CN114493290A - Safety risk grade evaluation method of operation management and control system based on information fusion - Google Patents
Safety risk grade evaluation method of operation management and control system based on information fusion Download PDFInfo
- Publication number
- CN114493290A CN114493290A CN202210103483.2A CN202210103483A CN114493290A CN 114493290 A CN114493290 A CN 114493290A CN 202210103483 A CN202210103483 A CN 202210103483A CN 114493290 A CN114493290 A CN 114493290A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- real
- risk
- time
- evaluated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 291
- 230000004927 fusion Effects 0.000 title claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims abstract description 88
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000013210 evaluation model Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012502 risk assessment Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- BTCSSZJGUNDROE-UHFFFAOYSA-N gamma-aminobutyric acid Chemical compound NCCCC(O)=O BTCSSZJGUNDROE-UHFFFAOYSA-N 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 231100000279 safety data Toxicity 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an operation management and control system security risk grade assessment method based on information fusion, which comprises the following steps: dividing each pre-evaluation point of pre-evaluation, and determining a risk value of each type of pre-evaluation according to each pre-evaluation point; establishing a pre-evaluation matrix for pre-evaluation, and calculating the weight of each type of pre-evaluation according to the pre-evaluation matrix; acquiring a pre-evaluated risk score according to the pre-evaluated risk value of each class and the pre-evaluated weight of the corresponding class; dividing each real-time evaluation point of real-time evaluation, and determining a danger value of each type of real-time evaluation; establishing a real-time evaluation matrix for evaluation implementation, and calculating the weight of each type of real-time evaluation; acquiring a risk score of real-time evaluation; acquiring an individual total risk score and an individual total risk; and determining the safety risk level of the personal homework according to the personal total risk score and the personal total risk. The invention can more comprehensively and reasonably evaluate the safety risk level of the operating personnel.
Description
Technical Field
The invention belongs to the technical field of information technology and safety production fusion, and particularly relates to an operation management and control system safety risk grade evaluation method based on information fusion.
Background
The management and control of the safety risk of the power operation are one of the work centers of the power industry, and documents such as ' safety risk division standard of the power operation ', standard work specification of the safety management and control of the production operation ' and the like are formed on the work level, are regulations and specifications for a predicted condition, and cannot be accurately judged according to the condition of an operation site.
The operable method for risk assessment also includes an expert scoring evaluation method, an operation condition risk evaluation method, a probabilistic risk evaluation method, and the like. The expert scoring evaluation method is a referential opinion given by an expert group for analyzing a danger source and a hazard degree, and has the defect that the expert scoring evaluation method belongs to the advance judgment of a risk condition and cannot judge in real time along with a field condition. The operation condition risk evaluation is that overall scoring is carried out according to three dimensions of risk of accidents, frequency of human bodies exposed in dangerous environments and possible consequences of the accidents, the higher the score is, the greater the risk is, the defects that the higher the risk factor is, the higher the score is, the top is not closed, the dangerous case judgment is still approximate, and the capability of site condition judgment is not provided. The probabilistic risk evaluation method is a systematic evaluation method by comprehensively analyzing the accident occurrence probability of each operation unit, and is different from the traditional method in that the accident of various initial events is sequenced, the frequency and the consequence are considered at the same time, quantitative analysis can be performed to the maximum extent, and the probabilistic risk evaluation method has the defects that the accident unit is concerned more, and the fusion degree of other relevant factors such as operation information is not high.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an operation management and control system security risk level assessment method based on information fusion. The technical problem to be solved by the invention is realized by the following technical scheme:
a safety risk grade assessment method of an operation management and control system based on information fusion comprises the following steps:
dividing each pre-evaluation point to be evaluated in advance, and determining each type of risk value to be evaluated in advance according to each pre-evaluation point;
establishing a pre-evaluation matrix for pre-evaluation, and calculating the weight of each type of pre-evaluation according to the pre-evaluation matrix;
acquiring a pre-evaluated risk score according to the pre-evaluated risk value of each type and the pre-evaluated weight of the corresponding type;
dividing each real-time evaluation point of real-time evaluation, and determining a danger value of each type of real-time evaluation according to a danger value monitored by each real-time evaluation point in real time;
establishing a real-time evaluation matrix for implementing evaluation, and calculating the weight of each type of real-time evaluation according to the real-time evaluation matrix;
acquiring a risk score of the real-time evaluation according to the risk value of each type of real-time evaluation and the weight of the corresponding type of real-time evaluation;
acquiring a total personal risk score and a total personal risk according to the pre-evaluated risk score and the real-time evaluated risk score;
and determining the safety risk level of the personal operation according to the personal total risk score and the personal total risk.
In an embodiment of the present invention, the dividing the pre-evaluation points for pre-evaluation and determining the risk value of each type of pre-evaluation according to each pre-evaluation point includes:
and dividing the pre-evaluated evaluation points into operation program perfection condition evaluation, personnel work participation condition evaluation, operation site danger level evaluation and operation project danger level evaluation, and determining each type of pre-evaluated danger value according to the safety operation standard requirement and the expert experience value of the power industry.
In an embodiment of the present invention, the establishing a pre-evaluation matrix for pre-evaluation, and calculating a weight of each type of pre-evaluation according to the pre-evaluation matrix, includes:
taking an operation safety risk pre-evaluation index as a first level, taking an operation program, a worker type, an operation field and an operation item as a second level according to an evaluation point of the pre-evaluation, taking index factors of the operation program, the worker type, the operation field and the operation item as third levels respectively, and suggesting a pre-evaluation matrix of the pre-evaluation;
according to the pre-evaluation matrix, performing pairwise comparison in each layer of elements to construct a pre-evaluation judgment matrix;
and calculating the weight of each type of pre-evaluation by using a square root method according to the pre-evaluation judgment matrix.
In an embodiment of the present invention, obtaining a pre-evaluated risk score according to each of the pre-evaluated risk values and the pre-evaluated weight of the corresponding class includes:
and obtaining a pre-evaluated risk score according to the pre-evaluated risk value of each type and the pre-evaluated weight of the corresponding type, wherein the adopted evaluation model is as follows:
in the formula: (ii) a A represents the pre-evaluation risk score; kB1、KB2、KB3、KB4Respectively represent the weights of an operation program, a personnel work type, an operation field and an operation project; rB1i、RB2i、RB3i、RB4iRespectively representing the danger values of the items pre-evaluated indexes of the evaluation experts; n represents the number of evaluation experts.
In an embodiment of the present invention, the dividing the real-time evaluation points of the real-time evaluation, and determining the risk value of each type of real-time evaluation according to the risk value monitored by each real-time evaluation point in real time includes:
and dividing the evaluation points of the real-time evaluation into personnel exposure dangerous case evaluation, operation environment dangerous case evaluation and operation content dangerous case evaluation, and determining each type of pre-evaluated dangerous value according to the real-time monitoring dangerous value of each evaluation point.
In one embodiment of the present invention, the real-time monitoring risk value of each evaluation point is obtained by using a sensor or a neural network recognition model.
In an embodiment of the present invention, the establishing a real-time evaluation matrix for real-time evaluation, and calculating a weight of each type of real-time evaluation according to the real-time evaluation matrix includes:
taking the real-time evaluation index of the operation safety risk as a first level, taking a personnel exposure dangerous case, an operation environment dangerous case and an operation content dangerous case as a second level according to the evaluation point of the real-time evaluation, taking index factors of the personnel exposure dangerous case, the operation environment dangerous case and the operation content dangerous case as third levels respectively, and suggesting a real-time evaluation matrix of the real-time evaluation;
according to the real-time evaluation matrix, pairwise comparison is carried out in each layer of elements, and a judgment matrix for real-time evaluation is constructed;
and calculating to obtain the weight of each type of real-time evaluation by using a root method according to the judgment matrix of the real-time evaluation.
In an embodiment of the present invention, the risk score of the real-time evaluation is obtained according to the risk value of each type of real-time evaluation and the weight of the corresponding type of real-time evaluation, and an evaluation model adopted is as follows:
in the formula: d represents a real-time evaluation risk score; kE1、KE2、KE3Respectively representing the weight of 'personnel exposure dangerous case', 'operation environment dangerous case' and 'operation content dangerous case'; rE1i、RE2i、RE3iRespectively representing the risk values of real-time evaluation; and m represents the number of real-time evaluations.
In an embodiment of the present invention, the obtaining a total personal risk score and a total personal risk score according to the pre-evaluated risk score and the real-time evaluated risk score includes:
the personal total risk score is divided into 150 points, the highest pre-risk value is 50 points, and the real-time risk value is 100 points;
by the formula: calculating the total risk score G of the individual;
by the formula: g/150, total personal risk H.
In one embodiment of the present invention, the determining the safety risk level of the personal assignment according to the personal total risk score and the personal total risk comprises:
the individual total split level is divided into 5 levels, wherein,
the individual total risk degree is more than or equal to 80 percent or the individual total risk score is more than or equal to 120 and is evaluated as follows: extremely dangerous and incapable of continuing operation;
the individual total risk degree of 60% -80% or the individual total risk score of 90-120 is rated as: high risk, need to be rectified immediately;
the individual total risk score of 40% -60% or the individual total risk score of 60-90 is rated as: significant risk, need for rectification;
the individual total risk score of 20% -40% or the individual total risk score of 30-60 is rated as: general risk, need of attention;
the individual's total risk score of < 20% or the individual's total risk score of < 30 was rated as: slightly risky and acceptable.
Compared with the prior art, the invention has the beneficial effects that: according to the safety risk grade evaluation method of the operation management and control system based on information fusion, an evaluation method combining pre-evaluation and real-time evaluation is adopted, the safety risk indexes of operation and the real-time risk of birth of an operation link of field operation can be considered, and the safety risk grade of an operator can be evaluated more comprehensively and reasonably; and the real-time evaluation index system can timely and efficiently acquire real-time evaluation index information through a multi-sensor information real-time acquisition and image intelligent identification algorithm of intelligent terminal equipment worn by field operating personnel.
Drawings
Fig. 1 is a flowchart of a method for assessing a security risk level of an operation management and control system based on information fusion according to an embodiment of the present invention;
FIG. 2 is a diagram of a basic network architecture of an SSD target detection network model according to an embodiment of the present invention;
FIG. 3 is a diagram of an auxiliary convolutional layer structure of an SSD target detection network model according to an embodiment of the present invention;
fig. 4 is a diagram of a predicted convolution layer structure of an SSD object detection network model according to an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to specific examples, but the embodiments of the present invention are not limited thereto.
