基于粒子群优化神经网络的卫星故障预测方法

Method of Prognostics for Satellite Based on Particle Swarm Optimized Neural Network

随着卫星数量和应用领域的日益增多,确保卫星的安全稳定运行,及时发现故障、处理故障,已成为运行管理工作的重点,因此有必要开展故障预测技术的研究;提出了一种粒子群优化的神经网络方法,实现卫星的故障预测;首先,基于卫星的原理和运行特点,通过卫星遥测参数获取特征;其次,利用神经网络对卫星关键遥测参数进行近似和建模,并利用粒子群算法对神经网络进行优化;之后,利用时间序列方法对遥测参数进行预测,并将预测结果与粒子群优化的神经网络的输出进行比较,根据神经网络的输入层与输出层之间的关联信息实现对卫星的预测;最后,利用带有故障信息的电源系统真实遥测数据来对本文提出的方法的可行性进行验证,使用粒子群优化神经网络对遥测参数进行建模,能够很好地检测遥测参数是否正常,预测值与真实值的验证结果证明了在卫星故障预测中应用粒子群优化神经网络的有效性。

As the number of satellite is growing, ensuring safe and stable operation of the satellite, finding and handling the faults on time has become the foucus of the operation and mangement for satellite, it is necessary to study the prognostic technology in order to find the fault in advance. This paper puts forward a method of particle swarm optimized neural network used to realize prognostics for satellite consid- ering the importance of prognostics in the field of PHM study. Firstly based on the principle and operation traits of the satellite, the fault modes and fault characteristics are analyzed to obtain the feature that the prognostics can be achieved through the telemetry parameters of the satellite. Secondly the neural network is invoked to approximate and model the key telemetry parameters of the satellite, and the neural net- work is optimized through particle swarm optimization algorithm. Thirdly times series method is incurred to predict the data of the telemetry parameters. Furthermore the predict data are contrasted to the outputs of the particle swarm optimized neural network, and the prognostics for satellite are achieved with the information. Finally an experiment using telemetry data with fault data in the power system of a satellite is set up to verify the feasibility of the method proposed in this paper, and the experimental results prove the effectiveness of the particle swarm optimized neural network in prognostics for satellite.