The investigation of the failure envelope of control moment gyroscopes (CMGs) under simulated dynamic and thermal vacuum conditions on the ground is crucial for ensuring the reliability of CMGs. In this study, a test rig is employed to simulate the combined stresses in a vacuum environment, including the temperature, CMG gimbal rotating speed, and satellite rotating speed. The objective is to obtain high-fidelity running status data of the CMG. The particle swarm optimization and BP neural network (PSO-BP) model is utilized to learn from these test data and subsequently predict the running status for other stress combinations, ultimately enabling the determination of the failure envelope surface of the CMG. The results demonstrate that this method significantly reduces the cost of testing to detect the CMG failure envelope while achieving high prediction accuracy and adaptability under combined stress situations. By employing the k-fold cross-validation method, the PSO-BP model demonstrates superior generalization performance to the BP model in predicting the running status of CMGs. The optimized hidden layer size and learning rate of the PSO-BP model are also discussed. Furthermore, the method presented in this paper can effectively incorporate the hidden experience data from the test. Finally, the PSO-BP method, in comparison to the BP method, yields a smooth and stable initial predicted value, effectively preventing the prediction result from falling into local optimization.
Fluid loop pumps, critical to spacecraft thermal control subsystems, are more prone to failures than other spacecraft components. Timely fault diagnosis is therefore crucial to ensure operational reliability. This paper proposes a multi-neural network fusion model (MNN) to improve the fault diagnosis accuracy for spacecraft fluid loop pumps. The proposed model integrates four neural network algorithms—back propagation neural network (BPNN), particle swarm optimization-back propagation neural network (PSO-BPNN), genetic algorithm-back propagation neural network (GA-BPNN), and fuzzy neural network (FNN)—through a model scoring and weighting mechanism. Additionally, a dedicated software has also been developed and implemented for the intelligent fault diagnosis of fluid loop pumps in Chinese spacecraft. By analyzing a dataset derived from on-orbit telemetry and expert knowledge, the proposed model demonstrates superior performance over individual models, achieving significant improvements in key metrics such as mean squared error (MSE), prediction stability, correlation coefficient (R), Accuracy, Precision, Recall, and F1-score. Furthermore, validation using both on-orbit telemetry data and ground test data confirms that the model can accurately diagnose both normal operations and various types of faults, making it a reliable and practical tool for on-orbit fault detection. The study provides an efficient, stable, and practical solution for intelligent fault diagnosis of spacecraft fluid loop pumps, with significant engineering application value.