针对皮带秤在使用中难以保持标称计量精度的缺点,提出将过程神经网络引入皮带秤动态称重误差的补偿中。将动态称量过程中皮带秤单位长度上的重量、皮带速度、皮带垂度变化作为模型输入,设计了应用于皮带秤动态称重误差研究的单隐层过程神经网络误差反传播学习算法,利用Matlab软件对算法模型进行训练和测试,模型经过149次学习优化达到网络精度要求,测试组误差为1%,较使用网络前的原误差明显降低,验证了算法的可行性和有效性。
Abstract
To improve the weighing precision of the belt weigher, it was proposed to introduce process neural network (PNN) to compensate the dynamic weighing error of belt weigher. The weight per unit length of the belt weigher, speed of belt, and variation in belt sag in dynamic weighing process were used as model input. The single hidden layer PNN error back propagation learning algorithm was designed to apply to the study of the dynamic weighing error of the belt weigher. The algorithm model was trained and tested by MATLAB software and the model achieved network accuracy requirements after 149 learning optimizations. The test group error reaches 1%, which is significantly lower than the original error before using the network, and verifies the feasibility and effectiveness of the algorithm.
关键词
计量学 /
皮带秤 /
动态称重 /
误差补偿 /
学习算法 /
过程神经网络
Key words
metrology;belt weigher;dynamic weighing /
error compensation;learning algorithm;process neural network
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］施昌彦. 动态称重测力技术的现状和发展趋势［J］. 计量学报, 2001, 22(3): 201-205.
Shi C Y. State of Arts and Trends for the Dynamic Weiging and Force Measuring Technology［J］. Acta Metrologica Sinica, 2001, 22(3): 201-205.
［2］OIML R50 Continuous totalizing automatic weighing instrument(belt weighers)-Part 1: Metrological and technical requirements［S］. 2014.
［3］刘炜, 张永亮. 提高自动衡器的检测能力推动产业发展促进节能减排［C］//第10届称重技术研讨会,上海, 2011.
［4］袁延强. 皮带秤误差理论与耐久性讨论［C］//第11届称重技术研讨会, 江苏, 南京, 2012.
［5］王有贵, 吴双双, 陈红江. 称重传感器蠕变误差的神经网络补偿方法［J］. 计量学报, 2018, 39(4): 510-514.
Wang Y G, Wu S S, Chen H J. Compensation Method for Creep Error of Load Cell Based on Neural Networks［J］. Acta Metrologica Sinica, 2018, 39(4): 510-514.
［6］Hagan M T, Demuth H B, Beale M H. Neural Network Design ［M］. Boston: PWS Publishing Company, 1996.
［7］何新贵, 梁久祯. 过程神经元网络的若干理论问题［J］. 中国工程科学, 2000, 2(12): 40-44.
He X G, Liang J Z. Some Theoretical Issues on Procedure Neural Networks［J］. Engineering Science, 2000, 2(12): 40-44.
［8］初琦. 带式输送机动态称重检测理论与试验研究［D］. 北京: 中国矿业大学, 2014.
［9］梅松, 周月娥, 李东波, 等. 基于最小二乘曲线拟合法的皮带垂度与张力关系研究［J］. 制造业自动化, 2012,34(10): 123-126.
Mei S, Zhou Y E,Li D B, et al. The relational analysis of sag and tension based on the method of least square curve fitting［J］. Manufacturing automation, 2012,34(10): 123-126.
［10］邓韧, 李著信, 樊友洪. 基于多种正交基函数的模块化过程神经元网络［J］. 计算机工程与应用, 2005, 41(30): 69-71.
Deng R, Li Z X, Fan Y H. Modular Process Neural Network Based on Multi-Basis-functions［J］. Computer Engineering and Applications, 2005, 41(30): 69-71.
［11］何新贵, 梁久祯, 许少华. 过程神经网络的训练及其应用［J］. 中国工程科学, 2001, 3(4): 31-35.
He X G, Liang J Z, Xu S H. Learning and Applications of Procedure Neural Networks［J］. Engineering Science, 2001, 3(4): 31-35.
［12］朱亮. 散状物料连续累计称重系统精度补偿研究［D］. 南京: 南京理工大学, 2016.
［13］丁刚, 钟诗胜. 对向传播过程神经网络及其学习算法［C］//中国神经网络学术会议. 安徽, 合肥, 2004.
［14］许少华, 刘扬, 何新贵. 基于过程神经网络的水淹层自动识别系统［J］. 石油学报, 2004, 25(4): 54-57.
Xu S H, Liu C, He X G. Automatic identification of water-flooded formation based on process neural network［J］. Acta Petrolei Sinica, 2004, 25(4): 54-57.
［15］钟诗胜, 朴树学, 丁刚. 改进BP算法在过程神经网络中的应用［J］. 哈尔滨工业大学学报, 2006, 38(6): 840-842.
Zhong S S, Piao S S, Ding G. Application research of improved BP algorithm in process neural networks［J］. Journal of Harbin Institute of Technology, 2006, 38(6): 840-842.
［16］Li B Y, Li Y X, Wang H T, et al. Compensation of automatic weighing error of belt weigher based on BP neural network［J］. Measurement, 2018,129: 625-632.
PDF(516 KB)
