Structural optimization and intelligent parameter control of ventilation and dust removal systems for comprehensive excavation workface
-
摘要: 针对传统长压短抽式通风除尘系统易形成涡流和风流死角的问题，结合康达效应对长压短抽式通风除尘系统进行结构优化，将抽风管与压风管进行嵌套处理，使负压风筒中的风流在抽风筒管口产生康达效应，确保气流紧贴巷道壁面，减少了空气中粉尘的扩散，并显著降低了能耗。通过流场和离散相模型（DPM）仿真得到最佳压抽比为2∶3，在最佳压抽比下的仿真结果显示，与传统长压短抽式通风除尘系统相比，优化系统除尘后司机处及下风侧的粉尘浓度分别降低了5.56%和55.41%。确定通风除尘系统整体结构及压抽比后，通过参数调控可进一步提高除尘效率。选择风筒与产尘面的距离、风筒中轴线与地面的距离及抽压风筒之间的距离作为通风除尘系统的优化调控参数，通过卷积神经网络（CNN）对优化通风除尘系统的除尘参数进行智能调控，匹配出不同初始粉尘浓度下的最优参数，实现智能除尘。通过等比例缩小的通风除尘实验平台对45组参数调控方案进行实验，结果表明：对比BP神经网络，采用CNN模型进行粉尘浓度预测的准确性和稳定性更优；司机处和下风侧初始粉尘浓度为300～900 mg/m³时，采用优化通风除尘系统后，平均粉尘浓度分别下降了51.49%～83.88%，验证了参数调控的有效性。Abstract: This study addressed the challenges of vortex formation and dead air zones in traditional long-pressure short suction ventilation and dust removal systems. By leveraging the Coanda effect, the system's structure was optimized through the nesting of the exhaust and pressure ducts. This design enhanced airflow in the negative pressure duct, promoting adherence to the tunnel walls, reducing dust dispersion, and significantly lowering energy consumption. Simulations utilizing flow field analysis and discrete phase model (DPM) revealed an optimal pressure-extraction ratio of 2∶3. Under this ratio, results indicated that the optimized system reduced dust concentrations at the driver's position and downwind side by 5.56% and 55.41%, respectively, compared to traditional systems. With the structure and pressure-extraction ratio established, further improvements in dust removal efficiency were achievable through parameter regulation. Key parameters included the distance between the duct and the dust-producing surface, the distance from the duct's central axis to the ground, and the distance between the pressure and extraction ducts. Convolutional neural network (CNN) was employed for intelligent parameter control, enabling the identification of optimal parameters for varying initial dust concentrations. Experiments conducted on 45 parameter regulation schemes using a scaled-down experimental platform demonstrated that the CNN model outperformed BP neural networks in accuracy and stability for dust concentration predictions. When initial dust concentrations at the driver's position and downwind side ranged from 300 to 900 mg/m3, the optimized system achieved an average dust concentration reduction of 51.49% to 83.88%, thereby validating the effectiveness of parameter control.
-
图 2 结合康达效应优化后的通风管道结构
Figure 2. Optimized ventilation duct structure based on Coanda effect
图 3 优化通风除尘系统几何模型
Figure 3. Geometric model of optimized ventilation and dust removal system
图 10 调控参数优化实验平台
1−模拟巷道；2−CCD工业相机；3−红色线激光；4−嵌套式通风管道。
Figure 10. Experimental platform for optimizing parametesr control
图 11 CNN模型预测值与真实值对比
Figure 11. Comparison of predicted values from CNN model and actual values
图 12 不同初始粉尘浓度下CNN模型预测结果
Figure 12. Prediction results of CNN model at different initial dust concentrations
表 1 模型主要部件尺寸
Table 1. Dimensions of main parts of the model
名称 尺寸 压风风筒 ϕ0.65 m 抽风风筒 ϕ0.50 m 压风风筒喇叭 ϕ1.8 m 抽风风筒喇叭 ϕ1.5 m 产尘面 ϕ0.8 m 掘进机 6.5 m×2.0 m×1.0 m（长×宽×高） 
下载: 导出CSV
表 2 DPM参数设定
Table 2. Discrete phase model (DPM) parameters settings
参数类别 参数设定 Interaction with Continuous Phase（相间耦合） On DPM Iteration Interval（耦合步长） 200 Injection Type（射出类型） Surface Particle Type（颗粒类型） Inert Material（材料） Coal-hv Diameter Distribution（粒径分布） rosin-rammler Total Flow Rate（质量流率）/（$ {\mathrm{kg}}\cdot {{\mathrm{s}}}^{-1} $） 0.0025 Min Diameter（最小粒径）/μm 1×10−6 Max Diameter（最大粒径）/μm 1×10−4 Mean Diameter（中间粒径）/μm 1×10−5 Spread Parameter（传播参数） 3.5 Number of Diameters（颗粒个数） 15
下载: 导出CSV
表 3 参数调控方案
Table 3. Parameter control scheme
序号 d/m h/m H/m 1 0.30 0.2 0.55 2 0.30 0 0.55 3 0.30 -0.2 0.55 4 0.35 0 0.45 5 0.35 0.2 0.45 41 0.50 0 0.50 42 0.50 0.2 0.50 43 0.50 0.2 0.55 44 0.50 0 0.55 45 0.50 −0.2 0.55
下载: 导出CSV
表 4 调控参数对除尘效果影响的实验数据
Table 4. Experimental data on the influence of control parameters on dust removal efficiency
序号 初始粉尘浓度/
（mg·m−3）d/m h/m H/m 通风后粉尘浓度/
（mg·m−3）司机处 下风侧 司机处 下风侧 1 542 513 0.35 0 0.45 137 291 2 392 359 0.35 0.2 0.45 207 356 3 611 493 0.35 −0.2 0.45 248 185 4 912 917 0.40 −0.2 0.45 292 303 5 844 944 0.40 0 0.45 249 227 1 121 646 647 0.35 0 0.55 185 127 1 122 562 565 0.35 0.2 0.55 199 170 1 123 238 234 0.30 0.2 0.55 172 257 1 124 469 461 0.30 0 0.55 237 181 1 125 461 454 0.30 −0.2 0.55 281 292
下载: 导出CSV
表 5 BP神经网络与CNN模型性能对比
Table 5. Comparison of BP neural network and CNN model performance
神经网
络模型数据集 位置 决定
系数平均绝对
误差均方根
误差BP神经网络 训练集 司机处 0.909 4 11.286 7 14.609 6 测试集 司机处 0.897 1 11.876 7 15.964 1 训练集 下风侧 0.889 2 14.247 1 19.778 9 测试集 下风侧 0.897 3 15.421 5 20.612 1 CNN 训练集 司机处 0.974 0 5.655 7 7.823 3 测试集 司机处 0.973 0 6.160 2 8.181 5 训练集 下风侧 0.964 5 6.881 6 11.188 3 测试集 下风侧 0.953 1 7.960 8 13.935 0
下载: 导出CSV
表 6 不同初始粉尘浓度下最优调控方案的除尘效果
Table 6. Dust removal effectiveness of the optimal control scheme at different initial dust concentrations
初始粉
尘浓度/
（mg·m−3）最优调
控方案d/m h/m H/m 司机处粉
尘浓度/
（mg·m−3）下风侧粉
尘浓度/
（mg·m−3）平均除尘
效率/%300 32 0.5 0 0.55 157.59 133.46 51.49 500 11 0.5 0 0.45 98.87 128.22 77.29 700 24 0.4 0.2 0.50 162.44 94.21 81.67 900 6 0.4 0.2 0.45 176.89 113.20 83.88
下载: 导出CSV
-
[1] 程卫民,周刚,陈连军,等. 我国煤矿粉尘防治理论与技术20年研究进展及展望[J]. 煤炭科学技术,2020,48(2):1-20.CHENG Weimin,ZHOU Gang,CHEN Lianjun,et al. Research progress and prospect of dust control theory and technology in China's coal mines in the past 20 years[J]. Coal Science and Technology,2020,48(2):1-20. [2] 蒋仲安,闫鹏,陈举师,等. 岩巷掘进巷道长压短抽通风系统参数优化[J]. 煤炭科学技术,2015,43(1):54-58.JIANG Zhong'an,YAN Peng,CHEN Jushi,et al. Optimization on parameters of long distance forced and short distance exhausted ventilation system in mine rock heading roadway[J]. Coal Science and Technology,2015,43(1):54-58. [3] 侯树宏,郝军,李腾龙,等. 综掘工作面通风控尘参数匹配关系研究及应用[J]. 煤炭技术,2022,41(1):166-169.HOU Shuhong,HAO Jun,LI Tenglong,et al. Research and application of ventilation and dust control parameters matching in fully mechanized driving face[J]. Coal Technology,2022,41(1):166-169. [4] 乔金林,安世岗,孙连胜,等. 长压短抽除尘系统不同因素变化对粉尘运移影响的模拟研究[J]. 煤矿机械,2021,42(9):187-191.QIAO Jinlin,AN Shigang,SUN Liansheng,et al. Simulation study on influence of different factors change on dust migration in long pressure and short suction dedusting system[J]. Coal Mine Machinery,2021,42(9):187-191. [5] 肖旸,孙帅强,杨雪儿,等. 可变角度新鲜风流下煤巷掘进长压短抽除尘效果数值模拟[J]. 煤矿安全,2023,54(1):38-45.XIAO Yang,SUN Shuaiqiang,YANG Xue'er,et al. Numerical simulation of dust removal effect of long pressure and short drainage in coal roadway tunneling with variable angle fresh air flow[J]. Safety in Coal Mines,2023,54(1):38-45. [6] 莫金明,马威. 大采高综采工作面负压除尘微雾净化装置应用研究[J]. 煤炭学报,2023,48(3):1267-1279.MO Jinming,MA Wei. Negative-pressure dust removal and micro-mist purification device application in fully-mechanised mining faces with a large mining height[J]. Journal of China Coal Society,2023,48(3):1267-1279. [7] LI Angui. Extended Coanda effect and attachment ventilation[J]. Indoor and Built Environment,2019,28(4):437-442. doi: 10.1177/1420326X19833850 [8] 卢文. 吹吸式空气幕的气流特性及控烟效果研究[D]. 徐州:中国矿业大学,2022.LU Wen. Research on the airflow characteristics and smoke control effect of blowing and sucking air curtains[D]. Xuzhou:China University of Mining and Technology,2022. [9] 司俊鸿,王昊宇,霍小泉,等. 综掘工作面半封闭式区域联合控尘技术研究[J]. 金属矿山,2024(5):126-133.SI Junhong,WANG Haoyu,HUO Xiaoquan,et al. Study on semi-enclosed area joint dust control technology of comprehensive excavation face[J]. Metal Mine,2024(5):126-133. [10] 王国法,杜毅博,任怀伟,等. 智能化煤矿顶层设计研究与实践[J]. 煤炭学报,2020,45(6):1909-1924.WANG Guofa,DU Yibo,REN Huaiwei,et al. Top level design and practice of smart coal mines[J]. Journal of China Coal Society,2020,45(6):1909-1924. [11] 张浪,刘彦青. 矿井智能通风与关键技术研究[J]. 煤炭科学技术,2024,52(1):178-195. doi: 10.12438/cst.2023-1987ZHANG Lang,LIU Yanqing. Research on technology of key steps of intelligent ventilation in mines[J]. Coal Science and Technology,2024,52(1):178-195. doi: 10.12438/cst.2023-1987 [12] 张景钢,王清焱,何鑫. 矿井智能通风现状与智能控制系统构建[J]. 