algorithm of rolling bearing based on optimization algorithm fusion convolutional neural network. Mathematical Biosciences & Engineering, 2023, vol. 11, pp. 63–82.Qiushi Wang, Zhicheng Sun, Yueming Zhu, Chunhe Song. Intelligent fault diagnosis algorithm of rolling bearing based on optimization algorithm fusion convolutional neural network. Mathematical Biosciences & Engineering, 2023, vol. 11, pp. 63–82.Renjie Wang, Ningyuan Yu, Bin An. Research on Power Equipment Fault Diagnosis Based on Improved SVM Algorithm. Journal of Electrical Systems, 2024, vol. 5, pp. 112–125.Renjie Wang, Ningyuan Yu, Bin An. Research on Power Equipment Fault Diagnosis Based on Improved SVM Algorithm. Journal of Electrical Systems, 2024, vol. 5, pp. 112–125.Tian Y., Liu X. A Deep Adaptive Learning Method for Rolling Bearing Fault Diagnosis Using Immunity. Tsinghua Science and Technology, 2019, vol. 24, no. 6, pp. 1–14.Tian Y., Liu X. A Deep Adaptive Learning Method for Rolling Bearing Fault Diagnosis Using Immunity. Tsinghua Science and Technology, 2019, vol. 24, no. 6, pp. 1–14.Sahu S., Kumar P.B., Parhi D.R. Analysis of hybrid CSA-DEA method for fault detection of cracked structures. Journal of Theoretical and Applied Mechanics, 2019, vol. 57, no. 2, pp. 369–382.Sahu S., Kumar P.B., Parhi D.R. Analysis of hybrid CSA-DEA method for fault detection of cracked structures. Journal of Theoretical and Applied Mechanics, 2019, vol. 57, no. 2, pp. 369–382.Pinto C., Pinto R., Gonçalves G. Towards. Bio-Inspired Anomaly Detection Using the Cursory Dendritic Cell Algorithm. Algorithms, 2022, vol. 15, no. 1, pp. 1–28.Pinto C., Pinto R., Gonçalves G. Towards. Bio-Inspired Anomaly Detection Using the Cursory Dendritic Cell Algorithm. Algorithms, 2022, vol. 15, no. 1, pp. 1–28.Xiaochen Zhang, Chen Wang, Wei Zhou, Jiajia Xu. Trustworthy Diagnostics With Out-of-Distribution Detection: A Novel Max-Consistency and Min-Similarity Guided Deep Ensembles for Uncertainty Estimation. IEEE Internet of Things Journal, 2024, vol. 1.1, pp. 99–120.Xiaochen Zhang, Chen Wang, Wei Zhou, Jiajia Xu. Trustworthy Diagnostics With Out-of-Distribution Detection: A Novel Max-Consistency and Min-Similarity Guided Deep Ensembles for Uncertainty Estimation. IEEE Internet of Things Journal, 2024, vol. 1.1, pp. 99–120.Meng Wang, Jiong Yu, Hongyong Leng, Xusheng Du. Bearing fault detection by using graph autoencoder and ensemble learningю Scientific Reports, 2024, vol.14, no. 1.Meng Wang, Jiong Yu, Hongyong Leng, Xusheng Du. Bearing fault detection by using graph autoencoder and ensemble learningю Scientific Reports, 2024, vol.14, no. 1.Weihua Li, Jingke He, Huibin Lin, Ruyi Huang. A LightGBM-based Multi-scale Weighted Ensemble Model for Few-shot Fault Diagnosis. IEEE Transactions on Instrumentation and Measurementm, 2023, vol. 1, p. 99.Weihua Li, Jingke He, Huibin Lin, Ruyi Huang. A LightGBM-based Multi-scale Weighted Ensemble Model for Few-shot Fault Diagnosis. IEEE Transactions on Instrumentation and Measurementm, 2023, vol. 1, p. 99.Arnaud Nanfak, Charles Hubert Kom, Samuel Eke. Hybrid Method for Power Transformers Faults Diagnosis Based on Ensemble Bagged Tree Classification and Training Subsets Using Rogers and Gouda Ratios. International Journal of Intelligent Engineering and Systems, 2022, vol. 5, pp. 12–24.Arnaud Nanfak, Charles Hubert Kom, Samuel Eke. Hybrid Method for Power Transformers Faults Diagnosis Based on Ensemble Bagged Tree Classification and Training Subsets Using Rogers and Gouda Ratios. International Journal of Intelligent Engineering and Systems, 2022, vol. 5, pp. 12–24.Zhiyuan Chen, Olugbenro. O. Selere, Nicholas Lu Chee Seng. Equipment Failure Analysis for Oil and Gas Industry with an Ensemble Predictive Model. Proceedings of the 9th International Conference on Computational Science and Technology, 2023, pp. 569–581.Zhiyuan Chen, Olugbenro. O. Selere, Nicholas Lu Chee Seng. Equipment Failure Analysis for Oil and Gas Industry with an Ensemble Predictive Model. Proceedings of the 9th International Conference on Computational Science and Technology, 2023, pp. 569–581.Hezla L., Gurina R., Hezla M., Rezaeian N. The Role of Artificial Intelligence in Improving Failure Mode and Effects Analysis (FMEA) Efficiency in Construction Safety