CN111144751A - Method and system for determining power accident occurrence risk based on behavior analysis - Google Patents
Method and system for determining power accident occurrence risk based on behavior analysis Download PDFInfo
- Publication number
- CN111144751A CN111144751A CN201911369767.0A CN201911369767A CN111144751A CN 111144751 A CN111144751 A CN 111144751A CN 201911369767 A CN201911369767 A CN 201911369767A CN 111144751 A CN111144751 A CN 111144751A
- Authority
- CN
- China
- Prior art keywords
- accident
- power
- determining
- power accident
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004458 analytical method Methods 0.000 title claims abstract description 31
- 230000006399 behavior Effects 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000006698 induction Effects 0.000 claims description 89
- 238000005065 mining Methods 0.000 claims description 21
- 230000003542 behavioural effect Effects 0.000 claims description 17
- 230000000763 evoking effect Effects 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 abstract description 13
- 238000012216 screening Methods 0.000 description 7
- 230000033228 biological regulation Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000001965 increasing effect Effects 0.000 description 4
- 239000000411 inducer Substances 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013506 data mapping Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012954 risk control 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
- G06Q10/06398—Performance of employee with respect to a job function
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention relates to a method and a system for determining the occurrence risk of an electric power accident based on behavior analysis. The method comprises the steps of obtaining power accident data in a power accident database; performing Boolean discretization processing on the power accident data to determine Boolean discrete accident data; constructing an accident incentive model according to the Boolean discrete accident data; acquiring the current behavior of an operator; determining the probability of accidents caused by the behaviors of the operators according to the current behaviors by utilizing the accident incentive model; and determining the power accident occurrence risk according to the probability. The method and the system for determining the occurrence risk of the power accident based on the behavior analysis solve the problem that the power safety production accident cannot be effectively prevented in the prior art.
Description
Technical Field
The invention relates to the field of data processing, in particular to a method and a system for determining power accident occurrence risk based on behavior analysis.
Background
With the continuous expansion and development of the scale of the energy Internet and the power grid, the data of the electric power safety production accidents are continuously increased and the complexity is continuously increased, and the data of the electric power safety production accidents are gradually formed. The traditional power production accident analysis method based on the theory of accident theory has strong experience and subjectivity, and can not accurately deduce whether the operation behavior of an operator causes an accident or not, thereby being incapable of effectively preventing the occurrence of the power safety production accident.
Disclosure of Invention
The invention aims to provide a method and a system for determining the occurrence risk of an electric power accident based on behavior analysis, which solve the problem that the occurrence of the electric power safety production accident cannot be effectively prevented in the prior art.
In order to achieve the purpose, the invention provides the following scheme:
a power accident occurrence risk determination method based on behavior analysis comprises the following steps:
acquiring power accident data in a power accident database; the power accident data comprises a power accident type and a corresponding cause of the power accident; the cause of the power accident comprises the behavior of an operator;
performing Boolean discretization processing on the power accident data to determine Boolean discrete accident data;
constructing an accident incentive model according to the Boolean discrete accident data;
acquiring the current behavior of an operator;
determining the probability of accidents caused by the behaviors of the operators according to the current behaviors by utilizing the accident incentive model;
and determining the power accident occurrence risk according to the probability.
Optionally, the performing boolean discretization on the power accident data to determine boolean discretization accident data further includes:
and sequencing the Boolean discrete accident data to determine a cause sequence.
Optionally, the constructing an accident incentive model according to the boolean discrete accident data specifically includes:
determining a high-frequency power grid operation accident element set by adopting a deduction algorithm and an iterative method of layer-by-layer searching according to the incentive sequence;
determining a first induction degree of an induction factor of the power accident corresponding to each power accident type by adopting a rule mining algorithm based on an accident frequent tendency theory according to the high-frequency power grid operation accident element set;
determining a key cause of the power accident corresponding to each power accident type according to the first induction degree;
performing association rule mining on the key causes of the power accidents, and determining a second induction degree between the key causes of the power accidents corresponding to each power accident type;
and constructing an accident incentive model according to the first and second inducements.
