皮带伸缩机动态称重数据处理优化算法研究  

Research on Optimization Algorithm of Dynamic Weighing Data Processing for Belt Telescopic Conveyor

作　　者：章玉 杨其华 何雨辰 李锐鹏 ZHANG Yu;YANG Qihua;HE Yuchen;LI Ruipeng(School of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,China)

机构地区：[1]中国计量大学机电工程学院,浙江杭州310018

出　　处：《仪表技术与传感器》2023年第8期114-119,共6页Instrument Technique and Sensor

基　　金：国家自然科学基金项目(61903352);浙江省自然科学基金项目(LY23F030004)。

摘　　要：针对皮带伸缩机包裹传输过程中设备振动干扰等问题,提出利用粒子群(PSO)算法优化径向基(RBF)神经网络的动态称重数据处理算法。使用倾角传感器检测到的称重段三轴加速度信号,与称重传感器检测到的包裹动态质量信号一起作为特征变量,通过低通滤波处理后,分别输入到RBF以及优化的PSO-RBF预测模型中。与前述各阶段数据处理结果相比,优化后的PSO-RBF算法的预测结果相对误差更小。在验证中,分别取1、5、10 kg等载荷下的测量数据进行预测,该优化算法预测结果的误差均在0.9%以内。Aiming at problems such as equipment vibration interference during the parcel transmission process of the belt telescopic conveyor,a dynamic weighing data processing algorithm using the particle swarm optimization(PSO)algorithm to optimize the radial basis(RBF)neural network was proposed.The three-axis acceleration signal of the weighing section detected by the inclination sensor was used as the characteristic variable together with the package dynamic quality signal detected by the load cell.After low-pass filtering,they were input into the RBF and the optimized PSO-RBF prediction model respectively.Compared with the data processing results of the previous stages,the prediction results of the optimized PSO-RBF algorithm had smaller relative errors.In the verification,the measured data under loads of 1 kg,5 kg,10 kg and so on were respectively used for prediction,and the errors of the prediction results of the optimization algorithm were all within 0.9%.

关 键 词：动态称重 信号处理 RBF神经网络 PSO算法 预测 

分 类 号：TH715[机械工程—测试计量技术及仪器]