Event-Triggered Relearning Modeling Method for Stochastic System with Non-Stationary Variable Operating Conditions

Liu, Jiyan; Zhang, Yong; Zhou, Yuyang; Chen, Jing

Abstract

This study presents a novel event-triggered relearning framework for neural network modeling, designed to improve prediction precision in dynamic stochastic complex industrial systems under non-stationary and variable conditions. Firstly, a sliding window algorithm combined with entropy is applied to divide the input and output datasets across different operational conditions, establishing clear data boundaries. Following this, the prediction errors derived from the neural network under different operational states are harnessed to define a set of event-triggered relearning criteria. Once these conditions are triggered, the relevant dataset is used to recalibrate the model to the specific operational condition and predict the data under this operating condition. When the predicted data fall within the training input range of a pre-trained model, we switch to that model for immediate prediction. Compared with the conventional BP neural network model and random vector functional-link network, the proposed model can produce a better estimation accuracy and reduce computation costs. Finally, the effectiveness of our proposed method is validated through numerical simulation tests using nonlinear Hammerstein models with Gaussian noise, reflecting complex stochastic industrial processes.

• Journal Article Type: Article
• Acceptance Date: Feb 21, 2024
• Online Publication Date: Feb 24, 2024
• Publication Date: 2024
• Deposit Date: Mar 11, 2024
• Publicly Available Date: Mar 11, 2024
• Journal: Mathematics
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 12
• Issue: 5
• Article Number: 667
• DOI: https://doi.org/10.3390/math12050667
• Keywords: 93-10, sliding window algorithm, stochastic processes, 68T07, non-stationary and variable conditions, information entropy, event-triggered conditions