Optionally, the determining, according to the first induction degree, a key cause of the power accident corresponding to each power accident type specifically includes:
acquiring an induction threshold;
judging whether the first induction degree is larger than the induction degree threshold value;
if the first induction degree is larger than the induction degree threshold value, reserving the cause of the power accident; the reserved inducement of the power accident is a key inducement;
and if the first induction degree is not greater than the induction degree threshold value, rejecting the cause of the power accident.
A system for determining risk of occurrence of an electrical accident based on behavioral analysis, comprising:
the electric power data accident acquisition module is used for acquiring electric power accident data in an electric power accident database; the power accident data comprises a power accident type and a corresponding cause of the power accident; the cause of the power accident comprises the behavior of an operator;
the Boolean discrete accident data determining module is used for performing Boolean discrete processing on the electric power accident data to determine Boolean discrete accident data;
the accident incentive model building module is used for building an accident incentive model according to the Boolean discrete accident data;
the current behavior acquisition module is used for acquiring the current behavior of the operator;
the probability determination module is used for determining the probability of accidents caused by the behaviors of the operators according to the current behaviors by utilizing the accident incentive model;
and the power accident occurrence risk determining module is used for determining the power accident occurrence risk according to the probability.
Optionally, the method further includes:
and the incentive sequence determining module is used for sequencing the Boolean discrete accident data and determining an incentive sequence.
Optionally, the accident incentive model building module specifically includes:
the high-frequency power grid operation accident element set determining unit is used for determining a high-frequency power grid operation accident element set by adopting a deduction algorithm and an iteration method of layer-by-layer search according to the incentive sequence;
the first induction degree determining unit is used for determining a first induction degree of an induction factor of the power accident corresponding to each power accident type by adopting a rule mining algorithm based on an accident frequent tendency theory according to the high-frequency power grid operation accident element set;
the key inducement determining unit is used for determining the key inducement of the power accident corresponding to each power accident type according to the first inducement degree;
the second induction degree determining unit is used for mining the association rules of the key causes of the power accidents and determining a second induction degree between the key causes of the power accidents corresponding to each power accident type;
and the accident incentive model building unit is used for building an accident incentive model according to the first induction degree and the second induction degree.
Optionally, the key incentive determining unit specifically includes:
an evoked potential threshold acquisition subunit configured to acquire an evoked potential threshold;
a judging subunit, configured to judge whether the first induction degree is greater than the induction degree threshold;
a key inducement determining subunit, configured to reserve the inducement of the power accident if the first inducement is greater than the inducement threshold; the reserved inducement of the power accident is a key inducement;
and the non-key cause determining subunit is used for rejecting the causes of the power accident if the first induction degree is not greater than the induction degree threshold value.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
according to the method and the system for determining the occurrence risk of the power accident based on the behavioral analysis, an accident inducement model is established according to the power accident data after Boolean discretization processing and a rule mining algorithm based on an accident frequent tendency theory, the type of the power accident and the corresponding inducement of the power accident are induced, converted and coupled, and the mapping relation between the type of the power accident and the corresponding inducement of the power accident is determined; the evaluation of the behavior of the operator in the power safety production activity is realized through the mapping relation, the probability of accidents caused by the behavior of the operator is determined, the accidents are evaluated based on the behavior of the operator, the defect that a traditional power production accident analysis method based on an accident theory has strong experience and subjectivity is overcome, whether the operation behavior of the operator can cause the accidents or not can be evaluated more objectively, and therefore the occurrence of the power safety production accidents is effectively prevented.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a method for determining the risk of occurrence of an electrical accident based on behavioral analysis according to the present invention;
FIG. 2 is a graph of a Boolean type discrete incident data mapping provided by the present invention;
FIG. 3 is a diagram illustrating a first distribution of inducements of the power accident corresponding to each power accident type according to the present invention;
FIG. 4 is a graph of the results of key incentive determinations provided by the present invention;
FIG. 5 is a graph of key cause determinations for different inducement thresholds provided by the present invention;
fig. 6 is a schematic structural diagram of a power accident occurrence risk determining system based on behavior analysis according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for determining the occurrence risk of an electric power accident based on behavior analysis, which solve the problem that the occurrence of the electric power safety production accident cannot be effectively prevented in the prior art.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a schematic flow chart of a method for determining a risk of an electrical accident based on behavioral analysis, as shown in fig. 1, the method for determining a risk of an electrical accident based on behavioral analysis includes:
s101, acquiring power accident data in a power accident database; the power accident data comprises a power accident type and a corresponding cause of the power accident; the cause of the power accident includes an action of an operator.
