Mars Express Orbiter Power Consumption Prediction Based on Bionic Hierarchical Learning Network.

Abstract

Predicting power consumption for the Mars Express (MEX) mission is essential for optimizing its operational lifespan and mission assignments. However, the complexity of the Martian environment and the extended solar cycle obscure the periodicity of power consumption, making it difficult for existing methods to capture both intraperiodic and interperiodic features. This study introduces the bionic hierarchical learning network (BHL-Net) to enhance power consumption predictions. Leveraging 2-D frequency preprocessing and brain visual modeling techniques, BHL-Net mimics natural image encoding in the prefrontal cortex (PFC) to improve predictive performance. It incorporates a temporal oscillation activation module and a stripe intensity attention module to focus on local features, while a multihead attention adaptive aggregation module identifies key global features. Comparative experiments show that BHL-Net outperforms existing transformer-based models for MEX power consumption prediction. Ablation studies further validate the effectiveness of the FFT-based 2-D transformation and bionic attention framework. By emulating human brain response coding mechanisms, BHL-Net captures variations within and between complex cycles, providing a competitive solution for time series prediction in industrial applications.