采空区煤自燃极限参数灰色关联分析及预测
Grey relational analysis and prediction on limit parameters of coal spontaneous combustion in goaf
-
摘要: 采空区动态变化特征决定了煤自燃极限参数与其影响因素之间的复杂性。为了实现煤自燃极限参数精准预测，引入灰色综合关联度分析方法，定量分析了上限漏风强度与其影响因素之间的关联程度，并基于此建立了改进粒子群优化算法（IPSO）优化支持向量回归（SVR）参数的煤自燃极限参数预测模型；以上限漏风强度为例，分别建立了标准PSO-SVR模型和多元线性回归模型（MLR），进行上限漏风强度预测并与已有的变步长网格搜索优化SVR参数方法和神经网络对比。结果表明：浮煤厚度与上限漏风强度的灰色综合关联度最大，氧体积分数与煤温次之，放热强度与采空区距工作面距离最小；煤自燃极限参数与其影响因素之间非线性关系较线性关系更显著；SVR相比于神经网络方法具有更强的非线性处理能力；IPSO-SVR模型预测值与真实值之间的相对误差在2.6 %以内，其预测精度明显优于其他4种模型，IPSO参数优化对提高SVR模型的预测精度有很大帮助，IPSO-SVR方法应用于煤自燃极限参数预测是有效的。Abstract: The dynamic change of goaf determines the complexity between limit parameters of coal spontaneous combustion and its influencing factors. In order to achieve accurate prediction of limit parameters of coal spontaneous combustion, the grey correlation analysis was introduced to quantitatively analyze the correlation between the superior intensity limit of air leakage and its influencing factors. Further, the key parameters of support vector regression（ＳＶＲ） were optimized by improved particle swarm optimization （ＩＰＳＯ）, and the prediction model on limit parameters of coal spontaneous combustion in goaf was established. Taking the superior intensity limit of air leakage as an example, the standard PSO-SVR and the multiple linear regression model （ＭＬＲ） were respectively established. Moreover, the models mentioned above were used for predicting the superior intensity limit of air leakage and compared with the existing method of variable-step grid search for optimizing SVR parameters and the neural network. The results show that the grey synthetic degree between the inferior thickness limit of coal and the superior intensity limit of air leakage was the largest, the oxygen concentration and the coal temperature were the second, and the exothermic intensity and the distance of the goaf from the working face were the smallest. The nonlinear relationship between limit parameters of coal spontaneous combustion and its influencing factors is more remarkable than the linear relationship. SVR has stronger nonlinear processing ability than neural network method. The relative error between predicted values and real values of IPSO-SVR model is within 2.6%, and its prediction accuracy is better than other four models. It is helpful for the key parameters optimization by IPSO to improve the prediction precision of SVR model. The IPSO-SVR method is effective for the prediction on limit parameters of coal spontaneous combustion.
-
-
[1] 王德明，邵振鲁，朱云飞．煤矿热动力重大灾害中的几个科学问题[J]．煤炭学报，2021，46（1）：57－64. WANG Deming, SHAO Zhenlu, ZHU Yunfei. Several scientific issues on major thermodynamic disasters in coal mines[J]. Journal of China Coal Society, 2021, 46（1）: 57-64.
[2] 秦波涛，仲晓星，王德明，等．煤自燃过程特性及防治技术研究进展[J]．煤炭科学技术，2021，49（1）：66. QIN Botao, ZHONG Xiaoxing, WANG Deming, et al. Research progress of coal spontaneous combustion process characteristics and prevention technology[J]. Coal Science and Technology, 2021, 49（1）: 66.
[3] Deng J, Lei C, Xiao Y, et al. Determination and prediction on “three zones” of coal spontaneous combustion in a gob of fully mechanized caving face[J]. Fuel, 2018, 211: 458-470. [4] Beamish B B, Barakat M A, George J D S. Spontaneous-combustion propensity of New Zealand coals under adiabatic conditions[J]. International Journal of Coal Geology, 2011, 45: 217-224. [5] 徐精彩．煤自燃危险区域判定理论[Ｍ]．北京：煤炭工业出版社，2001. [6] 徐精彩，文虎，邓军，等．煤自燃极限参数研究[J]．火灾科学，2000，9（2）：14－18. XU Jingcai, WEN Hu, DENG Jun, et al. Study limit parameter of coal self-ignite[J]. Fire Safety Science, 2000, 9（2）: 14-18.
[7] 徐精彩，王华．煤自燃极限参数的神经网络预测方法[J]．煤炭学报，2002，27（4）：366－370. XU Jingcai, WANG Hua. The neural network prediction method for the limit parameters of coal self-ignition[J]. Journal of China Coal Society, 2002, 27（4）: 366-370.
[8] 孟倩，王洪权，王永胜，等．煤自燃极限参数的支持向量机预测模型[J]．煤炭学报，2009，34（11）：1489. MENG Qian, WANG Hongquan, WANG Yongsheng, et al. Predicting limit parameters of coal self-ignition based on support vector machine[J]. Journal of China Coal Society, 2009, 34（11）: 1489-1493.
[9] 周西华，牛田元，白刚，等．供风量对褐煤自燃极限参数的影响研究[J]．中国安全生产科学技术，2018，14（1）：82－86. ZHOU Xihua, NIU Tianyuan, BAI Gang, et al. Study on influence of air supply on limit parameters of spontaneous combustion of lignite[J]. Journal of Safety Science and Technology, 2018, 14（1）: 82-86.
[10] 郭亚军，邬剑明，王俊峰，等．风量对煤自燃极限参数影响的实验研究[J]．煤矿安全，2018，49（2）：27－30. ＧＵＯ Ｙajun, WU Jianming, WANG Junfeng, et al. Experimental study on the effect of air volume on coal spontaneous combustion limit parameters[J]. Safety in Coal Mines, 2018, 49（2）: 27-30.