The electric power accident data in the electric power accident database mainly come from accident event analysis reports written by expert research groups, and the accident event analysis reports are obtained by abstracting and integrating information about personnel safety behaviors of different accidents.
From historical power production safety accident event reports, the type and behavioral cause of a certain accident event can be screened out.
And S102, performing Boolean discretization processing on the electric power accident data to determine Boolean discrete accident data.
Boolean discretization processing is performed on a large amount of power accident data to obtain a boolean discrete accident data mapping relation as shown in fig. 2. As shown in FIG. 2, T*Of (2) element(s)
For a boolean value of the cause of the jth power incident corresponding to the ith corresponding power incident, for the cause of the power incident corresponding to each power incident type,
and forming a row vector for the corresponding causes of all power accidents.
After S102, further comprising:
and sequencing the Boolean discrete accident data to determine a cause sequence.
More than one inducement corresponding to each electric power accident type is provided, the sequence of the inducements is different, and the output of the constructed accident inducement model is slightly different. That is, when the first inducement is changed, the probability of the subsequent inducement is also changed.
For example, when a certain type of power accident occurs, the accident is continuously evolved and transformed under the action of causes of a plurality of causes. The method is characterized in that a targeted auxiliary strategy is provided for analyzing the evolution relation among various inducers, helping power grid operation maintenance personnel to prevent and control risk points and formulating pre-control measures of the inducers, the occurrence probability of a full 2-order high-frequency element set and the occurrence probability of a corresponding 1-order high-frequency element set are calculated through a rule mining algorithm based on an accident frequency tendency theory on the basis of the inducers A6, B3, C1, F4, F5 and F9 with high correlation, and the evolution relation among key inducers of a single accident is calculated by using a conditional probability formula, wherein the evolution relation is shown in Table 1.
TABLE 1
The method is easy to obtain, and when the leading key cause is changed, the occurrence probability of the following key cause is changed. For example, when a violation of regulations (B3) occurs, the probability of causing risk management not in place (F5) is 48.1%; and under the condition that the risk management and control is not in place (F5), the probability of causing the violation of the regulation (B3) is 35.5%, and in order to reduce the influence of the group of coupling key inducement sets on the safe and stable operation of the power system, the relevant regulation and control should be regulated in priority, the regulation and awareness of operation and maintenance personnel is improved, and the risk management and control level is improved through the correlation effect.
Therefore, in order to improve the accuracy of model output, the Boolean discrete accident data are sorted, and all incentive sequences corresponding to the same power accident type are determined.
S103, constructing an accident incentive model according to the Boolean discrete accident data.
Wherein, S103 specifically includes:
1) and determining the high-frequency power grid operation accident element set by adopting a deduction algorithm and an iterative method of layer-by-layer searching according to the incentive sequence.
2) And determining a first induction degree of the inducement of the power accident corresponding to each power accident type by adopting a rule mining algorithm based on an accident frequent tendency theory according to the high-frequency power grid operation accident element set.
The calculation process of the rule mining algorithm based on the accident frequent tendency theory is as follows:
A. and scanning the high-frequency power grid operation accident element set. And calculating the support degree of each element set to obtain a set of high-frequency element 1 element sets.
B. And (4) connecting. By mixing Lk-1Performs concatenation on each element in (1), resulting in LkWhen selecting the set G of k-ary setsk。
C. And (4) branch reduction. Due to GkIs LkThe elements of the superset of (2) also have non-high frequencies, and by virtue of the nature of the algorithm, all non-empty subsets of the high frequency element set are high frequency, reducing GkDetermining LkAnd (5) mining the high-frequency element set.
D. And scanning the high-frequency power grid operation accident element sets once again, calculating the support degree of each element set, and removing the element sets which do not meet the support degree.
