金属露天矿旋回式破碎机在线故障诊断模型构建与实时分析

发布时间：2019-05-19 11:20

【摘要】：矿石破碎是露天矿采矿生产工艺的重要环节,旋回式破碎机作为露天矿进行破碎的大型设备,其故障的诊断通常较为复杂,难以利用主观经验进行精确及快速诊断。针对旋回式破碎设备的故障诊断问题,利用传感器实时采集数据,基于改进后BP神经网络构建故障诊断模型,以偏心套故障、轴承磨损、平行轴缺油、平行轴油温异常作为故障类型,以回流油温、润滑油油压、轴承振动频率、轴承转速作为故障特征参数,利用已知故障类型和故障样本数据对BP神经网络故障诊断模型进行了训练和优化,最后通过测试数据对优化后的旋回式破碎机故障诊断模型进行了验证。结果表明:基于BP神经网络的故障诊断模型能够对旋回式破碎机故障状态实时地做出有效判断,实现以预防为主的故障诊断方式,满足了露天矿大型旋回式破碎机的故障诊断的需求。
[Abstract]:Ore crushing is an important link in the mining production technology of open pit mine. As a large equipment for crushing open pit mine, the fault diagnosis of rotary crusher is usually complex, so it is difficult to make accurate and rapid diagnosis by using subjective experience. In order to solve the problem of fault diagnosis of circular crushing equipment, the fault diagnosis model is constructed based on the improved BP neural network by using the sensor to collect the data in real time, and the fault diagnosis model is constructed with eccentric sleeve fault, bearing wear and oil shortage of parallel shaft. The abnormal oil temperature of parallel shaft is taken as the fault type, and the return oil temperature, lubricating oil pressure, bearing vibration frequency and bearing speed are taken as the fault characteristic parameters. The fault diagnosis model of BP neural network is trained and optimized by using known fault types and fault sample data. Finally, the optimized fault diagnosis model of rotary crusher is verified by test data. The results show that the fault diagnosis model based on BP neural network can effectively judge the fault state of circular crusher in real time, and realize the fault diagnosis mode based on prevention. It meets the requirements of fault diagnosis of large cycle crusher in open pit mine.
【作者单位】：西安建筑科技大学管理学院;中钢集团矿业开发有限公司;
【基金】：国家自然科学基金项目(编号:51774228,51404182) 陕西省自然科学基金项目(编号:2017JM5043) 陕西省教育厅专项科研计划项目(编号:17JK0425)
【分类号】：TD451

【相似文献】