CN116227706A - Prediction method, prediction apparatus, prediction device, storage medium, and program product - Google Patents
Prediction method, prediction apparatus, prediction device, storage medium, and program product Download PDFInfo
- Publication number
- CN116227706A CN116227706A CN202310223769.9A CN202310223769A CN116227706A CN 116227706 A CN116227706 A CN 116227706A CN 202310223769 A CN202310223769 A CN 202310223769A CN 116227706 A CN116227706 A CN 116227706A
- Authority
- CN
- China
- Prior art keywords
- target
- risk factor
- occurrence state
- human error
- probability
- 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 43
- 238000005457 optimization Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 37
- 238000004458 analytical method Methods 0.000 claims description 30
- 238000009826 distribution Methods 0.000 claims description 30
- 238000011002 quantification Methods 0.000 claims description 7
- 230000006872 improvement Effects 0.000 abstract description 8
- 230000002265 prevention Effects 0.000 abstract description 6
- 230000000875 corresponding effect Effects 0.000 description 65
- 230000001364 causal effect Effects 0.000 description 8
- 238000013139 quantization Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000011835 investigation Methods 0.000 description 3
- 230000003340 mental effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000037081 physical activity Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 125000002015 acyclic group Chemical group 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000013517 stratification 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Monitoring And Testing Of Nuclear Reactors (AREA)
Abstract
The present application relates to a prediction method, apparatus, device, storage medium, and program product. The method comprises the following steps: acquiring target event information corresponding to a target human error event in a nuclear power debugging operation human error event, wherein the target event information comprises the occurrence state of at least one target risk factor; acquiring posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model; the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event. The method can be used for taking optimization measures such as prevention, improvement and the like for human errors, and has important practical significance.
Description
Technical Field
The present application relates to the field of nuclear power technology, and in particular, to a prediction method, apparatus, device, storage medium, and program product.
Background
As the last technical barrier before the nuclear power plant investors operate, the nuclear power debugging operation has the characteristics of being compact in construction period, large in cooperation activities, large in equipment to be verified, complex in operation environment and the like, and human error in debugging is easy to occur.
Taking human errors in nuclear power debugging operation as an example, the human errors refer to that when the nuclear power debugging operation is executed, the health and safety of the operators are threatened, the instruments and equipment are damaged or the debugging progress is influenced due to some psychological activities and operation behaviors of the operators. Human errors in nuclear power debugging operation have a considerable influence on the safety and reliability of a nuclear power plant.
In view of the above, for human error events occurring in nuclear power debugging operation, the occurrence probability of possible risk factors is effectively predicted, so that optimization measures such as prevention, improvement and the like can be conveniently taken for human error, and the method has important practical significance.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a prediction method, apparatus, device, storage medium, and program product that can effectively predict the occurrence probability of each risk factor in a human error event.
In a first aspect, the present application provides a prediction method. The method comprises the following steps:
acquiring target event information corresponding to a target human error event in a nuclear power debugging operation human error event, wherein the target event information comprises the occurrence state of at least one target risk factor;
Acquiring posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model;
the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event.
In one embodiment, the obtaining the posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model includes:
determining an occurrence state value of the target risk factor according to the occurrence state of the target risk factor;
and updating the prior probability of each candidate risk factor in the probability map model according to the target risk factor and the occurrence state value to obtain the posterior probability of each candidate risk factor.
In one embodiment, if the occurrence status of the target risk factor is an already occurrence status, determining that the occurrence status value is a first value;
and if the occurrence state of the target risk factor is a non-occurrence state, determining that the occurrence state value is a second value, wherein the first value and the second value are different.
In one embodiment, the method further comprises:
determining each risk factor in the nuclear power debugging operation;
calculating association quantized values between every two risk factors in the risk factors, and generating a topological structure of a probability map model according to the association quantized values between every two risk factors;
based on the topology, the probability map model is generated that includes quantized relationships.
In one embodiment, the calculating the association quantization value between every two risk factors in the risk factors includes:
acquiring historical event information corresponding to a plurality of historical human error events, and generating event analysis results according to the historical event information, wherein the event analysis results are used for representing risk occurrence relations between the historical human error events and the risk factors;
and calculating the association quantification value between every two risk factors in the risk factors according to the event analysis result.
