基于RBF网络的断路器电流自适应保护研究

针对传统断路器电流保护方法存在受系统运行方式影响、整定困难、智能化低等问题,本文提出了基于RBF的断路器电流自适应保护算法,并给出了算法的模型。该算法融合了RBF神经网络的故障检测和电流自适应保护。首先通过RBF网络检测负载线路的电流故障,然后用电流自适应算法进行保护。在对神经网络进行训练时,利用PSO算法对RBF神经网络的参数进行优化以此来提高网络的泛化能力和学习能力；然后采用优化后的PSO-RBF神经网络对电流故障进行诊断。实验表明,该算法较大地提高了断路器智能化管理水平。

An algorithm for current auto-adaptive protection of circuit breaker based RBF

To solve the problems such as tuning difficulties, low intelligence of the traditional current protection method in circuit breakers, this paper presents an adaptive current protection algorithm based on RBF and gives the model of the algorithm model. The algorithm combines fault detection based on RBF neural network and adaptive current protection. The algorithm detects the current fault of load line by RBF network, and then employs the current adaptive algorithm to deal with it . In the algorithm, the PSO method is used to optimize the RBF neural network in order to improve the generalization ability and learning capacity of the network. Experiments showed that the algorithm greatly improves intelligent management level of the circuit breaker.