The invention provides an operation management and control system safety risk grade assessment method based on information fusion, which is mainly based on the safety operation requirement, the distributed management requirement, the information fusion requirement and the requirement of a management and control platform in the power industry.
(1) Requirement for safe operation
In order to deal with the behavior risks, the safety operation requirement is decomposed into three levels according to the requirements of safety regulations. The method is characterized by comprising the following steps of ensuring general safety measures, including safety helmet wearing regulations, working place illumination brightness regulations, high-altitude operation protection regulations, pit excavation and blasting regulations, hoisting and transportation regulations, pole tower construction and maintenance regulations, and paying-off and line tightening and withdrawing regulations. And secondly, ensuring technical safety measures including power failure, electricity inspection, grounding wire installation, personal security wire use, signboard (fence) setting and other link operation rules. And finally, ensuring professional operation measures including line operation and maintenance operation rules, near live conductor operation rules, distribution equipment operation rules, live operation rules, power cable operation rules and construction equipment management rules.
(2) Distributed management requirements
To cope with administrative class risks, the distributed management needs can be broken down into two large dimensions. One dimension, according to the requirements of safety regulations, ensures safety organization measures, including an on-site investigation system, a work ticket system, a work license system, a work monitoring system, a work interruption system and a power transmission recovery system after work. And the other dimension ensures layered supervision and management according to the requirements of power enterprise safety production emergency management, and comprises a field work group layer, a field command department layer, a county company management layer, a city company management layer and a province company management layer, and a layered early warning management mechanism is carried out.
(3) Information fusion requirements
According to various contents related to safety operation requirements and distributed management requirements, stage work such as user analysis, system design and scheme implementation is carried out, integration of data, voice, video, geographic information and the like is achieved based on modes of communication fusion, video fusion, network fusion, data fusion and service fusion, and then unified management and control of related power operation services are achieved.
(4) Management and control platform requirements
Because of the energy revolution and the digital revolution, the production and dispatching of the power system are in an interconnected and communicated networked form, and a safety management and control system adapted to the power system must enter a digital, networked and intelligent platform state. And carrying out graphic display, data fusion, safety early warning and service scheduling on the safety operation related information acquired by the head-mounted comprehensive information acquisition terminal.
Based on the above requirements, the specific scheme provided by the invention is as follows:
referring to fig. 1, fig. 1 is a flowchart of a method for assessing a security risk level of an operation management and control system based on information fusion according to an embodiment of the present invention; the safety risk grade evaluation method of the operation management and control system based on information fusion comprises the following steps:
and S1, dividing each pre-evaluation point of the pre-evaluation, and determining the risk value of each type of pre-evaluation according to each pre-evaluation point.
Specifically, the step may include:
and dividing the pre-evaluated evaluation points into operation program perfection condition evaluation, personnel work participation condition evaluation, operation site danger level evaluation and operation project danger level evaluation, and determining each type of pre-evaluated danger value according to the safety operation standard requirement and the expert experience value of the power industry.
And S2, establishing a pre-evaluation matrix for pre-evaluation, and calculating the weight of each type of pre-evaluation according to the pre-evaluation matrix.
Specifically, the step may include:
s21, taking the operation safety risk pre-evaluation index as a first level, taking the operation program, the worker type, the operation field and the operation project as a second level according to the pre-evaluation point, taking the index factors of the operation program, the worker type, the operation field and the operation project as a third level, and suggesting a pre-evaluation matrix for pre-evaluation;
s22, comparing every two elements in each layer according to the pre-evaluation matrix to construct a pre-evaluation judgment matrix;
and S23, calculating the weight of each type of pre-evaluation by using a root method according to the pre-evaluation judgment matrix.
And S3, acquiring the risk score of the pre-evaluation according to the risk value of each type of pre-evaluation and the weight of the corresponding type of pre-evaluation.
Specifically, the price model used in this step may be:
in the formula: (ii) a A represents the pre-evaluation risk score; kB1、KB2、KB3、KB4The weights respectively represent an operation program, a worker type, an operation field and an operation project; rB1i、RB2i、RB3i、RB4iRespectively representing the danger values of the items pre-evaluated indexes of the evaluation experts; n represents the number of evaluation experts.
And S4, dividing each real-time evaluation point of the real-time evaluation, and determining the danger value of each type of real-time evaluation according to each real-time evaluation point.
Specifically, the step may include:
and dividing evaluation points for real-time evaluation into personnel exposure dangerous case evaluation, operation environment dangerous case evaluation and operation content dangerous case evaluation, and determining each type of pre-evaluated dangerous value according to the real-time monitoring dangerous value of each evaluation point.
It should be noted that the real-time monitoring risk value of each evaluation point is obtained by using a sensor or a neural network recognition model.
And S5, establishing a real-time evaluation matrix for evaluation, and calculating the weight of each type of real-time evaluation according to the real-time evaluation matrix.
Specifically, the step may include:
s51, taking the real-time evaluation index of the operation safety risk as a first level, taking the personnel exposure dangerous case, the operation environment dangerous case and the operation content dangerous case as a second level according to the evaluation point of real-time evaluation, taking the index factors of the personnel exposure dangerous case, the operation environment dangerous case and the operation content dangerous case as third levels respectively, and suggesting a real-time evaluation matrix of real-time evaluation;
s52, comparing every two elements in each layer according to the real-time evaluation matrix to construct a judgment matrix of real-time evaluation;
and S53, calculating the weight of each type of real-time evaluation by using a root method according to the judgment matrix of the real-time evaluation.
And S6, acquiring the risk score of the real-time evaluation according to the risk value of each type of real-time evaluation and the weight of the corresponding type of real-time evaluation.
Specifically, the step may include:
acquiring a risk score of real-time evaluation according to the risk value of each type of real-time evaluation and the weight of the corresponding type of real-time evaluation, wherein an evaluation model is as follows:
in the formula: d represents a real-time evaluation risk score; kE1、KE2、KE3Respectively representing the weight of 'personnel exposure dangerous case', 'operation environment dangerous case' and 'operation content dangerous case'; rE1i、RE2i、RE3iRespectively representing the risk values of real-time evaluation; and m represents the number of real-time evaluations.
And S7, acquiring the total personal risk score and the total personal risk according to the pre-evaluated risk score and the real-time evaluated risk score.
Specifically, the step may include:
the total personal risk degree integral is divided into 150 points, the highest pre-risk value is 50 points, and the real-time risk value is 100 points;
by the formula: calculating the total risk score G of the individual;
by the formula: g/150, total personal risk H.
And S8, determining the safety risk level of the personal homework according to the personal total risk score and the personal total risk.
Specifically, the step may include:
the individual total split level is divided into 5 levels, wherein,
the individual total risk degree is more than or equal to 80 percent or the individual total risk score is more than or equal to 120 and is evaluated as follows: extremely dangerous and incapable of continuing operation;
the individual total risk degree of 60% -80% or the individual total risk score of 90-120 is rated as: high danger and immediate rectification;
the individual total risk score of 40% -60% or the individual total risk score of 60-90 is rated as: significant risk, need for rectification;
the individual total risk score of 20% -40% or the individual total risk score of 30-60 is rated as: general risk, need of attention;
the individual's total risk score of < 20% or the individual's total risk score of < 30 was rated as: slightly risky and acceptable.
The following describes the embodiments of the present invention in further detail with reference to the power industry.
According to the safety risk grade evaluation method of the operation management and control system based on information fusion, an evaluation method is constructed by combining pre-evaluation and real-time evaluation.
1. Preliminary evaluation
(1) Dividing pre-evaluated evaluation points
1) Assessment of job procedure perfection
The common work flow is as follows: reporting a plan, determining a scheme, transacting an application, issuing a work order, making work preparation, allowing work, entering a site, carrying out operation, terminating and transmitting power.
And according to the specific progress condition and the operation information perfection condition of the workflow, giving the danger value of the operation program perfection condition of the operator according to a preset danger value standard.
2) And evaluating the participation condition of workers.
According to the links of power generation, power transmission, power transformation, power distribution and power utilization, 14 specialties and 88 work categories in the power industry are classified.
And giving the risk value of the personnel work category participation condition according to the work category working characteristics and the pre-established risk value standard.
3) Evaluation of
The site conditions are definitely classified into sites which do not need to be surveyed, sites which need to be surveyed on site and sites which have dangerous grades of operation sites recently according to safety regulations.
And setting the danger value of the danger level of the operation site according to the site condition and a preset danger value standard.
4) Work item risk rating
The operations are classified into non-live operations, live operations and emergency repair operations according to the safety regulations.
And setting the danger value of the danger level of the work project according to the work characteristics and a preset danger value standard.
(2) Establishing a pre-evaluation matrix for pre-evaluation
The pre-evaluation matrix is shown in table 1:
TABLE 1 Pre-evaluation matrix
(3) Calculating the weight
According to the analysis of the safety risk evaluation index of the operation management and control system and the principle of an analytic hierarchy process, the safety risk evaluation index hierarchical analysis model structure of the operation management and control system is determined through industry research, safety data search and expert opinion solicitation. The evaluation system comprises two types of safety risk pre-evaluation indexes and safety risk real-time evaluation indexes, wherein each type of safety risk pre-evaluation index and safety risk real-time evaluation index is divided into three layers.
The pre-evaluation target of the operation safety risk is the first level, namely the pre-evaluation index weight (A) of the operation safety risk. Then, the aspects of the operation program, the labor type, the operation site and the operation project 4 are evaluated according to the index points specified by the safety regulations, and the 4 elements form a criterion layer (Bx) of the evaluation system. The 4 levels are respectively provided with index factors, and an index layer (Cn) which is the third level is formed.
After the hierarchical analysis model is established, pairwise comparison can be carried out in each layer of elements, and a comparison judgment matrix is constructed. The analytic hierarchy process is mainly to judge the relative importance of each factor in each layer, and the judgment is expressed by numerical values through drawing proper scales and written into a judgment matrix. The decision matrix represents a comparison of relative importance between the factor of the current level and the factor related to the current level for the factor of the previous level. The judgment matrix is the basic information of the analytic hierarchy process and is also an important basis for calculating the relative importance. How to establish the pairwise comparison determination matrix is described below.
Assuming that the element Bx of the previous layer is used as a criterion and has a dominant relationship with the element Cn of the next layer, the objective of the present invention is to give corresponding weight to Cn according to the relative importance of the element Bx. The following questions are answered in this step: for the criterion Bx, the two elements C1, C2 are of that importance, the magnitude of importance. A certain value needs to be assigned to "importance". The basis or source of the valuation can be provided directly by the decision-maker, or determined through a dialog between the decision-maker and the analyst, or obtained through some technical consultation by the analyst, or as appropriate by other suitable means. Generally, the decision matrix should be given independently by an expert familiar with the problem.
For n elements, we get pairwise comparison decision matrix C ═ (Cij) nxn where Cij represents factor i and factor j relative to the target significance value. The constructed decision matrix takes the form:
TABLE 2 schematic judgment matrix
C1 | C11 | C12 | … | C1n |
C2 | C21 | C22 | … | C2n |
… | … | … | … | … |
Cn | Cn1 | Cn2 | … | Cnn |
The evaluation matrix is the basis for carrying out the calculation of relative weight and comprehensive weight by hierarchical analysis. The relative weight of the hierarchical element is relative to the element of the previous hierarchical layer, and the relative weight is calculated by judging the characteristic vector of the matrix and normalizing the characteristic vector. The comprehensive weight of the elements is calculated for the target layer from top to bottom layer by layer. The magnitude of the integrated weight of each level is calculated by weighting and summing the levels. And for the judgment matrix, calculating a characteristic root and a characteristic vector of the judgment matrix by using linear algebra knowledge, wherein the calculated characteristic vector is a relative weight vector. The invention adopts a square root method as a calculation method. The method for calculating the relative value of the elements comprises the following steps:
(1) calculating the product M of each row of elements of the judgment matrixi
Mi=ΠCij (ij=1,2,…,n)
In the formula: n is the dimension of the judgment matrix of the layer; cijFor determining the elements of the ith row and the jth column of the matrix
(2) Calculating the component w of the eigenvector of the judgment matrix Ai
(3) The characteristic vector is normalized, and the processed result is the relative weight W of the element of the layeri
(4) Calculating the element comprehensive weight U of the hierarchy
In the formula: n and m are the dimensions of the judgment matrix of the current layer and the upper layer respectively; alpha is alphaijIs the element of the judgment matrix A; u shapehThe comprehensive weight of the next-level secondary element h is obtained; whiThe relative weight of the element i in the current level to the secondary element h in the previous level.
(5) Calculating the maximum characteristic root lambda of the judgment matrixmax
In order to ensure the compatibility of the judgment matrix, namely the consistency of the thinking judgment process of an evaluator, the consistency index CI of the judgment matrix, the random consistency ratio CR and the randomness of the comprehensive weightConsistency ratio CRHealdThe following conditions must be satisfied
CI=(λmax CR=CI/RI≤0.1
In the formula, RI is an average random consistency index of the judgment matrix, and for the judgment matrix with dimensions of 1-11, RI values are listed in Table 5; CIhiThe consistency index of the element i of the current level to the element h of the previous level is shown; RI (Ri)hiThe average random consistent index of the element i of the level relative to the element i of the previous level h; lambda [ alpha ]maxJudging the maximum characteristic root of the matrix A; w is the transpose matrix of the relative weights of each layer.
If the above condition is not satisfied, the matrix is determined to be incompatible, and the value of the determination matrix must be readjusted until the above condition is satisfied.
TABLE 3 random consistency index Table
|
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 |
RI | 0 | 0 | 0.58 | 0.90 | 1.12 | 1.24 | 1.32 | 1.41 | 1.45 | 1.49 | 1.53 |
The relative weight results of the safety risk pre-evaluation indexes are shown in the table, and the comprehensive weight of the elements is shown in the table. The research result shows that: the consistency index of each matrix is less than 0.1, so that each matrix has satisfactory consistency. The attitude questionnaire and consumer questionnaire that illustrate the design experts are serious and scientific.
TABLE 4 layer A-B decision matrix and corresponding weight table
TABLE 5B1-C layer decision matrix and corresponding weight table
TABLE 6B2-C layer decision matrix and corresponding weight table
TABLE 7B3-C layer decision matrix and corresponding weight table
TABLE 8B4-C layer decision matrix and corresponding weight table
TABLE 9 comprehensive weight table of elements
Based on the principle and the method, the weights of the operation program, the personnel work type, the operation field and the operation project in the operation safety risk pre-evaluation are calculated.
(4) Calculating a pre-evaluation risk score
Calculating a pre-evaluation risk score by adopting a pre-evaluation model:
in the formula: (ii) a A represents the pre-evaluation risk score; kB1、KB2、KB3、KB4Respectively represent 'operation program', 'personnel' and 'operation field'The weight of the "job item"; rB1i、RB2i、RB3i、RB4iRespectively representing the danger values of the items pre-evaluated indexes of the evaluation experts; n represents the number of evaluation experts.