Management. AI Technologies and Virtual Reality, 2024, pp. 397–411.Hezla L., Gurina R., Hezla M., Rezaeian N. The Role of Artificial Intelligence in Improving Failure Mode and Effects Analysis (FMEA) Efficiency in Construction Safety Management. AI Technologies and Virtual Reality, 2024, pp. 397–411.Podoplelova E.S., Knyazev I.I. Modification of the fmea method using machine learning algorithms. Izvestiya SFedU engineering sciences, 2023.Podoplelova E.S., Knyazev I.I. Modification of the fmea method using machine learning algorithms. Izvestiya SFedU engineering sciences, 2023.Jiao J., Zhao M., Lin J. and Ding C. Deep Coupled Dense Convolutional Network With Complementary Data for Intelligent Fault Diagnosis. IEEE Trans. Ind. Electron, 2019, vol. 6, pp. 92–98.Jiao J., Zhao M., Lin J. and Ding C. Deep Coupled Dense Convolutional Network With Complementary Data for Intelligent Fault Diagnosis. IEEE Trans. Ind. Electron, 2019, vol. 6, pp. 92–98.Lei Y., Jia F., Lin J., Xing S. and Ding S.X. An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data. IEEE Trans. Ind. Electron., 2019, p. 78.Lei Y., Jia F., Lin J., Xing S. and Ding S.X. An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data. IEEE Trans. Ind. Electron., 2019, p. 78.Dimitar P. Filev, Ratna Babu Chinnam, Finn Tseng and Pundarikaksha Baruah. An Industrial Strength Novelty Detection Framework for Autonomous Equipment Monitoring and Diagnostics. IEEE Transactions on Industrial Informatics, 2010, vol. 4, pp. 61–78.Dimitar P. Filev, Ratna Babu Chinnam, Finn Tseng and Pundarikaksha Baruah. An Industrial Strength Novelty Detection Framework for Autonomous Equipment Monitoring and Diagnostics. IEEE Transactions on Industrial Informatics, 2010, vol. 4, pp. 61–78.Venkatasubramanian V., Rengaswamy R., Yin K. and Kavuri S.N. A review of process fault detection and diagnosis: Part I: Quantitative model-based methods. Computers & Chemical Engineering, 2003, vol. 27, no. 9, pp. 293–311.Venkatasubramanian V., Rengaswamy R., Yin K. and Kavuri S.N. A review of process fault detection and diagnosis: Part I: Quantitative model-based methods. Computers & Chemical Engineering, 2003, vol. 27, no. 9, pp. 293–311.Hwang I., Kim S., Kim Y. and Seah C.E. A Survey of Fault Detection, Isolation, and Reconfiguration Methods. IEEE Transactions on Control Systems Technology, 2010, vol.18, no. 3, pp. 636–653.Hwang I., Kim S., Kim Y. and Seah C.E. A Survey of Fault Detection, Isolation, and Reconfiguration Methods. IEEE Transactions on Control Systems Technology, 2010, vol.18, no. 3, pp. 636–653.Lei Y., Lin J., He Z. and Zuo M.J. Condition monitoring and fault diagnosis of planetary gearboxes: A review. Measurement journal, 2014, vol.35, pp. 108–126.Lei Y., Lin J., He Z. and Zuo M.J. Condition monitoring and fault diagnosis of planetary gearboxes: A review. Measurement journal, 2014, vol.35, pp. 108–126.Henriquez P., Alonso J.B., Ferrer M.A. and Travieso C.M. Automatic Fault Diagnosis Systems Using Audio and Vibration Signals. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2012, vol. 5, pp. 642–652.Henriquez P., Alonso J.B., Ferrer M.A. and Travieso C.M. Automatic Fault Diagnosis Systems Using Audio and Vibration Signals. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2012, vol. 5, pp. 642–652.Yan R., Gao R.X. and Chen X. Non-stationary signal processing for bearing health monitoring. Signal Processing, 2014, vol. 1.Yan R., Gao R.X. and Chen X. Non-stationary signal processing for bearing health monitoring. Signal Processing, 2014, vol. 1.Venkatasubramanian V., Rengaswamy R., Kavuri S.N. and Yin K. A review of process fault detection and diagnosis. Compuers & chemical engineering, Part III: Process history based methods, 2003, pp. 327–346.Venkatasubramanian V., Rengaswamy R., Kavuri S.N. and Yin K. A review of process fault detection and diagnosis. Compuers & chemical engineering, Part III: Process history based methods, 2003, pp. 327–346.Yin S., Ding S.X., Xie X. and Luo H. A Review on Basic Data-Driven Approaches for Industrial Process Monitoring. IEEE Transactions on Industrial Electronic, 2014, vol. 11, pp. 6418–6428.Yin S., Ding S.X., Xie X. and Luo H. A Review on Basic Data-Driven Approaches for Industrial Process Monitoring. IEEE Transactions on