张强,刘志恒,王海舰,顾颉颖,田莹,仲丛华.基于多特征信息融合的截齿磨损程度识别研究[J].电子测量与仪器学报,2017,31(12):1974-1983 |
基于多特征信息融合的截齿磨损程度识别研究 |
Research on wear degree recognition of picks based on multi feature information fusion |
|
DOI:10.13382/j.jemi.2017.12.014 |
中文关键词: 截齿 磨损程度 BP神经网络 模糊隶属度 振动信号 声发射信号 |
英文关键词:pick wear degree BP neural network fuzzy membership vibration signal acoustic emission signal |
基金项目:国家自然科学基金(51504121)、辽宁省自然基金(201601324)、煤炭资源安全开采与洁净利用工程研究中心开放课题(LNTU16KF02)、机械传动国家重点实验室开放基金(SKLMT KFKT 201515)、国家自然科学基金面上项目(51774161)资助 |
|
Author | Institution |
Zhang Qiang | 1. College of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China; 2. Coal Resource Safety Mining and Clean Utilization
Engineering Research Center, Fuxin 123000, China;3. State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing 400044, China |
Liu Zhiheng | College of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China |
Wang Haijian | School of Mechanical and Electrical Engineering, Guilin University of Electronic Technology, Guilin 541004, China |
Gu Jieying | College of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China |
Tian Ying | College of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China |
Zhong Conghua | College of Photoelectric Information,Changchun University of Science and Technology,Changchun 130012,China |
|
摘要点击次数: 2562 |
全文下载次数: 7407 |
中文摘要: |
为实现截割过程中截齿磨损程度的在线监测和精准识别,提出一种基于多特征信息融合的采煤机截齿磨损程度识别方法。针对不同磨损程度截齿截割过程中的振动和声发射信号进行时域分析和小波包分析;针对两相邻磨损程度截齿的特征样本存在数据交集,增加系统识别难度的问题,构建最小模糊度优化模型并计算各特征参数的最优模糊隶属度函数,获取特征样本的最大隶属度。运用多特征数据样本对BP(back propagation)神经网络识别模型进行学习和训练。实验结果表明,截齿磨损程度识别模型的判别结果和样本实际磨损类别相符,能够实现对截齿磨损程度的在线监测和精准识别。研究结果对于实际工程中截齿的监测和更换具有重要意义。 |
英文摘要: |
In order to realize the on line monitoring and accurate identification of picks wear degree in the cutting process, a new method based on multi feature information fusion was proposed for identifying shearer pick wear degree. The vibration and acoustic emission signals in the cutting process of different picks wear degree were analyzed by time domain analysis and wavelet packet analysis. According to the features of two adjacent pick wear degrees, there were data intersections for characteristic samples, which increased the difficulty of system identification. The optimal fuzzy membership function for each characteristic signal was calculated by using the least fuzzy optimization model, the maximum membership degree of the feature sample was obtained. The back propagation(BP) neural network recognition model was trained and learned by using multi feature data samples. The experimental results show that the results of network discrimination are consistent with actual wear level of test sample. It can accurately monitor and identify the type of picks wear. The research results have great significance to monitoring and replacement of picks in actual engineering. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|