2. Real-time evaluation
(1) Dividing evaluation points for real-time evaluation
1) Personnel exposure risk assessment
A. And field personnel classify: site operator, monitoring supervisor, technical support, scheduling manager.
B. The time of the personnel in the danger area: the working time of a general danger area and the working time of a core danger area.
C. The physiological indications of the operator: heart rate, blood pressure index.
2) Work environment risk assessment
A. It is obvious in the danger source: judging that the danger source is displayed. The apparent danger source is divided into a fixed danger source and a movable danger source according to the conventional method.
B. Potential hazard sources: temperature, humidity, height, distance index from the electric field, concentration of harmful gas and illumination of the working surface.
C. Hazard level of hazard source: major disaster (death of multiple people), disaster (death of several people), very serious (death of one person), serious (disability), serious (serious injury), eye-catching
3) Job content risk assessment
A. Operation project dangerous case index: power transformation operation, power transformation maintenance, power distribution operation and power distribution maintenance
B. Operation dangerous case index: electric shock, falling from high place, object striking, mechanical injury and misoperation.
(2) Establishing a pre-evaluation matrix for real-time evaluation
The real-time evaluation matrix is shown in table 1:
TABLE 10 real-time evaluation matrix
(3) Calculating the weight
The principle and method for calculating the index weight of each evaluation point evaluated in real time are the same as those for calculating the index weight of each evaluation point evaluated in advance, and are not described herein again. The weights of the personnel exposure dangerous case, the operation environment dangerous case and the operation content dangerous case are obtained through the steps.
(4) Obtaining the risk value of each evaluation point evaluated in real time
And acquiring the real-time monitoring danger value of each evaluation point by adopting a sensor or a neural network recognition model.
For example, the classification of the field personnel in the personnel exposure danger index can be performed by acquiring images of a field operator, a monitoring supervisor, a technical support and a scheduling manager and identifying different colors of a safety helmet worn by the field personnel through a neural network identification model. The exposure time of the danger zone can be obtained through a graph sensor and a neural network identification model. The physiological characteristics such as heart rate and blood pressure can be obtained through a physiological characteristic sensor arranged in the safety helmet. Specific monitoring methods are given as examples later.
(5) Calculating a real-time assessment risk score
Calculating a real-time evaluation risk score through a real-time evaluation model:
in the formula: d represents a real-time evaluation risk score; k isE1、KE2、KE3Respectively representing the weights of personnel exposure dangerous case, operation environment dangerous case and operation content dangerous case; rE1i、RE2i、RE3iRespectively representing the risk values of real-time evaluation; and m represents the number of real-time evaluations.
3. Personal risk rating
And according to the obtained pre-evaluated risk score and the real-time evaluated risk score, calculating to obtain the total personal risk score and the total personal risk, and judging the risk level according to the total personal risk score and the total personal risk.
The total personal risk degree integral is divided into 150 points, the highest pre-risk value is 50 points, and the real-time risk value is 100 points;
by the formula: calculating the total risk score G of the individual;
by the formula: g/150, total personal risk H.
And corresponding the calculated personal total risk score and the personal total risk to the following table to obtain the corresponding risk degree.
TABLE 11 evaluation criteria for personal Risk
Risk rating | Total degree of risk of individual | Individual total risk score | Degree of |
Level | |||
1 | ≥80% | ≥120 | Is extremely dangerous and cannot continue to operate |
|
60%-80% | 90-120 | High risk, need to be rectified immediately |
Grade 3 | 40%-60% | 60-90 | Significant risk, need to be rectified |
|
20%-40% | 30-60 | General risk, need to pay attention to |
|
<20% | <30 | Is slightly risky and can accept |
In the above monitoring method for an evaluation point of real-time evaluation, the neural network model based on which the target is identified may be an SSD target detection network model. The network model is explained below.
The SSD target detection Network model structure comprises a Base Network (Base Network), an Auxiliary convolutional layer (Autoliary nodes) and a Prediction convolutional layer (predictionnodes).
The SSD basic network adopts a VCG-16 network architecture, the VCG-16 network comprises a convolutional layer and a fully-connected layer (FC Layers), the tasks of the fully-connected layer are used for classification, the fully-connected layer only needs to be replaced by the convolutional layer because the basic network only needs to extract a feature mapping diagram, and the parameters of the part and the parameters of the convolutional layer of the VCG-16 network are obtained by a transfer learning method. The basic network architecture is shown in fig. 2.
The auxiliary convolutional layer is connected with the final feature map of the basic network, and 4 high-scale feature maps are output through the convolutional neural network, and the structure diagram is shown in fig. 3.
The structure diagram of the rectangular frame information and the class information of each point of the predicted convolutional layer prediction feature map is shown in fig. 4.
The SSD target detection network model obtains the human body target based on a video human body behavior target detection algorithm, and has the advantages that: the human body detection speed is high, the anti-interference capability is high, the background model is updated by adopting a random updating strategy, and the problem of uncertainty of the pixel change of the video image of the construction site can be effectively solved.
It should be noted that, with the target detection network model, in the model training stage, training can be performed based on a plurality of training samples of different types, such as people, helmets, hazard sources, and the like, so that the hazard values of various real-time evaluation points can be obtained in actual use.
According to the safety risk grade evaluation method of the operation management and control system based on information fusion, an evaluation method combining pre-evaluation and real-time evaluation is adopted, the safety risk indexes of operation and the real-time risk of birth of an operation link of field operation can be considered, and the safety risk grade of an operator can be evaluated more comprehensively and reasonably; and the real-time evaluation index system timely and efficiently acquires real-time evaluation index information through a multi-sensor information real-time acquisition and image intelligent identification algorithm of intelligent terminal equipment worn by field operating personnel.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (10)
1. A safety risk grade assessment method for an operation management and control system based on information fusion is characterized by comprising the following steps:
dividing each pre-evaluation point to be evaluated in advance, and determining each type of risk value to be evaluated in advance according to each pre-evaluation point;
establishing a pre-evaluation matrix for pre-evaluation, and calculating the weight of each type of pre-evaluation according to the pre-evaluation matrix;
acquiring a pre-evaluated risk score according to the pre-evaluated risk value of each type and the pre-evaluated weight of the corresponding type;
dividing each real-time evaluation point of real-time evaluation, and determining a danger value of each type of real-time evaluation according to a danger value monitored by each real-time evaluation point in real time;
establishing a real-time evaluation matrix for evaluation implementation, and calculating the weight of each type of real-time evaluation according to the real-time evaluation matrix;
acquiring a risk score of the real-time evaluation according to the risk value of each type of real-time evaluation and the weight of the corresponding type of real-time evaluation;
acquiring a total personal risk score and a total personal risk according to the pre-evaluated risk score and the real-time evaluated risk score;
and determining the safety risk level of the personal operation according to the personal total risk score and the personal total risk.
2. The safety risk rating method for the operation management and control system based on the information fusion according to claim 1, wherein the dividing of the pre-evaluated pre-evaluation points and the determining of the risk value of each type of pre-evaluation according to each pre-evaluation point comprise:
and dividing the pre-evaluated evaluation points into operation program perfection condition evaluation, personnel work participation condition evaluation, operation site danger level evaluation and operation project danger level evaluation, and determining each type of pre-evaluated danger value according to the safety operation standard requirement and the expert experience value of the power industry.
3. The safety risk rating method for the operation management and control system based on information fusion according to claim 2, wherein the establishing a pre-evaluation matrix for pre-evaluation and calculating the weight of each type of pre-evaluation according to the pre-evaluation matrix comprises:
taking an operation safety risk pre-evaluation index as a first level, taking an operation program, a worker type, an operation field and an operation item as a second level according to an evaluation point of the pre-evaluation, taking index factors of the operation program, the worker type, the operation field and the operation item as third levels respectively, and suggesting a pre-evaluation matrix of the pre-evaluation;
according to the pre-evaluation matrix, performing pairwise comparison in each layer of elements to construct a pre-evaluation judgment matrix;
and calculating to obtain the weight of each type of pre-evaluation by using a root method according to the pre-evaluation judgment matrix.
4. The safety risk rating method for the operation management and control system based on the information fusion according to claim 1, wherein obtaining a pre-evaluated risk score according to the pre-evaluated risk value of each category and the pre-evaluated weight of the corresponding category comprises:
and obtaining a pre-evaluated risk score according to the pre-evaluated risk value of each type and the pre-evaluated weight of the corresponding type, wherein the adopted evaluation model is as follows:
in the formula: (ii) a A represents the pre-evaluation risk score; kB1、KB2、KB3、KB4Respectively represent the weights of an operation program, a personnel work type, an operation field and an operation project; rB1i、RB2i、RB3i、RB4iRespectively representing the risk values of the pre-evaluation indexes of the project by the evaluation experts; n represents the number of evaluation experts.
5. The method for assessing the safety risk level of the operation management and control system based on the information fusion according to claim 1, wherein the dividing of real-time evaluation points and the determining of the risk value of each type of real-time evaluation according to the risk value monitored by each real-time evaluation point in real time comprise:
and dividing the evaluation points of the real-time evaluation into personnel exposure dangerous case evaluation, operation environment dangerous case evaluation and operation content dangerous case evaluation, and determining each type of pre-evaluated dangerous value according to the real-time monitoring dangerous value of each evaluation point.
6. The safety risk rating method for the operation management and control system based on information fusion as claimed in claim 5, wherein the real-time monitoring risk value of each evaluation point is obtained by using a sensor or a neural network recognition model.
7. The safety risk rating method for the operation management and control system based on information fusion according to claim 5, wherein the establishing a real-time evaluation matrix for real-time evaluation and calculating the weight of each type of real-time evaluation according to the real-time evaluation matrix comprises:
taking the operation safety risk real-time evaluation index as a first level, taking a personnel exposure dangerous case, an operation environment dangerous case and an operation content dangerous case as a second level according to the evaluation point of the real-time evaluation, taking index factors of the personnel exposure dangerous case, the operation environment dangerous case and the operation content dangerous case as third levels respectively, and suggesting a real-time evaluation matrix of the real-time evaluation;
according to the real-time evaluation matrix, pairwise comparison is carried out in each layer of elements, and a judgment matrix for real-time evaluation is constructed;
and calculating the weight of each type of real-time evaluation by using a square root method according to the judgment matrix of the real-time evaluation.
