Research On Operation Status Intelligent Monitoring Method For Thermal Power Plant Typical Equipment

In 2020,China formally proposed the dual carbon goal of "striving to peak carbon dioxide emissions before 2030 and strive to achieve carbon neutrality before 2060".In the report of the 20th National Congress of the Communist Party of China,it is clearly proposed that we must actively and steadily promote carbon peaking and carbon neutrality.The carbon dioxide generated by China’s energy utilization accounts for about 88%of the total carbon dioxide emissions,of which the electricity industry accounts for about 40%of the energy industry emissions.To achieve carbon peak carbon neutrality,energy is the main battlefield,and electricity is the main force.To achieve carbon peak carbon neutrality,energy is the main battlefield,and electricity is the main force.At present,coal-based thermal power is still the main body of my country’s power supply.In the future,thermal power will still play an indispensable role in ensuring power security and providing flexible peak-shaving capabilities for renewable energy.In order to ensure the reliable operation of the thermal power plant,it is necessary to ensure the reliable operation of the core equipment in the unit.Large-scale thermal power plants have complex structures and numerous systems.Once a fault occurs in certain equipment and cannot be detected and dealt with in time,it will easily expand into a larger fault and cause the entire unit to shut down.Therefore,conducting research on intelligent monitoring methods for the operation status of typical equipment in thermal power units is of great significance to ensuring the safe,stable,and reliable operation of thermal power plants.Firstly,based on the process flow of thermal power units,the main causes of typical equipment failures in thermal power units were analyzed.Secondly,in response to the intelligent monitoring problem of typical equipment operation status in thermal power units,Tensorflow deep learning framework functional API programming method was used to establish intelligent monitoring models for equipment operation status of primary fan,secondary fan,induced draft fan,and high-pressure fluidized fan.After preprocessing the data derived from the scene,the hyperparameter of the multi output long short memory neural network is optimized using the adaptive chaotic innovative optimizer named weighted mean of vectors based on the fusion quantum particle swarm optimization algorithm.In order to verify the modeling effect,the accuracy of the neural network model was tested using the time series cross validation method.In order to achieve equipment operation status monitoring,the sequential probability ratio test method is used to determine the operating conditions of the equipment and monitor its operation status.Finally,an intelligent monitoring system for the operation status of typical equipment in thermal power units was developed,and the intelligent monitoring method for the operation status of typical equipment in thermal power units proposed in this article was applied to a certain electric field in Shanxi.The OPC client was developed using VB programming language to read real-time data of typical equipment in thermal power units.The TCP server and TCP client were developed using Python programming language to achieve real-time data transmission of thermal power unit equipment.The intelligent monitoring software for the operation status of typical equipment in thermal power units was developed using Python programming language to monitor the operation status of typical equipment and display the equipment operation status through web pages.This provides a certain reference for the practical application of intelligent monitoring methods for the operation status of typical equipment in thermal power units in engineering.