And repeating the steps until all the high-frequency element sets are searched. Finally, L is recalculatedkThe credibility of the element set is in line if the credibility of the element set is greater than a given minimum confidence thresholdAnd potential semantic mining of the condition.
Fig. 3 is a schematic diagram illustrating a first distribution of inducements of the power accident corresponding to each power accident type, as shown in fig. 3, the inducements of the power accident corresponding to each power accident type are different.
3) And determining the key cause of the power accident corresponding to each power accident type according to the first induction degree.
And calculating the induction degree of the accident state factors, and screening the accident factors smaller than the threshold value by using an artificially set induction degree threshold value so as to finally obtain the key induction factors causing the accident. And screening the key causes of the power accidents corresponding to each power accident type by setting an induction degree threshold.
As shown in fig. 5, the key cues obtained by the different evoked potential thresholds are also different. Namely, the induction degree threshold value plays a role of filtering in key induction screening, wherein the induction screening degree refers to the percentage of the screened induction quantity in the total induction quantity; the association rule matching rate is the same rate of the association rules mined at different inducement thresholds as the standard association rule (the mining result when γ is 15% is the standard association rule). With the increase of the induction degree threshold, the induction screening degrees of the accidents X7 and X8 are increased, but the induction screening rate of X8 is obviously higher than that of X7, because the induction factor of the key accident event of X8 is more single, and the induction factor of the non-key accident event is obviously screened out by increasing the induction degree threshold; within a certain induction threshold range, the change of the result of the association rule is reduced and cannot be caused, the key inducement plays a crucial decisive role in the development and evolution of the power production safety accident event, and when the induction threshold is too large (such as 35 percent), the association rule mining result is lost after the key inducement is screened out. In practice, the threshold value of the induction degree needs to be reasonably determined, and key causes of power production safety accident events are reserved.
The determining the key cause of the power accident corresponding to each power accident type according to the first induction degree specifically includes:
1) and acquiring an evoked potential threshold.
2) Determining whether the first evoked level is greater than the evoked level threshold.
3) If the first induction degree is larger than the induction degree threshold value, reserving the cause of the power accident; the cause of the electrical accident that remains is a key cause.
4) And if the first induction degree is not greater than the induction degree threshold value, rejecting the cause of the power accident.
Fig. 4 is a diagram of a result of determining a key cause provided by the present invention, as can be seen from fig. 4, taking a third-level event and a fourth-level event as examples, respectively, taking an induction degree γ of 15%, screening out a key behavior cause of 2 types of accidents, omitting unreliable accident state factors in the various accidents, setting a minimum support α of 5%, a minimum confidence β of 30%, taking the second-level cause as a lead, and the accident types as a successor, and mining by using a rule mining algorithm based on a frequent accident tendency theory, so as to obtain an induction associated feature of the 2 types of accidents.
As can be seen from fig. 4, the relation between the lack of knowledge and skill (a6), the violation of regulations (B3), the unreasonable planning and design (C1), the insufficient supervision and management (F4), the inadequate risk control (F5), the inadequate repair and maintenance (F9) and the tertiary event X7 is the closest, which indicates that the occurrence of the tertiary time is mainly related to the improper behavior of the operation and maintenance personnel, and therefore the pre-control of the tertiary event is performed by the operation and maintenance personnel of the power system, and is regulated and strict.
4) Performing association rule mining on the key causes of the power accidents, and determining a second induction degree between the key causes of the power accidents corresponding to each power accident type;
5) and constructing an accident incentive model according to the first and second inducements.
And S104, acquiring the current behavior of the operator.
And S105, determining the probability of accidents caused by the behaviors of the operators according to the current behaviors by using the accident inducement model.
And S106, determining the occurrence risk of the power accident according to the probability.
Corresponding to the method for determining the risk of occurrence of the power accident based on the behavioral analysis provided by the present invention, the present invention further provides a system for determining the risk of occurrence of the power accident based on the behavioral analysis, fig. 6 is a system for determining the risk of occurrence of the power accident based on the behavioral analysis, as shown in fig. 6, a system for determining the risk of occurrence of the power accident based on the behavioral analysis comprises: the system comprises a power data accident obtaining module 601, a Boolean discrete accident data determining module 602, an accident inducement model constructing module 603, a current behavior obtaining module 604, a probability determining module 605 and a power accident occurrence risk determining module 606.
