A long-term prediction approach based on long short-term memory neural networks with automatic parameter optimization by Tree-structured Parzen Estimator and applied to time-series data of NPP steam generators

• Published in: Applied soft computing Vol. 89; p. 106116
• Main Authors: Nguyen, Hoang-Phuong, Liu, Jie, Zio, Enrico
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2020; Elsevier
• Subjects: Artificial Intelligence; Computer Science; Long-short term memory; Machine Learning; Multi-step ahead prediction; Nuclear power plant prognostics; Prognostics and health management; Steam generator; Time-series forecasting; Multi-step ahead prediction; Nuclear power plant prognostics; Long-short term memory; Prognostics and health management; Time-series forecasting; Steam generator; Long short-term memory
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2020.106116

Developing an accurate and reliable multi-step ahead prediction model is a key problem in many Prognostics and Health Management (PHM) applications. Inevitably, the further one attempts to predict into the future, the harder it is to achieve an accurate and stable prediction due to increasing uncertainty and error accumulation. In this paper, we address this problem by proposing a prediction model based on Long Short-Term Memory (LSTM), a deep neural network developed for dealing with the long-term dependencies in time-series data. Our proposed prediction model also tackles two additional issues. Firstly, the hyperparameters of the proposed model are automatically tuned by a Bayesian optimization algorithm, called Tree-structured Parzen Estimator (TPE). Secondly, the proposed model allows assessing the uncertainty on the prediction. To validate the performance of the proposed model, a case study considering steam generator data acquired from different French nuclear power plants (NPPs) is carried out. Alternative prediction models are also considered for comparison purposes. •The paper presents an original multi-step ahead prediction framework for PHM applications.•An LSTM neural network and an MIMO prediction strategy are integrated to predict a long-term horizon.•Automatic hyperparameter optimization and prediction uncertainty quantification are addressed.•A case study considering SG data acquired from French NPPs is carried out.