基于改进SAE的提升机制动系统故障诊断.pdfVIP

基于改进SAE 的提升机制动系统故障诊断 摘　 要：为了减少传统故障诊断方法人工主观干预对诊断结果的影响，使用无监督学习方式提取提升机监测数 据的故障特征，提出了一种基于稀疏自编码器的故障诊断方法. 首先分析了制动系统的故障机理，采集了提升机 正常运行和故障模拟状态下的监测数据，生成了故障诊断数据集；然后建立了SAE 故障诊断模型，并使用Dropout 和Adam 算法对其进行了优化；最后使用测试数据集对模型的性能进行了测试. 试验结果表明，提出的方法较好地 避免了稀疏数据的训练误差，减少了过拟合现象，降低了稀疏数据局部最优点的影响，故障类型的平均分类精度 达到94%，能有效地进行矿井提升机的故障诊断. 关键词： 故障诊断 ；稀疏自编码器 (SAE) ；Dropout 算法 ；制动系统 ；矿井提升机 Fault Diagnosis of Mine Hoist Brake System Based on Improved SAE Abstract：In order to reduce the influence of manual subjective intervention on the diagnosis results in tradition- al fault diagnosis methods, a fault diagnosis method was proposed based on sparse auto-encoder (SAE), using an unsupervised learning method to extract the fault characteristics of hoist monitoring data. First, the failure mech- anism of the brake system was analyzed, the monitoring data under the normal operation and failure simulation state of the hoist were collected, and a failure diagnosis datum set was generated. Then a SAE fault diagnosis model was established and optimized based on the Dropout and Adam algorithm. Finally, the performance of the model was tested using a test data set. The experimental results show that the presented method can better avoid the training error of sparse data, reduce the over-fitting phenomenon, and reduce the influence of the local optim- um of sparse data. The average classification accuracy of fault types can reach up to 94%, the presented method can realize mine hoist fault diagnosis effectively. Key words ：fault diagnosis；sparse auto-encoder (SAE)；Dropout algorithm；brake system；mine hoist 矿井提升机作为连接井上、井下的关键运输设 在传统故障诊断领域，众多学者针对矿井提升