The electric power data accident acquisition module 601 is used for acquiring electric power accident data in an electric power accident database; the power accident data comprises a power accident type and a corresponding cause of the power accident; the cause of the power accident includes an action of an operator.
The boolean discrete accident data determination module 602 is configured to perform boolean discretization on the power accident data to determine boolean discrete accident data.
The accident incentive model constructing module 603 is configured to construct an accident incentive model according to boolean discrete accident data.
The current behavior obtaining module 604 is configured to obtain a current behavior of the operator.
The probability determination module 605 is configured to determine, according to the current behavior, a probability that an accident is caused by the behavior of the operator by using the accident incentive model.
The power accident occurrence risk determining module 606 is configured to determine a power accident occurrence risk according to the probability.
The invention provides a power accident occurrence risk determining system based on behavior analysis, which further comprises: and a cause sequence determination module.
And the incentive sequence determining module is used for sequencing the Boolean discrete accident data and determining an incentive sequence.
The accident incentive model building module 603 specifically includes: the system comprises a high-frequency power grid operation accident element set determining unit, a first induction degree determining unit, a key incentive determining unit, a second induction degree determining unit and an accident incentive model constructing unit.
And the high-frequency power grid operation accident element set determining unit is used for determining the high-frequency power grid operation accident element set by adopting a deduction algorithm and an iteration method of layer-by-layer search according to the incentive sequence.
The first induction degree determining unit is used for determining a first induction degree of the inducement of the power accident corresponding to each power accident type by adopting a rule mining algorithm based on an accident frequent tendency theory according to the high-frequency power grid operation accident element set.
The key cause determining unit is used for determining the key causes of the power accidents corresponding to each power accident type according to the first induction degree.
The second induction degree determining unit is used for performing association rule mining processing on the key causes of the power accidents and determining a second induction degree between the key causes of the power accidents corresponding to each power accident type.
The accident incentive model building unit is used for building an accident incentive model according to the first induction degree and the second induction degree.
The key incentive determining unit specifically comprises: the system comprises an inducement degree threshold value acquisition subunit, a judgment subunit, a key inducement determination subunit and a non-key inducement determination subunit.
The induction degree threshold value obtaining subunit is used for obtaining an induction degree threshold value.
The judging subunit is configured to judge whether the first evoked potential is greater than the evoked potential threshold.
And the key cause determining subunit is used for reserving the cause of the power accident if the first induction degree is greater than the induction degree threshold value. The cause of the electrical accident that remains is a key cause.
The non-key cause determining subunit is used for rejecting the cause of the power accident if the first degree of induction is not greater than the threshold value of the degree of induction.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A method for determining the occurrence risk of a power accident based on behavior analysis is characterized by comprising the following steps:
acquiring power accident data in a power accident database; the power accident data comprises a power accident type and a corresponding cause of the power accident; the cause of the power accident comprises the behavior of an operator;
performing Boolean discretization processing on the power accident data to determine Boolean discrete accident data;
constructing an accident incentive model according to the Boolean discrete accident data;
acquiring the current behavior of an operator;
determining the probability of accidents caused by the behaviors of the operators according to the current behaviors by utilizing the accident incentive model;
and determining the power accident occurrence risk according to the probability.
2. The method for determining the power accident occurrence risk based on the behavioral analysis according to claim 1, wherein the boolean discretization processing is performed on the power accident data to determine boolean discretization accident data, and then the method further comprises:
and sequencing the Boolean discrete accident data to determine a cause sequence.
