论文部分内容阅读
针对模拟电路的软故障,提出一种基于混合粒子群算法的BP网络方法来诊断模拟电路中的故障。该方法是把遗传算法和粒子群算法结合起来优化BP网络的权值和阈值,试图解决传统的BP网络在模拟电路故障诊断过程中易陷入局部最小的问题。详细阐述了该算法的实现,给出了该算法的详细流程图,并通过仿真实例比较了传统BP网络与混合粒子群算法优化下的BP网络在故障诊断中的表现,给出了实验实例仿真结果的图形和数据表格。由仿真图形和数据表格,形象直观地看出了两种算法运用在模拟电路故障诊断中的差别,验证了混合粒子群算法优化BP网络在模拟电路故障诊断中的有效性及可行性。
Aiming at the soft fault of analog circuit, a BP network method based on hybrid PSO is proposed to diagnose the fault in analog circuit. This method combines genetic algorithm and particle swarm optimization to optimize the weights and thresholds of BP network, trying to solve the problem that traditional BP network is easy to fall into local minimum in the process of analog circuit fault diagnosis. The realization of this algorithm is expounded in detail, and a detailed flow chart of the algorithm is given. The performance of BP network under the condition of traditional BP network and hybrid particle swarm optimization is compared in the fault diagnosis by simulation examples. The experimental example simulation Results of the graphs and data tables. The differences between the two algorithms used in the fault diagnosis of analog circuits are visually observed from the simulation graphs and data tables. The effectiveness and feasibility of the hybrid particle swarm optimization algorithm in the fault diagnosis of analog circuits are verified.