| 金文祥.基于IQGA-ELM的无绝缘轨道电路故障诊断研究[J].唐山学院学报,2024,37(6):34-42 |
| 基于IQGA-ELM的无绝缘轨道电路故障诊断研究 |
| Research on Fault Diagnosis of Jointless Track Circuits Based on IQGA-ELM |
| 投稿时间：2024-02-14 |
| DOI：10.16160/j.cnki.tsxyxb.2024.06.006 |
| 中文关键词: 角度编码 量子旋转门 量子遗传算法 极限学习机 轨道电路 故障诊断 |
| 英文关键词: angle encoding quantum rotation gate quantum genetic algorithm extreme learning machine track circuits fault diagnosis |
| 基金项目: |
|
| 摘要点击次数: 824 |
| 全文下载次数: 944 |
| 中文摘要: |
| 根据二端口网络理论建立了ZPW-2000A型轨道电路等效模型,在此基础上分析了区段轨道不同状态对机车感应电压信号幅值的影响并进行仿真。采用角度编码与小区间种群初始化、联合交叉与量子非门变异及量子旋转门自适应动态调整三个策略改进了量子遗传算法,并对极限学习机的输入层与隐含层间连接权值及隐含层神经元阈值进行寻优;通过改进的量子遗传算法优化极限学习机实现了对轨道电路的故障诊断。结果表明,该分类方法在保持较快收敛速率的同时,分类识别准确率也较高。 |
| 英文摘要: |
| According to the two-port network theory, an equivalent model of the ZPW 2000A track circuit is established, and the influence of different section track states on the amplitude of the locomotive-induced voltage signal is analyzed and simulated. The quantum genetic algorithm is improved through three strategies: angle encoding and small interval population initialization, joint crossover and quantum non-gate mutation, and adaptive dynamic adjustment of the quantum rotation gate. The connection weights between input layer and hidden layer and neuron thresholds in hidden layer of the extreme learning machine are optimized; The fault diagnosis of track circuit is realized by optimizing extreme learning machine based on improved quantum genetic algorithm. The results show that the classification method maintains a fast convergence rate while also achieving high classification recognition accuracy. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |