摘要
为了更充分地利用矿井提升机在运转过程中的监测数据,对制动系统进行精确诊断,提出了一种基于稀疏自动编码器(SAE)的故障诊断方法。通过模拟故障试验,获取故障数据,经标准化处理后生成训练集和测试集。并加入Dropout正则化方法对故障诊断模型进行了优化,根据训练结果采用梯度下降法优化模型参数。最后使用测试数据集对优化前后的诊断模型进行对比试验。结果表明,文中提出的提升机故障诊断方法,减少了过拟合现象,降低了获取标签数据的工作量,故障类型的平均分类精度能够达到96%。此方法使用提升机的监测数据,减少人为的影响,可以对矿井提升机的故障进行准确诊断。
In order to make full use of the monitoring data of the mine hoist during operation and accurately diagnose the brake system,a fault diagnosis method based on Sparse Auto-Encoder(SAE)is proposed.Through the simulated failure test,the failure data is obtained,and the training set and the test set are generated after standardized processing.And add the Dropout regulariza⁃tion method to optimize the fault diagnosis model,and use the gradient descent method to optimize the model parameters accord⁃ing to the training results.Finally,the test data set is used to compare the diagnosis model before and after optimization.The re⁃sults show that the hoist fault diagnosis method proposed in this paper reduces the over-fitting phenomenon and the workload of obtaining label data,and the average classification accuracy of fault types can reach 96%.This method uses the monitoring data of the hoist for diagnosis,without subjective intervention of personnel,and can accurately diagnose the fault of the mine hoist.
作者
闫方元
李娟莉
苗栋
YAN Fang-yuan;LI Juan-li;MIAO Dong(College of Mechanical and Vehicle Engineering,Taiyuan University of Technology,Shanxi Taiyuan 030024,China;Shanxi Key Laboratory of Fully Mechanized Coal Mining Equipment,Shanxi Taiyuan 030024,China)
出处
《机械设计与制造》
北大核心
2024年第9期215-218,共4页
Machinery Design & Manufacture
基金
山西省自然科学基金面上项目(201901D111056)
山西省回国留学人员科研资助项目(2020-034)。
