Research On Energy-saving Control System Of Circulating Cooling Water Based On Multi-temperature Objectives Of Process Medium

In the background of the global energy crisis,improving energy utilization is of great significance to achieving sustainable development.There is often a "big horse drive the little car" phenomenon between the cooling supply amount and the process medium cooling demand in the circulating cooling water system,resulting in a large amount of waste of cooling resources.Existing circulating cooling water variable frequency and variable pressure control system only controls the feed water pressure,and does not consider the impact of process medium load changes and production environment temperature changes on cooling water flow requirements.In this paper,the cooling water flow is adjusted according to the temperature of the process medium to further reduce the energy consumption of the circulating cooling water pump unit.A minimum differential pressure control system for circulating cooling water based on the multi-process medium temperature target is proposed.The main research contents and achievements of this paper include:(1)Under the condition that the original f variable frequency and variable pressure control system effectively controls the outlet pressure of the circulating cooling water,a cascade energy-saving control system for the minimum pressure difference of the circulating cooling water based on the multi-temperature target of the process medium is proposed.The cascade control system includes a process medium temperature control outer ring and a feed and return water pressure difference control inner ring.In order to control the temperature of all process media within their respective safety range,by adjusting the opening of the upper tower valve,we can change the circulating cooling water flow to the minimum value to meet the cooling demand,and reduce the energy waste caused by the pump unit to deal with the excess water flow.(2)For the outer loop of process medium temperature control mentioned in(1),a predictive control method of process medium temperature in circulating cooling water system based on improved stack automatic encoder is proposed.First,clean the industrial filed data.Then,multiple autoencoders are stacked to build a deep learning network structure,and the network parameters are trained using the layer-by-layer greedy unsupervised pre-training-parameter fine-tuning method.In order to reduce the probability of falling into local optimum,the network parameters are fine tuned based on the root mean square back propagation optimization method.Finally,the historical data of the 1 # heat exchanger of CNOOC Tianye Chemical Plant are used to test and the results are compared with shallow neural network and the unimproved SAE method.The prediction accuracy of the ISAE method proposed in this paper is high,and the average percentage error of the predicted process medium temperature is only 0.85%.The generalization ability is better than the unimproved SAE algorithm.Accurate temperature prediction is of great significance for stably controlling the temperature of the process medium within the range of safe production temperature range.For the inner loop of backwater pressure difference control mentioned in(1),an intelligent PID control method for circulating cooling water is proposed.According to the simulation results of the differential pressure model of feed and return water,the algorithm has good fast response and stability.(3)The cascade energy-saving control system for the minimum differential pressure of circulating cooling water mentioned in(1)is applied to the Tianye Chemical Plant with hierarchical control architecture.Based on the electricity consumption records of the past year,0 process medium temperature over-standard records and 0 fault operation records,the energy-saving performance of the control system,the validity of the algorithm and the rationality of the hardware and software configuration are verified.