Evaluation index values.

As an equipment failure that often occurs in coal production and transportation, belt conveyor failure usually requires many human and material resources to be identified and diagnosed. Therefore, it is urgent to improve the efficiency of fault identification, and this paper combines the internet of things (IoT) platform and the Light Gradient Boosting Machine (LGBM) model to establish a fault diagnosis system for the belt conveyor. Firstly, selecting and installing sensors for the belt conveyor to collect the running data. Secondly, connecting the sensor and the Aprus adapter and configuring the script language on the client side of the IoT platform. This step enables the collected data to be uploaded to the client side of the IoT platform, where the data can be counted and visualized. Finally, the LGBM model is built to diagnose the conveyor faults, and the evaluation index and K-fold cross-validation prove the model’s effectiveness. In addition, after the system was established and debugged, it was applied in practical mine engineering for three months. The field test results show: (1) The client of the IoT can well receive the data uploaded by the sensor and present the data in the form of a graph. (2) The LGBM model has a high accuracy. In the test, the model accurately detected faults, including belt deviation, belt slipping, and belt tearing, which happened twice, two times, one time and one time, respectively, as well as timely gaving warnings to the client and effectively avoiding subsequent accidents. This application shows that the fault diagnosis system of belt conveyors can accurately diagnose and identify belt conveyor failure in the coal production process and improve the intelligent management of coal mines.带式输送机故障是煤炭生产与运输环节中频发的设备故障类型，其识别与诊断通常需要耗费大量人力与物力资源。因此，提升故障识别效率迫在眉睫。本文结合物联网（Internet of Things, IoT）平台与轻量级梯度提升机（Light Gradient Boosting Machine, LGBM）模型，构建了带式输送机故障诊断系统。首先，针对带式输送机选取并安装传感器以采集其运行数据；其次，将传感器与Aprus适配器相连，并在物联网平台客户端配置脚本语言，此步骤可将采集到的数据上传至物联网平台客户端，实现数据的统计与可视化；最后，构建LGBM模型以实现输送机故障诊断，并通过评价指标与K折交叉验证验证了该模型的有效性。此外，该系统经搭建与调试后，在实际矿井工程中进行了为期三个月的应用测试。现场测试结果表明：（1）物联网客户端可顺利接收传感器上传的数据，并以图表形式呈现数据；（2）LGBM模型具备较高的识别精度。测试中，该模型精准检测出了各类输送机故障，包括皮带跑偏（发生2次）、皮带打滑（发生2次）、皮带撕裂（发生1次）及其他故障（发生1次），并及时向客户端发出预警，有效规避了后续事故的发生。本次应用表明，所构建的带式输送机故障诊断系统可在煤炭生产过程中精准诊断与识别带式输送机故障，提升煤矿的智能化管理水平。