基于声发射信号的蜗轮磨损程度在线监测

发布时间：2018-10-31 20:55

【摘要】：为实现对蜗轮蜗杆减速器工作过程中蜗轮磨损程度的精确监测,利用多通道声发射检测仪器对不同磨损程度的蜗轮声发射信号进行在线采集。采用小波分析方法对信号进行去噪处理,提取声发射特征信号值,根据最小模糊熵优化模型构造出不同磨损程度蜗轮的模糊隶属度函数。采用ANFIS多维模糊神经网络实现多通道声发射信号的决策融合,提高了蜗轮磨损程度识别结果的准确性。通过对随机磨损程度的蜗轮进行实际验证,实验结果验证了系统的有效性和可靠性。
[Abstract]:In order to accurately monitor the wear degree of worm gear in the working process of worm gear reducer, the acoustic emission signals of worm gear with different wear degree are collected on line by means of multi-channel acoustic emission detection instrument. The wavelet analysis method is used to de-noising the signal, and the acoustic emission characteristic signal is extracted. According to the minimum fuzzy entropy optimization model, the fuzzy membership function of the wormgear with different wear degree is constructed. The multi-channel acoustic emission signal decision fusion is realized by using ANFIS multi-dimensional fuzzy neural network, and the accuracy of the recognition result of worm-gear wear degree is improved. The validity and reliability of the system are verified by the actual verification of the worm gear with random wear degree.
【作者单位】：辽宁工程技术大学机械工程学院;大连理工大学工业装备结构分析国家重点实验室;重庆大学机械传动国家重点实验室;中国煤矿机械装备有限责任公司;
【基金】：国家自然科学基金(51504121) 辽宁省自然科学基金(201601324)资助项目辽宁“百千万人才工程”培养经费(2014921070) 辽宁省优秀人才支持计划(LJQ2014036)资助项目
【分类号】：TH132.44

【相似文献】