Fault prediction method and device for power distribution system

Abstract

The invention relates to a fault prediction method and device for a power distribution system, belongs to the technical field of fault prediction, and solves the problem that the conventional prediction method cannot realize fault prediction based on historical data. The method comprises the following steps that output voltage of the power distribution system is collected to form a voltage sampleset, a sample set mean value and a sample variance S<2> are calculated to obtain a confidence interval of the expectation mu and the standard deviation sigma at the confidence level 1-alpha; every time a new voltage sample is collected, a new voltage sample set is formed together with the voltage sample set at the previous moment, and the confidence interval of the new voltage sample set at the confidence level is 1-alpha is calculated, and the confidence intervals of mu and sigma are calculated; and the process is repeated to obtain continuous confidence intervals of mu and sigma of the plurality of voltage sample sets, if the confidence intervals of mu and sigma of the voltage sample sets are both stable in a preset fluctuation range, sigma<2>= S<2> is taken to obtain a voltage output interval of the power distribution system in a normal working state, and the fault prediction of the power distribution system is realized according to the voltage output interval in the normal workingstate.

Description

technical field [0001] The invention relates to the technical field of fault prediction, in particular to a fault prediction method and device for a power distribution system. Background technique [0002] Fault prediction is defined as the prediction of electrical equipment before failure through technical means. The failure prediction mechanism is that before the failure of electrical equipment, some internal systems or components have deviated from the normal operating range, although the system can still be guaranteed to operate and maintain within the index. output, but as the operation time goes by, its internal system or components deviate from the normal working range more and more seriously until the system fails. Fault prediction is to monitor the internal nuances of the system through technical means before the system fails, so as to achieve the purpose of early forecast, early preparation and early maintenance, so as to prevent sudden system failure in the future...

AI Technical Summary

Problems solved by technology

[0005] In view of the above analysis, the present invention aims to provide a fault prediction method and device for a power distribution system to solve the problem that the existing prediction method does not comprehensively use data processing means and historical output data analysis system operation status, and cannot realize the real fault problem of prediction

Images