论文部分内容阅读
为了减少地铁车站设备故障导致的人员伤亡,本文提出了粒子群算法结合BP神经网络对屏蔽门系统的故障进行预测。利用BP神经网络结构作为粒子群算法的适应度函数对BP网络的权值与阈值进行优化。在确定神经网络结构之后,该模型以权值和阈值作为粒子,利用粒子群算法的寻找全局最优的思想为BP网络寻找最优权值和阈值。减少了BP神经网络的训练结果出现较大偏差的概率。该算法可以适用于地铁站内受多种不定因素影响的设备,本文采用屏蔽门系统故障较为频繁的门锁机构来分析模型,得到的预测结果相差不到一天范围内,因此该算法具有理想的预测精度。最后利用MATLAB仿真验证该算法的可用性。
In order to reduce the casualties caused by the subway station equipment failure, this paper proposes a particle swarm optimization algorithm combined with BP neural network to predict the failure of the screen door system. BP neural network structure is used as the fitness function of particle swarm optimization to optimize the weight and threshold of BP network. After determining the structure of the neural network, the model uses weights and thresholds as particles, and uses the particle swarm optimization algorithm to find the global optimal solution to find the optimal weights and thresholds for the BP network. Reduce the probability of BP neural network training results appear larger deviation. The algorithm can be applied to the equipment affected by many uncertainties in the subway station. In this paper, the door lock mechanism with more frequent failures in the screen door system is adopted to analyze the model and the prediction results are within one day. Therefore, the algorithm has an ideal prediction Accuracy. Finally, the feasibility of this algorithm is verified by MATLAB simulation.