Research on dynamic weighing algorithm based on CEEMD -GRU model
YANG Bang¹, LAI Zhengchuang^1,2, YANG Xiaoxiang^1,3
1. College of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350108, China;
2. Fujian Province Institute of Metrology, Fuzhou 350003, China;
3. Quanzhou Normal University, Quanzhou 362000, China
Abstract: Aiming at the problem of low weighing accuracy caused by external interference in the weighing process of dynamic truck scale, a weighing algorithm combining complementary ensemble empirical mode decomposition (CEEMD) and GRU neural network was proposed. Firstly the original weighing signal was decomposed by CEEMD, and the residual component obtained was the axle load signal that preliminarily filtered out the interference signal. Then the residual component was used as the input layer of GRU neural network to construct the network model and output the vehicle axle load. The research results show that the vehicle dynamic weighing error of this method is controlled within 1.2% after removing individual abnormal data caused by measurement error. Compared with the traditional single model, it has higher weighing accuracy and stronger practicability.
Keywords: dynamic weighing;complementary ensemble empirical mode decomposition;gated recurrent unit neural network;signal processing;deep learning
2023, 49(9):108-114  收稿日期: 2021-11-19;收到修改稿日期: 2022-01-27
基金项目: 福建省属公益类科研院所基本科研专项项目（2019R1016-2）；泉州市科技局科技计划项目（2020C055）
作者简介: 杨帮（1997-），男，江西南昌市人，硕士研究生，专业方向为动态称重系统的开发
参考文献
[1] 文常保, 高丽红, 方吉善, 等. 基于改进型限幅平均滤波法的高精度称重系统研究[J]. 传感技术学报, 2014, 27(5): 649-653
[2] ISUFI E, LOUKAS A, SIMONETTO A, et al. Autoregressive moving average graph filtering[J]. IEEE Transactions on Signal Processing, 2016, 65(2): 274-288
[3] 邹永宁, 姚功杰. 自适应窗口形状的中值滤波[J]. 光学精密工程, 2018, 26(12): 161-172
[4] 文仲寺, 江毅. 光纤分布式振动系统中的信号处理算法研究[J]. 仪表技术与传感器, 2020(6): 95-99
[5] 王中立, 李丽宏. 基于石英传感器的动态称重数据处理算法研究[J]. 传感技术学报, 2017, 30(2): 236-241
[6] 何定桥, 王鹏军, 杨军. 深度神经网络在EMD虚假分量识别中的应用[J]. 工程力学, 2021, 38(S1): 195-201
[7] 陈德昊, 林建恒, 衣雪娟, 等. 基于小波包时频图特征和卷积神经网络的水声信号分类[J]. 声学技术, 2021, 40(3): 336-340
[8] 黄玉杨, 黄咏梅. 基于遗传算法的涡街信号随机共振检测方法[J]. 中国测试, 2021, 47(4): 101-106
[9] 唐思豪, 滕召胜, 孙彪, 等. ADAM改进BP神经网络与动态称重应用[J]. 电子测量与仪器学报, 2021, 35(4): 127-135
[10] SILVA M M, SIMAS E F, FARIAS P C, et al. Intelligent embedded system for decision support in pulsed eddy current corrosion detection using Extreme Learning Machine[J]. Measurement, 2021, 185: 110069
[11] GAJDA J, SROKA R, BURNOS P. Sensor data fusion in multi-sensor weigh-in-motion systems[J]. Sensors (Basel Switzerland), 2020, 20(12): 3357
[12] KIRUSHANTH S, KABASO B. Design and development of weigh-in-motion using vehicular telematics[J]. Journal of Sensors, 2020, 2020(4): 1-22
[13] 秦伟, 徐国艳, 余贵珍. 基于BP神经网络的汽车车载称重系统研究[J]. 汽车工程, 2017, 39(5): 599-605
[14] 郝晓娴, 牛昱光, 韩芝星, 等. 基于小波和BP神经网络的车载动态称重算法[J]. 仪表技术与传感器, 2017(8): 110-113
[15] 方剑青, 矫桂琼. 频响函数作为神经网络输入的BP算法实现[J]. 计算机仿真, 2007(3): 86-89
[16] 陈家益, 战荫伟, 曹会英, 等. 连续可微阈值函数与尺度阈值的小波去噪[J]. 电子测量与仪器学报, 2018, 32(10): 169-176
[17] 张鹏林, 杨超, 董拴涛, 等. 基于Lamb波的风电叶片复合材料声发射源定位研究[J]. 中国测试, 2019, 45(7): 140-146
[18] 陈克, 张晓冬, 李宁. 基于CEEMD与自适小波阈值组合降噪在OPAX方法的应用[J]. 振动与冲击, 2021, 40(16): 192-198
[19] 王晓东, 宁静, 陈春俊. 1D CNN和LSTM高速列车横向稳定性状态识别研究[J]. 中国测试, 2020, 46(11): 25-30
[20] 叶興, 薛家祥. 改进型LSTM网络光伏发电功率预测研究[J]. 中国测试, 2019, 45(11): 14-20
[21] 赵兵, 王增平, 纪维佳, 等. 基于注意力机制的CNN-GRU短期电力负荷预测方法[J]. 电网技术, 2019, 43(12): 4370-4376
[22] 杜长东. 低频动态载荷理论分析及称重精度提高算法研究[J]. 公路交通科技, 2018, 35(4): 153-158
[23] 严鸿, 管燕萍. BP神经网络隐层单元数的确定方法及实例[J]. 控制工程, 2009, 16(S2): 100-102