| 董慧芬,郑 坤,杨占刚.基于 GA-BRBPNN 的航空自耦变压整流器
故障诊断方法[J].电子测量与仪器学报,2022,36(9):217-225 |
| 基于 GA-BRBPNN 的航空自耦变压整流器
故障诊断方法 |
| Fault diagnosis method for auto-transformerrectifier unit based on GA-BRBPNN |
| |
| DOI： |
| 中文关键词: 航空自耦变压整流器 BP 神经网络 遗传算法 贝叶斯正则化 故障诊断 |
| 英文关键词:aeronautical autotransformer rectifier unit BP neural network genetic algorithm Bayesian regularization fault diagnosis |
| 基金项目:国家自然科学基金（51377161）、中国民航大学实验技术创新基金（2020CXJJ87）项目资助 |
|
|
|
|
| 摘要点击次数: 1407 |
| 全文下载次数: 1084 |
| 中文摘要: |
| 航空自耦变压整流器(auto-transformer rectifier unit, ATRU)是飞机高压直流电网关键电能变换装置,在运行过程中受高
温、机械应力、荷载波动等因素持续影响,其内部元件可能出现相应故障,进而威胁飞机可靠运行及持续适航。 针对 ATRU 整流
部分故障信号频谱难以区分、诊断准确率不高问题,提出一种遗传算法(genetic algorithm,GA)与贝叶斯正则化反向传播神经网
络(Bayesian regularisation back propagation neural network,BRBPNN)相结合的故障诊断识别方法。 首先,实现 ATRU 故障仿真,
以时频分析方式处理所得信号,从而挖掘不同故障状态的特征信息;随后采用 GA 算法优化 BRBPNN 初始权阈值并建立最优
GA-BRBNPNN 诊断模型,将特征样本输入诊断模型进行故障分类识别,测试模型性能;最后,搭建故障模拟实验平台对实测数
据进行模型验证。 实验结果分析可知,对于仿真故障,该模型诊断准确率可达 99. 46%,对于实测故障,该模型可全部诊断识别
待测样本;由此表明提出的 GA-BRBPNN 优化模型诊断效果好,具有较高实用价值。 |
| 英文摘要: |
| Aeronautical auto-transformer rectifier unit (ATRU) is the key power conversion device of aircraft high-voltage DC power
grid. It is continuously affected by high temperature, mechanical stress, load fluctuation and other factors during operation, then its
internal components may appear corresponding failure, which can lead to threaten the reliable operation and continued airworthiness of
the aircraft. The spectrum of the fault signal in the rectifier part of ATRU is difficult to distinguish and the diagnostic accuracy is low, a
fault diagnosis method based on genetic algorithm ( GA) combined with Bayesian regularization back propagation neural network
(BRBPNN) is proposed. Firstly, an ATRU fault simulation model is implemented and then the collected signals are processed by means
of time-frequency analysis so as to mine the feature information of different fault states. Subsequently, genetic algorithm is used to
optimize the initial weights and thresholds of BRBPNN and the optimal GA-BRBPNN diagnosis model is established. The feature samples
are introduced into the diagnosis model for fault identification and model performance testing. Finally, the experiment platform of fault
simulation is built and the measured fault data is used to validate the method. The experimental results show that the diagnostic accuracy
of the proposed method can reach 99. 46% for the simulated faults and the method can diagnose and identify all the samples to be tested
for the actual faults. Therefore, the method based on GA-BRBPNN has good diagnostic effect and high practical value. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
