Research On Intelligent Operation And Maintenance Strategy Of Charging Facilities Based On Operational Risk Assessment

With the rapid development of the new energy vehicle market,the demand for its supporting infrastructure is also increasing,and the scale of charging facilities is becoming larger and larger.However,due to the complex failure factors of charging facilities and the wide distribution of equipment,the traditional inspection and maintenance methods are inefficient and costly.At present,they cannot meet the operation and maintenance needs of large-scale charging facilities,which seriously affects the development of the new energy vehicle industry.Therefore,this paper proposes an intelligent operation and maintenance strategy for charging facilities based on operational risk assessment to provide support for the intelligent operation and maintenance of electric vehicle charging facilities.Firstly,analyze the risk theory and risk assessment method,formulate the risk assessment process of charging facilities,study the operation mechanism of AC and DC charging equipment and common faults in daily operation,combine the actual operation data to extract the risk factors of charging facilities operation,and screen charging facilities Operational risk indicators,constructing a risk indicator system for charging facilities operation.Then,the risk assessment of charging facility operation is regarded as a prediction problem,and machine learning algorithms are used for risk assessment in order to simplify the risk assessment work in practical applications.Based on the relevant national standards and literature,a single index rating rule is formulated,and different risk indicators are considered to have different influences on the operation status of charging equipment,and different weights are given to different risk indicators.According to the multi-factor comprehensive evaluation method,the comprehensive evaluation of the charging facility operation risk indicators is obtained.The risk health value of the facility,a data set is established after comprehensive evaluation.Normalize the index data as sample data training model,use BP neural network to train the base predictor of Adaboost algorithm,build a strong predictor by adjusting the weight of each base predictor,and then improve the prediction accuracy,based on BP-The Adaboost algorithm establishes a risk assessment model for the operation of charging facilities.Finally,an intelligent optimization operation and maintenance strategy for charging facilities is proposed.Based on the operating risk and health value of charging facilities,the cost of equipment failure depreciation loss is calculated.Considering the impact of equipment failure on the charging time of charging users,the charging facility after failure is obtained by modeling the electric vehicle charging network.Charging loss time,calculate the cost of charging resource loss after quantifying the cost of time loss.Combining the cost of charging resource loss and the cost of failure depreciation loss,establish a risk loss model of charging facilities,comprehensively consider the cost of risk loss and the minimum operation and maintenance cost,establish an intelligent optimization operation and maintenance model of charging facilities,and formulate the order of operation and maintenance according to the risk health value of charging stations and charging facilities,considering the minimum total cost of operation and maintenance to allocate the operation and maintenance time,the improved artificial bee colony algorithm is used to calculate the objective function,and determine the operation and maintenance strategy of charging facilities,which reduces the workload of operation and maintenance and reduces the cost of operation and maintenance.