Measuring instrument demand prediction method and system, computing device and storage medium

A measuring instrument and demand forecasting technology, applied in computing, neural learning methods, instruments, etc., can solve the problems of high time cost and low forecasting accuracy, reduce enterprise costs, ensure timeliness of forecasting, improve information comprehensiveness and The effect of algorithmic fault tolerance

Pending Publication Date: 2022-03-11
国网重庆市电力公司营销服务中心 +2
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is: in order to solve the technical problem of low prediction accuracy and high time cost of the above-mentioned measuring instrument demand forecasting method, the present invention provides a measuring instrument demand forecasting method, system, computing device and storage medium, without consuming On the basis of excessive computing resources and computing time, the prediction accuracy and prediction accuracy of the algorithm are improved

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Measuring instrument demand prediction method and system, computing device and storage medium
  • Measuring instrument demand prediction method and system, computing device and storage medium
  • Measuring instrument demand prediction method and system, computing device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0107] Such as figure 1 As shown, this embodiment provides a method for forecasting demand for measuring instruments, including the following steps:

[0108] Step 1: Obtain the historical data of the installation volume of each type of measuring instrument and the external data of each influencing factor in the corresponding period, and calculate the chi-square value of the two variables through the chi-square test. If the chi-square value is small and close to 0, install The quantity is related to external factors, and the installation type of measuring instruments is "industry expansion, new installation, transformation and rotation", go to step 2; if the chi-square value is large, it is determined that the installation quantity has nothing to do with external factors, and it is an installation type of "fault repair" , execute step 3;

[0109] Step 2: Use the SRU+RBF algorithm to make predictions, and measure the historical data of the past installation / demand of measuring ...

Embodiment 2

[0114] On the basis of Example 1, such as Figure 2-3 As shown, the SRU+RBF algorithm predicts, and the general process of forecasting the demand for measuring instruments of the installation type of "transformation rotation, business expansion and new installation" is as follows:

[0115] A1: Collect historical order data of measuring instruments and perform data preprocessing;

[0116] A1.1: Collect the historical orders of the installation types of measuring instruments for "retrofit and rotation" and "industry expansion and new installation" in the MDS system or SG186 system, and obtain the historical installation volume of each type of measuring instrument on a weekly / monthly / quarterly basis, and The historical data matrix is ​​formed according to the row direction of different models and the column direction of different weeks / months / quarters;

[0117] A1.2: In the historical data matrix, each column of data constitutes a column vector The minimum value data and maxim...

Embodiment 3

[0151] On the basis of Example 1, the SRU+Bayesian network algorithm is used for prediction. By predicting the failure of the measuring instruments in operation, the type and quantity of the measuring instruments that have failed are obtained, and the demand for "fault repair" installation type measuring instruments is calculated. Quantity P bn .

[0152] Specifically, such as Figure 4 As shown, the general process of the SRU+Bayesian network combination algorithm for forecasting the demand of the "fault repair" installation type measuring instruments is as follows:

[0153] B1: Obtain attribute data of faulty measuring instruments from the power site: collection success rate, online rate, usage time, specification and model, manufacturer, production batch, communication flow, communication protocol, channel type, and the number of important items sent , clock out-of-tolerance times, address;

[0154] B2: Perform data preprocessing on the attribute data collected in step B...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a measuring instrument demand prediction method and system, a calculation device and a storage medium, belongs to the technical field of electric energy demand prediction, and solves the technical problems of low prediction accuracy and high time cost of an existing measuring instrument. Prediction is carried out through SRU + RBF and SRU + Bayesian network algorithms, and if the installation amount is related to external factors, the measurement accuracy of the measuring instrument is improved. Performing prediction through an SRU + RBF algorithm, accurately predicting the demand quantity of the measurement instruments of the installation types of'transformation rotation 'and'business expansion new installation', and outputting a prediction result; if the installation amount is irrelevant to external factors, prediction is carried out through an SRU + Bayesian network algorithm, the demand quantity of the'fault repair 'installation type measuring instrument is accurately predicted, and a prediction result is output; scientific support is provided for optimizing electric power material inventory management and reducing enterprise cost.

Description

technical field [0001] The present invention relates to the technical field of demand forecasting for measuring instruments, and more particularly relates to the technical field of a demand forecasting method, system, computing device and storage medium for measuring instruments. Background technique [0002] Demand forecasting for measuring instruments refers to the accurate prediction of the demand for electric energy measuring instruments of power companies in a certain period of time in the future through the prediction algorithm embedded in the system, and the acquisition of reliable demand data that can be used by power companies to formulate scientific material procurement plans; With the development of the economy and the promotion of the reform of electric power enterprises, the demand for electric energy measuring instruments is increasing year by year. In order to ensure the rapid response to the needs of electric power users and avoid the waste of materials, the p...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/06G06Q50/06G06N3/04G06N3/08
CPCG06Q10/06315G06Q50/06G06N3/08G06N3/048Y02P80/10
Inventor 张羽舒永生赵莉欧习洋黄磊王奕周游李刚孙恺霞邓红梅吕梁贺业梅
Owner 国网重庆市电力公司营销服务中心
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap