Post-evaluation method of the construction effect of power distribution network project, based on BP neural network

A BP neural network and artificial neural network technology, applied in the field of distribution network, can solve problems such as too strong subjectivity, too one-sidedness, and strong subjectivity

Inactive Publication Date: 2017-07-28
STATE GRID CORP OF CHINA +2
View PDF1 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In Yu Gang (YU Gang). Study on Post-evaluation Method of Investment Effect of Investment in Distribution Networks [J]. Value Engineering, 2013,12:324 The index system, index scoring method, weight determination method and comprehensive evaluation method proposed in -325 can evaluate the investment effect of distribution network construction and renovation projects; however, its weight calculation method is only analytic hierarchy process, which is too one-sided
[0004] In Xu Zhiyong, Zhang Xudong, Zeng Ming, et al. (Application of ANP-based multilevel fuzzy comprehensive evaluation methods to post-evaluation for grid construction projects) [J]. East China Electric Power (East China Electric Power), 2003, 37(3): 488-490 established a complete set of post-evaluation index system for grid construction projects, and applied ANP-based The multi-level fuzzy comprehensive evaluation method weights and scores the indicators, but the method is too subjective
[0005] In Wu Hongliang (WU Hongliang). Application of Improved in Post-Evaluation for Power Grid Projects [J]. Power System and Clean Energy, 2011, In 27(10): 4-7+12, a special post-evaluation research on the function and effect of distribution network construction was carried out. By improving the conventional logical framework method, the ideas of before and after comparison and with or without comparison in the post-evaluation were introduced to more clearly reflect the However, this method belongs to the traditional post-evaluation method, which is too subjective and one-sided

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
  • Post-evaluation method of the construction effect of power distribution network project, based on BP neural network
  • Post-evaluation method of the construction effect of power distribution network project, based on BP neural network
  • Post-evaluation method of the construction effect of power distribution network project, based on BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] A post-evaluation method of distribution network project construction effect based on BP neural network, the steps are as follows: step S1, select a number of grassroots indicators reflecting the current situation of distribution network project construction effect, and establish an evaluation index system; figure 2 As shown, the evaluation index system includes first-level indicators and second-level indicators, the first-level indicators include power supply quality, network structure, power supply capacity and assembly level; the second-level indicators of power supply quality include power supply reliability and comprehensive voltage Pass rate; the secondary index of the network structure includes 10Kv line connection rate, 10Kv line average power supply radius, 10Kv line average segment number, 10Kv line N-1 pass rate and 380V line average segment number; described power supply capacity The secondary indicators include the heavy overload rate of 10Kv lines and the ...

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 post-evaluation method of the construction effect of a power distribution network project, based on a BP neural network. The post-evaluation method includes the steps: S1, establishing an evaluation index system; S2, acquiring base index data and preprocessing; S3, through scoring of experts, obtaining the target scores corresponding to Ntrain training samples; S4, determining the network layer number; S5, determining the network node number; S6, determining a transfer function; S7, selecting a training method; S8, establishing a BP artificial neural network post-evaluation model; S9, setting a training parameter, and training; S10, judging the training effect; S11, inspecting the trained BP artificial neural network post-evaluation model; and S12, observing the fitting effect. The established BP artificial neural network post-evaluation model of the post-evaluation method of the construction effect of a power distribution network project, based on a BP neural network can fully absorb the determination experience of experts so as to save the step of weight determining and scoring, so that the evaluation becomes more concise and clear.

Description

technical field [0001] The invention relates to the technical field of distribution network, in particular to a post-evaluation method for the construction effect of a distribution network project based on a BP neural network. Background technique [0002] The post-project evaluation is the last important link in the project cycle. It is a work to conduct a comprehensive evaluation of the project after the project is completed and delivered for a period of time. The post-evaluation has been carried out in some industries at home and abroad for a long time and has achieved good results. However, at this stage, the post-evaluation work of power grid projects in China is relatively short at this stage, focusing on the post-evaluation of main network engineering projects, and the post-evaluation of distribution network engineering projects is still in its infancy. At present, only China Southern Power Grid Corporation has promulgated and implemented the "Implementation Measures ...

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): G06Q10/06G06Q50/06G06N3/08
CPCG06N3/084G06Q10/0639G06Q50/06
Inventor 王利利李秋燕关朝杰孙义豪丁岩全少理李锰郭新志胡钋殷奕恒杨丰阁
Owner STATE GRID CORP OF CHINA
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