A novel approach of full state tendency measurement for complex systems based on information causality and PageRank: A case study of a hydropower generation system. (15th March 2023)

• Record Type: Journal Article
• Authors: Wang, Pengfei; Guo, Yixuan; Xu, Zhenkun; Wang, Weihao; Chen, Diyi
• Is Part Of: Mechanical systems and signal processing. Volume 187(2023)
• Publication Date: 2023-03-15
• Subjects: Information causality -- PageRank -- Hydropower generation system -- Prediction strategy -- Neural network model -- Transfer entropy; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2022.109956
• Languages: English
• ISSNs: 0888-3270

Abstract

Highlights: A novel approach of state tendency measurement for complex systems based on information causality is developed. The precise roles of the interaction relationship in complex systems are revealed for modeling. Complementarity between mechanism- and data-driven approaches is realized. Accurate measurement is realized by mining the state causality mechanism for prediction. Abstract: The hydropower generation system is a typical complex nonlinear system with hybrid state responses. The interaction between the state responses of the system is affected closely by the coupling of hydraulic, mechanical, and electromagnetic factors and the frequent changes in working conditions during operation. However, the precise roles of the interaction relationship are unknown. Here, we show that this interaction depends on the causal coupling between subsystems, and use this relationship to propose a time series data mining and data prediction strategy based on the information causality and the PageRank algorithm. A nonlinear model is used to prove that the proposed prediction strategy can effectively reduce the dimension of auxiliary variables. Finally, the strategy is validated with a 250 MW hydropower unit. Our results show that the information causal coupling between variables is cross-scale with definite Markov orders of time series, and the prediction accuracy can be improved by considering the information transfer sequences between the prediction object variable and the causal variable in the absence of state auxiliary variables. Furthermore, the proposed method can be also applied to data mining of other complex systems and variable selection of prediction models and builds a bridge between mechanism- and data-driven approaches, which has a high engineering application value.