Industrial Electronic, 2014, vol. 11, pp. 6418–6428.Ding S.X. A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process. Journal of Process Control., 2014, vol. 24, no. 2, pp. 431–449.Ding S.X. A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process. Journal of Process Control., 2014, vol. 24, no. 2, pp. 431–449.Gao Z., Cecati C. and Ding S.X. Fault Diagnosis and Fault-Tolerant Techniques, Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches. IEEE Transactions on Industrial Electronics, Part I, 2015, vol. 62, pp. 3757–3767.Gao Z., Cecati C. and Ding S.X. Fault Diagnosis and Fault-Tolerant Techniques, Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches. IEEE Transactions on Industrial Electronics, Part I, 2015, vol. 62, pp. 3757–3767.Gao Z., Cecati C. and Ding S.X. Fault Diagnosis and Fault-Tolerant Techniques, Part II, IEEE Transactions on Industrial Electronics, 2015.Gao Z., Cecati C. and Ding S.X. Fault Diagnosis and Fault-Tolerant Techniques, Part II, IEEE Transactions on Industrial Electronics, 2015.Evstifeev A.A. and Zaeva M.A. A hybrid teaching factory model towards personalized education. Method of Applying Fuzzy Situational Network to Assess the Risk of the Industrial Equipment Failure, 2021.Evstifeev A.A. and Zaeva M.A. A hybrid teaching factory model towards personalized education. Method of Applying Fuzzy Situational Network to Assess the Risk of the Industrial Equipment Failure, 2021.Mourtzis D., Angelopoulos J. and Panopoulos N., 2020, vol. 5, pp. 166–171.Mourtzis D., Angelopoulos J. and Panopoulos N., 2020, vol. 5, pp. 166–171.Saeed Rajabi, Mehdi Saman Azari, Stefania Santini, and Francesco Flammini. Expert Systems with Applications, 2022.Saeed Rajabi, Mehdi Saman Azari, Stefania Santini, and Francesco Flammini. Expert Systems with Applications, 2022.Teerawat Thepmanee, Sawai Pongswatd, Farzin Asadi, and Prapart Ukakimaparn. Implementation of control and scada system: Energy Reports, 2022, vol. 8, pp. 934–941.Teerawat Thepmanee, Sawai Pongswatd, Farzin Asadi, and Prapart Ukakimaparn. Implementation of control and scada system: Energy Reports, 2022, vol. 8, pp. 934–941.Dietterich T.G. Ensemble methods in machine learning. Multiple Classifier Systems, 2015, pp. 1–15.Dietterich T.G. Ensemble methods in machine learning. Multiple Classifier Systems, 2015, pp. 1–15.Zhou Z.H. Ensemble Methods: Foundations and Algorithms. Chapman and Hall/CRC, 2012.Zhou Z.H. Ensemble Methods: Foundations and Algorithms. Chapman and Hall/CRC, 2012.Kuncheva L.I. Combining Pattern Classifiers: Methods and Algorithms. John Wiley & Sons, 2014.Kuncheva L.I. Combining Pattern Classifiers: Methods and Algorithms. John Wiley & Sons, 2014.Rokach L. Ensemble-based classifiers. Artificial Intelligence Review, 2010, vol. 33, no. 1–2, pp. 1–39.Rokach L. Ensemble-based classifiers. Artificial Intelligence Review, 2010, vol. 33, no. 1–2, pp. 1–39.Kadi Mohamed, Amine Naim, Akkouche Naim, AkkoucheSary, Awad Sary and Awad Show., 2010.Kadi Mohamed, Amine Naim, Akkouche Naim, AkkoucheSary, Awad Sary and Awad Show., 2010.Imran Rahman Pandian, Vasant Balbir, Singh Mahinder and Abdullah-Al-Wadud. Alexandria Engineering Journal, 2016.Imran Rahman Pandian, Vasant Balbir, Singh Mahinder and Abdullah-Al-Wadud. Alexandria Engineering Journal, 2016.Ponni Ponnusamy and Prabha Dhandayudam. Journal of Electrical Engineering and Technology journal, 2023.Ponni Ponnusamy and Prabha Dhandayudam. Journal of Electrical Engineering and Technology journal, 2023.Ali Aldrees, Hamad Hassan Awan, Arbab Faisal and Abdeliazim Mustafa Mohamed, Process Safety and Environmental Protection journal, 2022.Ali Aldrees, Hamad Hassan Awan, Arbab Faisal and Abdeliazim Mustafa Mohamed, Process Safety and Environmental Protection journal, 2022.Sinem Bozkurt and Kemal Keskin, 2022.Sinem Bozkurt and Kemal Keskin, 2022.Sriparna Saha and Asif Ekbal. Combining multiple classifiers using vote based classifier ensemble technique for named entity recognition. Data & Knowledge Engineering journal, 2018.Sriparna Saha and Asif Ekbal. Combining multiple classifiers using vote based classifier ensemble technique for named entity recognition. Data & Knowledge Engineering journal, 2018.

The authors declare that there are no conflicts of interest present.