In one embodiment, the generating the probability map model according to each risk factor and the associated quantized value between every two risk factors includes:
According to the association quantized values between every two risk factors, calculating the edge connection relation and probability distribution result corresponding to each risk factor;
and taking each risk factor as a model node, and connecting each model node according to the edge connection relation corresponding to each risk factor and the probability distribution result to obtain the probability map model.
In a second aspect, the present application also provides a prediction apparatus. The device comprises:
the system comprises a first acquisition module, a second acquisition module and a first control module, wherein the first acquisition module is used for acquiring target event information corresponding to a target human error event in a nuclear power debugging operation human event, and the target event information comprises an occurrence state of at least one target risk factor;
the second acquisition module is used for acquiring posterior probabilities of candidate risk factors corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability map model;
the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of any of the first aspects when the computer program is executed.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any of the first aspects.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of any of the first aspects.
According to the prediction method, the prediction device, the prediction equipment, the storage medium and the program product, the target event information corresponding to the target human error event in the human event of the nuclear power debugging operation is obtained, and the target event information comprises the occurrence state of at least one target risk factor; acquiring posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model; the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event. Therefore, the embodiment of the application can effectively predict the occurrence probability of the possible risk factors through the target event information and the probability map model corresponding to the target human error event, so that optimization measures such as prevention, improvement and the like can be taken for human error.
Drawings
FIG. 1 is a flow diagram of a prediction method in one embodiment;
FIG. 2 is a flowchart illustrating steps for obtaining posterior probabilities of candidate risk factors corresponding to a target human error event in one embodiment;
FIG. 3 is a schematic diagram of a probability map model, shown schematically in one embodiment;
FIG. 4 is a flow chart of generating a probability map model according to risk factors and associated quantized values between risk factors in one embodiment;
FIG. 5 is a flowchart illustrating a step of calculating a quantitative value of the association between two risk factors in each risk factor according to an embodiment;
FIG. 6 is a diagram illustrating the results of historical human event analysis in one embodiment;
FIG. 7 is a flow diagram of generating a probability map model including quantized relationships according to a topology of the probability map model in one embodiment;
FIG. 8 is a block diagram of a predictive device in one embodiment;
fig. 9 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The embodiment of the application provides a prediction method, which comprises the steps of obtaining target event information corresponding to a target human error event in a nuclear power debugging operation human event, wherein the target event information comprises the occurrence state of at least one target risk factor; acquiring posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model; the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event. Therefore, the embodiment of the application can effectively predict the occurrence probability of the possible risk factors by acquiring the target event information corresponding to the human error event, so that optimization measures such as prevention, improvement and the like can be taken for human error.
Next, an implementation environment related to the prediction method provided in the embodiment of the present application will be briefly described.
The execution body of the prediction method provided by the embodiment of the application may be a computer device, and the computer device may be a terminal, and of course, may also be a server. The terminal can be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things equipment, portable wearable equipment and medical electronic equipment, wherein the internet of things equipment can be an intelligent sound box, an intelligent television, an intelligent air conditioner, intelligent vehicle-mounted equipment and the like, and the portable wearable equipment can be an intelligent watch, an intelligent bracelet, a head-mounted equipment and the like; the server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers.
In one embodiment, as shown in FIG. 1, a prediction method is provided, comprising the steps of:
Human error events in nuclear power commissioning refer to all undesirable mental activities (mental activities) and physical activities (physical activity) of the operator when performing the commissioning task, which may lead (or potentially lead to) threatened health and safety of the operator, damaged equipment, or impacted commissioning progress.
In the embodiment of the present application, the target human error event may be any human error event in the nuclear power debugging operation. When a personal error event occurs in nuclear power debugging operation, an operator inputs event information corresponding to the personal error event into computer equipment, and the computer equipment takes the personal error event as a target personal error event, so that target event information corresponding to the target personal error event is obtained. The target event information includes an occurrence state of at least one target risk factor, i.e. whether the target risk factor occurs in the target human error event, such as an occurred state or a non-occurred state.
The preset probability map model is generated by computing historical event information corresponding to a plurality of historical human error events by the computer device, and the preset probability map model can be a Bayesian network model.
