摘要
破碎机是采矿行业中应用十分广泛的设备。随着自动化程度的提高和设备的结构与性能的复杂化,设备管理与维护用在矿山生产中占有举足轻重的地位。本文针对破碎机故障征兆参数的变化趋势与程度,利用模糊数学知识和相关理论,采用不同的变化等级和阈值,建立破碎机典型故障现象与故障征兆列表。同时利用基于MATLAB环境下的BP模糊神经网络,实现了对破碎机故障的模糊诊断。通过仿真和试验结果表明,这种方法可有效地进行破碎机故障样本模式的模糊量化处理,极大地改善了神经网络训练的收敛性,有利于破碎机的故障诊断。
The crusher is quite important and widespread equipment in mining industry. Along with automaticity enhancement and equipment complication, the equipment maintenance cost holds the pivotal status in the cost of metallurgy production. The fault phenomena and fault symptom list are established through the use of fuzzy mathematics knowledge and related theories with regard to the various change directions and degrees of the fault symptom parameters of the crusher, using different variation grades and thresholds. Meanwhile, by utilizing a BP neural network based on a MATLAB environment realized was a fuzzy fault diagnostic for the crusher. At last, this fuzzy neural networks fault diagnosis is simulated with Matlab" s Neural Networks Toolbox. The simulation results show that it" s highly effective in conducting the fuzzy quantitative treatment of fault sample modes of a crusher, dramatically improving the convergence of a neural network training and facilitating the fault diagnosis of the crusher.
出处
《微计算机信息》
北大核心
2006年第03S期207-208,206,共3页
Control & Automation
基金
十五国家科技攻关课题:(2004BA616A-11-01)