Human factor reliability analysis method and device based on cognitive mechanism

Abstract

The invention relates to a human factor reliability analysis method and device based on a cognitive mechanism, and the method comprises the steps: extracting at least one operation behavior based on a nuclear power plant operation instruction text; based on the operation behavior, modeling by adopting a cognitive psychology architecture ACT-R to construct a cognitive model; performing multiple rounds of cognitive simulation experiments on the basis of the cognitive model, obtaining execution time distribution of various operation behaviors in a real scene, and estimating occurrence time parameters of human factors according to the execution time distribution; and inputting the occurrence time parameter of the human factor event into the IDHEAS-ECA human factor reliability analysis model, and calculating a common driving human factor error probability in combination with the cognitive failure probability so as to obtain a human factor error probability and determine a human factor reliability analysis result. Therefore, the problem that the scientificity and reliability of HRA analysis are affected due to the fact that relevant technologies depend on expert experience or simplified hypothesis in Pt parameter estimation and lack of cognitive mechanism support, and results are high in subjectivity and poor in repeatability is solved.

Description

Technical Field

[0001] The present application relates to the field of human factors engineering technology, and in particular to a human factors reliability analysis method and device based on cognitive mechanism. Background Art

[0002] HRA (Human Reliability Analysis) is an important part of nuclear power plant safety assessment and is used to assess the probability of operator error in different scenarios.

[0003] Among related technologies, the IDHEAS-ECA (Integrated Human Event Analysis System for Event and Condition Assessment) method is currently the mainstream analytical framework in the HRA field and is widely adopted in practical applications. Based on the human event tree (EventTree) and cognitive analysis framework, this method converts external stressors, task complexity, and personnel status in operational scenarios into quantitative influencing factors to estimate the probability of human-caused events. Among these factors, the performance time (Pt) of human-caused events is a key parameter that directly affects the accuracy and rationality of the analysis results.

[0004] However, in related technologies, HRA practice mainly relies on expert experience or simplified assumptions in Pt parameter estimation, lacks mechanism modeling of the operator's actual cognitive and behavioral processes, and is difficult to characterize the dynamic cognitive response and time evolution characteristics during task execution. This leads to highly subjective and poorly reproducible estimation results, thus limiting the scientific nature and credibility of the HRA method, which needs to be urgently addressed. Summary of the Invention

[0005] The present application provides a human reliability analysis method and device based on cognitive mechanisms to address the problems in related technologies, such as the reliance on expert experience or simplified assumptions in Pt parameter estimation in HRA practices, the lack of modeling support for the operator's cognitive and behavioral processes, the difficulty in reflecting their dynamic response characteristics, resulting in highly subjective results and poor repeatability, thereby affecting the scientific nature and reliability of HRA analysis.

[0006] The first aspect of the present application provides a human reliability analysis method based on a cognitive mechanism, comprising the following steps: extracting at least one operating behavior based on the operating procedure text of a nuclear power plant; based on the at least one operating behavior, modeling is performed using the cognitive psychology framework ACT-R (Adaptive Control of Thought-Rational) to construct a cognitive model; conducting multiple rounds of cognitive simulation experiments on the basis of the cognitive model to repeatedly run different operating tasks, obtain the execution time distribution of various operating behaviors in real scenarios, and estimate the time parameters of human events based on the execution time distribution; inputting the time parameters of human events into the IDHEAS-ECA human reliability analysis model, and combining the cognitive failure probability to calculate the probability of jointly driven human errors to obtain the probability of human errors and determine the human reliability analysis results.

[0007] Through the above technical means, the cognitive psychology framework ACT-R is used to build an operator cognitive model, extract the execution time distribution of various operating behaviors in real scenarios, and combine the cognitive failure probability at different cognitive stages to jointly drive the calculation of human error probability. It can achieve a mechanism-based and quantitative estimation of the time parameters of human event occurrence and the task risk level, overcome the problems of strong reliance on expert experience and high subjectivity, and thus improve the scientificity, objectivity and repeatability of human reliability analysis.

