Abstract：The temperature sensitivity of the key components such as the electromagnetic force compensation cell is the main factor causing the temperature drift in the electronic analytical balance. In order to eliminate the error caused by the temperature drift, a model and compensation method for electronic analytical balance were proposed based on the support vector machine. Through analyzing the factors of the temperature drift, the temperature rise of the temperature sensitive element and the temperature drift data of the electronic analytical balance were taken as the inputs of the model, the adaptive parameter optimization method was used to search the optimal parameter, the temperature drift error model of electronic analytical balance was established and the temperature drift compensation was performed. The test results demonstrate that the absolute value of the full load indication error of electronic analytical balance, of which the range is 200g and the resolution is 0.1mg, not more than 0.3mg, that the indication error caused by temperature drift is superior to the impact index of the 1st class balance defined by Chinese National Standard GB/T 26497—2011 “Electronic balance”.
刘亚坤,黄强,李建闽,孙彪. 基于SVM的电子分析天平温度漂移补偿方法[J]. 计量学报, 2018, 39(6): 826-831.
LIU Ya-kun,HUANG Qiang,LI Jian-min,SUN Biao. Temperature Drift Compensation Method for Electronic Analytical Balance Based on Support Vector Machine. Acta Metrologica Sinica, 2018, 39(6): 826-831.
［1］GB/T 26497—2011 电子天平［S］.
［2］滕召胜, 郁文贤, 夏胜平. 电子分析天平温漂与时漂的自动补偿［J］. 国防科技大学学报, 2000,22(3):6-10.
［3］黄强, 滕召胜, 唐享, 等. 电子分析天平温度漂移补偿算法研究［J］. 仪器仪表学报, 2015,36(9):1987-1995.
［4］Kudryk Y Y, Slipokurov V S, Koltsov G S. Measurement of p-n junction-to-case thermal resistance in impatt diodes［C］// 23rd International Crimean Conference on Microwave & Telecommunication Technology. Crimea, Ukraine, 2013:762-763.
［5］Yang C, Li C, Zhang C. The application of RBF neural network in the compensation for temperature drift of the silicon pressure sensor［C］//2010 International Conference on Computer Design and Applications. Qinhuangdao, China, 2010:434-437.
［6］周玮, 张妹红, 张赜, 等. 一种新的高精度电子天平温度补偿方法［J］. 东北大学学报(自然科学版), 2006,27(4):371-374.
［7］Vapnik V N. The nature of statistical learning theory［J］. IEEE Transactions on Neural Networks, 2002,8 (6):1564-1564.
［8］程骏超, 房建成, 吴伟仁, 等. 基于SVM的激光陀螺温度误差建模与补偿方法［J］. 仪器仪表学报, 2013,34(4):721-727.
［9］程淑红 高许 周斌. 基于多特征提取和SVM参数优化的车型识别研究［J］.计量学报,2018, 39(3):348-352.
［10］孟宗,季艳,谷伟明,等. 基于支持向量机和窗函数的DEMD端点效应抑制方法［J］. 计量学报, 2016, 37(2):180-184.
［11］杨景明,陈伟明,车海军,等. 基于粒子群算法优化支持向量机的铝热连轧机轧制力预报［J］. 计量学报, 2016, 37(1):71-74.
［12］陈良柱, 滕召胜, 杨敏, 等. 电磁力平衡传感器的磁缸温度稳定控制方法研究［J］. 仪器仪表学报, 2012,33(9):1995-2001.
［13］邰永, 刘赵淼. 感应电机全域三维瞬态温度场分析［J］. 中国电机工程学报, 2010,30(30):114-120.
［14］刘艳芳, 徐克宝. 变电所高压开关触点无线温度测量技术研究［J］. 电子测量技术, 2014,37(12):75-79.
［15］Wang H F, Hu D J. Comparison of SVM and LS-SVM for Regression［C］//2005 International Conference on Neural Networks and Brain.Beijing,China,2005:279-283.
2018, Vol. 39 