After the computer equipment acquires the target event information corresponding to the target human error event, quantifying the occurrence state of the target risk factor according to the occurrence state of the target risk factor in the corresponding target event information, and then inputting the quantified result into a preset probability graph model so as to acquire the posterior probability of each candidate risk factor corresponding to the target human error event.
The occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event.
According to the prediction method, the target event information corresponding to the target human error event in the nuclear power debugging operation human event is obtained, and the target event information comprises the occurrence state of at least one target risk factor; acquiring posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model; the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event. Therefore, the embodiment of the application can effectively predict the occurrence probability of the possible risk factors through the target event information and the probability map model corresponding to the target human error event, so that optimization measures such as prevention, improvement and the like can be taken for human error.
In one embodiment, the present embodiment relates to obtaining posterior probabilities of candidate risk factors corresponding to a target human error event according to an occurrence state of the target risk factor and a preset probability map model. As shown in fig. 2, the method comprises the following steps:
in step 201, the computer device determines an occurrence status value of the target risk factor according to the occurrence status of the target risk factor.
As described above, the occurrence status of the target risk factor, that is, the status of whether the target risk factor occurs in the target human error event, for example, the occurred status or the non-occurred status.
In this embodiment of the present application, if the occurrence status of the target risk factor is an already occurrence status, the occurrence status value is determined to be a first value, that is, when the occurrence of the target risk factor has been confirmed, the computer device confirms that the occurrence status value of the target risk factor is a first value, where the first value may be 1, for example.
If the occurrence status of the target risk factor is a non-occurrence status, the occurrence status value is determined to be a second value, i.e. when the target risk factor has confirmed that no occurrence has occurred, the computer device confirms that the occurrence status value of the target risk factor is a second value, which may be, for example, 0.
For example, the target human error event may be a wrong operation of the switch valve, the target risk factor may be a "decision error", the occurrence status value of the target risk factor is 1 if the risk factor "decision error" has occurred in the wrong operation of the switch valve event, and the occurrence status value of the target risk factor is 0 if the risk factor has not occurred.
As shown in fig. 3, fig. 3 exemplarily shows a probability map model, where probability values represented in the probability map model reflect occurrence probabilities of risk factors in a debugging job under the current situation, and as indicated by values in a "1.1 management culture missing" node, the probability of management culture missing is 32% in the current human error event. The arrows displayed in the probability graph model reflect the causal relationship of each risk factor, and all possible influencing factors need to be searched according to the arrows when accident investigation and current situation improvement are carried out, for example, the arrows between 2.4 rule violation supervision or management and 4.4 rule violations indicate that the rule violations of a supervisor can influence the rule violations of an operator in the process of executing debugging tasks, and when the supervisor makes some rule violations, the possibility of the rule violations of the operator is increased.
When a new human error event occurs, the computer equipment inputs the updated target risk factors and the occurrence state values into the probability map model, for example, when the human error event is an error operation switch valve, and the target risk factors which are determined to occur are decision errors (in a manner of accident investigation and the like), the computer equipment modifies the probability values of the decision error nodes in the probability map model into Yes 100% and NO 0, and the prior probability of each candidate risk factor in the probability map model is updated by the computer equipment after the modification by recalculating the probability map model, so that the posterior probability of each candidate risk factor is obtained.
In this embodiment, the computer device determines the occurrence status value of the target risk factor according to the occurrence status of the target risk factor. And updating the prior probability of each candidate risk factor in the probability map model according to the target risk factor and the occurrence state value to obtain the posterior probability of each candidate risk factor. Therefore, the occurrence probability of candidate risk factors is scientifically and effectively predicted, human error is effectively prevented, and the reliability and safety of nuclear power debugging operation are improved.
In one embodiment, based on the embodiment shown in fig. 2, the present embodiment relates to a process for generating a probability map model, as shown in fig. 4, and further includes the following steps:
In step 401, the computer device determines risk factors in a nuclear power debugging operation.
A human factor risk framework for nuclear power plant commissioning operation is illustratively presented for nuclear power plant commissioning operation features, as shown in table 1. The framework contains 3 levels of risk stratification, risk factors, manifestations. The risk factors refer to specific human factor risk items, and the expression forms are specific expressions of the risk factors in daily debugging operations.
The method comprises the steps that target event information corresponding to a target human error event is obtained by computer equipment, the target event information comprises the occurrence state of at least one target risk factor, and the occurrence state value of the target risk factor is determined according to the occurrence state of the target risk factor by the computer equipment.
