An Intelligent Control Strategy For Gas Precise Drainage Problem Based On Model Predictive Control

In recent years,China's shallow coal reserves have gradually decreased,and the proportion of deep mining has increased year by year.Effective gas extraction can eliminate the potential safety hazards caused by deep mining in coal mines to a certain extent.Therefore,aiming at the needs of safe and efficient gas extraction,it is of great research significance to carry out intelligent control on gas extraction system.In order to improve the safety and efficiency of gas extraction and reduce the economic cost of gas extraction,the safety constraints and efficiency constraints of gas extraction system operation are analyzed.The four control tasks of gas drainage system are analyzed and the mathematical optimization model of gas drainage is established.According to the theoretical control strategy,the complete process of intelligent control of gas extraction is put forward.Based on the above regulation process,an intelligent regulation model of gas extraction is proposed,which takes gas extraction concentration,gas extraction pure quantity,gas extraction negative pressure and extraction pump efficiency ratio as controlled quantities,and the valve opening of extraction drilling hole and extraction pump power as control quantities,and analyzes and processes the time variation law of historical data of controlled quantities by using the cyclic neural network,and learns to obtain the ideal dynamic fitting curve of controlled quantities changing with time.The MPC(Model Predictive Control)algorithm is used to intelligently control the control variable,so that the actual value of the controlled variable infinitely approaches the reference value at the corresponding time of its ideal dynamic fitting curve.Using correction feedback and rolling optimization,the anti-interference ability of intelligent control model of gas extraction is continuously enhanced.Based on the simulation data of gas extraction,the algorithm simulation experiment is completed.The experimental results show that when the superparameter is 128 neurons and the iteration times are 100,the ideal dynamic fitting curve obtained by the cyclic neural network has good data fitting degree and low model complexity.The ideal dynamic fitting curve can accurately reflect the change law of gas extraction concentration data and gas extraction pure quantity data,and the ideal dynamic fitting curve of gas extraction negative pressure and extraction pump efficiency ratio can be accurately maintained between 15-25Kpa and 1.3-1.5m3/(kW*h),which meets the economic and safety needs of gas extraction process.Dynamic regulation of control quantity by model predictive control algorithm can overcome the interference of environment and non-linear factors to achieve better control effect.The adjustable range of control quantity is:the valve opening is between 0%and 100%,and the power of extraction pump is between 200-500 kW/h.The whole intelligent control process of gas extraction is complete and effective,which can provide some reference suggestions for the process of gas extraction in coal mines.