摘要
为有效监测带式输送机异常温升,通过固定式传感器与人工巡检采集关键部位实时温度,利用变分模态分解对温度数据进行去噪和分解,同时引入蛇优化算法对长短时记忆网络中的参数进行优化,改善温度时序数据处理效果,最终提出了一种温度智能监测模型。试验结果表明,在公开数据集测试中,该模型温度监测误差为 2.1 ℃。该方法对驱动电动机、滚筒和液压系统的监测精度分别达到 93.9%、90.2% 和 95.1%,监测时延最短为 5.97 s,参数量仅为 152 万,误差收敛至 2.6 ℃。由此可知,该模型能够有效提升温度异常检测时的实时性与精确性,为带式输送机的智能化运维提供技术支撑。
In order to effectively monitor the abnormal temperature rise of the belt conveyor,the real-time temperature of key parts was collected by fixed sensors and manual inspection.The variational mode decomposition was used to denoise and decompose the temperature data.At the same time,the snake optimization was introduced to optimize the parameters in the long short-term memory network to improve the effect of the temperature time series data processing.Finally,an intelligent temperature monitoring model was proposed.The test results showed that the temperature monitoring error of the model was 2.1℃in the open data set test.The monitoring accuracy of this method for driving motor,drum and hydraulic system reached 93.9%,90.2%and 95.1%respectively.The shortest monitoring delay was 5.97 s,the parameter quantity was only 1.52 million,and the error converged to 2.6℃.It could be seen that the model could effectively improve the real-time and accuracy of temperature anomaly detection,and provide technical support for the intelligent operation and maintenance of the belt conveyor.
作者
韩宝虎
杨坤
包涵
赵亮
姜成昊
邵建华
HAN Baohu;YANG Kun;BAO Han;ZHAO Liang;JIANG Chenghao;SHAO Jianhua(CHN Energy Baorixile Energy Co.,Ltd.,Hulun Buir 021025,Inner Mongolia,China;CCTEG Beijing Huayu Engineering Co.,Ltd.,Beijing 100120,China)
出处
《矿山机械》
2025年第7期71-75,共5页
Mining & Processing Equipment
关键词
带式输送机
智能监测
变分模态分解
蛇优化算法
belt conveyor
intelligent monitoring
variational mode decomposition
snake optimization
