作者：张龙, 张宝国, 张继军, 张东亮, 孔德骞

作者单位：西北核技术研究所，陕西 西安 710024

关键词：最小二乘支持向量机;粒子群优化算法;热电偶;非线性校正

摘要：

为改善热电偶温度传感器的非线性特性，构建基于粒子群优化算法（particle swarm optimization，PSO）和最小二乘支持向量机（least squares support vector machine，LSSVM）的热电偶非线性校正模型。针对LSSVM算法参数难确定的问题，选用PSO算法搜索LSSVM算法中惩罚系数和核函数参数的最优组合，用优化后的PSO-LSSVM校正模型逼近热电偶的非线性函数关系。为验证该模型的有效性，分别采用BP网络模型、RBF网络模型、LSSVM模型和PSO-LSSVM模型进行热电偶非线性校正，结果表明：PSO-LSSVM模型在热电偶非线性校正应用中表现出最优的稳定性和准确性，其最大拟合误差仅为0.12 ℃，均方误差为0.0033，准确率达到99.82%。将该模型应用于有限空间爆炸温度的非线性校正中，可取得较好的实际应用效果。

Research on nonlinear correction method of thermocouple based on PSO-LSSVM
ZHANG Long, ZHANG Baoguo, ZHANG Jijun, ZHANG Dongliang, KONG Deqian
Northwest Institute of Nuclear Technology, Xi’an 710024, China
Abstract: In order to improve the nonlinear characteristics of thermocouple temperature sensor, a nonlinear correction model of thermocouple based on particle swarm optimization (PSO) and least squares support vector machine (LSSVM) was constructed. Given the high difficulty of determining the parameters of LSSVM algorithm, PSO algorithm was used to search the optimal combination of penalty factor and kernel function parameter in LSSVM algorithm. Subsequently, the optimized PSO-LSSVM correction model was used to approximate the thermocouple nonlinear function. Furthermore, to detect the validity of the model, BP network model, RBF network model, LSSVM model and PSO-LSSVM model were used to correct the thermocouple nonlinearity. The results showed that the PSO-LSSVM model has the best stability and accuracy in the application of thermocouple nonlinear correction. Its maximum fitting error is only 0.12 ℃; the mean square error is 0.0033; and the accuracy rate is 99.82%. In summary, this model has been applied to nonlinear correction of explosion temperature in finite space, and has achieved good practical application results.
Keywords: least squares support vector machine;particle swarm optimization;thermocouple;nonlinear correction
2021, 47(3):110-115  收稿日期: 2019-06-10;收到修改稿日期: 2019-09-01
基金项目:
作者简介: 张龙(1992-),男,山东潍坊市人,助理工程师,硕士,主要从事仪器科学与技术研究
参考文献
[1] 张继军, 张东亮, 赵建伟, 等. 小比距离密闭空腔爆炸爆后气体温度和压力测量技术研究[J]. 爆炸与冲击, 2019, 39(2): 104-109
[2] 马红, 徐继东, 朱长春, 等. 密封容器内爆炸实验瞬态温度测试技术[J]. 太赫兹科学与电子信息学报, 2014, 12(5): 750-756
[3] 刘丁, 李晓斌, 左磊. 基于最小二乘支持向量机的N型热电偶非线性校正及应用[J]. 仪器仪表学报, 2007, 28(4): 640-644
[4] 吴德会, 王晓红. 一种基于LS-SVM构造FLANN的热电偶非线性校正方法[J]. 传感技术学报, 2007, 20(6): 1321-1324
[5] 杨洪军, 董玉华. 基于GA-BP算法的超声波测量精度优化研究[J]. 计算机工程与科学, 2016, 38(5): 1066-1070
[6] 黄永刚. 基于正交多项式拟合的称重传感器非线性校正[J]. 中国测试, 2018, 44(4): 91-95
[7] 黄永红, 沈洋洋, 陈坤华, 等. 基于PSO-LSSVM的锂离子电池荷电状态预测方法[J]. 电测与仪表, 2018, 55(16): 26-31
[8] 曹净, 丁文云, 赵党书, 等. 基于PSO-LSSVM模型的基坑周边建筑倾斜预测[J]. 计算机工程与应用, 2016, 52(1): 254-259
[9] 张春晓, 张涛. 基于最小二乘法支持向量机和粒子群算法的两相流含油率软测量方法[J]. 中国电机工程学报, 2010, 30(2): 86-91
[10] HE S M, LIU X G, WANG Y L, et al. An effective fault diagnosis approach based on optimal weighted least squares support vector machine[J]. Canadian Journal of Chemical Engineering, 2017, 95(12): 2357-2366.
[11] 冯凯, 卢建刚, 陈金水. 基于最小二乘支持向量机的MIMO线性参数变化模型辨识及预测控制[J]. 化工学报, 2015, 66(1): 197-205
[12] 邱伟, 唐求, 林海军, 等. 基于PSO-LSSVM的水分仪称重传感器非线性补偿研究[J]. 仪器仪表学报, 2017, 38(3): 757-764
[13] 杨婷, 卢文科, 左锋. 基于PSO-LSSVM模型的扩散硅压力传感器的温度补偿[J]. 仪表技术与传感器, 2017(12): 25-29