针对传统支持向量机回归模型应用在红外甲烷传感器测量数据处理时出现预测精度低的问题,提出了一种基于灰狼优化算法的支持向量机回归模型。该模型在传统支持向量机的基础上,利用灰狼优化算法自适应搜索特征空间来选择最佳特征组合,经过循环比较,能快速、准确地搜索到最优的惩罚因子C与gamma参数。用实验室研制的红外甲烷传感器对0～5.05%浓度范围的标准甲烷气体进行测量后,建立了3种SVM回归模型,并进行对比。结果表明,采用灰狼优化算法建立的支持向量机回归模型其绝对误差和相对误差小,精度高。
Abstract
A SVM regression model based on grey wolf optimization (GWO) algorithm was proposed to solve the problem of low prediction accuracy when the traditional support vector machine (SVM) regression model was applied to measurement data processing of infrared methane sensor. Based on the traditional support vector machine, the model used the grey wolf optimization algorithm to adaptively search the feature space to select the best feature combination. After cyclic comparison, the model could quickly and accurately search for the optimal penalty factor C and gamma parameters. After the measurement of standard methane gas in the concentration range of 0～5.05% with the infrared methane sensor developed in the laboratory, three SVM regression models were established and compared. The results showed that the support vector machine regression model established by the grey wolf optimization algorithm had the smaller absolute and relative errors and the higher accuracy.
关键词
计量学 /
甲烷传感器 /
支持向量机 /
灰狼优化算法 /
回归分析
Key words
metrology /
methane sensor /
SVM /
grey wolf optimizer /
analysis of regression
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］Zheng Y, Dang P P, Zheng C T, et al. A handheld mid-infrared methane sensor using a dual-step differential method for additive/multiplicative noise suppression［J］. Infrared Physics and Technology, 2016, 79(10): 151-159.
［2］Triki M, Ba T N, Vicet A. Compact sensor for methane detection in the mid infrared region based on Quartz Enhanced Photoacoustic Spectroscopy［J］. Infrared Physics and Technology, 2015, 69(1): 74-80.
［3］Gulbag A, Temurtas F, Tasaltin C, et al. A study on radial basis function neural network size reduction for quantitative identification of individual gas concentrations in their gas mixtures［J］. Sensors and Actuators B: Chemical, 2007, 124(2): 383-392.
［4］杨景明, 郭秋辰, 孙浩, 等. 基于改进果蝇算法与最小二乘支持向量机的轧制力预测算法研究［J］. 计量学报, 2016, 37(5): 505-508.
Yang J M, Guo Q C, Sun H, et al. Research on the Predictive Algorithm of Rolling Force Based on the Improved Fruit Flies Optimization Algorithm with LSSVM［J］. Acta Metrologica Sinica, 2016, 37(5): 505-508.
［5］吴永忠, 程文娟, 韩江洪, 等. 一种新型的红外甲烷测量定量分析模型［J］. 煤炭学报, 2009, 34(2): 275-279.
Wu Y Z, Cheng W J, Han J H, et al. A Quantitative Analysis Model to Determine Methane Concentration by Infrared Absorbance Method［J］. Journal of China Coal Society, 2009, 34(2): 275-279.
［6］梁杰, 李庆超. 车载气体传感器测量结果修正算法研究［J］. 计量学报, 2019, 40(6): 1140-1145.
Liang J, Li Q C. Research on Correction Algorithm of Vehicle Gas Sensor Measurement［J］. Acta Metrologica Sinica, 2019, 40(6): 1140-1145.
［7］Burges J C C. A tutorial on support vector machine for pattern recognition［J］. Data Mining and Knowledge Discovery, 1998, 2: 121-167.
［8］Vapnik V. The nature of statistical learning theory［M］. New York: Springer, 1999.
［9］Mirjalili S, Mirjalili S M, Lewis A. Grey Wolf Optimizer［J］. Advances in Engineering Software, 2014, 69(3): 46-61.
［10］Kamboj V K, Bath S K, Dhillon J S. Solution of non-convex economic load dispatch problem using Grey Wolf Optimizer［J］. Neural Computing and Applications, 2016, 27(5): 1301-1316.
［11］Dietachmayr F W, Winkler A W, Zagar B G. Model based analysis of non-dispersive infrared gas sensors with thermal emitters and thermopile detectors［J］. Tm-Technisches Messen, 2018, 85: 221-232.
［12］Tan Q L, Tang L C, Xue C, et al. Three-gas detection system with IR optical sensor based on NDIR technology［J］. Optics and Lasers in Engineering, 2015, 74(12): 103-108.
［13］鲍立, 陈红岩, 郭晶晶, 等. 基于改进PSO算法的SVM在甲烷测量中的应用［J］. 传感技术学报, 2017, 30(9): 1454-1458.
Bao L, Chen H Y, Guo J J, et al. Application of SVM Based on Improved Particle Swarm Optimization Algorithm in Methane Measurement［J］. Chinese Journal of Sensors and Actuators, 2017, 30(9): 1454-1458.
［14］Bian X Q, Zhang L, Du Z M, et al. Prediction of sulfur solubility in supercritical sour gases using grey wolf optimizer-based support vector machine［J］. Journal of Molecular Liquids, 2018, 261(4): 431-438.
［15］Bian X Q, Zhang Q, Zhang L, et al. A grey wolf optimizer-based support vector machine for the solubility of aromatic compounds in supercritical carbon dioxide［J］. Chemical Engineering Research and Design, 2017, 123(5): 284-294.
基金
国家自然科学基金(61775203);国家重点研发计划(2017YFFQ210802);浙江省基础公益研究计划(JGF21E040005);浙江省一流学科(B)机械工程建设项目(2016年)
PDF(2274 KB)
