基于CSSA-LSTM神经网络的动态称重算法的研究
Research on dynamic weighing algorithm based on CSSA-LSTM neural network
狄俊豪 1郭晨霞 1杨瑞峰1
作者信息
- 1. 中北大学仪器与电子学院 太原 030051
- 折叠
摘要
为了提高动态称重的测量精度,实现智慧牧场的实时监测和精细化管理,提出利用混沌麻雀搜索算法优化LSTM的神经网络的动态称重算法.通过动态称重台进行数据采集,并使用卡尔曼滤波算法对干扰数据进行处理.利用Tent映射策略和高斯变异后的麻雀搜索算法优化LSTM神经网络各参数,从而建立CSSA-LSTM神经网络模型.结果表明,CSSA-LSTM神经网络的平均绝对百分比误差在1.5％以内,平均绝对误差减少了0.874,均方根误差减少了1.1153.对比实验证明,该混合算法预测的误差最小,有效提高了动态称重的测量精度.
Abstract
In order to improve the measurement accuracy of dynamic weighing and realize real-time monitoring and fine management of intelligent pasture,a dynamic weighing algorithm based on chaotic sparrow search algorithm to optimize LSTM neural network is proposed.The data is collected by the dynamic weighing platform,and the Kalman filter algorithm is used to process the interference data.The CSSA-LSTM neural network model is established by using the Tent mapping strategy and the sparrow search algorithm after Gaussian mutation to optimize the parameters of the LSTM neural network.The results show that the average absolute percentage error of CSSA-LSTM neural network is within 1.5％,the average absolute error is reduced by 0.874,and the root mean square error is reduced by 1.1153.The comparative experiments show that the hybrid algorithm has the smallest prediction error and effectively improves the measurement accuracy of dynamic weighing.
关键词
动态称重/卡尔曼滤波算法/混沌麻雀搜索算法/LSTM神经网络Key words
dynamic weighing/Kalman filter algorithm/chaos sparrow search algorithm/LSTM neural network引用本文复制引用
基金项目
山西省中央引导地方科技发展自由探索类基础研究项目(YDZJSX20231A032)
出版年
2024
NETL
NSTL
万方数据