CN114757557A - On-site operation risk assessment prediction method and device based on electric work ticket - Google Patents
On-site operation risk assessment prediction method and device based on electric work ticket Download PDFInfo
- Publication number
- CN114757557A CN114757557A CN202210452009.0A CN202210452009A CN114757557A CN 114757557 A CN114757557 A CN 114757557A CN 202210452009 A CN202210452009 A CN 202210452009A CN 114757557 A CN114757557 A CN 114757557A
- Authority
- CN
- China
- Prior art keywords
- risk
- work ticket
- factors
- work
- sub
- 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
- 238000012502 risk assessment Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000010410 layer Substances 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
Abstract
The invention provides a method and a device for predicting the risk assessment of field operation based on an electric work ticket, which comprises the steps of constructing an operation risk assessment index system according to risk factors of the field operation; extracting risk elements from an operation risk evaluation index system, splitting and matching the risk elements based on a personnel information base and a large-scale safety tool base, and extracting the content of a work ticket; calculating the content of the work order by using a pre-trained operation site risk intelligent evaluation model; performing risk assignment on the calculated contents of the work ticket according to a professional risk evaluation standard library to obtain a risk score; and outputting a corresponding risk grade according to the risk score. The invention can completely get rid of human factors, effectively evaluate the safety risk of the operation site and provide support for management decision.
Description
Technical Field
The invention belongs to the technical field of electric power system safety protection, and particularly relates to a method and a device for evaluating and predicting on-site operation risks based on an electric power work ticket.
Background
With the increasing expansion of the power grid scale, the power operation activities become frequent, and the lean and modern management requirements of power supply enterprises in new situations are difficult to meet by the traditional manual on-site supervision and inspection and the management and control mode reviewed afterwards. The electric power enterprise has urgent needs to establish an electric power operation field visualization and intelligent management and control platform, and more efficient and intelligent cooperative supervision and management are carried out on the electric power operation field. The power grid overhaul work ticket contains a large amount of valuable information, the decision of overhaul work tickets can be effectively assisted through retrieval and utilization of historical work tickets, and finally intelligent risk assessment of various distribution network operations is realized through work ticket risk classification.
At present, the manual safety monitoring mode is generally adopted for electric power field operation, but a monitoring person and an operating person are easily influenced by external factors, attention may not be focused, and safety accidents may be caused. With the frequent activities of electric power operation, the problems of low efficiency and waste of human resources exist in manual safety monitoring.
Disclosure of Invention
In view of this, the present invention aims to solve the problems that the existing manual security monitoring mode for controlling the power field operation is easily affected by external factors, the efficiency is low, and human resources are wasted.
In order to solve the technical problems, the invention provides the following technical scheme:
in a first aspect, the invention provides a method for estimating and predicting the risk of field operation based on an electric work ticket, which constructs an operation risk estimation index system according to risk factors of the field operation, and comprises the following steps:
acquiring a work ticket of electric power field operation;
separating and matching various risk factors in the work ticket by using the personnel information base and the large-scale safety tool base, extracting semantic information of the work ticket, and determining various risk factors in the work ticket according to an operation risk evaluation index system;
recognizing semantic information of the work ticket by using a pre-trained work ticket text classifier based on KPCA and ELM;
Performing risk assignment on the identified content of the work ticket according to a professional risk evaluation standard library to obtain a risk score;
and outputting a corresponding risk grade according to the risk score.
Further, the construction of the operation risk assessment index system according to the risk factors of the field operation specifically comprises the following steps:
selecting risk factors of field operation, wherein the risk factors comprise personnel factors and sub factors thereof, equipment factors and sub factors thereof, operation methods and sub factors thereof, tools and sub factors thereof, and environmental factors and sub factors thereof;
and constructing an operation risk assessment index system according to the various risk factors and the corresponding sub-factors.
Further, the pre-training process of the work ticket text classifier based on KPCA and ELM specifically includes:
importing work ticket text data from a power grid historical database and dividing the work ticket text data into a training sample set and a testing sample set;
performing word segmentation and stop word removal processing on each type of work ticket text data in the training sample set and the test sample set;
calculating the weights of words in the work ticket text data, and forming an original characteristic vector set by the weights of all the words;
selecting a first feature set from a training sample set by adopting a kernel principal component analysis method based on the original feature vector;
The first feature set is used as input, the type of the work ticket is used as output, an extreme learning machine is adopted to learn the training sample, and a text classifier is established;
and extracting and selecting a second feature set from the test sample set, inputting the second feature set into the established text classifier, and outputting the classification result of the work order.
And further, performing word segmentation processing on the text data of the work ticket by adopting a search engine mode in a crust algorithm.
Further, the weight of the word of the work ticket text data is calculated according to the following formula:
in the formula, tiRepresenting the ith word, ω, in the text datatiRepresents tiWeight of (tf)iIs a word tiFrequency of occurrence, N is the number of text data, DF (t)i) To comprise tiNumber of text data of fi(d) Representing a function of the frequency of the calculated word.
In a second aspect, the present invention provides a device for estimating and predicting a risk of a field operation based on an electric work ticket, including:
the evaluation index building module is used for building an operation risk evaluation index system according to the risk factors of the field operation;
the content matching module is used for splitting and matching various risk elements in the work ticket by utilizing the personnel information base and the large-scale safety tool base, extracting semantic information of the work ticket, and determining various risk elements in the work ticket according to the operation risk evaluation index system;
The work ticket classification module is used for identifying semantic information of the work ticket by utilizing a pre-trained work ticket text classifier based on KPCA and ELM;
the risk evaluation module is used for carrying out risk assignment on the identified content of the work ticket according to the professional risk evaluation standard library to obtain a risk score;
and the risk grade prediction module is used for outputting a corresponding risk grade according to the risk score.
Further, the evaluation index construction module specifically includes:
the index determining module is used for selecting risk factors of field operation, wherein the risk factors comprise personnel factors and sub-factors thereof, equipment factors and sub-factors thereof, operation methods and sub-factors thereof, tools and sub-factors thereof, and environmental factors and sub-factors thereof;
and the system construction module is used for constructing an operation risk assessment index system according to various risk factors and corresponding sub-factors.
In a third aspect, the present invention provides a device for estimating and predicting a risk of a field operation based on an electric work ticket, which includes a processor and a memory:
the memory is used for storing the computer program and sending the instructions of the computer program to the processor;
the processor executes the method for predicting the risk assessment based on the electric work ticket field operation according to the instructions of the computer program.
In a fourth aspect, the present invention provides a computer storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for predicting risk assessment of field work based on electric work ticket according to the first aspect.
In conclusion, the invention provides a method and a device for evaluating and predicting the risk of the field operation based on the electric work ticket. The invention can completely get rid of human factors and effectively reduce the safety risk of the operation site. The data sharing is realized through the integrated information integration, the support is provided for management decision, the repeated maintenance of the same type of data in different systems is saved, the manual maintenance cost is saved, and the economic benefit is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without inventive labor.
Fig. 1 is a schematic flowchart of a method for estimating and predicting risk of field operation based on an electric work ticket according to an embodiment of the present invention;
FIG. 2 is a block diagram of an embodiment of an operation risk assessment system according to the present invention;
fig. 3 is a schematic diagram of a training process of a KPCA and ELM-based work ticket text classifier according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1-3, the present embodiment provides a method for estimating and predicting a risk of a field operation based on an electric work ticket, including:
and inputting a work ticket, namely acquiring the work ticket of the power field operation.
The work ticket is a written basis and a safety license for a service worker to perform work (collectively referred to as "service work") such as maintenance, installation, modification, debugging, and testing on an electric power production site, equipment, and a system, and is a written safety contract that both the service worker and the operation worker commonly hold and forcibly follow. The work ticket is a written order that permits work on the electrical device and is also a written basis for executing safety-ensuring technical measures.
And automatically disassembling and matching various risk elements in the work ticket by using the personnel information base and the large-scale safety tool base, wherein the risk elements in the work ticket are obtained according to an operation risk assessment index system.
It should be noted that, in this embodiment, an operation risk assessment index system is constructed according to 18 risk factors identified by an accident event, a violation and a person.
As shown in fig. 2, the personnel factors in the job risk assessment index system include 4 sub-factors of familiarity of the same job, past violation deduction conditions of the job principal, job qualification, and age of the member of the main work class; the equipment factors comprise 3 sub-factors of equipment type, equipment quality defect and construction machinery inspection defect; the operation method comprises operation mode, power failure, cross operation, operation property and operation guidance according to 5 sub-factors; the tools comprise 2 sub-factors of a safety tool inspection defect and a personal protective article inspection defect; the environmental factors comprise working weather and 2 sub-factors of a working area; the management factors comprise 2 sub-factors of bearing state evaluation and violation unit ranking.
In the embodiment, electric power operation risk analysis is mainly carried out from 5 types of risk elements including personnel factors, equipment factors, operation methods, tools and environmental factors.
Furthermore, matching risk elements are automatically split through the personnel information base and the large-scale safety tool base, namely the personnel information base and the large-scale safety tool base are matched according to the work ticket information of each operation to obtain more detailed personnel information and tool information, so that the single operation content is split into 5 types of risk elements such as personnel conditions, equipment configuration, operation properties, operation environment, key operation content and the like.
And extracting the content of the work ticket, calculating based on a KPCA and ELM mixed model text classification algorithm, namely extracting the semantic information of the work ticket, and identifying the semantic information of the work ticket by using a pre-trained work ticket text classifier based on KPCA and ELM.
It should be noted that, according to the above step, the work ticket content for the category 5 risk elements in the work ticket can be obtained. Based on the content of the work ticket, the embodiment adopts a pre-trained work ticket text classifier based on KPCA and ELM to identify the extracted semantic information of the work ticket, so as to perform the field operation risk assessment based on the 5 types of risk element items.
Further, as shown in fig. 3, the KPCA and ELM-based work ticket text classifier in this embodiment may be pre-trained by the following method:
1) And (3) dividing a training sample set and a test sample set of the text classification, namely importing the work order text data from the power grid historical database and dividing the work order text data into the training sample set and the test sample set.
2) And text preprocessing, namely performing word segmentation and word-off-process on each type of work ticket text data in the training sample set and the test sample set.
It should be noted that, in this embodiment, a final algorithm is used to perform word segmentation processing on the work ticket text data, which integrates the characteristics of character string matching word segmentation and statistical word segmentation. Besides the dictionary, the professional vocabulary in the power field is added according to the function of the self-defined dictionary. And if the words not contained in the dictionary appear in the text, identifying the words by using a hidden Markov model based on probability statistics.
In addition, the crust algorithm has three word segmentation modes: full mode, precision mode, search engine mode. The invention adopts the search engine mode to perform word segmentation, thereby not only overcoming the defect that the full mode can not solve the ambiguity of sentences, but also improving the recall ratio of phrases on the basis of the accurate mode, and the word segmentation effect is more practical.
3) And (4) extracting characteristics, namely calculating the weights of words in the text data of the work ticket, and forming an original characteristic vector set by the weights of all the words.
It should be noted that, the weight of the word of the work ticket text data may be calculated according to the following formula:
in the formula, tiRepresenting the ith word, ω, in the text datatiRepresents tiWeight of (1), tfiIs a word tiFrequency of occurrence, N is the number of text data, DF (t)i) To comprise tiNumber of text data of (f)i(d) Representing a function of the frequency of the calculated word.
The weights of all words form a set F ═ ω (ω)t1,ωt2,...,ωtm) And m is the number of all words.
4) Selecting features, namely extracting a first feature set from a training sample set by adopting a kernel principal component analysis method based on an original feature vector set;
it should be noted that F is used as an original feature of text classification, and since F includes many features, the dimensions of the features are high, and some features may interfere with each other, it is also necessary to select the original feature to reduce the number of features for text classification.
A specific implementation selects text classification features (first feature set) based on Kernel Principal Component Analysis (KPCA). KPCA introduction function phi classifies original text into feature vectors xkConversion is carried out (N is x)kDimension of) should satisfy:
the covariance matrix of all training sample data for text classification is:
to CφIs solved (lambda is C) φV is the eigenvector corresponding to λ):
λV＝Cφv
the feature vector V of the text classification is:
wherein, the first and the second end of the pipe are connected with each other,
and finally, selecting the text classification features with the first k larger values as effective features for modeling.
5) Training by using an extreme learning machine to obtain a text classifier, namely, taking a first feature set as input and a work ticket type as output, learning a training sample by using the extreme learning machine, and establishing the text classifier;
it should be noted that the Extreme Learning Machine (ELM) is a forward neural network with only one single layer, and the working principle is different from the traditional neural network, for example, the weight of the BP neural network is obtained by a gradient descent algorithm, while the weight of the ELM is obtained by an analytic expression, without intermediate iterative computation, and the running speed of the ELMAnd is faster. Let x represent the value of the input sample, and the threshold, weight and node of the hidden layer are bi，αiAnd L, then the output value of ELM is:
where G is the activation function of the hidden layer, the radial basis function is used herein, specifically as follows:
ELM divides all text data into m categories by the activation function of the hidden layer, and represents G by h (x), then the above formula becomes:
finally, according to the output value f of ELML(x) The classification of the input text data can be realized.
