37results about How to "Improve fault location speed" patented technology

The embodiment of the invention provides a fault prediction method, device and equipment and a readable storage medium, and the method can comprise the steps: obtaining a service log; based on the content contained in the service log, determining feature information of the service log, wherein the feature information is used for representing features of the service log; obtaining fault feature information, wherein the fault feature information is obtained based on training of a plurality of historical service logs; and matching the feature information of the service log with the fault featureinformation, and performing fault prediction through a preset matching rule based on the matching degree of the feature information of the service log and the fault feature information. Through the fault prediction method, device and equipment and the readable storage medium provided by the embodiment of the invention, the fault positioning speed can be improved.

The invention provides a power distribution network single-phase grounding fault section positioning method based on a generalized group knapsack. Traditional fault positioning algorithms based on a power system transient signal all adopt a fixed basis function to decompose the signal and have the problems of insufficient decomposition accuracy and redundant decomposition results. The invention proposes to use a sparse decomposition theory to extract an attenuation DC component in the power system transient signal, and an area where the single-phase grounding fault is located is judged according to the existence of the attenuation DC component. In order to overcome the problem of huge space-time complexity of a sparse decomposition theory classical MP algorithm, a generalized group knapsack model is constructed based on dynamic programming, and a linear combination of selected atoms approximates an original transient signal with O(VN) time complexity. According to the method, the basisfunction can be adaptively selected according to the characteristics of the transient signal to obtain a simplest form of signal decomposition, and a new idea is provided for the single-phase groundfault positioning method of the power distribution network.

The invention discloses an abnormality elimination management system and method based on the increment of abnormality information database. The system comprises: abnormality information processing state monitoring part; abnormality cause analysis part, which executes abnormality cause analysis process for abnormal records whose causes are not analyzed; The defect elimination processing execution unit performs anomaly elimination processing on the abnormal information whose unique abnormal cause is identified by the anomaly cause analysis unit. The combination improves the processing, analysis, processing efficiency and accuracy of abnormal information in substations, ensures integrated processing of abnormal information and closed-loop management and control of abnormal problems, and provides an effective substation equipment maintenance and accident prevention measures for the power sector.