[0008] Optionally, in one embodiment of the present application, the calculation formula for the time parameter of the human-caused event is:

[0009]

[0010] Among them, P t T represents the time-related probability of human-caused events; reqd Indicates the time required to complete a specific task; T avail represents the time an operator can use to complete a task in a real scenario; P(T reqd >T avail ) indicates T reqd More than T avail The probability of reqd means required; avail means available; Indicates T reqd The cumulative distribution function of Indicates T avail The cumulative distribution function of t represents the time it takes for personnel to execute the procedure.

[0011] Through the above technical means, the time required to complete a specific task and the time available to complete the task in actual scenarios are used to calculate the time-related probability of human error events. This can accurately reflect the impact of time pressure on human behavior, avoid subjective reliance on expert experience, improve the quantitative accuracy of the time parameter (Pt) of human error events, and provide a more objective and repeatable input basis for the subsequent calculation of the human error probability (HEP).

[0012] Optionally, in one embodiment of the present application, the calculation formula for the probability of human error is:

[0013] P HFE =1-(1-P c )*(1-P t ),

[0014] Among them, P HFE Indicates the probability of human error; P c represents the probability of cognitive failure; HFE represents human error event.

[0015] Through the above technical means, the probability of human error is calculated by combining the probability of cognitive failure and the probability related to the time of occurrence of human-induced events. This not only takes into account the failure risk of operators in different cognitive states, but also integrates the uncertainty of task execution time. It can improve the accuracy and reliability of HEP calculations, enhance the model's ability to explain and predict potential human risks in complex operating scenarios, and provide more refined and systematic support for human risk control in high-risk systems such as nuclear power plants.

[0016] Optionally, in one embodiment of the present application, estimating the time parameters of human-caused events based on the execution time distribution includes: extracting at least one of the average time consumption, variance range and potential extreme values ​​of key behaviors under different cognitive states based on the execution time distribution; and performing a mechanism-based quantitative estimation of the time parameters of human-caused events based on at least one of the average time consumption, variance range and potential extreme values ​​under different cognitive states.

[0017] Through the above technical means, a mechanism-based quantitative estimation of the time parameters of human error events is carried out based on the average time consumption, variance range and potential extreme values ​​under different cognitive states, which can more comprehensively characterize the timeliness and stability of operator behavior under different cognitive states. The joint estimation of multi-dimensional parameters can not only improve the expression accuracy of Pt parameters, but also enhance the model's ability to identify extreme operating behaviors, thereby significantly improving the scientificity and accuracy of the human error probability (HEP) calculation.

[0018] The second aspect of the present application provides a human reliability analysis device based on a cognitive mechanism, including: an extraction module for extracting at least one operating behavior based on the text of the nuclear power plant operating procedures; a construction module for modeling based on the at least one operating behavior using the cognitive psychology framework ACT-R to construct a cognitive model; an estimation module for conducting multiple rounds of cognitive simulation experiments on the basis of the cognitive model to repeatedly run different operating tasks, obtain the execution time distribution of various operating behaviors in real scenarios, and estimate the time parameters of human events based on the execution time distribution; an analysis module for inputting the time parameters of human events into the IDHEAS-ECA human reliability analysis model, and combining the cognitive failure probability to calculate the probability of jointly driven human errors to obtain the probability of human errors and determine the human reliability analysis results.

[0019] Through the above technical means, the cognitive psychology framework ACT-R is used to build an operator cognitive model, extract the execution time distribution of various operating behaviors in real scenarios, and combine the cognitive failure probability at different cognitive stages to jointly drive the calculation of human error probability. It can achieve a mechanism-based and quantitative estimation of the time parameters of human event occurrence and the task risk level, overcome the problems of strong reliance on expert experience and high subjectivity, and thus improve the scientificity, objectivity and repeatability of human reliability analysis.