6) And outputting a classification result: and extracting a second feature set from the test sample set (when the text classifier is tested by using the test sample set, the text preprocessing, the original feature extraction, the feature selection and other processing are carried out on the test sample set by referring to the training sample set, and the like), inputting the second feature set into the established text classifier, and outputting the classification result of the work order.
It should be noted that the job site risk intelligent evaluation model obtained by training according to the above steps can identify and automatically classify the text features of the input job ticket.
And performing risk assignment by using the operation risk evaluation standard library to obtain a total score, namely performing risk assignment on the calculated content of the work order according to the professional risk evaluation standard library to obtain a risk score.
It should be noted that, according to the foregoing steps, each content in the work order may be classified, and then the risk score of the classified work order is obtained comprehensively based on the evaluation criteria for different risk factor items in the professional risk evaluation criteria library. The specific operation is that different weights are given to the risk elements according to different risk factors, and 5 types of risk elements in the work ticket are calculated according to different weights, so that the corresponding risk score of the work ticket is obtained.
And outputting the risk grade to guide the field work, namely outputting a corresponding risk grade according to the risk score, and guiding the operation of the power field by using the risk grade.
The embodiment provides a field operation risk assessment and prediction method based on an electric work ticket, which comprises the steps of constructing an operation risk assessment index system, calculating the work ticket by using a pre-trained operation field risk intelligent assessment model, determining the risk condition of each risk element in the frame according to the content of the work ticket, and further judging the risk level of the work ticket. The invention can completely get rid of human factors and effectively reduce the safety risk of the operation site. The data sharing is realized through the integrated information integration, the support is provided for management decision, the repeated maintenance of the same type of data in different systems is saved, the manual maintenance cost is saved, and the economic benefit is realized.
The above is a detailed description of an embodiment of the method for estimating and predicting the risk of the field operation based on the electric work ticket, and the following is a detailed description of an embodiment of the device for estimating and predicting the risk of the field operation based on the electric work ticket.
The embodiment provides a based on-the-spot operation risk assessment prediction unit of electric power work ticket, includes: the system comprises an evaluation index construction module, a content matching module, a work ticket classification module, a risk evaluation module and a risk level prediction module.
In this embodiment, the evaluation index construction module is configured to construct an operation risk evaluation index system according to risk factors of field operations;
it should be noted that the evaluation index building module specifically includes:
the index determining module is used for selecting risk factors of field operation, wherein the risk factors comprise personnel factors and sub factors thereof, equipment factors and sub factors thereof, an operation method and sub factors thereof, tools and sub factors thereof, and environmental factors and sub factors thereof;
and the system construction module is used for constructing an operation risk assessment index system according to various risk factors and corresponding sub-factors.
In this embodiment, the content matching module is configured to split and match each risk element of the work ticket by using the personnel information base and the large-scale security tool base, and extract semantic information of the work ticket, where each risk element of the work ticket is determined according to the job risk assessment index system.
In this embodiment, the work ticket classification module is configured to identify semantic information of a work ticket by using a pre-trained work ticket text classifier based on KPCA and ELM.
In this embodiment, the risk evaluation module is configured to perform risk assignment on the identified content of the work ticket according to the professional risk assessment standard library to obtain a risk score;
In this embodiment, the risk level prediction module is configured to output a corresponding risk level according to the risk score.
It should be noted that, the device for evaluating and predicting a risk of a field operation based on an electric work ticket provided in this embodiment is used to implement the method for evaluating and predicting a risk of a field operation based on an electric work ticket in the foregoing embodiment, and specific settings of the modules are based on implementation of the method, which are not described herein again.
The above is a detailed description of an embodiment of the electric work ticket based field work risk assessment and prediction device of the present invention, and the following is a detailed description of an embodiment of the electric work ticket based field work risk assessment and prediction device of the present invention.
The embodiment provides a prediction device based on electric work ticket field operation risk assessment, which comprises a processor and a memory, wherein the processor comprises:
the memory is used for storing the computer program and sending the instructions of the computer program to the processor;
the processor executes the method for predicting the risk assessment of the field operation based on the electric work ticket according to the instructions of the computer program.
