In this paper, we address several issues with existing methods for predicting the residual electrical life of railway relays. These issues include the difficulty of single feature prediction in characterizing the degradation process, the neglect of temporal and backward–forward correlations in the degradation process, and low prediction accuracy. To overcome these challenges, we propose a novel approach that combines convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) to facilitate the life prediction of railway relays and provide an accurate data basis for the maintenance of railway relays. Firstly, we collected voltage and current signals from railway relay electrical life tests and extracted feature parameters that captured the relay’s operating state. Next, we applied Spearman correlation coefficient analysis combined with random forest importance analysis to perform double-feature selection. This process eliminates redundant feature parameters and identifies the optimal feature subset. Finally, we constructed a convolutional neural network bidirectional long short-term memory (CNN BiLSTM) prediction model to accurately predict the remaining electrical life of the railway relay. Through our analysis of the prediction results, we observed that the CNN BiLSTM model achieves an effective prediction accuracy of 96.3%. This accuracy is significantly higher, more stable, and more practical compared to other prediction models such as recurrent neural networks (RNNs), long short-term memory (LSTM), and BiLSTM models. Overall, our proposed CNN BiLSTM model offers higher accuracy, better stability, and greater practicality in predicting the remaining electrical life of railway relays.

With the deepening of power market reform, further study on power trading mechanisms has become the core issue of power market study. The development stage of the industrial electricity market requires efficient and flexible pricing mechanisms. Currently available pricing strategies are inadequate for demand response management. Therefore, this paper provides an in-depth study of the pricing mechanism in the industrial electricity market in the context of electricity market reform. It proposes a demand–response-based dynamic pricing strategy for industrial parks. The method proposes a dynamic pricing strategy for demand-side response in industrial parks based on master–slave game by establishing an exogenous model of demand-side response and incentives. Compared with the existing strategies, the strategy is more efficient and flexible, and effectively improves the economic efficiency of power trading and load regulation. Firstly, an exogenous model of demand-side response and incentive is built to characterize the demand-side response cost. The method focuses more on describing the exogenous characteristics of user incentives and response quantities. It only needs to analyze the exogenous indicators and random errors in various typical scenarios. The description of user demand-side response is more efficient. Secondly, a master–slave-game-based dynamic pricing strategy for industrial parks with demand-side response is proposed. The strategy is composed of a two-stage optimization. The primary regulation of customers is achieved by day-ahead time-of-use tariffs. The secondary regulation of customers is achieved by means of the same-day regulation of demand and purchase regarding clean electricity. The proposed two-stage price formation mechanism is more economical, more effective in load regulation, and improves the flexibility of industrial pricing. Finally, a case study is conducted on an industrial power user in a park in Liaoning Province. The results show that the proposed method is significantly better than existing methods in terms of improving the economic efficiency and load control effectiveness of the pricing strategy.