Table 1 Nuclear Power plant debugging operation human factor risk framework
Wherein, the risk factors refer to specific human factor risk items, and the risk factors can be divided into four risk levels: management organization influence, unsafe supervision or management, preconditions for unsafe behavior, unsafe behavior. Managing organizational effects includes: the management culture is lost, the management system is defective, and the resource guarantee is not in place. Unsafe supervision or management includes: inadequate supervision or management, unreasonable task scheduling, and failure to discover and correct problems in time, illegal supervision or management. Preconditions for unsafe behavior include: daily exposure to high risk traps, lengthy periods of time, holiday weekend effects, night duty, exposure to new conditions, time stress, communication failures, program/file defects, poor personal mental/physiological status, insufficient personal readiness, insufficient risk identification, lack of team cooperation, working environment, technical environment. Unsafe behavior includes: skill errors, decision errors, perception errors, violations.
It should be noted that only part of risk factors are shown in the embodiment, and more risk factors can be added according to the actual situation of the nuclear power station.
In step 402, the computer device calculates a quantized value of the association between every two risk factors, and generates a probability map model according to the risk factors and the quantized value of the association between every two risk factors.
The computer equipment calculates association quantized values between every two risk factors to obtain causal relations between every two risk factors, and then obtains a probability map model according to the association quantized values between every risk factor and every two risk factors.
In the embodiment, the computer equipment determines each risk factor in the nuclear power debugging operation, calculates the association quantization value between every two risk factors in each risk factor, and generates a probability map model according to each risk factor and the association quantization value between every two risk factors. Therefore, the computer equipment generates a probability map model through scientific and effective calculation, and the generated model can accurately and reliably reflect each risk factor and the associated quantized value between every two risk factors, so that the reliability of the model is improved.
In one embodiment, the present embodiment relates to calculating a quantitative value of association between two risk factors in each risk factor to generate a topology of a probability map model. As shown in fig. 5, the method comprises the following steps:
in step 501, the computer device obtains historical event information corresponding to a plurality of historical human error events, and generates an event analysis result according to each historical event information.
The computer equipment acquires historical event information corresponding to a plurality of historical human error events, and each piece of historical event information at least comprises an occurrence state of one risk factor. As shown in fig. 6, 50 historical human event analysis results are exemplarily shown, where each risk factor is a binary variable, 0 is taken to indicate that the risk factor does not observe an occurrence in the corresponding event, and 1 is taken to indicate that the risk factor observes an occurrence in the corresponding event. The final analysis results for 50 debug history human error events are shown in fig. 6. The event analysis result is used for representing the risk occurrence relation between each historical human error event and each risk factor.
And the computer equipment establishes a human factor risk reasoning Bayesian network model based on the debugging operation human factor risk framework according to the event analysis result, and calculates the association quantization value between every two risk factors in the risk factors. Wherein the method comprises the steps ofBN is a directed acyclic network, nodes (nodes) in the network represent different random variables, edges (directed edges) between nodes represent causal relationships between different variables, nodes without parent nodes are called root nodes, probability distributions of the root nodes are called edge probability distributions (marginal probability distribution), probability distributions corresponding to other nodes X are conditional probability distributions (conditional probability distribution) P (x|pi (X)), where pi (X) represents a parent node set of node X. Assuming that the random variable in BN is X i When X is i When independent of each other, the probabilities corresponding to the random variables are multiplied, and the result obtained by calculation is a joint distribution (joint probability distribution):
wherein P (X) 1 ,X 2 ,…X n ) Represents the joint probability distribution of BN, pi (X i ) Is node X i When pi (X i ) P [ X ] when empty i |π(X i )]＝P(X i )。
In this BN, each node is a risk factor, which is a binary variable. The BN is a 4-layer BN (corresponding to the class 4 risk level in table 1), where each layer includes all risk factors under the risk level, there is no causal relationship between nodes in each layer, i.e. there is no edge (edge), there may be causal relationship between nodes in different layers, i.e. there may be edges, and the direction of the edges (if any) is directed from the upper risk level to the lower risk level. The correlation of each risk factor is checked to determine if there is a significant causal relationship for the risk factor. To statistically examine this causality, a null hypothesis is proposed: there is no significant causal relationship between a pair of risk factors.
