Data-Driven Based Fault Prognosis for Systems – a Review

Resumen: Condition-based maintenance (CBM), is a maintenance strategy that is based on the continuous monitoring of systems. With Fault Prognosis, prediction such as at what time an element of a system will fail, or its Remaining Useful Life can be made. A review on Fault Prognosis and its most used algorithms to apply it, evaluating the obtained results is made. While Machine Learning is the preferred methodology, a hybrid algorithm using data-driven and knowledge-based methods can sometimes offer a better solution, depending on the system and the available data from it.

¿Cómo citar?

Jose L. Guadiana Alvarez, Luisa F. Montoya Herrera, Adriana Vargas Martinez, Jorge de J. Lozoya Santos, Ricardo A. Ramirez Mendoza & Ruben Morales Menendez. Data-Driven Based Fault Prognosis for Systems – a Review. Memorias del Congreso Nacional de Control Automático, pp. 483-488, 2019.

Palabras clave

Detección y Aislamiento de Fallas, Redes Neuronales

• Diez Oliv´an, A. (2017). Machine Learning for Datadriven Prognostics: Methods and Applications. Ph.D. thesis, Industriales.
• Feng, L.L., Shen, F.R., Zhou, J.H., and Chen, Y.G. (2019). Expression of the lncRNA ZFAS1 in Cervical Cancer and its Correlation with Prognosis and Chemosensitivity. Gene, 696, 105 – 112.
• Fu, B., Liu, P., Lin, J., Deng, L., Hu, K., and Zheng, H. (2018). Predicting Invasive Disease-Free Survival for Early-stage Breast Cancer Patients Using Followup Clinical Data. IEEE Transs on Biomedical Eng, 1–1.
• Giantomassi, Andrea. Ferracuti, F.B.A.I.G.L.S.P.A. (2011). Hidden Markov Model for Health Estimation and Prognosis of Turbofan Engines. volume 3, 681 – 689.
• Gómez-Ruiz, J.A., Jerez-Aragonés, J.M., Munoz -Pérez, J., and Alba-Conejo, E. (2004). A neural network based model for prognosis of early breast cancer. Applied Intelligence, 20(3), 231–238.
• Hong, Z. (2011). A Preliminary Study on Artificial Neural Network. In 6 th IEEE Joint Int Information Tech y and Art Intelligence Conf, volume 2, 336–338.
• Hu, X., Jiang, J., Cao, D., and Egardt, B. (2016). Battery Health Prognosis for Electric Vehicles Using Sample Entropy and Sparse Bayesian Predictive Modeling. IEEE Trans on Ind Electronics, 63(4), 2645–2656.
• Juesas, P., Ramasso, E., Drujont, S., and Placet, V. (2017). On Partially Supervised Learning and Inference in Dynamic Bayesian Networks for Prognostics with Uncertain Factual Evidence : Illustration with Markov Switching Models.
• Khan, S.A., Prosvirin, A.E., and Kim, J. (2018). Towards Bearing Health Prognosis Using Generative Adversarial Networks: Modeling Bearing Degradation. In Int Conf on Advancements in Computational Sc, 1–6.
• Kiakojoori, S. and Khorasani, K. (2014). Dynamic Neural Networks for Jet Engine Degradation Prediction and Prognosis. In Int Joint Conf on Neural Networks, 2531– 2538.
• Kim, H.E., Tan, A.C., Mathew, J., and Choi, B.K. (2012a). Bearing Fault Prognosis Based on Health State Probability Estimation. Expert Systems with Applications, 39(5), 5200 – 5213.
• Kim, H.E., Tan, A.C., Mathew, J., and Choi, B.K. (2012b). Bearing fault prognosis based on health state probability estimation. Expert Systems with Applications, 39(5), 5200–5213.
• Komyakov, A.A., Nikiforov, M.M., Erbes, V.V., Cheremisin, V.T., and Ivanchenko, V.I. (2016). Construction of Electricity Consumption Mathematical Models on Railway Transport Using Artificial Neural Network and Fuzzy Neural Network. In IEEE 16th Int Conf on Env and Elecl Eng, 1–4.
• Kordestani, M., Samadi, M.F., Saif, M., and Khorasani, K. (2018). A New Fault Prognosis of MFS System Using Integrated Extended Kalman Filter and Bayesian Method. IEEE Trans on Ind Inf, 1–1.
• Lehman, L.w., Ghassemi, M., Snoek, J., and Nemati, S. (2015). Patient prognosis from vital sign time series: Combining convolutional neural networks with a dynamical systems approach. In 2015 Computing in Cardiology Conference (CinC), 1069–1072. IEEE.
• Liu, S., Mao, Q., Xue, W., Zhang, X., Qi, Y., Wang, Y., Chen, P., and Zhou, Q. (2019). High Expression of ALPPL2 is Associated with Poor Prognosis in Gastric Cancer. Human Pathology, 86, 49 – 56.