3. The method for determining the occurrence risk of the power accident based on the behavioral analysis according to claim 2, wherein the constructing the accident incentive model according to the boolean discrete accident data specifically comprises:
determining a high-frequency power grid operation accident element set by adopting a deduction algorithm and an iterative method of layer-by-layer searching according to the incentive sequence;
determining a first induction degree of an induction factor of the power accident corresponding to each power accident type by adopting a rule mining algorithm based on an accident frequent tendency theory according to the high-frequency power grid operation accident element set;
determining a key cause of the power accident corresponding to each power accident type according to the first induction degree;
performing association rule mining on the key causes of the power accidents, and determining a second induction degree between the key causes of the power accidents corresponding to each power accident type;
and constructing an accident incentive model according to the first and second inducements.
4. The method for determining the occurrence risk of the power accident based on the behavioral analysis according to claim 3, wherein the determining the key cause of the power accident corresponding to each power accident type according to the first induction degree specifically comprises:
acquiring an induction threshold;
judging whether the first induction degree is larger than the induction degree threshold value;
if the first induction degree is larger than the induction degree threshold value, reserving the cause of the power accident; the reserved inducement of the power accident is a key inducement;
and if the first induction degree is not greater than the induction degree threshold value, rejecting the cause of the power accident.
5. A system for determining risk of occurrence of an electrical accident based on behavioral analysis, comprising:
the electric power data accident acquisition module is used for acquiring electric power accident data in an electric power accident database; the power accident data comprises a power accident type and a corresponding cause of the power accident; the cause of the power accident comprises the behavior of an operator;
the Boolean discrete accident data determining module is used for performing Boolean discrete processing on the electric power accident data to determine Boolean discrete accident data;
the accident incentive model building module is used for building an accident incentive model according to the Boolean discrete accident data;
the current behavior acquisition module is used for acquiring the current behavior of the operator;
the probability determination module is used for determining the probability of accidents caused by the behaviors of the operators according to the current behaviors by utilizing the accident incentive model;
and the power accident occurrence risk determining module is used for determining the power accident occurrence risk according to the probability.
6. An electrical accident risk determination system based on behavioral analysis according to claim 5, characterized by further comprising:
and the incentive sequence determining module is used for sequencing the Boolean discrete accident data and determining an incentive sequence.
7. The system for determining the risk of occurrence of an electric power accident based on behavioral analysis according to claim 6, wherein the accident incentive model building module specifically comprises:
the high-frequency power grid operation accident element set determining unit is used for determining a high-frequency power grid operation accident element set by adopting a deduction algorithm and an iteration method of layer-by-layer search according to the incentive sequence;
the first induction degree determining unit is used for determining a first induction degree of an induction factor of the power accident corresponding to each power accident type by adopting a rule mining algorithm based on an accident frequent tendency theory according to the high-frequency power grid operation accident element set;
the key inducement determining unit is used for determining the key inducement of the power accident corresponding to each power accident type according to the first inducement degree;
the second induction degree determining unit is used for mining the association rules of the key causes of the power accidents and determining a second induction degree between the key causes of the power accidents corresponding to each power accident type;
and the accident incentive model building unit is used for building an accident incentive model according to the first induction degree and the second induction degree.
8. The system for determining the risk of occurrence of an electric power accident based on behavioral analysis according to claim 7, wherein the key cause determining unit specifically comprises:
an evoked potential threshold acquisition subunit configured to acquire an evoked potential threshold;
a judging subunit, configured to judge whether the first induction degree is greater than the induction degree threshold;
a key inducement determining subunit, configured to reserve the inducement of the power accident if the first inducement is greater than the inducement threshold; the reserved inducement of the power accident is a key inducement;
