摘要
刮板输送机作为煤矿综采工作面的核心运输设备,其运行可靠性直接影响煤矿生产效率与作业安全。针对传统刮板输送机故障诊断依赖人工巡检、诊断滞后、准确率低等问题,设计了一种基于多传感器融合与BP神经网络的智能化故障诊断系统。首先,分析刮板输送机关键部件的常见故障机理,确定振动、温度、电流为核心监测参数;其次,完成该系统硬件设计,包括传感器选型与布置、数据采集模块及以太网通信模块搭建;最后,通过MATLAB构建BP神经网络故障诊断模型,采用煤矿现场采集的1 200组工况数据对模型进行训练与验证。实验结果表明:该系统对刮板输送机典型故障的诊断准确率达到96.8%,响应时间少于0.5 s,可实现故障的实时监测与精准识别,为煤矿机械的智能化运维提供了技术支撑。
As the core transportation equipment in fully mechanized mining face of coal mine,the operational reliability of scraper conveyor directly affects coal mine production efficiency and operational safety.Aiming at the problems of traditional scraper conveyor fault diagnosis,such as reliance on manual inspection,delayed diagnosis and low accuracy,designed an intelligent fault diagnosis system based on multi-sensor fusion and BP neural network.Firstly,the common fault mechanisms of key components of the scraper conveyor were analyzed,and vibration,temperature and current were determined as the core monitoring parameters.Secondly,the hardware of this system was designed,including sensor selection and layout,construction of the data acquisition module,and Ethernet communication module.Finally,a BP neural network fault diagnosis model was built by using MATLAB,and 1200 sets of working condition data collected from the coal mine site were used to train and verify the model.The experimental results show that this system achieves a diagnostic accuracy of 96.8%for typical faults of the scraper conveyor,with a response time of less than 0.5 s.It can realize real-time monitoring and accurate identification of faults,providing technical support for the intelligent operation and maintenance of coal mine machinery.
作者
孔令成
Kong Lingcheng(College of Mechanical and Electronic Engineering,Shandong University of Science and Technology,Qingdao 266590,China;Shuangma No.1 Coal Mine,Ningxia Coal Industry Co.,Ltd.,CHN Energy Group,Yinchuan 750408,China)
出处
《煤矿机械》
2026年第1期188-192,共5页
Coal Mine Machinery
基金
国家能源集团宁夏煤业有限责任公司双马一矿科研项目(ZBX202405020-CX)。