[0020] Optionally, in one embodiment of the present application, the calculation formula for the time parameter of the human-caused event is:

[0021]

[0022] Among them, P t T represents the time-related probability of human-caused events; reqd Indicates the time required to complete a specific task; T avail represents the time an operator can use to complete a task in a real scenario; P(T reqd >T avail ) indicates T reqd More than T avail The probability of reqd means required; avail means available; Indicates T reqd The cumulative distribution function of Indicates T avail The cumulative distribution function of t represents the time it takes for personnel to execute the procedure.

[0023] Through the above technical means, the time required to complete a specific task and the time available to complete the task in actual scenarios are used to calculate the time-related probability of human error events. This can accurately reflect the impact of time pressure on human behavior, avoid subjective reliance on expert experience, improve the quantitative accuracy of the time parameter (Pt) of human error events, and provide a more objective and repeatable input basis for the subsequent calculation of the human error probability (HEP).

[0024] Optionally, in one embodiment of the present application, the calculation formula for the probability of human error is:

[0025] P HFE =1-(1-P c )*(1-P t ),

[0026] Among them, P HFE Indicates the probability of human error; P c represents the probability of cognitive failure; HFE represents human error event.

[0027] Through the above technical means, the probability of human error is calculated by combining the probability of cognitive failure and the probability related to the time of occurrence of human-induced events. This not only takes into account the failure risk of operators in different cognitive states, but also integrates the uncertainty of task execution time. It can improve the accuracy and reliability of HEP calculations, enhance the model's ability to explain and predict potential human risks in complex operating scenarios, and provide more refined and systematic support for human risk control in high-risk systems such as nuclear power plants.

[0028] Optionally, in one embodiment of the present application, the estimation module includes: an extraction unit for extracting at least one of the average time consumption, variance range and potential extreme values ​​of key behaviors in different cognitive states based on the execution time distribution; an estimation unit for performing a mechanism-based quantitative estimation of the time parameters of the human-induced event based on at least one of the average time consumption, variance range and potential extreme values ​​in different cognitive states.

[0029] Through the above technical means, a mechanism-based quantitative estimation of the time parameters of human error events is carried out based on the average time consumption, variance range and potential extreme values ​​under different cognitive states, which can more comprehensively characterize the timeliness and stability of operator behavior under different cognitive states. The joint estimation of multi-dimensional parameters can not only improve the expression accuracy of Pt parameters, but also enhance the model's ability to identify extreme operating behaviors, thereby significantly improving the scientificity and accuracy of the human error probability (HEP) calculation.

[0030] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the human reliability analysis method based on cognitive mechanisms as described in the above embodiment.

[0031] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the human reliability analysis method based on cognitive mechanism as described above.

[0032] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned human reliability analysis method based on cognitive mechanism.

[0033] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0035] Figure 1 A flowchart of a human reliability analysis method based on a cognitive mechanism according to an embodiment of the present application;

[0036] Figure 2 This is a flowchart of a human reliability analysis method based on a cognitive mechanism according to an embodiment of the present application;

[0037] Figure 3 Schematic diagram of a human reliability analysis device based on a cognitive mechanism according to an embodiment of the present application;

[0038] Figure 4 The figure is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application.

[0039] Reference numerals:

[0040] 10 - Human reliability analysis device based on cognitive mechanism; 100 - Extraction module, 200 - Construction module, 300 - Estimation module, 400 - Analysis module; 401 - Memory, 402 - Processor, 403 - Communication interface. DETAILED DESCRIPTION

[0041] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0042] The following describes a human reliability analysis method and device based on a cognitive mechanism according to an embodiment of the present application with reference to the accompanying drawings. In view of the fact that the HRA practice mentioned in the above background technology mainly relies on expert experience or simplified assumptions in Pt parameter estimation, lacks a mechanism modeling of the operator's actual cognitive and behavioral processes, and is difficult to characterize the dynamic cognitive response and time evolution characteristics during task execution, resulting in a highly subjective and poorly reproducible estimation result, thereby limiting the scientificity and credibility of the HRA method. The present application provides a human reliability analysis method based on a cognitive mechanism. In this method, a cognitive model is constructed based on ACT-R to obtain the execution time distribution of various operating behaviors in real scenarios, and combined with the cognitive failure probability, the IDHEAS-ECA model is driven to calculate the human error probability. This method can achieve a mechanism-based and quantitative estimation of the time parameters of human event occurrence, with higher objectivity, consistency and repeatability, and can provide accurate input parameters for the IDHEAS-ECA model, further improving the scientificity and accuracy of the human error probability (HEP) calculation, thereby significantly enhancing the credibility and application value of human risk assessment in high-reliability systems such as nuclear power. This solves the problem that related technologies rely too much on expert experience or simplified assumptions in Pt parameter estimation, lack cognitive mechanism support, resulting in highly subjective results and poor repeatability, thus affecting the scientificity and reliability of HRA analysis.

[0043] Specifically, Figure 1 A flowchart of a human reliability analysis method based on cognitive mechanism provided in an embodiment of the present application.

[0044] like Figure 1 As shown, the human reliability analysis method based on cognitive mechanism includes the following steps:

[0045] In step S101 , at least one operation behavior is extracted based on the nuclear power plant operation procedure text.

[0046] Among them, nuclear power plant operating specifications may include but are not limited to unit grid connection / offline, feedwater pump start and stop operations, main steam valve and control rod operating specifications, etc.

[0047] It can be explained that, for the nuclear power plant operating procedure text, the embodiment of the present application can use a structured analysis method to parse the procedure content one by one, identify the key operating tasks involved, and combine the operating background, equipment interface and human-computer interaction information to gradually refine the procedure content into executable operating behavior units, clarify the execution object, operation content and trigger conditions of each behavior, and then construct a structured sequence of the operator's task execution process, providing a behavioral input basis for subsequent cognitive modeling.

[0048] As a specific example, taking the initial event of a pipe rupture before the water flow meter as an example, the embodiment of the present application refers to the corresponding emergency response plan, as shown in Table 1, to determine its key measures. Table 1 is an emergency response plan table.

[0049] Table 1

[0050]

[0051] Furthermore, the embodiment of the present application can be based on the nuclear power plant operating procedures, refine the contents of the procedures one by one, and map them to specific operator behavior units, thereby forming a structured task sequence. The specific contents can be shown in Table 2, which is a task structured sequence table.

[0052] Table 2

[0053]

[0054]

[0055] In step S102 , based on at least one operation behavior, a cognitive psychology framework ACT-R is used for modeling to construct a cognitive model.

[0056] ACT-R is a cognitive architecture developed by psychologist John R. Anderson at Carnegie Mellon University to simulate how humans perceive, remember, reason, learn, and act.

[0057] As a possible implementation, embodiments of the present application can use Lisp to write model code, constructing substructures within the cognitive model, including the operator's procedural memory, declarative knowledge, goal module, and vision and action module. This model can simulate the operator's cognitive activities during task execution, including but not limited to identifying the operation target, extracting relevant information, invoking and applying rules, and ultimately, perceptual-motor responses, thereby achieving a dynamic simulation of the actual task execution process.

[0058] In step S103, multiple rounds of cognitive simulation experiments are conducted based on the cognitive model to repeatedly run different operation tasks, obtain the execution time distribution of various operation behaviors in real scenarios, and estimate the time parameters of human-caused events based on the execution time distribution.

[0059] Optionally, in one embodiment of the present application, the time parameters of human-caused events are estimated based on the execution time distribution, including: extracting at least one of the average time consumption, variance range and potential extreme values ​​of key behaviors under different cognitive states based on the execution time distribution; and performing a mechanism-based quantitative estimation of the time parameters of human-caused events based on at least one of the average time consumption, variance range and potential extreme values ​​under different cognitive states.

