Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Quantitative evaluation system and method for reducing risks of production operators

A quantitative evaluation and operator technology, applied in neural learning methods, information technology support systems, biological neural network models, etc., can solve the problems of less personal safety risks and no one cares about it, so as to improve the level of personal safety and ensure accuracy , to ensure comprehensive and scientific results

Pending Publication Date: 2022-04-01
STATE GRID GANSU ELECTRIC POWER CORP +2
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The study found that there are very few quantitative studies on personal safety risks at home and abroad, especially for the quantitative evaluation of personal safety risks in production operations in the power industry.

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
  • Quantitative evaluation system and method for reducing risks of production operators
  • Quantitative evaluation system and method for reducing risks of production operators
  • Quantitative evaluation system and method for reducing risks of production operators

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] Embodiment 1 A quantitative evaluation method for reducing the risk of production workers

[0074] 1. Construction of key risk factor database

[0075] 1.1 Frequency extraction of personal safety risk words based on TF-IDF

[0076] 1.1.1 Using the TF-IDF algorithm, through the Python software, the "Accident Report" and "National Power Safety Production Situation" of the National Energy Administration from January 2016 to May 2020, and some accident report documents of the State Grid Corporation of China to carry out key words Analyze, sort and sort the Python execution results according to the weight of TF-IDF, filter out the 40 words with the highest weight of TF-IDF in the file, and list the keyword extraction result table, as shown in Table 1;

[0077] Table 1 Keyword extraction result table

[0078]

[0079]

[0080] 1.1.2 Based on the keyword extraction results, combined with the actual work and characteristic elements of the production operation site, 24 k...

Embodiment 2

[0171] Example 2 Analysis of Typical Samples of Production Operations 1

[0172] (1) Analysis of the original sample

[0173] 1. Data collection and model testing

[0174] Different from Example 1, this example takes the production operation plan from March to August 2020 as a screening sample, and finally determines a total of 2,500 original samples covering key information such as companies, temporary plans and non-temporary plans in various cities in Gansu Province , according to the distribution of samples in each unit, after sorting and screening, 2087 effective samples were recovered in this embodiment, and the effective recovery rate was 83.48%. The situation of each unit is as follows Figure 10 shown. After eliminating invalid samples, the model test is carried out according to 2087 valid samples. The 2087 effective samples are tested in the form of "overall + sub-unit", and the vectorized evaluation model is imported into the input file to obtain the operation res...

Embodiment 3

[0177] Example 3 Analysis of typical samples of production operations II

[0178] (1) New sample analysis

[0179] 1. Data collection

[0180] The difference from Example 2 is that in this example, based on the analysis of the production and operation day control plan of the Gansu company, taking October 2020 as the sample period, five prefecture cities of Jinchang, Jiuquan, Lanzhou, Longnan, and Qingyang were randomly and equally selected. Each company has 100 pieces of production operation information, a total of 500 pieces of production operation information, and issued the "State Grid Gansu Provincial Electric Power Company Production Operation Personal Safety Risk Quantitative Evaluation-Data Collection Form" to collect key field information, and found through the recovery and sorting of the data collection form, excluding formats and There are 452 invalid samples whose content is incorrectly filled in, and the remaining valid samples are 452. For the distribution of eac...

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 provides a quantitative evaluation system and method for reducing risks of production operators, and belongs to the technical field of power operation safety risk management and control. The method comprises the steps of risk key factor library construction, quantitative evaluation model establishment and quantitative result output application. According to the method, a 5M factor method and a TF-IDF algorithm are adopted, a power production operation personal risk quantitative evaluation index system composed of 26 key indexes including operation principal basic information, operation site actual information and the like is constructed from five dimensions of human, machine, material, method and ring, and the comprehensiveness and scientificity of the quantitative evaluation system are ensured; the personal safety quantitative evaluation model based on the principal component neural network is constructed by integrating respective advantages and characteristics of a principal component analysis method and a neural network algorithm, and the most stable neural network structure is constructed on the basis of complete coverage of evaluation index information, so that the accuracy of a quantitative evaluation result is ensured; and a logistic regression model is introduced to realize risk early warning of different production operations.

Description

technical field [0001] The invention belongs to the technical field of electric power operation safety risk management and control, and in particular relates to a quantitative evaluation system and method for reducing the risk of production workers. Background technique [0002] At present, various accident hazards and safety risks are intertwined in electric power production, and personal safety accidents in production operations are prone to and frequent, and the situation of personal safety risk management is still severe. [0003] At present, in the process of risk assessment of production operations, hazard identification, risk level determination and general measure identification are usually carried out in accordance with risk assessment technical standards, mainly based on experience judgment, while historical accidents, violations, personnel management, environment and other operational risk management processes are generated The large amount of data lacks systemati...

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): G06Q10/06G06N3/04G06N3/08G06F17/16
CPCY04S10/50
Inventor 贺洲强陈钊刘超王利平聂江龙夏天赵连斌马之力王跃杨鹏云朱海涛高翔任毅华陆浩赵金雄马志程张驯李志茹杨勇马宏忠
Owner STATE GRID GANSU ELECTRIC POWER CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products