The above is a detailed description of an embodiment of the electric power work ticket based on-site operation risk assessment and prediction apparatus of the present invention, and the following is a detailed description of an embodiment of a computer storage medium of the present invention.
The present embodiment provides a computer storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for predicting risk assessment of field work based on electric work tickets according to the foregoing embodiments is implemented.
The above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. A field operation risk assessment prediction method based on an electric power work ticket is characterized in that an operation risk assessment index system is built according to risk factors of field operation, and the method comprises the following steps:
acquiring a work ticket of electric power field operation;
separating and matching each risk factor in the work ticket by utilizing a personnel information base and a large-scale safety tool base, extracting semantic information of the work ticket, and determining each risk factor in the work ticket according to the operation risk evaluation index system;
Recognizing semantic information of the work ticket by utilizing a pre-trained work ticket text classifier based on KPCA and ELM;
performing risk assignment on the identified content of the work ticket according to a professional risk evaluation standard library to obtain a risk score;
and outputting a corresponding risk grade according to the risk score.
2. The electric power work ticket based field work risk assessment prediction method according to claim 1, wherein the construction of the work risk assessment index system according to the risk factors of the field work specifically comprises:
selecting risk factors of field operation, wherein the risk factors comprise personnel factors and sub factors thereof, equipment factors and sub factors thereof, operation methods and sub factors thereof, tools and sub factors thereof, and environmental factors and sub factors thereof;
and constructing an operation risk assessment index system according to the various risk factors and the corresponding sub-factors.
3. The method for estimating and predicting the risk of the field operation based on the electric work ticket as claimed in claim 1, wherein the pre-training process of the work ticket text classifier based on KPCA and ELM specifically comprises the following steps:
importing work ticket text data from a power grid historical database and dividing the work ticket text data into a training sample set and a testing sample set;
Performing word segmentation and word-out-of-use processing on the work ticket text data of each type in the training sample set and the test sample set;
calculating the weights of words in the work ticket text data, and forming an original characteristic vector set by the weights of all the words;
selecting a first feature set from the training sample set by adopting a kernel principal component analysis method based on the original feature vector;
taking the first feature set as input, taking the type of a work order as output, learning the training sample by adopting an extreme learning machine, and establishing a text classifier;
and extracting and selecting a second feature set from the test sample set, inputting the second feature set into the established text classifier, and outputting the classification result of the work order.
4. The method as claimed in claim 3, wherein a search engine mode in a settlement algorithm is used to perform word segmentation processing on the work ticket text data.
5. The method according to claim 3, wherein the weight of the word of the work ticket text data is calculated according to the following formula:
In the formula, tiRepresenting the ith word, ω, in the text datatiRepresents tiWeight of (tf)iIs a word tiFrequency of occurrence, N is the number of text data, DF (t)i) To comprise tiNumber of text data of fi(d) Representing a function of the frequency of the calculated word.
6. A field operation risk assessment prediction device based on an electric power work ticket is characterized by comprising:
the evaluation index building module is used for building an operation risk evaluation index system according to the risk factors of the field operation;
the content matching module is used for splitting and matching various risk elements in the work ticket by utilizing a personnel information base and a large-scale safety tool base, extracting semantic information of the work ticket, and determining various risk elements in the work ticket according to the operation risk evaluation index system;
the work ticket classification module is used for identifying semantic information of the work ticket by utilizing a pre-trained work ticket text classifier based on KPCA and ELM;
the risk evaluation module is used for carrying out risk assignment on the identified content of the work ticket according to the professional risk evaluation standard library to obtain a risk score;
and the risk grade prediction module is used for outputting a corresponding risk grade according to the risk score.
7. The device for evaluating and predicting the risk of the field operation based on the electric work ticket according to claim 6, wherein the evaluation index constructing module specifically comprises:
the index determining module is used for selecting risk factors of field operation, wherein the risk factors comprise personnel factors and sub factors thereof, equipment factors and sub factors thereof, operation methods and sub factors thereof, tools and sub factors thereof, and environmental factors and sub factors thereof;
and the system construction module is used for constructing an operation risk assessment index system according to the various risk factors and the corresponding sub-factors.
