A Maximum Power Point Tracking Strategy for Wave Energy Converter Based on CNN-LSTM Prediction

In order to enable the wave energy converter (WEC) device to capture maximum power under irregular wave conditions, a deep learning-based maximum power point tracking (MPPT) control strategy is proposed. Firstly, the mechanical model of the WEC device is derived, and the parameters Rpto and Xpto are introduced in the mathematical model to determine the control signals for the q-axis current of the permanent magnet synchronous motor (PMSM). The parameters Rpto and Xpto are calculated using the Sparrow Search Algorithm (SSA), and by satisfying the complex conjugate control condition, the WEC device achieves maximum power capture. A prediction model combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) based on deep learning is used to perform short-term predictions of the parameters Rpto and Xpto, providing parameter guidance for the control strategy. Finally, the feasibility of this strategy is verified through simulation experiments.