改造的SVM在矿井气2020欧洲杯竞猜app体定量阐明中的应用

发布于2021-01-15 09:59    文章来源:网络整理

自行搭建了气体收罗系统, 按照井下的气体环境, 收罗了包罗甲烷、乙烷、丙烷、正丁烷和二氧化碳五种气体的中红外光谱数据共236组, 个中校正集186组, 验证集50组。在对光谱数据举办预处理惩罚之后, 操作主身分阐明技能将获得的主接收峰区域的红外光谱数据举办降维处理惩罚, 通过特征提取获得3个特征值作为矿井气体光谱数据的输入量。该要领有效淘汰了模子的计较劲, 加速了模子的收敛速度。然后, 操作改造支持向量机别离对这五种气体成立了定量阐明模子。为提高该算法的预测精度, 操作遗传算法和粒子群优化算法别离对SVM参数举办参数寻优。最后, 选择优化结果更好的粒子群算法, 并通过验证集对这五种气体举办了浓度预测阐明。尝试功效表白: 五种气体浓度预测功效的平均误差均小于1.78%, 最大误差均小于4.98%, 且对付50组的气体预测耗时均小于103 s。表白所提出的改造的SVM算法可以或许精确、快速地预测矿井气体浓度, 对实现矿井气体检测有着努力的意义。

要害词

Abstract

A quantitative analysis model of mine gas concentration based on improved support vector machine(SVM) was adopted. Five mine gases were used for experiment, which included methane, ethane, propane, n-butane and carbon dioxide. Mid-infrared spectral data of these five gases and mixed gases were collected with Fourier infrared spectrometer. 236 groups of these mixed gases were divided into 186 groups for calibration set and 50 groups for validation set. Principal component analysis (PCA) was used to reduce the dimensionality of the infrared spectral data, and 3 eigenvalues were extracted as input, which helped to improve convergence speed and reduce calculation time. Particle swarm optimization (PSO) and genetic algorithm (GA) were used to optimize parameters of support vector machine (SVM) method respectively, and PSO was adopted for its better optimization effect over GA. The mixed gases were detected through this algorithm, and experiment results show that the average errors of concentration predictions of five gases are all less than 1.78%, and the maximum errors of concentration predictions of five gases are all less than 4.98%. The time cost for concentration prediction is all less than 103 s for the 50 groups. This suggested that the improved SVM method based on PSO can be used to predict the gas concentration accurately, and can meet the requirement of real-time detection of mine gases, which has great value in the study of concentration prediction of mine gases.

改革的SVM在矿井气2020欧洲杯竞猜app体定量阐发中的应用

增补资料

中图分类号:O657.33

DOI:10.3788/irla201645.0617011

所属栏目:光电丈量

基金项目:国度自然科学基金(51476154; 51404223)

收稿日期:2015-10-10

修改稿日期:2015-11-18

网络出书日期:--

作者单元    点击查察

郭天太:中国计量大学 计量测试工程学院, 浙江 杭州 310018
洪博:中国计量大学 计量测试工程学院, 浙江 杭州 310018
潘增荣:福建进出境检讨检疫局, 福建 福州 350000
孔明:中国计量大学 计量测试工程学院, 浙江 杭州 310018

接洽人作者:郭天太(guotiantai@163.com)

备注:郭天太(1968-), 男, 副传授, 硕士生导师, 主要从事自校正技能与红外光谱阐明技能方面的研究。

【1】Zhang Liqing, Qin Yujin, Jiang Wenzhong, et al. State-of-the-art of the prediction method and prospect of mine gas emission in China[J]. Coal Mine Safety, 2007(8): 58-60. (in Chinese)
章立清, 秦玉金, 姜文忠, 等. 我国矿井瓦斯涌出量预测要领研究近况及展望[J]. 煤矿安详, 2007(8): 58-60.

【2】Li Jingyu, Zhang Yingwei, Li Wenzhe, et al. Study on biogas content by gas chromatography[J]. Study on Agricultural Mechanization, 2015(6): 255-257. (in Chinese)
李晶宇, 张影微, 李文哲, 等. 气相色谱法测定沼气气体身分及含量的研究[J]. 农机化研究, 2015(6): 255-257.

【3】Wang Xiaozeng, Yang Jiuhong, Zeng Hui. Study of CH4 electrochemical sensor non-linear self-correction in extended range[J]. Coal Mine Safety, 2010(9): 18-20. (in Chinese)
王小增, 杨久红, 曾辉. 瓦斯气体电化学传感器超量程段的非线性自校正研究[J]. 煤矿安详, 2010(9): 18-20.

【4】Chen Yuanyuan, Wang Zhibin, Wang Zhaoba, et al. Research on concentration retrieval of gas FTIR spectra by interval extreme learning machine and genetic algorithm[J]. Spectroscopy and Spectral Analysis, 2014, 34(5): 1244-1248. (in Chinese)
陈媛媛, 王志斌, 王召巴, 等. 区间极限进修机团结遗传算法用于红外光谱气体浓度反演的研究[J]. 光谱学与光谱阐明, 2014, 34(5): 1244-1248.