and the non-key cause determining subunit is used for rejecting the causes of the power accident if the first induction degree is not greater than the induction degree threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911369767.0A CN111144751A (en) | 2019-12-26 | 2019-12-26 | Method and system for determining power accident occurrence risk based on behavior analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911369767.0A CN111144751A (en) | 2019-12-26 | 2019-12-26 | Method and system for determining power accident occurrence risk based on behavior analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111144751A true CN111144751A (en) | 2020-05-12 |
Family
ID=70520616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911369767.0A Pending CN111144751A (en) | 2019-12-26 | 2019-12-26 | Method and system for determining power accident occurrence risk based on behavior analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144751A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469531A (en) * | 2021-07-02 | 2021-10-01 | 国网北京市电力公司 | Power customer state monitoring method and device, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009288918A (en) * | 2008-05-28 | 2009-12-10 | Railway Technical Res Inst | Risk management support method for human error in railroad operation work |
| CN106505568A (en) * | 2016-12-26 | 2017-03-15 | 国网山东省电力公司泰安供电公司 | The method and apparatus of prediction accident set |
| CN107993017A (en) * | 2017-12-12 | 2018-05-04 | 中国矿业大学(北京) | A kind of worker's unsafe acts analysis method and system |
| CN108108909A (en) * | 2018-01-05 | 2018-06-01 | 广东电网有限责任公司中山供电局 | Data analysing method towards electric power accident, misoperation fault with operating accident against regulations |
| CN110363649A (en) * | 2019-06-27 | 2019-10-22 | 上海淇馥信息技术有限公司 | A kind of method for prewarning risk based on user operation case, device, electronic equipment |
-
2019
- 2019-12-26 CN CN201911369767.0A patent/CN111144751A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009288918A (en) * | 2008-05-28 | 2009-12-10 | Railway Technical Res Inst | Risk management support method for human error in railroad operation work |
| CN106505568A (en) * | 2016-12-26 | 2017-03-15 | 国网山东省电力公司泰安供电公司 | The method and apparatus of prediction accident set |
| CN107993017A (en) * | 2017-12-12 | 2018-05-04 | 中国矿业大学(北京) | A kind of worker's unsafe acts analysis method and system |
| CN108108909A (en) * | 2018-01-05 | 2018-06-01 | 广东电网有限责任公司中山供电局 | Data analysing method towards electric power accident, misoperation fault with operating accident against regulations |
| CN110363649A (en) * | 2019-06-27 | 2019-10-22 | 上海淇馥信息技术有限公司 | A kind of method for prewarning risk based on user operation case, device, electronic equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469531A (en) * | 2021-07-02 | 2021-10-01 | 国网北京市电力公司 | Power customer state monitoring method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107292502B (en) | Power distribution network reliability assessment method | |
| CN111898831B (en) | Real-time flood probability forecasting practical method | |
| CN108681815B (en) | Power distribution system operation reliability evaluation method based on rapid sequencing and block matrix | |
| CN110751383B (en) | Multi-strategy fusion dimensionality reduction-based electric power spot market clearing calculation method | |
| CN115906160B (en) | Information processing method and system based on artificial intelligence analysis | |
| CN106970987A (en) | A kind of data analysing method and device | |
| CN112383045B (en) | Transient stability out-of-limit probability calculation method and device for new energy power generation uncertainty | |
| CN104850933A (en) | Scheduling automation data checking system and method based on credible characteristic values | |
| CN111740865B (en) | Flow fluctuation trend prediction method and device and electronic equipment | |
| TWI677830B (en) | Method and device for detecting key variables in a model | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN111144751A (en) | Method and system for determining power accident occurrence risk based on behavior analysis | |
| CN114548493A (en) | Method and system for predicting current overload of electric energy meter | |
| US20180010982A1 (en) | Engine performance modeling based on wash events | |
| CN112199805A (en) | Power transmission line hidden danger identification model evaluation method and device | |
| CN114860808B (en) | Power distribution network equipment abnormal event correlation analysis method based on big data | |
| CN111626497A (en) | People flow prediction method, device, equipment and storage medium | |
| CN115907461A (en) | Electric power engineering method based on mechanism derivation equation | |
| CN113449933B (en) | Regional medium-term load prediction method and device based on clustering electric quantity curve decomposition | |
| CN105842535B (en) | A kind of main syndrome screening technique of harmonic wave based on similar features fusion | |
| CN103745312A (en) | A production quality control method | |
| CN111130098B (en) | Risk assessment method for power distribution network system with distributed power supplies | |
| CN110991841B (en) | Analysis method for nonstandard behaviors in bidding process based on AI technology | |
| CN113807751A (en) | Safety risk grade assessment method and system based on knowledge graph | |
| CN111143622A (en) | Fault data set construction method based on big data platform |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200512 |
|
| WD01 | Invention patent application deemed withdrawn after publication |