Spare unit and part prediction method of electric energy meters based on state maintenance of electric energy meters

Abstract

The invention discloses a spare unit and part prediction method of electric energy meters based on state maintenance of the electric energy meters. The method comprises the following steps that (1) multidimensional indexes of the electric energy meters are analyzed, a colinearity problem is solved in a gradual regression analysis method, an obtained main variable is weighted and scored via a statistical average method, a calculation formula of the unhealthy degree is reduced by one dimension, and the batch of electric energy meters whose unhealthy degree is high is replaced; (2) a gradient tree improving algorithm model is used to predict the unhealthy degree of the electric energy meters which do not have serious problems, and the batch of electric energy meters which tend to have serious problems is obtained and replaced; and (3) an Arima time sequence algorithm is used to predict the quantity of newly added users locally in each year. According to the invention, manufacturers and batches serve as analysis objects, an electric energy meter health degree evaluation model, an electric energy meter health degree prediction model and an electric energy meter newly added user quantity prediction model are established, and thus, spare units and parts of the electric energy meters are predicted and analyzed.

Description

technical field [0001] The invention relates to the technical field of electric energy meter measurement and data mining, in particular to a method for predicting spare parts of electric energy meters based on the state maintenance of electric energy meters. Background technique [0002] State Grid Anhui Electric Power Company has 25,000,000 electric energy meters, most of which belong to IV and V electric energy meters, a total of 25,363,693 (accounting for about 98%). Type III electric energy meters accounted for about 101,852 (1.5%) of Anhui's operating electric energy meters, and the remaining electric energy meters of type I and II accounted for less than 0.5%. At present, according to the requirements of DL / T448-2000 "Technical Management Regulations for Electric Energy Metering Devices", electric energy meters are divided into five grades: I, II, III, IV, and V. On-site random spot checks are carried out for electric energy meters of types I, II, and III. Calibrate t...

AI Technical Summary

Problems solved by technology

Due to the different manufacturing process, component batch quality and operating environment of various electric energy meter manufacturers, some electric energy meters have quality problems before they expire and cause high complaints from users; some electric energy meters are of better quality, Waste due to replacement

The number of energy meters that actually need to be replaced and the number of energy meters that need to be added due to policy, environmental and other factors are often judged based on experience and cannot be accurately predicted. Therefore, it is necessary to use the algorithm in machine learning to accurately predict how many energy meters will be prepared in the coming year.

Images