• Lu, F., Huang, J., and Lv, Y. (2013). Gas Path Health Monitoring for a Turbofan Engine Based on a Nonlinear Filtering Approach. Energies, 6(1), 492–513.
• Luo, J., Tu, H., Pattipati, K., Qiao, L., and Chigusa, S. (2005). Graphical models for diagnosis knowledge representation and inference. In IEEE Autotestcon, 483–489. IEEE.
• Ma, H., Wu, J., Li, X., and Kang, R. (2018). ConditionBased Maintenance Optimization for Multi-Component Systems under Imperfect Repair-Based on RFADT Model. IEEE Trans on Fuzzy Systems, 1–1.
• Ma, Y.Y., Zhang, G.H., Li, J., Wang, S.B., Hu, Z.M., Zhang, C.W., and Li, E. (2018). The Correlation of NLRC3 Expression with the Progression and Prognosis of Hepatocellular carcinoma. Human Pathology, 82, 273 – 281.
• Moon, S., Balch, C., Park, S., Lee, J., Sung, J., and Nam, S. (2019). Systematic Inspection of the Clinical Relevance of TP53 Missense Mutations in Gastric Cancer. IEEE/ACM Trans on Computational Biology and Bioinformatics, 1–1.
• Peng, C., Zheng, Y., and Huang, D. (2019). Capsule Network based Modeling of Multi-omics Data for Discovery of Breast Cancer-related Genes. IEEE/ACM Trans on Computational Biology and Bioinformatics, 1–1.
• Ramasso, E. and Gouriveau, R. (2010). Prognostics in switching systems: Evidential markovian classification of real-time neuro-fuzzy predictions. In 2010 Prognostics and System Health Management Conference, 1–10. IEEE.
• Sankavaram, C., Pattipati, B., Kodali, A., Pattipati, K., Azam, M., Kumar, S., and Pecht, M. (2009). ModelBased and Data-Driven Prognosis of Automotive and Electronic Systems. In 2009 IEEE Int Conf on Auto Science and Eng, 96–101.
• Shen, W., Niu, N., Lawson, B., Qi, L., Zhang, J., Li, T., Zhang, H., and Liu, J. (2019). GATA6: A New Predictor for Prognosis in Ovarian Cancer. Human Pathology, 86, 163 – 169.
• Shridhar, K. (2019). Bayesian Neural Network Series Post 1: Need for Bayesian Neural Networks.
• Shubhangi Vashisth, Alexander Linden, J.H.P.K. (2019). Hype cycle for data science and machine learning.
• Soualhi, A., Razik, H., Clerc, G., and Doan, D.D. (2014). Prognosis of Bearing Failures Using Hidden Markov Models and the Adaptive Neuro-Fuzzy Inference System. IEEE Trans on Ind Elec, 61(6), 2864–2874.
• Sun, D., Wang, M., and Li, A. (2018). A Multimodal Deep Neural Network for Human Breast Cancer Prognosis Prediction by Integrating Multi-Dimensional Data. IEEE/ACM Trans on Computational Biology and Bioinformatics, 1–1.
• Vachtsevanos G., Lewis Frank. Roemer M, H.A. and Wu, B. (2006). Intelligent Fault Diagnosis and Prognosis for Engineering Systems.
• Vundavilli, H., Datta, A., Sima, C., Hua, J., Lopes, R., and Bittner, M.L. (2018). In Silico Design and Experimental Validation of Combination Therapy for Pancreatic Cancer. IEEE/ACM Trans on Computational Biology and Bioinformatics, 1–1.
• Wang, X., McArthur, S.D.J., Strachan, S.M., Kirkwood, J.D., and Paisley, B. (2018). A Data Analytic Approach to Automatic Fault Diagnosis and Prognosis for Distribution Automation. IEEE Trans on Smart Grid, 9(6), 6265–6273.
• Wu, Q., Ding, K., and Huang, B. (2018). Approach for Fault Prognosis using Recurrent Neural Network. Jrnl of Intelligent Manufacturing, 1–13.
• Wu, S., Wu, D., Pan, Y., Liu, H., Shao, Z., and Wang, M. (2019). Correlation Between EZH2 and CEP55 and Lung Adenocarcinoma Prognosis. Pathology – Research and Practice, 215(2), 292 – 301.
• Yu, M., Lan, D., Huang, Y., Wang, H., Jiang, C., and Zhao, L. (2018). Event-Based Sequential Prognosis for Uncertain Hybrid Systems With Intermittent Faults. IEEE Trans on Ind Inf, 1–1.
• Yuan Xie, T.Z. (2016). The Application of Echo State Network and Recurrent Multilayer Perceptron in Rotating Machinery Fault Prognosis. In IEEE Chinese Guidance, Navigation and Control Conf, 2286–2291.
• Zheng, H., Yu, J., Li, W., Yang, D., Gao, C., Zhang, Q., and Xu, L. (2019). Is Co-Expression of USP22 and HSP90 More Effective in Predicting Prognosis of Gastric Cancer. Pathology – Research and Practice, 215(4), 653 – 659.