8. An electric power work ticket based on-site operation risk assessment prediction device, characterized in that the device comprises a processor and a memory:
the memory is used for storing a computer program and sending instructions of the computer program to the processor;
the processor executes the prediction method based on the electric work ticket field operation risk assessment according to any one of claims 1-5 according to the instructions of the computer program.
9. A computer storage medium, wherein a computer program is stored on the computer readable storage medium, and when executed by a processor, the computer program implements a method for predicting risk assessment of field work based on electric work ticket according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210452009.0A CN114757557A (en) | 2022-04-24 | 2022-04-24 | On-site operation risk assessment prediction method and device based on electric work ticket |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210452009.0A CN114757557A (en) | 2022-04-24 | 2022-04-24 | On-site operation risk assessment prediction method and device based on electric work ticket |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114757557A true CN114757557A (en) | 2022-07-15 |
Family
ID=82332463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210452009.0A Pending CN114757557A (en) | 2022-04-24 | 2022-04-24 | On-site operation risk assessment prediction method and device based on electric work ticket |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114757557A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596411A (en) * | 2023-07-18 | 2023-08-15 | 广州健新科技有限责任公司 | Production safety evaluation method and system combining two-ticket detection |
| CN116910224A (en) * | 2023-09-13 | 2023-10-20 | 四川金信石信息技术有限公司 | Method and system for extracting switching operation information based on large language model |
-
2022
- 2022-04-24 CN CN202210452009.0A patent/CN114757557A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116596411A (en) * | 2023-07-18 | 2023-08-15 | 广州健新科技有限责任公司 | Production safety evaluation method and system combining two-ticket detection |
| CN116596411B (en) * | 2023-07-18 | 2023-12-22 | 广州健新科技有限责任公司 | Production safety evaluation method and system combining two-ticket detection |
| CN116910224A (en) * | 2023-09-13 | 2023-10-20 | 四川金信石信息技术有限公司 | Method and system for extracting switching operation information based on large language model |
| CN116910224B (en) * | 2023-09-13 | 2023-11-21 | 四川金信石信息技术有限公司 | Method and system for extracting switching operation information based on large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460167A (en) | Method for positioning pollution discharge object based on knowledge graph and related equipment | |
| CN114757557A (en) | On-site operation risk assessment prediction method and device based on electric work ticket | |
| CN110765268B (en) | Client appeal-based accurate distribution network investment strategy method | |
| US20230213895A1 (en) | Method for Predicting Benchmark Value of Unit Equipment Based on XGBoost Algorithm and System thereof | |
| CN110636066B (en) | Network security threat situation assessment method based on unsupervised generative reasoning | |
| CN113688169B (en) | Mine potential safety hazard identification and early warning system based on big data analysis | |
| CN114970508A (en) | Power text knowledge discovery method and device based on data multi-source fusion | |
| CN113742733B (en) | Method and device for extracting trigger words of reading and understanding vulnerability event and identifying vulnerability type | |
| CN111159396B (en) | Method for establishing text data classification hierarchical model facing data sharing exchange | |
| CN112348662B (en) | Risk assessment method and device based on user occupation prediction and electronic equipment | |
| CN112966259A (en) | Power monitoring system operation and maintenance behavior security threat assessment method and equipment | |
| CN114580978A (en) | System and method for inspecting quality of ring-comment report | |
| CN114202243A (en) | Engineering project management risk early warning method and system based on random forest | |
| CN111104483A (en) | ICT system fault analysis and auxiliary discrimination method based on machine learning | |
| CN113449072A (en) | Construction method of excavator fault knowledge map based on deep learning | |
| CN111737993B (en) | Method for extracting equipment health state from fault defect text of power distribution network equipment | |
| CN111666748A (en) | Construction method of automatic classifier and method for recognizing decision from software development text product | |
| CN115544272A (en) | Attention mechanism-based chemical accident cause knowledge graph construction method | |
| CN114328819A (en) | Power safety production hidden danger pre-control method based on knowledge graph | |
| Jun-e et al. | Gas outburst risk analysis based on pattern recognition of RSSVM model | |
| CN113064962B (en) | Environment complaint reporting event similarity analysis method | |
| CN113837440B (en) | Blasting effect prediction method and device, electronic equipment and medium | |
| CN115344870A (en) | Software vulnerability analysis method based on Bert neural network model | |
| Wang et al. | A new energy policy text classification and recognition model based on convolutional neural networks | |
| Guo et al. | Research on Text Mining Technology for Power Grid Safety Hazard Identification |
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 |