Dynamic Setting Of Back Pressure Setting Value And Optimization Of Back Pressure Control Strategy For 300 MW Direct Air-cooling Unit

Direct-air cooling technology is widely used in the "three north" areas of China where coal is rich and water is poor due to its significant water-saving advantages.Up to now,the installed capacity of direct air-cooled units has accounted for 62.64% of the total installed capacity of thermal power units in China.Although the direct air-cooled unit has the advantages of low water consumption,low cost and high thermal economy,it also has the problems of high back pressure and high coal consumption of power generation standard.In the current situation that thermal power units continue to conduct deep peak shaving in order to accept new energy grid connection,power generation companies have also set higher requirements for unit economic evaluation indicators.As one of the key parameters affecting the economic performance of direct air-cooled units,how to quickly and stably control the back pressure to keep it within the optimal range has become the current research of thermal power generation control system Top of the list.Based on the study of 300 MW subcritical direct air-cooled unit,this paper calculates the economic back pressure value of the unit under different operating conditions,and establishes the optimal back pressure initial data group of multiple operating points in combination with operating experience,which serves as the learning set of dynamic given model of back pressure setting value of BP neural network.The BP neural network is optimized by particle swarm optimization to improve the model accuracy,learning generalization ability and learning speed.Finally,the back pressure setting value dynamic given model under the influence of multiple factors is established.Through this model,the set value of back pressure can be dynamically given on-line according to different working conditions,so as to maximize the economic benefits of the unit and reduce the workload of the staff under the premise of safe operation of the unit,which provides a theoretical guidance for the realization of the dynamic set value of back pressure of the direct air-cooling unit in the future.In view of the fact that the actual back pressure is difficult to track the set value quickly and stably,this paper applies the predictive control algorithm(GPC)which can respond quickly,has good robustness and is easy to realize in the industrial production site to optimize the back pressure control,and designs the corresponding back pressure control system according to the back pressure model under different loads.The control performance of the back pressure control system with PID,fuzzy PID and GPC is compared and analyzed through the simulation test.The simulation results show that the GPC algorithm has better dynamic performance than PID and fuzzy PID control in the case of set point disturbance and internal disturbance,and has stronger robustness in the face of model mismatch.To sum up,GPC algorithm is more suitable for the back pressure control system under complex working conditions,and the optimization control method has a certain guiding significance for the actual production site back pressure control strategy improvement.Through in-depth optimization research on the direct air-cooling system from the back pressure setting value and the back pressure control strategy,the dynamic setting model of back pressure setting value is established by combining theoretical research and actual operation of the unit,and the back pressure control strategy is improved by GPC algorithm.The above optimization measures have certain reference value for the optimization and improvement of back pressure control of the same type of direct air-cooling unit.