[11] 马砺，任立峰，艾绍武，等．氯盐阻化剂对煤自燃极限参数影响的试验研究[J]．安全与环境学报，2015，15（4）：83－88. MA Li, REN Lifeng, AI Shaowu, et al. Experimental study on the impact of the chloride inhibitor upon the limited parameters of the coal spontaneous combustion[J]. Journal of Safety and Environment, 2015, 15（4）: 83-88.
[12] 马砺，任立峰，韩力，等．粒度对采空区煤自燃极限参数的影响试验研究[J]．煤炭科学技术，2015，43（6）：59－64. MA Li, REN Lifeng, HAN Li, et al. Experiment study on partical size affected to coal spontaneous combustion limit parameters in goaf[J]. Coal Science and Technology, 2015, 43（6）: 59-64.
[13] 易欣，白祖锦，肖旸，等．咪唑类离子液体对煤自燃极限参数的影响[J]．安全与环境学报，2018，18（5）：1805－1810. YI Xin, BAI Zujin, XIAO Yang, et al. Impact of imidazole ionic liquid on the maximal limit parameters of the coal spontaneous combustion[J]. Journal of Safety and Environment, 2018, 18（5）: 1805-1810.
[14] Ma L, Zou L, Ren L, et al. Prediction indices and limiting parameters of coal spontaneous combustion in the Huainan mining area in China[J]. Fuel, 2020, 264: 116883. [15] Wang C, Zhao X, Bai Z, et al. Comprehensive index evaluation of the spontaneous combustion capability of different ranks of coal[J]. Fuel, 2021, 291: 120087. [16] 谭波，胡瑞丽，李凯，等．不同变质程度烟煤的自燃极限参数对比分析[J]．煤炭科学技术，2013，41（5）：63－67. TAN Bo, HU Ruili, LI Kai, et al. Comparison analysis on spontaneous combustion limit parameters of bituminous coal with different metamorphic degree[J]. Coal Science and Technology, 2013, 41（5）: 63-67.
[17] Zhang Y, Zhang Y, Li Y, et al. Study on the characteristics of coal spontaneous combustion during the development and decaying processes[J]. Process Safety and Environmental Protection, 2020, 138: 9-17. [18] 章飞．复合采空区遗煤自燃极限参数变化及危险区域判定[J]．矿业安全与环保，2020，47（4）：66-72. ZHANG Fei. Limit parameter changes and hazardous area determination of residual coal spontaneous combustion in compound goaf[J]. Mining Safety & Environmental Protection, 2020, 47（4）: 66-72.
[19] 张辛亥，朱辉，安启启，等．凯达煤矿采空区煤自燃极限参数分析[J]．中国安全生产科学技术，2021，17（5）：86－92. ZHANG Xinhai, ZHU Hui, AN Qiqi, et al. Analysis on limit parameters of coal spontaneous combustion in goaf of Kaida coal mine[J]. Journal of Safety Science and Technology, 2021, 17（5）: 86-92.
[20] Sun G, Guan X, Yi X, et al. Grey relational analysis between hesitant fuzzy sets with applications to pattern recognition[J]. Expert Systems With Applications, 2018, 92: 521-532. [21] 刘思峰．灰色系统理论及其应用[Ｍ]．北京：科学出版社，2021. [22] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20: 273-297. [23] Dong G, Mu X. A novel second-order cone programming support vector machine model for binary data classification[J]. Journal of Intelligent and Fuzzy Systems, 2020, 39（3）: 4505-4513. [24] Wang L, Gao C, Zhao N, et al. Wavelet transform-based weighted v-twin support vector regression[J]. International Journal of Machine Learning and Cybernetics, 2020, 11（1）: 95-110. [25] 董美蓉，韦丽萍，陆继东，等．基于Ｋ－ＣＶ参数优化支持向量机的ＬＩＢＳ燃煤热值定量分析[J]．光谱学与光谱分析，2019，39（7）：2202. DONG Meirong, WEI Liping, LU Jidong, et al. Quantitative analysis of LIBS coal heat value based on K-CV parameter optimization support vector machine[J]. Spectroscopy and Spectral Analysis, 2019, 39（7）: 2202.
[26] Protic M, Shamshirband S, Petkovi D, et al. Forecasting of consumers heat load in district heating systems using the support vector machine with a discrete wavelet transform algorithm[J]. Energy, 2015, 87: 343. [27] Lei C, Deng J, Cao K, et al. A comparison of random forest and support vector machine approaches to predict coal spontaneous combustion in gob[J]. Fuel, 2019, 239: 297-311. [28] 曲健，陈红岩，刘文贞，等．基于改进网格搜索法的支持向量机在气体定量分析中的应用[J]．传感技术学报，2015，28（5）：774. QU Jian, CHEN Hongyan, LIU Wenzhen, et al. Application of support vector machine based on improved grid search in quantitative analysis of gas[J]. Chinese Journal of Sensors and Actuators, 2015, 28（5）: 774.
[29] Feng Q, Zhang J, Zhang X, et al. Proximate analysis based prediction of gross calorific value of coals: A comparison of support vector machine, alternating conditional expectation and artificial neural network[J]. Fuel Processing Technology, 2015, 129: 120-129. [30] Lei C, Deng J, Cao K, et al. A random forest approach for predicting coal spontaneous combustion[J]. Fuel, 2018, 223: 63-73.
计量
- 文章访问数: 42
- HTML全文浏览量: 0
- PDF下载量: 18
下载:
