煤矿井下掘进生产过程中，为了防止瓦斯等有害气体浓度超标，一般在掘进工作面会布置瓦斯抽放管路系统，而其抽放系统的一个极为重要设备即地面瓦斯抽采泵，瓦斯抽采泵的稳定运行关系到矿井的安全生产，如何确保其安全、稳定、高效地运行一直是该行业科技人员研究的重点和难点。本文依据陕西陕煤韩城矿业有限公司象山矿井板桥瓦斯抽采泵的实际运行情况展开研究工作。主要工作如下：

（1）针对瓦斯抽采泵具有大惯性、大迟延等特点，选择了高阶对象传递函数模型作为系统的辨识模型，然后使用改进PIO算法对系统模型的参数进行辨识，对辨识出的系统模型在正常运行工况下进行可靠性分析。

（2）针对标准PIO算法收敛速度较慢寻优精度较低，以及迭代后期容易陷入局部最优解的问题，提出一种改进的PIO算法，在提升算法收敛速度的同时，解决了算法在迭代后期容易陷入局部最优解的问题。在五种测试函数上的仿真结果表明：相比于标准PIO算法，改进PIO算法的收敛精度更高、收敛速度更快，并且具有更强的全局搜索能力。将改进后的算法应用到瓦斯抽采泵的模型辨识中，并对系统模型的输出结果和实际输出值进行误差分析，仿真结果显示，该模型的最大相对误差为5.61%，平均相对误差为3.46%；表明模型仿真的结果和实际数据的吻合度较高，使用改进PIO算法对瓦斯抽采泵模型进行辨识的方法可靠有效。

（3）设计了基于改进PIO-PID和BP-PID的瓦斯抽采泵系统控制方案，通过阶跃响应、鲁棒性和抗扰动性仿真验证，分析对比不同控制方案的控制性能。仿真结果表明：相较于传统的PID控制策略、BP-PID控制策略和ISOA-PID控制策略，改进PIO-PID控制策略有效地提升了系统的快速性、鲁棒性和抗扰动性能，应用在瓦斯抽采泵系统中超调量更小、调节速度更快、稳定性更好，具有一定的借鉴效果。

During the coal mine underground mining process, to prevent the concentration of harmful gases such as methane from exceeding the standard, a gas drainage pipeline system is generally installed at the mining face. The ground gas drainage pump is one of the most important devices in the drainage system, and the stable operation of the gas drainage pump is related to the safety production of the mine. Ensuring its safe, stable, and efficient operation has always been the focus and difficulty of scientific and technological personnel in this industry. The automatic control system for gas drainage pumps introduced in this paper is based on the stable operation of a certain gas drainage pump at the Xiangshan Mine of Hancheng Mining Co., Ltd. The main work is as follows:

Aiming at the characteristics of gas pumping with large inertia and delay, the higher-order object transfer function model is selected as the identification model of the system, and then the parameters of the system model are identified using the improved PIO algorithm, and the identified system model is analyzed for reliability under normal operating conditions.

To address the problems of slow convergence speed of the standard PIO algorithm with low search accuracy and the tendency to fall into local optimal solutions in the late iteration, an improved PIO algorithm is proposed to solve the problem of the algorithm falling into local optimal solutions in the late iteration while improving the convergence speed of the algorithm. Simulation results on five test functions show that the improved PIO algorithm has higher convergence accuracy, faster convergence speed, and stronger global search capability compared with the standard PIO algorithm. The simulation results show that the maximum relative error of the model is 5.61% and the average relative error is 3.46%; it shows that the results of the model simulation and the actual data are in good agreement, and the method of using the improved PIO algorithm to identify the gas pumping model is reliable and effective.

The control scheme of gas pumping system based on improved PIO-PID and BP-PID is designed, and the control performance of different control schemes is analyzed and compared through step response, robustness and anti-disturbance simulation. The simulation results show that compared with the traditional PID control strategy, BP-PID control strategy and ISOA-PID control strategy, the improved PIO-PID control strategy effectively improves the speed, robustness and anti-disturbance performance of the system, and is applied to the gas extraction pumping system with smaller overshoot, faster regulation speed and better stability, which has certain reference effect.

[1] 许鹏飞.2000-2021年我国煤矿事故特征及发生规律研究[J].煤炭工程,2022,54(07):129-133.

[2] 宋志强.基于PLC控制的矿井中瓦斯抽放安全监控系统改进研究[J].自动化应用, 2020(07):33-35.

[3] Karabulut Korhan,Öztop Hande,Kandiller Levent,Tasgetiren M. Fatih. Modeling and optimization of multiple traveling salesmen problems: An evolution strategy approach[J]. Computers and Operations Research,2021,129:0305-0548.

[4] 任瑞龙,张士雄.非线性权重粒子群算法的机械臂动力学参数辨识[J].组合机床与自动化加工技术,2023,No.591(05):39-44.

[5] 姜斌祥,姜彤彤,王永雷.基于文化遗传算法的毒品检验区块链共识算法优化[J].吉林大学学报(工学版),2022,52(03):684-692.

[6] Storn R, Price K. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of global optimization, 1997, 11(4): 341.

[7] Peng Y, Cheng J, Jiang R. Inversion of UEP signatures induced by ships based on PSO method[J]. Defence Technology, 2020, 16(1): 172-177.

[8] Mirjalili S, Mirjalili S M, Lewis A. Grey wolf optimizer[J]. Advances in engineering software, 2014, 69: 46-61.

[9] Dhiman G, Kumar V. Seagull optimization algorithm: Theory and its applications for large-scale industrial engineering problems[J]. Knowledge-based systems, 2019, 165: 169-196.

[10] 程适,王锐,伍国华等.群体智能优化算法[J]. 郑州大学学报(工学版), 2018, 39(06): 1-2.

[11] 徐培文,陈仁祥,胡小林等.PSO优化多尺度一维卷积神经网络的风机基础螺栓松动诊断[J].振动与冲击,2022,41(04):86-92.

[12] 吴新忠,张芝超,王凯等.基于DE-GWO算法的矿井风网风量调节方法[J].中南大学学报(自然科学版),2021,52(11):3981-3989.

[13] Zhang D, Guan C. Active Vibration Control of Robot Gear System Based on Adaptive Control Algorithm[J]. Journal of Sensors, 2022,2022: 1-7.

[14] 王国梁,王文俊,成锴,等. 麻雀搜索算法优化BP算法结合高光谱预测小米米粉糊化特性[J]. 食品科学,2022,43(19):65-70.

[15] Che S, Chen Y, Wang L. Electric Vehicle Charging Station Layout for Tourist Attractions Based on Improved Two-Population Genetic PSO[J]. Energies, 2023, 16(2): 983-992.

[16] 朱思峰,赵明阳,柴争义.边缘计算场景中基于粒子群优化算法的计算卸载[J].吉林大学学报(工学版),2022,52(11):2698-2705.

[17] Zhang X, Hou J, Wang Z, et al. Joint SOH-SOC Estimation Model for Lithium-Ion Batteries Based on GWO-BP Neural Network[J]. Energies, 2022, 16(1): 132-139.

[18] Subramani S, Selvi M. Multi-objective PSO Based Feature Selection for Intrusion Detection in IoT Based Wireless Sensor Networks[J]. Optik, 2023, 273: 17411-170419.

[19] Liu D, Hu X, Jiang Q. Design and optimization of logistics distribution route based on improved ant colony algorithm[J]. Optik, 2023, 273: 170405-17411.

[20] 宋佳艳,苏圣超.基于改进蚁群优化算法的自动驾驶多车协同运动规划[J].计算机工程,2022,48(11):299-305.

[21] 樊慧晶,章文毅,田妙苗等.基于粒子群算法的卫星任务地面站资源调度方法[J].中国科学院大学学报,2022,39(06):801-808.

[22] 于国庆,韩芃芃.基于蝙蝠粒子群的二维OTSU图像分割方法[J].计算机仿真,2022,39(10):379-385.

[23] 苏俊,熊瑞平,温记明等.基于改进粒子群算法的六自由度工业机器人轨迹规划[J].制造技术与机床,2022, 724(10):38-45.

[24] 华冰,孙胜刚,吴云华等.一种基于PIO改进强化学习的航天器复杂多约束姿态机动规划新方法[J].中国科学:技术科学,2023,53(02):200-209.

[25] Selvaraj S, Choi E. Dynamic Sub-Swarm Approach of PSO Algorithms for Text Document Clustering[J]. Sensors, 2022, 22(24): 9653-9661.

[26] Liu X, Sui T. Expert control of mine hoist control system[J]. Wireless Communications and Mobile Computing, 2021, 2021: 1-8.

[27] Hadizadeh M, Farzanegan A, Noaparast M. A plant-scale validated MATLAB-based fuzzy expert system to control SAG mill circuits[J]. Journal of Process Control, 2018, 70: 1-11.

[28] Samuel M, Yahya K, Attar H, et al. Evaluating the performance of fuzzy-PID control for lane recognition and lane-keeping in vehicle simulations[J]. Electronics, 2023, 12(3): 724-732.

[29] Luo W, Chen H, Zhu S, et al. Design of a Wheel-Side Rear-Drive Distributed Electric Bus Control Strategy Based on Self-Correcting Fuzzy Control[J]. Electronics, 2022, 11(24): 4219-4224.

[30] 唐伎玲,赵宏伟,王婷婷等.LQR优化的BP神经网络PID控制器设计[J].吉林大学学报(理学版),2020,58(03):651-658.

[31] Rodríguez-Abreo O, Rodríguez-Reséndiz J, Fuentes-Silva C, et al. Self-tuning neural network PID with dynamic response control[J]. IEEE Access, 2021, 9: 65206-65215.

[32] Hou J, Li H, Nord N. Nonlinear model predictive control for the space heating system of a university building in Norway[J]. Energy, 2022, 253: 124157-124164.

[33] 刘省标,李美,张少波等.BP神经网络PID自适应控制悬架平顺性研究[J].机械设计与制造,2022, 382(12):11-14.

[34] 李子璇,邬明宇,周福强等.空气弹簧高度振荡自适应模糊PID控制方法研究[J].机床与液压,2022,50(19):115-119.

[35] 张世玉,陈东生,宋颖慧.基于自抗干扰的装配机器人阻抗控制技术[J].浙江大学学报(工学版),2022,56(09):1876-1881.

[36] 李浩,朱才朝,樊志鑫等.基于二阶滑膜-PID控制的风力发电机最大功率跟踪策略研究[J].太阳能学报,2022,43(03):306-314.

[37] Li H, Hui Y B, Wang Q, et al. Design of Anti-Swing PID Controller for Bridge Crane Based on PSO and SA Algorithm[J]. Electronics, 2022, 11(19): 3143-3149.

[38] 艾福强,包建东,刘正权.基于粒子群优化模糊PID控制的多足式真空吸附机器人控制方案设计[J].电子测量技术,2023,46(02):67-72.

[39] 沙林秀,王凯.基于PSO的钻机快速自适应PID控制[J].控制工程,2021,28(03):519-523.

[40] 周向阳,舒通通,吕子豪等.基于模糊切换增益调节的惯性稳定平台滑模控制[J].仪器仪表学报,2021,42(12):263-271.

[41] 陈飞,丁曙光,董玉革.基于BP神经网络优化模糊PID控制的防爆门控制策略研究[J].现代制造工程,2022(12):111-116.

[42] 艾青林,蒋锦涛,刘刚江等.基于遗传算法与模糊分数阶PID的钢结构损伤检测机器人姿态控制[J].高技术通讯,2022,32(06):615-623.

[43] 陈弈煿,张润锋,杨绍琼等.基于参数自整定PID的水下滑翔机航向控制方法[J].重庆大学学报,2022,45(08):26-33.

[44] 李莉,王俊衡,孟繁佳等.基于二次混合机构的营养液调控模型与PID算法实现[J].农业工程学报,2016,32(22):100-106.

[45] Malarvili S, Mageshwari S. Nonlinear PID (N-PID) Controller for SSSP Grid Connected Inverter Control of Photovoltaic Systems[J]. Electric Power Systems Research, 2022, 211: 108175-108183.

[46] 王建刚,杨洪涛,于晓周等.大型气候环境试验舱冷热端温度动态模糊PID协调控制[J].光学精密工程,2022,30(24):3159-3167.

[47] Duan H, Qiao P. Pigeon-inspired optimization: a new swarm intelligence optimizer for air robot path planning[J]. International journal of intelligent computing and cybernetics, 2014, 7(1): 24-37.

[48] 王娟,秦江涛.混沌映射与t-分布变异策略改进的海鸥优化算法[J].计算机应用研究,2022,39(01):170-176.

[49] Liu H, Xu G, Ding G, et al. Human behavior-based particle swarm optimization[J]. The Scientific World Journal, 2014, 2014:14.

[50] 尚志刚,王力,李蒙蒙等.引入迷失探索与集群分裂机制的改进鸽群优化算法[J].郑州大学学报(工学版),2019,40(04):25-31.

[51] 韩斐斐,刘升. 基于自适应t分布变异的缎蓝园丁鸟优化算法[J]. 微电子学与计算机,2018,35(8):117-121.

[52] 李昌聪. 矿井瓦斯抽采泵稳定运行控制系统的研究[D].西安:西安科技大学,2021.