Research On Intelligent Operation And Maintenance Of Wind Power Based On Knowledge Map Technology

With the increasing number of wind power installed,the high failure rate of wind power units and the high cost of operation and maintenance have become the bottleneck for the development of wind power companies.At present,fan fault monitoring mainly relies on the SCADA alarm system and the experience analysis of operation and maintenance engineers.However,there are certain differences in the knowledge reserve of operation and maintenance personnel,which may lead to problems such as delayed detection of potential faults and low accuracy of fault handling.In the field operation and maintenance work,due to the lack of operation and maintenance experience and professional skills,the failure handling ability is insufficient,which seriously affects the processing efficiency of operation and maintenance tasks and greatly increases the operation and maintenance cost.In view of the current problems of wind power operation and maintenance,this paper proposes an intelligent operation and maintenance scheme of wind power field with knowledge graph technology as the core.By constructing fault domain knowledge graph and cognitive diagnosis of operation and maintenance engineers,targeted dispatches are carried out.The unique advantages of using knowledge graph technology are reflected in that it can enhance human cognition of faults,assist engineers to analyze how to locate and maintain faults,have good human-computer interaction characteristics,and integrate cognitive diagnosis to achieve targeted dispatching,which is conducive to improving the intelligent degree and efficiency of operation and maintenance.The main tasks are as follows:Firstly,based on the existing business pain points in the field of wind power operation and maintenance,the framework of wind power intelligent operation and maintenance system with knowledge graph as the core is proposed.The research of intelligent operation and maintenance system includes two main research contents:fault diagnosis decision and targeted dispatch.The fault tree,ontology technology,Bayesian reasoning and decision tree algorithm used in the process of knowledge graph construction and application are analyzed,which lays a foundation for the realization of intelligent operation and maintenance of wind power.Secondly,the fault knowledge graph of the variable rotor system was designed and constructed and applied to the fault diagnosis decision.Based on the fault tree,the extracted fault characteristic parameters and probability importance,the fault ontology model is built by Protege tool.In order to clearly express and find the implied factual relationship between faults,SWRL rules and Jess inference engine are fused to carry out ontology reasoning.The knowledge graph based on ontology was imported into Neo4 j for storage and visualization,and three types of abnormal fault diagnosis cases of variable rotor were analyzed.It was proved that the domain knowledge graph based on ontology could provide operation and maintenance personnel with operation and maintenance assistance decision conveniently and effectively,and improve the sharing and reuse rate of operation and maintenance knowledge.Thirdly,intelligent dispatch of wind power operation and maintenance based on cognitive diagnosis.Firstly,a cognitive diagnosis model for inter-turn short circuit of variable rotor motor was established.Based on the traditional Bayesian inference,the conditional probability in the cognitive diagnosis model was modeled by using Bayesian psychometrical model and IRT algorithm,and the conditional probability parameters were estimated by MCMC method,and the posterior probability in the Bayesian network was calculated and simulated to form the personalized cognitive skill map.Finally,the decision tree algorithm is used to train the dispatching decision tree from the cognitive skill map data of operation and maintenance personnel,and the dispatching decision tree is predicted according to the cognitive skill map of operation and maintenance personnel,which improves the efficiency of operation and maintenance.Finally,based on the fault knowledge graph and cognitive skill graph,the wind power intelligent operation and maintenance system is realized based on the Neo4 j graph database and C# programming,and the functional test is carried out to prove the effectiveness and feasibility of the tuning system.