Electric vehicle charging and discharging abnormity test method based on multivariate Gaussian distribution model

Abstract

The invention relates to an electric vehicle charging and discharging abnormity detection method based on a multivariate Gaussian distribution model, and the method comprises the following steps: S1, obtaining charging and discharging data of an electric vehicle, and carrying out the data preprocessing, bad data processing, data conversion and data feature mining of the obtained charging and discharging data of the electric vehicle; s2, evaluating the processed data, and constructing a quality evaluation index system and a quality evaluation model for the charging and discharging data of the electric vehicle according to the characteristics of the charging and discharging data of the electric vehicle; and S3, carrying out visualization processing on the charging and discharging data to obtain an anomaly detection category and a standard curve, and predicting whether the new data is abnormal or not according to the determined anomaly detection model and the standard curve. According to the invention, the efficiency and accuracy of charging and discharging fault detection are improved, and the safety of using the electric vehicle is improved.

Description

Technical field [0001] The present invention involves an abnormal inspection method based on electric vehicle charging and discharge of electric vehicles based on multiple Gaussian distribution models, which belongs to the field of electrical equipment and electrical engineering technology. Background technique [0002] As one of the seven major areas of the new infrastructure, the rapid development direction of electric vehicles and supporting charging equipment is clear. As the charging and discharge service network becomes more dense, various types of faults during the charging and discharge process have even appeared frequently, causing major hazards to the electric vehicle user and the charging and distribution operation and dimension service network, and also affecting consumers' consumption of electric vehicles for electric vehicles. choose. At the same time, the abnormal state diagnostic system of the electric vehicle charging and discharge process has not yet been perfec...

AI Technical Summary

Problems solved by technology

As the charging and discharging service network becomes denser, various failures and even fires occur frequently during the charging and discharging process, causing significant damage to electric vehicle users and the charging and discharging operation and maintenance service network, and also affecting consumers' consumption of electric vehicles choose

At the same time, the abnormal state diagnosis system in the charging and discharging process of electric vehicles is not yet perfect, which makes it difficult for the actual safety emergency effect of electric vehicle supporting facilities to meet expectations

[0003] Most of the electric vehicle charging piles put into use now adopt the method of manual regular maintenance, which requires a lot of manpower, material resources and financial resources, which brings a lot of troubles to the charging pile operators, and it is difficult to guarantee the timeliness of fault discovery and troubleshooting

At present, my country has done relevant work on the faults of charging and discharging of electric vehicles, and proposed a variety of strategies and models, but there are few studies on intelligent diagnosis methods for faults, and the research on fault diagnosis of charging and discharging of electric vehicles in my country is urgently needed. in-depth

Images