航天器流体回路泵智能故障诊断方法  

Intelligent Fault Diagnosis Method for Fluid Loop Pumps in Spacecraft

作　　者：余溢方 黄首清[1] 刘庆海[1] 王郅豪 周昊澄 王晶[1] YU Yifang;HUANG Shouqing;LIU Qinghai;WANG Zhihao;ZHOU Haocheng;WANG Jing(National Key Laboratory of Science and Technology on Reliability and Environmental Engineering,Beijing Institute of Spacecraft Environment Engineering,Beijing 100094,China;Beijing Institute of Technology,Beijing 100081,China;Beijing Institute of Spacecraft System Engineering,Beijing 100094,China)

机构地区：[1]北京卫星环境工程研究所可靠性与环境工程技术国防科技重点实验室,北京100094 [2]北京理工大学,北京100081 [3]北京空间飞行器总体部,北京100094

出　　处：《航天器工程》2024年第3期61-67,共7页Spacecraft Engineering

基　　金：可靠性与环境工程技术重点实验室稳定支持科研项目(614200420230201,6142004WDZC210401)。

摘　　要：开展了航天器流体回路泵智能故障诊断方法研究,将BP神经网络、粒子群优化(PSO)-BP神经网络、遗传算法(GA)-BP神经网络和模糊神经网络4种模型应用于故障诊断,以温度、流量、出口压力、转速4类状态参数作为神经网络输入,状态标志作为输出进行训练,通过均方误差、相关系数、模型训练评分对模型训练效果评价,从而实现模型优选,完成故障诊断。利用在轨遥测数据进行应用验证,结果表明可以准确识别流体回路泵的正常和叶轮卡死泵功能丧失两种在轨实际状态类型,且模糊神经网络相对其他3种神经网络具有更好的诊断效果。A study is conduted on the research of intelligent fault diagnosis methods for spacecraft fluid loop pump in this paper.Four models,namely BP neural network,Particle Swarm Optimization(PSO)-BP neural network,Genetic Algorithm(GA)-BP neural network,and fuzzy neural network,are applied to fault diagnosis.These models utilize temperature,flow rate,outlet pressure,and rotational speed as inputs to the neural network,,with state labels as outputs for training.The training effectiveness of the models is evaluated through mean square error,correlation coefficient and model training score,thereby achieving model optimization and completing fault diagnosis.The application validation of the proposed method is performed using on-orbit telemetry data,demonstrating its ability to accurately identify normal operation and impeller jam pump function loss of the fluid loop pump,indicating that the fuzzy neural network has better diagnostic performance compared to the other three neural networks in terms of diagnostic accuracy.

关 键 词：航天器 空间站 流体回路泵 故障诊断 神经网络 

分 类 号：TP306[自动化与计算机技术—计算机系统结构] V476.1[自动化与计算机技术—计算机科学与技术]