电邮这篇文章 Data Preprocessing for Building a Neural Network Model to Predict the State of a Technical Object
- 作者: Kuvayskova Y.E.1, Nemykin A.A.1
-
隶属关系:
- Ulyanovsk State Technical University
- 期: 编号 1 (2025)
- 页面: 67-81
- 栏目: Machine Learning, Neural Networks
- URL: https://bakhtiniada.ru/2071-8594/article/view/293495
- DOI: https://doi.org/10.14357/20718594250106
- EDN: https://elibrary.ru/QSUXBG
- ID: 293495
如何引用文章
全文:
详细
In order to prevent emergency situations in the operation of a technical facility, it is necessary to predict its state. To solve this problem, neural network models are used in the work. However, for effective training of models and obtaining more accurate forecasting results, the input data should be preprocessed. In this paper, a new technique is proposed for preprocessing the initial data when constructing neural network models, which includes algorithms for finding outliers, restoring missing values, and removing correlating factors. A special program in the Python programming language was written to implement the proposed technique. The study of the effectiveness of the proposed data preprocessing technique for predicting the state of a technical facility was carried out using two objects as an example: a turbojet engine and a lithium-ion battery. The following approaches were used to compare the results: the data preprocessing technique from the AutoKeras library and the method based on the use of a compactness profile. It is shown that the use of the proposed data preprocessing approach increases the forecasting accuracy of neural network models by approximately 3–4 times compared to the other two approaches.
作者简介
Yuliya Kuvayskova
Ulyanovsk State Technical University
编辑信件的主要联系方式.
Email: u.kuvaiskova@mail.ru
Candidate of technical sciences, docent, Head of the Department of Applied Mathematics and Informatics
俄罗斯联邦, UlyanovskAlexander Nemykin
Ulyanovsk State Technical University
Email: nemykin.alexander@yandex.ru
Postgraduate student, Department of Applied Mathematics and Informatics
俄罗斯联邦, Ulyanovsk参考
- Klyachkin V.N., Krasheninnikov V.R., Kuvayskova Yu.E. Prognozirovanie i diagnostika stabil’nosti funkcionirovaniya tekhnicheskih ob’’ektov [Forecasting and diagnostics of stability of functioning of technical objects]. Moscow: Rusajns, 2020.
- Krasheninnikov V.R., Bubyr’ D.S., Klyachkin V.N. Povyshenie nadyozhnosti sistemy upravleniya vodoochistkoj pri ispol’zovanii programmnogo bloka rannego preduprezhdeniya o narushenii pokazatelej kachestva vody [Increasing the reliability of the water treatment control system when using a software block for early warning of violations of water quality indicators] // Avtomatizaciya. Sovremennye texnologii [Automation. Modern technologies]. 2017. V. 71. No 2. P. 61-66.
- Huang H.Z., Wang H.K., Li Y.F., Zhang L., Liu Z. Support vector machine based estimation of remaining useful life: current research status and future trends // Journal of Mechanical Science and Technology. 2015. V. 29. P. 151–163. doi: 10.1007/s12206-014-1222-z.
- Yan M., Wang X., Wang B., Chang M., Muhammad I. Bearing remaining useful life prediction using support vector machine and hybrid degradation tracking model // ISA Transactions. 2020. V. 98. P. 471–482. doi: 10.1016/j.isatra.2019.08.058.
- Uvaysov S.U., Chernoverskaya V.V., Quan D.A., Tuan N.V., Thanh G.V. Metod opornyx vektorov v zadache teplovoj diagnostiki konstruktivnyx defektov radioelektronnyx ustrojstv [Support vector machine applied to the problem of thermal diagnostics of design defects in radio electronic devices] // Vestnik Koncerna VKO Almaz Antej [Journal of Almaz Antey Air and Space Defence Corporation]. 2022. No 1. P. 58–70. doi: 10.38013/2542-0542-2022-1-58-70.
- Patil S., Patil A., Handikherkar V., Desai S., Phalle V.M., Kazi F.S. Remaining Useful Life (RUL) Prediction of Rolling Element Bearing Using Random Forest and Gradient Boosting Technique // Proceedings of the ASME 2018 International Mechanical Engineering Congress and Exposition. 2018. P.1-7.
- Kovalnogov V., Fedorov R., Klyachkin V., Generalov D., Kuvayskova Y., Busygin S. Applying the Random Forest Method to Improve Burner Efficiency // Mathematics. 2022. V. 10 (12). P. 2143.
- Calabrese M., Cimmino M., Fiume F., Manfrin M. et al. SOPHIA: An Event-Based IoT and Machine Learning Architecture for Predictive Maintenance in Industry 4.0 // Information. 2020. V. 11. P. 1-17.
- Kang Z., Catal C., Tekinerdogan B. Remaining Useful Life (RUL) Prediction of Equipment in Production Lines Using Artificial Neural Networks // Sensors. 2021. V. 21. P. 932.
- Gugulothu N., Vishnu TV, Malhotra P., Vig L., Agarwal P., Shroff G. Predicting Remaining Useful Life using Time Series Embeddings based on Recurrent Neural Networks // International Journal of Prognostics and Health Management. 2017. V. 9.
- Srinivasan A., Andresen J.C., Holst A. Ensemble Neural Networks for Remaining Useful Life (RUL) Prediction // Proceedings of the Asia Pacific Conference of the PHM Society. 2023. V. 4. No 1.
- Qin Y., Cai N., Gao C., Zhang Y., Cheng Y., Chen X. Remaining Useful Life Prediction Using Temporal Deep Degradation Network for Complex Machinery with Attentionbased Feature Extraction // arXiv:2202.10916. 2022.
- Saj V.K., Shherbakov M.V. Metod prognozirovaniya ostatochnogo resursa na osnove obrabotki mnogoob’’ektnyx slozhnyx sistem [A method for predicting the residual resource based on the processing of multi-object complex systems] // Prikaspijskij zhurnal: upravlenie i vysokie texnologii [Caspian Journal: management and high technologies]. 2019. No 1 (45). P. 33-44.
- Kachanovsky Yu.P., Korotkov E.A. Predobrabotka dannykh dlya obucheniya neyronnoy seti [Preprocessing data for training a neural network] // Fundamental'nyye issledovaniya [Fundamental research]. 2011. No 12. P. 117-120.
- Jin H., Song Q., Hu X. Auto-keras: An efficient neural architecture search system // Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2019. P. 1946-956.
- Jin H., Chollet F., Song Q., and Hu X. AutoKeras: An AutoML Library for Deep Learning // Journal of Machine Learning Research. 2023. V. 24. P. 1-6.
- Liu F.T., Ting K.M., Zhou Z.-H. Isolation Forest // 2008 Eighth IEEE International Conference on Data Mining. 2008. P. 413-422.
- Little R.J.A., Rubin D.B. Statistical Analysis with Missing Data. 2nd ed., Hoboken, NJ: Wiley-Interscience, 2014. 408 p.
- Mera-Gaona M., Neumann U., Vargas-Canas R., López D.M. Correction: Evaluating the impact of multivariate imputation by MICE in feature selection // PLoS ONE. 2021. V. 16. No 7. P. e0261739.
- Jolliffe I.T., Trendafilov N.T., Uddin M. A modified principal component technique based on the LASSO // Journal of computational and Graphical Statistics. 2003. V. 12. No 3. P. 531-547.
- NASA, Prognostics Center of Excellence Data Repository, NASA’s Open Data Portal // Electronic resource. URL: https://data.nasa.gov/dataset/C-MAPSS Aircraft-EngineSimulator-Data/xaut-bemq (accessed 23.01.2025).
- NASA Intelligent Systems Division. Discovery and Systems Health PCoE Data Set Repository // Electronic resource. URL: https://www.nasa.gov/intelligent-systems- division/discovery-and-systems-health/pcoe/pcoe-data-setrepository/ (accessed 23.01.2025).
- Zou F., Shen L., Jie Z., Zhang W., Liu W. A sufficient condition for convergences of Adam and RMSProp // Proceedings of the IEEE / CVF Conference on computer vision and pattern recognition. 2019. P. 11127-11135.
补充文件