And calculating a Pearson correlation coefficient for each pair of risk factors, so as to calculate a correlation quantized value between every two risk factors in each risk factor, wherein the values of the Pearson coefficient and the p-value are specific correlation quantized values. Null hypotheses may be rejected when the significance level (p-value) of the Pearson coefficient is less than 0.05, i.e., there is a significant correlation between the pair of risk factors. The Pearson coefficient is used to measure the degree of correlation between two data sets, and can be used to measure the linear relationship between distance variables, i.e. the greater the number, the greater the degree of correlation of the risk factor pairs. The "whether correlated" column in table 2 indicates that there is a significant correlation between pairs of risk factors. The analysis results of each pair of risk factors are shown in table 2, and it should be noted that table 2 only exemplarily shows the calculation results of the risk factor pairs with significant correlation among the partial final results, and Pearson coefficients and p-value are calculated associated quantized values. Based on the associated quantized values obtained in this step, the computer generates a topology of the probability map model: there are edges between the risk factor pairs with significant correlation (Yes in table 2, whether the correlation is "Yes") and the direction of the edges is directed from the upper risk level to the lower risk level; there are no edges between pairs of risk factors for which no significant correlation is found.
TABLE 2 Risk factors analysis results
In this embodiment, the computer device obtains historical event information corresponding to a plurality of historical human error events, and generates an event analysis result according to each of the historical event information. And the computer equipment calculates association quantification values between every two risk factors in the risk factors according to the event analysis result. The computer equipment calculates the associated quantized value of the risk factor by debugging the historical human factor event data, and the calculated associated quantized value becomes more and more accurate along with the continuous accumulation of the data, so that the reliability of building a model is greatly improved, and the human factor error can be more accurately and effectively prevented.
In one embodiment, this embodiment relates to generating a probability map model that includes quantized relationships based on the topology of the probability map model. As shown in fig. 7, the method comprises the following steps:
in step 701, the computer device calculates an edge connection relationship and a probability distribution result corresponding to each risk factor based on the topology structure of the probability map model.
Based on the topological structure of the probability graph model, the computer equipment generates a conditional probability table (conditional probability table, CPT) according to event data statistics, and obtains the edge connection relation and probability distribution result corresponding to each risk factor. Illustratively, table 3 shows probability distribution results of the node 4.3 (perceived error) under the conditions that the parent node 3.2 (overlong period), 3.9 (personal mental/physiological state difference), and 3.13 (working environment) are respectively in different states.
Table 3 conditional probability table example
Further, the computer equipment obtains a probability map model through the edge connection relation corresponding to each risk factor and the calculated probability distribution result.
In step 702, the computer device uses each risk factor as a model node, and connects each model node according to the edge connection relationship corresponding to each risk factor and the probability distribution result, so as to obtain a probability map model.
The computer equipment takes each risk factor as a node of the Bayesian network model, and establishes a probability map model in a Neica 5.18 software platform environment. And connecting the model nodes according to the edge connection relation corresponding to each risk factor and the probability distribution result to obtain a probability map model. As shown in fig. 3, a probability map model is exemplarily shown, where probability values represented in the probability map model reflect occurrence probabilities of risk factors in a debugging operation under the current situation, for example, values in "1.1 management culture missing" nodes indicate that in the case of human error, the probability of management culture missing is 32%. The arrows shown in the probability graph model, namely the edges among nodes, reflect the causal relationship of each risk factor, and all possible influencing factors need to be searched according to the arrows between 2.4 rule violation supervision or management and 4.4 rule violation when accident investigation and current situation improvement are carried out, for example, the arrows indicate that the rule violation of a supervisor can influence the rule violation of an operator in the process of executing a debugging task, and when the supervisor makes some rule violation activities, the possibility of the operator to generate rule violation operation is increased.
It should be noted that, for other nodes, information represented by arrows, which are the same as those discussed above, can be obtained from the probability map model.
In this embodiment, the computer device calculates the edge connection relationship and the probability distribution result corresponding to each risk factor according to the association quantization value between every two risk factors. And the computer equipment takes each risk factor as a model node, and connects each model node according to the edge connection relation corresponding to each risk factor and the probability distribution result to obtain a probability map model. And the probability graph model is obtained by calculating the edge connection relation and the probability distribution result corresponding to each risk factor, so that the prevention of human error is more accurate and efficient.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a prediction device for realizing the prediction method. The implementation of the solution provided by the apparatus is similar to the implementation described in the above method, so the specific limitation of one or more embodiments of the prediction apparatus provided below may be referred to above for limitation of the prediction method, which is not repeated here.
In one embodiment, as shown in fig. 8, there is provided a prediction apparatus including:
a first obtaining module 801, configured to obtain target event information corresponding to a target human error event in a human event of a nuclear power debugging operation, where the target event information includes an occurrence state of at least one target risk factor;
a second obtaining module 802, configured to obtain posterior probabilities of candidate risk factors corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability map model;
the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event.
In one embodiment, the second acquisition module 802 includes:
The first determining unit is used for determining an occurrence state value of the target risk factor according to the occurrence state of the target risk factor;
and the updating unit is used for updating the prior probability of each candidate risk factor in the probability map model according to the target risk factor and the occurrence state value to obtain the posterior probability of each candidate risk factor.
In one embodiment, the first acquisition module 801 includes:
the second determining unit is used for determining that the occurrence state value is a first value if the occurrence state of the target risk factor is an already occurrence state;
and the third determining unit is used for determining that the occurrence state value is a second value if the occurrence state of the target risk factor is a non-occurrence state, and the first value and the second value are different.
In one embodiment, the apparatus further comprises:
a determining module 803, configured to determine each risk factor in the nuclear power debugging operation;
the calculating module 804 is configured to calculate a correlation quantization value between every two risk factors in the risk factors, and generate a topology structure of a probability map model according to each risk factor and the correlation quantization value between every two risk factors;
Based on the topology, the probability map model is generated that includes quantized relationships.
In one embodiment, the computing module 804 includes:
the generation unit is used for acquiring historical event information corresponding to a plurality of historical human error events and generating event analysis results according to the historical event information, wherein the event analysis results are used for representing risk occurrence relations between the historical human error events and the risk factors;
and the first calculation unit is used for calculating the association quantification value between every two risk factors in the risk factors according to the event analysis result.
In one embodiment, the computing module 804 further includes:
the second calculation unit is used for calculating the edge connection relation and the probability distribution result corresponding to each risk factor according to the association quantized values between every two risk factors;
and the generation unit is used for taking each risk factor as a model node, and connecting each model node according to the edge connection relation corresponding to each risk factor and the probability distribution result to obtain the probability map model.
The various modules in the predictive device described above may be implemented in whole or in part in software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 9. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing prediction data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a prediction method.
It will be appreciated by those skilled in the art that the structure shown in fig. 9 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring target event information corresponding to a target human error event in a nuclear power debugging operation human error event, wherein the target event information comprises the occurrence state of at least one target risk factor;
acquiring posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model;
the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event.
In one embodiment, the processor when executing the computer program further performs the steps of:
Determining an occurrence state value of the target risk factor according to the occurrence state of the target risk factor;
and updating the prior probability of each candidate risk factor in the probability map model according to the target risk factor and the occurrence state value to obtain the posterior probability of each candidate risk factor.
In one embodiment, the processor when executing the computer program further performs the steps of:
if the occurrence state of the target risk factor is the already occurrence state, determining that the occurrence state value is a first value;
and if the occurrence state of the target risk factor is a non-occurrence state, determining that the occurrence state value is a second value, wherein the first value and the second value are different.
In one embodiment, the processor when executing the computer program further performs the steps of:
determining each risk factor in nuclear power debugging operation;
and calculating association quantized values between every two risk factors in the risk factors, and generating a probability map model according to the association quantized values between every two risk factors.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring historical event information corresponding to a plurality of historical human error events, and generating event analysis results according to the historical event information, wherein the event analysis results are used for representing risk occurrence relations between the historical human error events and risk factors;
And calculating association quantification values between every two risk factors in each risk factor according to the event analysis result.
In one embodiment, the processor when executing the computer program further performs the steps of:
according to the association quantized values between every two risk factors, calculating the edge connection relation and probability distribution result corresponding to each risk factor;
and taking each risk factor as a model node, and connecting each model node according to the edge connection relation corresponding to each risk factor and the probability distribution result to obtain a probability map model.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring target event information corresponding to a target human error event in a nuclear power debugging operation human error event, wherein the target event information comprises the occurrence state of at least one target risk factor;
acquiring posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model;
the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining an occurrence state value of the target risk factor according to the occurrence state of the target risk factor;
and updating the prior probability of each candidate risk factor in the probability map model according to the target risk factor and the occurrence state value to obtain the posterior probability of each candidate risk factor.
In one embodiment, the computer program when executed by the processor further performs the steps of:
if the occurrence state of the target risk factor is the already occurrence state, determining that the occurrence state value is a first value;
and if the occurrence state of the target risk factor is a non-occurrence state, determining that the occurrence state value is a second value, wherein the first value and the second value are different.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining each risk factor in nuclear power debugging operation;
calculating association quantized values between every two risk factors in each risk factor, and generating a topological structure of the probability map model according to the association quantized values between every risk factor and every two risk factors;
based on the topology, a probability map model is generated that contains quantized relationships.
In one embodiment, the computer program when executed by the processor further performs the steps of:
Acquiring historical event information corresponding to a plurality of historical human error events, and generating event analysis results according to the historical event information, wherein the event analysis results are used for representing risk occurrence relations between the historical human error events and risk factors;
and calculating association quantification values between every two risk factors in each risk factor according to the event analysis result.
In one embodiment, the computer program when executed by the processor further performs the steps of:
according to the association quantized values between every two risk factors, calculating the edge connection relation and probability distribution result corresponding to each risk factor;
and taking each risk factor as a model node, and connecting each model node according to the edge connection relation corresponding to each risk factor and the probability distribution result to obtain a probability map model.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
acquiring target event information corresponding to a target human error event in a nuclear power debugging operation human error event, wherein the target event information comprises the occurrence state of at least one target risk factor;
acquiring posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model;
The occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining an occurrence state value of the target risk factor according to the occurrence state of the target risk factor;
and updating the prior probability of each candidate risk factor in the probability map model according to the target risk factor and the occurrence state value to obtain the posterior probability of each candidate risk factor.
In one embodiment, the computer program when executed by the processor further performs the steps of:
if the occurrence state of the target risk factor is the already occurrence state, determining that the occurrence state value is a first value;
and if the occurrence state of the target risk factor is a non-occurrence state, determining that the occurrence state value is a second value, wherein the first value and the second value are different.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining each risk factor in nuclear power debugging operation;
and calculating association quantized values between every two risk factors in the risk factors, and generating a probability map model according to the association quantized values between every two risk factors.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring historical event information corresponding to a plurality of historical human error events, and generating event analysis results according to the historical event information, wherein the event analysis results are used for representing risk occurrence relations between the historical human error events and risk factors;
and calculating association quantification values between every two risk factors in each risk factor according to the event analysis result.
In one embodiment, the computer program when executed by the processor further performs the steps of:
according to the association quantized values between every two risk factors, calculating the edge connection relation and probability distribution result corresponding to each risk factor;
and taking each risk factor as a model node, and connecting each model node according to the edge connection relation corresponding to each risk factor and the probability distribution result to obtain a probability map model.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method of prediction, the method comprising:
acquiring target event information corresponding to a target human error event in a nuclear power debugging operation human error event, wherein the target event information comprises the occurrence state of at least one target risk factor;
acquiring posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability graph model;
The occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event.
2. The method according to claim 1, wherein the obtaining the posterior probability of each candidate risk factor corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability map model includes:
determining an occurrence state value of the target risk factor according to the occurrence state of the target risk factor;
and updating the prior probability of each candidate risk factor in the probability map model according to the target risk factor and the occurrence state value to obtain the posterior probability of each candidate risk factor.
3. The method of claim 2, wherein if the occurrence status of the target risk factor is an already occurrence status, determining the occurrence status value as a first value;
and if the occurrence state of the target risk factor is a non-occurrence state, determining that the occurrence state value is a second value, wherein the first value and the second value are different.
4. The method according to claim 1, wherein the method further comprises:
Determining each risk factor in the nuclear power debugging operation;
calculating association quantized values between every two risk factors in the risk factors, and generating a topological structure of a probability map model according to the association quantized values between every two risk factors;
based on the topology, the probability map model is generated that includes quantized relationships.
5. The method of claim 4, wherein calculating the associated quantified value between each of the risk factors comprises:
acquiring historical event information corresponding to a plurality of historical human error events, and generating event analysis results according to the historical event information, wherein the event analysis results are used for representing risk occurrence relations between the historical human error events and the risk factors;
and calculating the association quantification value between every two risk factors in the risk factors according to the event analysis result.
6. The method of claim 4, wherein the generating the probability map model containing quantized relationships based on the topology comprises:
according to the association quantized values between every two risk factors, calculating the edge connection relation and probability distribution result corresponding to each risk factor;
And taking each risk factor as a model node, and connecting each model node according to the edge connection relation corresponding to each risk factor and the probability distribution result to obtain the probability map model.
7. A predictive device, the device comprising:
the system comprises a first acquisition module, a second acquisition module and a first control module, wherein the first acquisition module is used for acquiring target event information corresponding to a target human error event in a nuclear power debugging operation human event, and the target event information comprises an occurrence state of at least one target risk factor;
the second acquisition module is used for acquiring posterior probabilities of candidate risk factors corresponding to the target human error event according to the occurrence state of the target risk factor and a preset probability map model;
the occurrence state of the target risk factors and the posterior probability of each candidate risk factor are used for obtaining an optimization strategy aiming at the target human error event.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310223769.9A CN116227706A (en) | 2023-03-09 | 2023-03-09 | Prediction method, prediction apparatus, prediction device, storage medium, and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310223769.9A CN116227706A (en) | 2023-03-09 | 2023-03-09 | Prediction method, prediction apparatus, prediction device, storage medium, and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116227706A true CN116227706A (en) | 2023-06-06 |
Family
ID=86585494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310223769.9A Pending CN116227706A (en) | 2023-03-09 | 2023-03-09 | Prediction method, prediction apparatus, prediction device, storage medium, and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116227706A (en) |
-
2023
- 2023-03-09 CN CN202310223769.9A patent/CN116227706A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bielza et al. | A comparison of graphical techniques for asymmetric decision problems | |
| CN111314173B (en) | Monitoring information abnormity positioning method and device, computer equipment and storage medium | |
| Dai et al. | A model for correlated failures in N-version programming | |
| CN108415990B (en) | Data quality monitoring method and device, computer equipment and storage medium | |
| WO2019165692A1 (en) | Carbon futures price prediction method, apparatus, computer device and storage medium | |
| CN112379913B (en) | Software optimization method, device, equipment and storage medium based on risk identification | |
| Sheikhalishahi et al. | Maintenance scheduling optimization in a multiple production line considering human error | |
| CN111106953B (en) | Method and device for analyzing abnormal root cause | |
| Toppila et al. | A computational framework for prioritization of events in fault tree analysis under interval-valued probabilities | |
| EP3058519A2 (en) | Case-based reasoning | |
| Романкевич et al. | On evaluation of reliability increase in fault-tolerant multiprocessor systems | |
| CN116523661A (en) | Claim settlement method, device, equipment and storage medium based on artificial intelligence | |
| CN116227706A (en) | Prediction method, prediction apparatus, prediction device, storage medium, and program product | |
| CN115564152A (en) | Carbon emission prediction method and device based on STIRPAT model | |
| Narman et al. | Enterprise architecture analysis for data accuracy assessments | |
| Bocciarelli et al. | Modeling resources to simulate business process reliability | |
| CN115204501A (en) | Enterprise evaluation method and device, computer equipment and storage medium | |
| CN114743703A (en) | Reliability analysis method, device, equipment and storage medium for nuclear power station unit | |
| EP2983084A1 (en) | Device for ranking software code sections to be reviewed for errors | |
| US9619765B2 (en) | Monitoring a situation by generating an overall similarity score | |
| US20150112914A1 (en) | Case-based reasoning | |
| Jongsawat et al. | Developing a Bayesian network model based on a state and transition model for software defect detection | |
| CN113361903B (en) | Method, device and equipment for evaluating corrosion risk outside oil and gas pipeline | |
| JP6466800B2 (en) | Network evaluation system, service failure rate calculation method, and program | |
| JP2007087121A (en) | Total management apparatus, database system, database management method, and database management program |
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 |