Irregular Time-Series Hybrid Model for Enhanced Prognostics of Engine Degradation and Failures
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Published
Jan 13, 2026
Rohit Deo
Aman Yadav
Shruti Bharti
Dr. Nilesh Powar
Abstract
Classification-based prognostics aims to predict the Remaining Useful Life (RUL) of components in diesel engines by identifying failure and degradation stages. This is critical for industries such as automotive, aviation, and manufacturing. Traditional methods rely on classification models trained on historical data from multiple engines to forecast failures based on current engine parameters. However, these global classifiers often struggle with generalization when applied to unseen engines, resulting in poor precision and recall. Moreover, they fail to capture the temporal dependencies inherent in engine degradation, which are crucial for accurate failure prediction. We propose a hybrid model that integrates predictions from global classifiers with time-based memory units to address these limitations, effectively building irregular time-series models. Our approach demonstrates a significant performance improvement, with precision and recall metrics doubling compared to traditional global classifiers.
##plugins.themes.bootstrap3.article.details##
Keywords
Remaining Useful Life, Prognostics, Predictive Maintenance, Engine Health Monitoring, Downtime Reduction, Long short-term memory (LSTM), Convolutional Neural Network (CNN), Recurrent NN (RNN)
References
Alhnaity, B., & Abbod, M. (2020). A new hybrid financial time series prediction model. Engineering Applications of Artificial Intelligence, 95, 103873.
Almaghrabi, S., Rana, M., Hamilton, M., & Rahaman, M. S. (2024). Multivariate solar power time series forecasting using multilevel data fusion and deep neural networks. Information Fusion, 104, 102180.
Bieber, M., Verhagen, W. J., & Santos, B. F. (2021). Data- driven prognostics incorporating environmental factors for aircraft maintenance. In 2021 annual reliability and maintainability symposium (rams) (pp. 1–6).
Chen, J., Chen, P., & Gu, H. (2023). Lstm-rf-pso combined algorithm for short-term passenger flow forecasting in scenic areas. In 2023 international conference on electronics and devices, computational science (icedcs) (pp. 544–548).
Cheng, Y., Wang, C., Wu, J., Zhu, H., & Lee, C. K. (2022). Multi-dimensional recurrent neural network for remaining useful life prediction under variable operating conditions and multiple fault modes. Applied Soft Computing, 118, 108507.
Cheng, Y., Zeng, J., Wang, Z., & Song, D. (2023). A health state-related ensemble deep learning method for aircraft engine remaining useful life prediction. Applied Soft Computing, 135, 110041.
Gong, R., Li, J., & Wang, C. (2022). Remaining useful life prediction based on multisensor fusion and attention tcn-bigru model. IEEE Sensors Journal, 22(21), 21101–21110.
Haibin, C., & Yongliang, H. (2023). A hybrid lstm and decision tree model: A novel machine learning architecture for complex data classification. In 2023 ieee international conference on sensors, electronics and computer engineering (icsece) (pp. 1441–1446).
Hamida, S., El Gannour, O., Lamalem, Y., Saleh, S., Lamrani, D., & Cherradi, B. (2023). Efficient medical diagnosis hybrid system based on rf-dnn mixed model for skin diseases classification. In 2023 3rd international conference on innovative research in applied science, engineering and technology (iraset) (pp. 01–08).
Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the ieee conference on computer vision and pattern recognition (pp. 7132– 7141).
Hu, W., & Shi, Y. (2020). Prediction of online consumers’ buying behavior based on lstm-rf model. In 2020 5th international conference on communication, image and signal processing (ccisp) (pp. 224–228).
Jiang, H., Liu, L., & Lian, C. (2022). Multi-modal fusion transformer for multivariate time series classification. In 2022 14th international conference on advanced computational intelligence (icaci) (pp. 284–288).
Jin, S., Weiqing, W., Bingcun, S., & Xiaobo, X. (2024). Research on time series prediction of hybrid intelligent systems based on deep learning. Intelligent Systems with Applications, 23, 200419.
Karat, G., Kannimoola, J. M., Nair, N., Vazhayil, A., VG, S., & Poornachandran, P. (2024). Cnn-lstm hybrid model for enhanced malware analysis and detection. Procedia Computer Science, 233, 492–503.
Karim, F., Majumdar, S., Darabi, H., & Harford, S. (2019) Multivariate lstm-fcns for time series classification. Neural networks, 116, 237–245.
Khan, S., & Kumar, V. (2024). A novel hybrid gru-cnn and residual bias (rb) based rb-gru-cnn models for prediction of ptb diagnostic ecg time series data. Biomedical Signal Processing and Control, 94, 106262.
Liu, Z., Zhang, C., Dong, E., Wang, R., Li, S., & Han, Y. (2023). Research progress and development trend of prognostics and health management key technologies for equipment diesel engine. Processes, 11(7), 1972.
Pu, W., Liu, K., Yang, F., Lu, J., Tan, H., & Zhang, C. (2024). Wind power ultra-short-term power prediction based on vmd and weighted combination model of bilstm and rf. In 2024 ieee 2nd international conference on power science and technology (icpst) (pp. 1507–1512).
Roshanzadeh, B., Choi, J., Bidram, A., & Mart´ınez-Ramon, ´ M. (2024). Multivariate time-series cyberattack detection in the distributed secondary control of ac microgrids with convolutional neural network autoencoder ensemble. Sustainable Energy, Grids and Networks, 38, 101374.
Vallejo, C. A. M., & Manzione, R. L. (2024). Multidimensional forecasting of precipitation and potential evapotranspiration in the paranapanema river basin using neural network time series. Journal of South American Earth Sciences, 142, 104961.