[0060] The embodiment of the present application can extract the average time consumption, variance range and potential extreme values ​​of key behaviors under different cognitive states through statistical analysis of simulation results, and then complete the mechanism-based quantitative estimation of the time parameter (Pt) of human-induced events. It can replace the traditional subjective judgment method that relies on expert experience and improve the objectivity and consistency of the evaluation results.

[0061] Specifically, in the embodiment of the present application, for the above case, the definition of human error events for calculating the probability of human error can be as shown in Table 3. There can be three types of human error events, where Table 3 is a human error event table.

[0062] Table 3

[0063]

[0064] Furthermore, for the above three types of operation events, the embodiment of the present application can use the ACT-R cognitive modeling architecture to model the operator's task execution process, and can construct a complete model framework including procedural rules, declarative knowledge, goal setting and perception-action modules. By performing multiple rounds of simulations on each type of event, the execution time data of the operation behavior under different cognitive conditions can be obtained.

[0065] As a specific example, in order to evaluate the characteristics and regularity of the operation time distribution, the embodiment of the present application can perform normal distribution (Normal), log-normal distribution (Log-Normal), gamma distribution (Gamma) and Weibull distribution (Weibull) fitting analysis on the time data output by the ACT-R simulation, which can be used to compare the applicability and goodness of fit of various distributions in modeling operation time uncertainty.

[0066] In step S104, the human event occurrence time parameter is input into the IDHEAS-ECA human reliability analysis model, and combined with the cognitive failure probability, the common driving human error probability is calculated to obtain the human error probability and determine the human reliability analysis result.

[0067] Specifically, this embodiment of the application can input the Pt parameter obtained from cognitive simulation analysis into the IDHEAS-ECA human reliability analysis model and combine it with the cognitive failure probability (Pc) evaluated based on factors such as task conditions, situational pressure, and interface complexity to jointly drive the calculation of HEP (Human Error Probability). Through this calculation process, this embodiment of the application not only improves the repeatability and scientific nature of HEP estimation, but also enhances the model's ability to interpret and predict potential human risks in complex operational scenarios, providing more refined and systematic support for human risk control in high-risk systems such as nuclear power plants.

[0068] It should be noted that, in the embodiment of the present application, for the three types of human failure events mentioned above, the cognitive failure probability P c The determination and analysis can be performed according to the standard process in the IDHEAS-ECA method manual. The specific calculation process will not be described in detail in this application. The time-related probability of human-caused events can be calculated according to the IDHEAS-ECA method framework.

[0069] Optionally, in one embodiment of the present application, the calculation formula for the time parameter of the human-caused event can be expressed as:

[0070]

[0071] Among them, P t T represents the time-related probability of human-caused events; reqd Indicates the time required to complete a specific task; T avail represents the time an operator can use to complete a task in a real scenario; P(T reqd >T avail ) indicates T reqd More than T avail The probability of reqd means required; avail means available; Indicates T reqd The cumulative distribution function of Indicates T avail The cumulative distribution function of t represents the time it takes for personnel to execute the procedure.

[0072] It should be noted that T availThe value of depends on the time limit set in the operating procedures or the system dynamic response window. By comparing the probability distributions of the two, we can obtain the time-dependent failure probability corresponding to the failure to complete the task in a timely manner, which is used to further drive the quantitative assessment of human error probability (HEP).

[0073] Furthermore, the embodiment of the present application estimates T reqd The distribution of T avail Use Monte Carlo sampling to calculate and obtain P t The parameters are input into the IDHEAS-ECA model and together with the cognitive failure probability (Pc), drive the calculation and evaluation of the human error probability (HEP), thereby improving the accuracy and objectivity of the HRA method.

[0074] Optionally, in one embodiment of the present application, the calculation formula for the probability of human error can be expressed as:

[0075] P HFE =1-(1-P c )*(1-P t ),

[0076] Among them, P HFE Indicates the probability of human error; P c represents the probability of cognitive failure; HFE represents human error event.

[0077] As a specific example, based on the cognitive modeling and probability distribution analysis method described above, the present embodiment can obtain the human error probability (HEP) calculation results for three types of human failure events, as shown in Table 4. Table 4 is a calculation and evaluation table for the human error probability (HEP). Among them, E0, E1, and ES1.2 are the procedures listed in Table 3.

[0078] Table 4

[0079]

[0080] It is understandable that in the embodiment of the present application, the result can be comprehensively considered with respect to the probability of cognitive failure P c The probability P associated with the time of occurrence of human-caused events t , which can reflect the overall human risk level of the operation task in a given situation, thereby providing data support for subsequent risk control and procedure optimization.

[0081] like Figure 2 As shown, the following uses a specific example to explain in detail the process of the human reliability analysis method based on cognitive mechanism.

[0082] In step 201, operation behavior is extracted.

[0083] First, the embodiment of the present application targets the operating procedure text of a nuclear power plant, adopts a structured analysis method to parse the content of the procedure one by one, and identify the key operating tasks involved therein. At the same time, combined with the operating background, equipment interface and human-computer interaction information, the procedure content is gradually refined into executable operating behavior units, and the execution object, operation content and triggering conditions of each behavior are clarified, thereby constructing a structured sequence of the operator's task execution process, providing a behavioral input basis for subsequent cognitive modeling.

[0084] In step S202, the ACT-R cognitive model is constructed.

[0085] In the embodiment of the present application, based on the operational behaviors extracted in the above steps, the cognitive psychology framework ACT-R is used for modeling.

[0086] In some cases, embodiments of the present application can use Lisp to write model code, constructing substructures such as the operator's procedural memory, declarative knowledge, goal module, and vision and action module within the model. This model can simulate the operator's cognitive activities during task execution, including identifying the operation target, extracting relevant information, calling and applying rules, and ultimately the perception-motor response, thereby achieving a dynamic simulation of the actual task execution process.

[0087] In step S203, cognitive simulation and event analysis are performed.

[0088] In the actual implementation process, the embodiment of the present application can carry out multiple rounds of cognitive simulation experiments based on the constructed ACT-R model, and repeatedly run different operation tasks to obtain the execution time distribution of various operation behaviors in real scenarios.

[0089] Furthermore, through statistical analysis of the simulation results, the embodiment of the present application can extract the average time consumption, variance range and potential extreme values ​​of key behaviors under different cognitive states, and then complete the mechanism-based quantitative estimation of the time parameter (Pt) of human-induced events, thereby replacing the traditional subjective judgment method that relies on expert experience.

[0090] In step S204, the probability of human error is calculated and evaluated.

[0091] In an embodiment of the present application, the Pt parameter obtained from the cognitive simulation analysis is input into the IDHEAS-ECA human reliability analysis model, and combined with the cognitive failure probability (Pc) obtained by evaluating factors such as task conditions, situational pressure, and interface complexity, thereby jointly driving the calculation of HEP (Human Error Probability).

[0092] Through this calculation process, the embodiments of the present application can not only improve the repeatability and scientific nature of HEP estimation, but also enhance the model's ability to explain and predict potential human risks in complex operating scenarios, providing a more refined and systematic support means for human risk control in high-risk systems such as nuclear power plants.

[0093] According to the human reliability analysis method based on cognitive mechanism proposed in the embodiment of the present application, a cognitive model is constructed based on ACT-R, the execution time distribution of various operating behaviors in real scenarios is obtained, and combined with the cognitive failure probability, the IDHEAS-ECA model is driven to calculate the human error probability. This can achieve a mechanism-based and quantitative estimation of the time parameters of human event occurrence, with higher objectivity, consistency and repeatability, and can provide accurate input parameters for the IDHEAS-ECA model, further improving the scientificity and accuracy of the human error probability (HEP) calculation, thereby significantly enhancing the credibility and application value of human risk assessment in high-reliability systems such as nuclear power.

[0094] Next, a human factor reliability analysis device based on a cognitive mechanism according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0095] Figure 3 4 is a block diagram of a human reliability analysis device based on a cognitive mechanism according to an embodiment of the present application.

[0096] like Figure 3 As shown, the human reliability analysis device 10 based on cognitive mechanism includes: an extraction module 100 , a construction module 200 , an estimation module 300 and an analysis module 400 .

[0097] The extraction module 100 is used to extract at least one operation behavior based on the nuclear power plant operation procedure text;

[0098] A construction module 200 is configured to construct a cognitive model based on at least one operational behavior by adopting a cognitive psychology framework ACT-R for modeling;

[0099] The estimation module 300 is used to conduct multiple rounds of cognitive simulation experiments based on the cognitive model, repeatedly running different operation tasks, obtaining the execution time distribution of various operation behaviors in real scenarios, and estimating the time parameters of human-induced events based on the execution time distribution;

[0100] The analysis module 400 is used to input the human event occurrence time parameter into the IDHEAS-ECA human reliability analysis model, and calculate the common driving human error probability in combination with the cognitive failure probability to obtain the human error probability and determine the human reliability analysis result.

[0101] Optionally, in one embodiment of the present application, the calculation formula for the time parameter of the human-caused event is:

[0102]

[0103] Among them, P t T represents the time-related probability of human-caused events; reqd Indicates the time required to complete a specific task; T avail represents the time an operator can use to complete a task in a real scenario; P(T reqd >T avail ) indicates T reqd More than T avail The probability of reqd means required; avail means available; Indicates T reqd The cumulative distribution function of Indicates T avail The cumulative distribution function of t represents the time it takes for personnel to execute the procedure.

[0104] Optionally, in one embodiment of the present application, the calculation formula for the probability of human error is:

[0105] P HFE =1-(1-P c )*(1-P t ),

[0106] Among them, P HFE Indicates the probability of human error; P c represents the probability of cognitive failure; HFE represents human error event.

[0107] Optionally, in one embodiment of the present application, the estimation module 300 includes: an extraction unit and an estimation unit.

[0108] The extraction unit is configured to extract at least one of the average time consumption, variance range, and potential extreme value of the key behavior in different cognitive states based on the execution time distribution;

[0109] The estimation unit is used to perform a mechanism-based quantitative estimation of the time parameter of the human-caused event based on at least one of the average time consumption, variance range and potential extreme value under different cognitive states.

[0110] It should be noted that the above explanation of the embodiment of the human reliability analysis method based on cognitive mechanism is also applicable to the human reliability analysis device based on cognitive mechanism in this embodiment, and will not be repeated here.

[0111] According to the human reliability analysis device based on cognitive mechanism proposed in the embodiment of the present application, a cognitive model is constructed based on ACT-R, the execution time distribution of various operating behaviors in real scenarios is obtained, and combined with the cognitive failure probability, the IDHEAS-ECA model is driven to calculate the human error probability. This can achieve a mechanism-based and quantitative estimation of the time parameters of human event occurrence, with higher objectivity, consistency and repeatability, and can provide accurate input parameters for the IDHEAS-ECA model, further improving the scientificity and accuracy of the human error probability (HEP) calculation, thereby significantly enhancing the credibility and application value of human risk assessment in high-reliability systems such as nuclear power.

[0112] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0113] Memory 401 , processor 402 , and computer programs stored in the memory 401 and executable on the processor 402 .

[0114] When the processor 402 executes the program, the human reliability analysis method based on the cognitive mechanism provided in the above embodiment is implemented.

[0115] Furthermore, the electronic device further includes:

[0116] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0117] The memory 401 is used to store computer programs that can be run on the processor 402 .

[0118] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0119] If the memory 401, the processor 402, and the communication interface 403 are implemented independently, the communication interface 403, the memory 401, and the processor 402 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0120] Optionally, in a specific implementation, if the memory 401 , the processor 402 and the communication interface 403 are integrated on a chip, the memory 401 , the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0121] The processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0122] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the human reliability analysis method based on the cognitive mechanism as described above is implemented.

[0123] An embodiment of the present application also provides a computer program product, including a computer program, which can run computer instructions. When the computer instructions are executed by a processor, the human reliability analysis method based on cognitive mechanism provided by the embodiment of the present application is implemented.

[0124] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0125] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0126] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0127] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0128] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, it can be implemented using any one or a combination of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0129] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0130] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0131] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A human reliability analysis method based on cognitive mechanism, characterized in that: The following steps are involved: Extract at least one operation behavior based on the nuclear power plant operation procedure text; Based on the at least one operational behavior, adopting the cognitive psychology framework ACT-R to perform modeling to construct a cognitive model; Based on the cognitive model, multiple rounds of cognitive simulation experiments are conducted to repeatedly run different operation tasks, obtain the execution time distribution of various operation behaviors in real scenarios, and estimate the time parameters of human-induced events based on the execution time distribution; The human event occurrence time parameters are input into the IDHEAS-ECA human reliability analysis model, and combined with the cognitive failure probability, the common driving human error probability is calculated to obtain the human error probability and determine the human reliability analysis results.

2. The method according to claim 1, characterized in that The calculation formula for the time parameter of the human-caused event is: Among them, P t T represents the time-related probability of human-caused events; reqd Indicates the time required to complete a specific task; T avail represents the time an operator can use to complete a task in a real scenario; P(T reqd >T avail ) indicates T reqd More than T avail The probability of reqd means required; avail means available; Indicates T reqd The cumulative distribution function of Indicates T avail The cumulative distribution function of t represents the time it takes for personnel to execute the procedure.

3. The method according to claim 2, characterized in that The calculation formula for the probability of human error is: P HFE =1-(1-P c )*(1-P t ), Among them, P HFE Indicates the probability of human error; P c represents the probability of cognitive failure; HFE represents human error event.

4. The method according to claim 1, wherein The estimating the occurrence time parameter of the human-caused event according to the execution time distribution includes: Based on the execution time distribution, extract at least one of the average time consumption, variance range, and potential extreme value of the key behavior in different cognitive states; A mechanism-based quantitative estimation of the time parameter of the human-caused event is performed based on at least one of the average time consumption, variance range and potential extreme value in different cognitive states.

5. A human factor reliability analysis device based on cognitive mechanism, characterized in that: include: An extraction module, configured to extract at least one operation behavior based on the nuclear power plant operation procedure text; A building module is used to model the at least one operation behavior using a cognitive psychology framework ACT-R to build a cognitive model; An estimation module is used to conduct multiple rounds of cognitive simulation experiments based on the cognitive model, repeatedly run different operation tasks, obtain the execution time distribution of various operation behaviors in real scenarios, and estimate the time parameters of human-induced events based on the execution time distribution; The analysis module is used to input the time parameters of the human event into the IDHEAS-ECA human reliability analysis model, and calculate the probability of common driving human error in combination with the cognitive failure probability to obtain the human error probability and determine the human reliability analysis result.

6. The device according to claim 5, characterized in that The calculation formula for the time parameter of the human-caused event is: Among them, P t T represents the time-related probability of human-caused events; reqd Indicates the time required to complete a specific task; T avail represents the time an operator can use to complete a task in a real scenario; P(T reqd >T avail ) indicates T reqd More than T avail The probability of reqd means required; avail means available; Indicates T reqd The cumulative distribution function of Indicates T avail The cumulative distribution function of t represents the time it takes for personnel to execute the procedure.

7. The device according to claim 6, characterized in that The calculation formula for the probability of human error is: P HFE =1-(1-P c )*(1-P t ), Among them, P HFE Indicates the probability of human error; P c represents the probability of cognitive failure; HFE represents human error event.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the human reliability analysis method based on cognitive mechanism according to any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the human reliability analysis method based on cognitive mechanism as described in any one of claims 1 to 4.

10. A computer program product comprising a computer program, characterized in that The computer program is executed to implement the human reliability analysis method based on cognitive mechanism according to any one of claims 1 to 4.

Images