矿业安全与环保,2023,50(5):37-42.ZHANG Jinggang,WANG Qingyan,HE Xin. Research status and system design of intelligent mine ventilation[J]. Mining Safety & Environmental Protection,2023,50(5):37-42. [13] 张钧琦,朱斌,张有为. 基于决策树的矿井通风智能调控研究[J]. 现代机械,2023(1):90-94.ZHANG Junqi,ZHU Bin,ZHANG Youwei. Intelligent control of mine ventilation based on decision tree[J]. Modern Machinery,2023(1):90-94. [14] QI Chongchong,ZHOU Wei,LU Xiang,et al. Particulate matter concentration from open-cut coal mines:a hybrid machine learning estimation[J]. Environmental Pollution,2020,263. DOI: 10.1016/j.envpol.2020.114517. [15] SEO J,KIM S,JALALVAND A,et al. Avoiding fusion plasma tearing instability with deep reinforcement learning[J]. Nature,2024,626:746-751. doi: 10.1038/s41586-024-07024-9 [16] 龚晓燕,程傲,邹浩,等. 综掘面风流调控下的瓦斯与粉尘浓度双目标预测模型研究[J]. 煤炭技术,2024,43(1):153-157.GONG Xiaoyan,CHENG Ao,ZOU Hao,et al. Study on dual-objective prediction mode of gas and dust concentration under regulation of airflow in fully mechanized excavation face[J]. Coal Technology,2024,43(1):153-157. [17] 陈湘源,秦伟,刘晏驰,等. 融合卷积神经网络与线性回归的带式输送机托辊故障音频识别方法 [J/OL]. 煤炭科学技术:1-9[2024-06-22]. http:// kns.cnki.net/kcms/detail/11.2402.TD.20240701.1327.001.html.CHEN Xiangyuan,QIN Wei,LIU Yanchi,et al. Audio recognition method for belt conveyor roller faults by integrating convolutional neural network and linear regression[J/OL]. Coal Science and Technology:1-9[2024-06-22]. http://kns.cnki.net/kcms/detail/11.2402.TD.20240701.1327.001.html. [18] JIAO Jinyang,ZHAO Ming,LIN Jing,et al. A comprehensive review on convolutional neural network in machine fault diagnosis[J]. Neurocomputing,2020,417:36-63. doi: 10.1016/j.neucom.2020.07.088 [19] GOH G B,HODAS N O,SIEGEL C,et al. SMILES2Vec:an interpretable general-purpose deep neural network for predicting chemical properties[EB/OL]. [2024-06-25]. https://arxiv.org/abs/1712.02034v2. [20] MICCIO L A,SCHWARTZ G A. From chemical structure to quantitative polymer properties prediction through convolutional neural networks[J]. Polymer,2020,193:122341. doi: 10.1016/j.polymer.2020.122341 [21] 满轲,武立文,刘晓丽,等. 基于CNN−LSTM模型的TBM隧道掘进参数及岩爆等级预测 [J/OL]. 煤炭科学技术:1-19[2024-06-22]. http:// kns.cnki.net/kcms/detail/11.2402.TD.20231026.1344.003.html.MAN Ke,WU Liwen,LIU Xiaoli,et al. TBM tunnel excavation parameters and rockburst level prediction based on CNN-LSTM model[J/OL]. Coal Science and Technology:1-19 [2024-06-22]. http://kns.cnki. net/kcms/detail/11. 2402.TD.20231026.1344.003.html. [22] 陈芳,张设计,马威,等. 综掘工作面压风分流控除尘技术研究与应用[J]. 煤炭学报,2018,43(增刊2):483-489.CHEN Fang,ZHANG Sheji,MA Wei,et al. Research and application of the technology of forced ventilation diversion to control and reduce dust in fully mechanized excavation face[J]. Journal of China Coal Society,2018,43(S2):483-489. -
点击查看大图
计量
- 文章访问数: 58
- HTML全文浏览量: 14
- PDF下载量: 8
- 被引次数: 0