Xuan, Y., Si, W., Zhu, J., Sun, Z., Zhao, J., Xu, M., & Xu, S. (2021). Multi-model fusion short-term load forecasting based on random forest feature selection and hybrid neural network. Ieee Access, 9, 69002–69009.
Yang, C., Wang, X., Yao, L., Long, G., Jiang, J., & Xu, G. (2023). Attentional gated res2net for multivariate time series classification. Neural Processing Letters, 55(2), 1371–1395.
Zhao, H., Li, X., Xu, J., Fu, X., & Chen, J. (2023). Financial time series data prediction by combination model adaboost-knn-lstm. In 2023 international joint conference on neural networks (ijcnn) (pp. 1–8).
Almaghrabi, S., Rana, M., Hamilton, M., & Rahaman, M. S. (2024). Multivariate solar power time series forecasting using multilevel data fusion and deep neural networks. Information Fusion, 104, 102180.
Bieber, M., Verhagen, W. J., & Santos, B. F. (2021). Data- driven prognostics incorporating environmental factors for aircraft maintenance. In 2021 annual reliability and maintainability symposium (rams) (pp. 1–6).
Chen, J., Chen, P., & Gu, H. (2023). Lstm-rf-pso combined algorithm for short-term passenger flow forecasting in scenic areas. In 2023 international conference on electronics and devices, computational science (icedcs) (pp. 544–548).
Cheng, Y., Wang, C., Wu, J., Zhu, H., & Lee, C. K. (2022). Multi-dimensional recurrent neural network for remaining useful life prediction under variable operating conditions and multiple fault modes. Applied Soft Computing, 118, 108507.
Cheng, Y., Zeng, J., Wang, Z., & Song, D. (2023). A health state-related ensemble deep learning method for aircraft engine remaining useful life prediction. Applied Soft Computing, 135, 110041.
Gong, R., Li, J., & Wang, C. (2022). Remaining useful life prediction based on multisensor fusion and attention tcn-bigru model. IEEE Sensors Journal, 22(21), 21101–21110.
Haibin, C., & Yongliang, H. (2023). A hybrid lstm and decision tree model: A novel machine learning architecture for complex data classification. In 2023 ieee international conference on sensors, electronics and computer engineering (icsece) (pp. 1441–1446).
Hamida, S., El Gannour, O., Lamalem, Y., Saleh, S., Lamrani, D., & Cherradi, B. (2023). Efficient medical diagnosis hybrid system based on rf-dnn mixed model for skin diseases classification. In 2023 3rd international conference on innovative research in applied science, engineering and technology (iraset) (pp. 01–08).
Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the ieee conference on computer vision and pattern recognition (pp. 7132– 7141).
Hu, W., & Shi, Y. (2020). Prediction of online consumers’ buying behavior based on lstm-rf model. In 2020 5th international conference on communication, image and signal processing (ccisp) (pp. 224–228).
Jiang, H., Liu, L., & Lian, C. (2022). Multi-modal fusion transformer for multivariate time series classification. In 2022 14th international conference on advanced computational intelligence (icaci) (pp. 284–288).
Jin, S., Weiqing, W., Bingcun, S., & Xiaobo, X. (2024). Research on time series prediction of hybrid intelligent systems based on deep learning. Intelligent Systems with Applications, 23, 200419.
Karat, G., Kannimoola, J. M., Nair, N., Vazhayil, A., VG, S., & Poornachandran, P. (2024). Cnn-lstm hybrid model for enhanced malware analysis and detection. Procedia Computer Science, 233, 492–503.
Karim, F., Majumdar, S., Darabi, H., & Harford, S. (2019) Multivariate lstm-fcns for time series classification. Neural networks, 116, 237–245.
Khan, S., & Kumar, V. (2024). A novel hybrid gru-cnn and residual bias (rb) based rb-gru-cnn models for prediction of ptb diagnostic ecg time series data. Biomedical Signal Processing and Control, 94, 106262.
Liu, Z., Zhang, C., Dong, E., Wang, R., Li, S., & Han, Y. (2023). Research progress and development trend of prognostics and health management key technologies for equipment diesel engine. Processes, 11(7), 1972.
Pu, W., Liu, K., Yang, F., Lu, J., Tan, H., & Zhang, C. (2024). Wind power ultra-short-term power prediction based on vmd and weighted combination model of bilstm and rf. In 2024 ieee 2nd international conference on power science and technology (icpst) (pp. 1507–1512).
Roshanzadeh, B., Choi, J., Bidram, A., & Mart´ınez-Ramon, ´ M. (2024). Multivariate time-series cyberattack detection in the distributed secondary control of ac microgrids with convolutional neural network autoencoder ensemble. Sustainable Energy, Grids and Networks, 38, 101374.
Vallejo, C. A. M., & Manzione, R. L. (2024). Multidimensional forecasting of precipitation and potential evapotranspiration in the paranapanema river basin using neural network time series. Journal of South American Earth Sciences, 142, 104961.
Xuan, Y., Si, W., Zhu, J., Sun, Z., Zhao, J., Xu, M., & Xu, S. (2021). Multi-model fusion short-term load forecasting based on random forest feature selection and hybrid neural network. Ieee Access, 9, 69002–69009.
Yang, C., Wang, X., Yao, L., Long, G., Jiang, J., & Xu, G. (2023). Attentional gated res2net for multivariate time series classification. Neural Processing Letters, 55(2), 1371–1395.
Zhao, H., Li, X., Xu, J., Fu, X., & Chen, J. (2023). Financial time series data prediction by combination model adaboost-knn-lstm. In 2023 international joint conference on neural networks (ijcnn) (pp. 1–8).
Section
Regular Session Papers
This work is licensed under a Creative Commons Attribution 3.0 Unported License.