8. The safety risk rating method for the operation management and control system based on the information fusion according to claim 1, wherein the risk score of the real-time evaluation is obtained according to the risk value of each type of real-time evaluation and the weight of the corresponding type of real-time evaluation, and the adopted evaluation model is as follows:
in the formula: d represents a real-time evaluation risk score; k isE1、KE2、KE3Respectively representing the weight of 'personnel exposure dangerous case', 'operation environment dangerous case' and 'operation content dangerous case'; r isE1i、RE2i、RE3iRespectively representing the risk values of real-time evaluation; and m represents the number of real-time evaluations.
9. The safety risk rating method for the operation management and control system based on information fusion according to claim 8, wherein the obtaining of the total personal risk score and the total personal risk score according to the pre-evaluated risk score and the real-time evaluated risk score comprises:
the total personal risk degree integral is divided into 150 points, the highest pre-risk value is 50 points, and the real-time risk value is 100 points;
by the formula: calculating the total risk score G of the individual;
by the formula: g/150, total personal risk H.
10. The safety risk rating method for the job management and control system based on information fusion according to claim 1, wherein the determining the safety risk rating of the personal job according to the personal total risk score and the personal total risk comprises:
the individual total split level is divided into 5 levels, wherein,
the individual total risk degree is more than or equal to 80 percent or the individual total risk score is more than or equal to 120 and is evaluated as follows: extremely dangerous and incapable of continuing operation;
the individual total risk degree of 60% -80% or the individual total risk score of 90-120 is rated as: high risk, need to be rectified immediately;
the individual total risk score of 40% -60% or the individual total risk score of 60-90 is rated as: significant risk, need to be rectified;
the individual total risk score of 20% -40% or the individual total risk score of 30-60 is rated as: general risk, need of attention;
the individual's total risk score of < 20% or the individual's total risk score of < 30 was rated as: slightly risky and acceptable.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210103483.2A CN114493290A (en) | 2022-01-27 | 2022-01-27 | Safety risk grade evaluation method of operation management and control system based on information fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210103483.2A CN114493290A (en) | 2022-01-27 | 2022-01-27 | Safety risk grade evaluation method of operation management and control system based on information fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114493290A true CN114493290A (en) | 2022-05-13 |
Family
ID=81475638
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210103483.2A Pending CN114493290A (en) | 2022-01-27 | 2022-01-27 | Safety risk grade evaluation method of operation management and control system based on information fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114493290A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115423387A (en) * | 2022-11-04 | 2022-12-02 | 国网浙江省电力有限公司金华供电公司 | Intelligent early warning method and system for field behaviors of live working personnel of extra-high voltage line |
-
2022
- 2022-01-27 CN CN202210103483.2A patent/CN114493290A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115423387A (en) * | 2022-11-04 | 2022-12-02 | 国网浙江省电力有限公司金华供电公司 | Intelligent early warning method and system for field behaviors of live working personnel of extra-high voltage line |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gul et al. | A new Fine-Kinney-based risk assessment framework using FAHP-FVIKOR incorporation | |
CN106529696B (en) | Early warning method and early warning device for equipment in power grid | |
CN110555617B (en) | Real-time dynamic quantitative assessment method for building fire risk based on Internet of things | |
Chen et al. | New model for occupational health and safety risk assessment based on Fermatean fuzzy linguistic sets and CoCoSo approach | |
Chen et al. | Emergency rescue capability evaluation on urban fire stations in China | |
CN113379267A (en) | Urban fire event processing method and system based on risk classification prediction and storage medium | |
CN206312210U (en) | A kind of status assessing system of Distribution Network Equipment | |
CN110046812A (en) | The integrated evaluating method of city safety development level | |
Lee et al. | Dynamic analysis of construction safety risk and visual tracking of key factors based on behavior-based safety and building information modeling | |
CN113506001B (en) | Smart management and control auxiliary decision-making method for safety risk lean of operation site | |
CN114493290A (en) | Safety risk grade evaluation method of operation management and control system based on information fusion | |
CN113869736A (en) | Method and system for evaluating and grading safety risks of firework and firecracker operating enterprises | |
CN113627739B (en) | Construction method of engineering construction project security risk evaluation index system | |
CN110889587A (en) | Power distribution network line risk assessment method | |
CN117151478B (en) | Chemical enterprise risk early warning method and system based on convolutional neural network | |
CN113935571A (en) | Gas station security risk assessment grading method and system | |
CN112668830A (en) | Multilayer fuzzy assessment method for transformer substation operation risk | |
CN116644929A (en) | Intelligent management method for operation and maintenance work orders of power distribution network equipment based on Internet of things perception | |
CN106655181A (en) | Priority setting method and system for power grid nodes | |
CN116341789A (en) | Emergency rescue capability assessment system and assessment method for large airport | |
CN115953046A (en) | Method for evaluating comprehensive capability of 10kV distribution network uninterrupted operating personnel | |
CN112132397A (en) | Large-scale business district security risk fuzzy comprehensive evaluation method and device based on network analysis | |
CN113627705A (en) | Safety city evaluation system and method | |
CN111160694A (en) | Method and device for evaluating emergency capacity of power system | |
Guofeng | Research on Safety Risk Assessment Method of Highway Bridge Construction Based on AHP-Fuzzy Comprehensive Evaluation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |