CN113963443B - Method, device, equipment and medium for identifying human error mode in nuclear power plant - Google Patents
Method, device, equipment and medium for identifying human error mode in nuclear power plant Download PDFInfo
- Publication number
- CN113963443B CN113963443B CN202111252277.XA CN202111252277A CN113963443B CN 113963443 B CN113963443 B CN 113963443B CN 202111252277 A CN202111252277 A CN 202111252277A CN 113963443 B CN113963443 B CN 113963443B
- Authority
- CN
- China
- Prior art keywords
- action
- human error
- task
- equipment
- mode
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method and a device for identifying a human error mode in a nuclear power plant, electronic equipment and a storage medium, wherein the method comprises the following steps: respectively carrying out hierarchical analysis and decomposition on a system function structure and an operation task in the system operation interaction process, and constructing an operation information base; according to the control information base, the target or the event/state is used as a guide to realize the operation navigation of the serialization action under the given task target; according to the control information base and the operation navigation, designing a personnel operation action mode recognition algorithm based on mode recognition; according to a personnel operation action mode recognition algorithm, the personnel error mode recognition in the nuclear power device is realized by combining real-time state monitoring data of the system. The invention realizes the identification of the typical human error modes in different operation scenes by detecting the consistency of the operation action modes and the equipment state modes in the control information base, thereby realizing early warning, preventing and reducing human error of operators and ensuring the operation safety of the marine nuclear power device.
Description
Technical Field
The invention belongs to the field of human factor reliability and nuclear safety analysis, and particularly relates to a human factor error mode identification method and device in a nuclear power device, electronic equipment and a storage medium.
Background
Human factors play an important role in man-machine interaction systems, especially for complex systems such as nuclear power plants, the intensity of which depends on human intervention of operators, a complex dynamic interaction process exists between an automatic device and the actions of the operators, and unknown man-machine interaction processes, especially misoperation of personnel, can have an important influence on system failure. More than 70% of nuclear power accidents are counted to be from human errors. Human error is used to describe the output or outcome of a human action, and refers to a series of human actions beyond some acceptable limit, either as actual operational actions themselves or as intentional violations of a person, which generally constitute the primary cause of an accident. Human error is often induced in a poor man-machine interaction design environment and is manifested during system task execution.
The purpose of the human factor reliability analysis is to achieve potential human factor error identification and to evaluate the impact of human factor failure events on system risk. Human error recognition is used as a basic component of human reliability analysis, and reasonable division and definition of human actions and human error types are the basis. Currently, there are a variety of different methods for classifying and modeling human error patterns, such as threpa human error pattern classification based on operator behavior models, rasmussen human error pattern classification based on rule/skill/knowledge (SRK) ladder models, CREAM human error pattern classification based on cause consequences, meason human error pattern classification based on purpose of operation, shapa human error pattern classification based on cognitive processes, and human error event classification for PSA analysis.
With the innovation and development of the digitizing technology in recent years, the main control room of the nuclear power plant is also being fully converted into the digitizing. The human-computer interaction system is different from the traditional human-computer interaction environment of a main control room, the operation mode, the operation procedure, the human-computer interaction behavior mode, the human-computer error mode characteristics and the like of the nuclear power device under the novel digital control environment are greatly changed, the consideration of the human-computer error mode under the novel digital environment transformation is not completely covered by the traditional human-computer analysis method, and the potential novel additional human-computer error risk exists. In addition, although the degree of automation, informatization, digitization and intellectualization of the nuclear power plant system is remarkably improved, the operation environment of the marine nuclear power plant is extremely complex, working conditions are changeable, and the structure, state and task purposes of the system under different working conditions are very strong in stages and time variability, so that the nuclear power plant system still depends on human intervention of operators to a great extent, and in addition, the rapid deterioration (high temperature and high humidity) of the operation environment and long-time high-strength operation possibly caused under accident working conditions can cause great cognition and operation load pressure to operators, human error is easily caused, and the operation safety of the system is endangered. Meanwhile, special combat mission of the marine nuclear power plant promotes the nuclear power plant to still have mobility when facing extreme strange and emergency running conditions, and operators often have no established operation rules to follow when the nuclear power plant has unknown system abnormality or over-design reference accidents, so how to help the operators to respond to emergency operation under the environment without rule guidance is a great challenge for the intelligent operation and maintenance support technology of the nuclear power plant at present.
Disclosure of Invention
In view of this, the invention provides a method, a device, an electronic device and a storage medium for identifying a personnel action mode in a nuclear power plant around the situation that the nuclear power plant has regulations (normal operation condition, design reference accident condition) and no regulations or is in shortage or incomplete (over design reference accident condition or design extension condition, extreme operation scene) under the novel digital transition trend, and aims to realize the identification of typical personnel error modes and supervision of personnel operation actions under different operation scenes (with regulations/without regulations) by detecting the consistency of the operation action modes and the device state modes in an operation information base, thereby realizing early warning, preventing and reducing personnel error of operators and ensuring the operation safety of the marine nuclear power plant.
A first object of the present invention is to provide a method for identifying a person's motion pattern in a nuclear power plant.
A second object of the present invention is to provide a human action pattern recognition device in a nuclear power plant.
A third object of the present invention is to provide an electronic device.
A fourth object of the present invention is to provide a storage medium.
The first object of the present invention can be achieved by adopting the following technical scheme:
A method of identifying a person's motion pattern in a nuclear power plant, the method comprising:
respectively carrying out hierarchical analysis and decomposition on a system function structure and an operation task in the system operation interaction process, and constructing an operation information base;
according to the control information base, the operation navigation of the serialization action under the given task target is realized by taking the target or the event/state as the guide;
according to the control information base and the operation navigation, designing a personnel operation action mode recognition algorithm based on mode recognition; the personnel operation action mode identification algorithm comprises a judgment basis and a judgment method of personnel operation action modes in a digital control environment of a plurality of nuclear power devices;
and according to the personnel operation action mode recognition algorithm, combining real-time state monitoring data of the system to realize the human error mode recognition in the nuclear power device.
Further, the control information base comprises a procedure action base and an equipment state information base, wherein:
the construction of the procedure action library takes a standard operation procedure as input, and a hierarchical task analysis method is applied to analyze and decompose procedure tasks to obtain a hierarchical sequence structure of 'manipulation task targets-subtasks-basic manipulation actions'; generating a rule action library through digital coding processing of the manipulation action sequence information;
Or the procedure action library is obtained by importing a digital operation procedure;
the device state information base takes system design data as input, analyzes and distributes a system function structure by applying 'target-means' and 'part-whole' abstract thinking to obtain 'system function target-system function-means structure-basic control component' hierarchical associated function structure distribution, and forms an interactive process relation model of 'system function target-control task target-subtask-basic control action-control action object' through interactive coupling of system functions and operation control tasks, so as to generate a device state information base table.
Further, the procedure action library construction process specifically includes:
taking a standard operation rule as input, and extracting the admission conditions of the rules under different operation working conditions and scenes based on rule response analysis; wherein, the different operation conditions and the protocols under the scene comprise a diagnosis protocol, a response protocol and a system protocol;
taking a standard operation rule as input, extracting an operation task target based on hierarchical task analysis, and decomposing an operation action sequence according to the requirement of the operation task target to obtain an operation task target-subtask-basic operation step serialization structure;
Abstracting basic operation steps in the serialization structure into equipment actions aiming at equipment state change, and establishing coupling association between the operation actions and the controlled objects;
extracting attribute characteristics of the operation action according to the coupling association between the operation action and the controlled object, wherein the attribute characteristics comprise the controlled object, the starting/ending time of the operation action and the task execution time, and encoding according to the action execution sequence, and storing the attribute characteristics into a database table in a data format of 'belonging to an operation task target-belonging to a subtask-operation action-task time', so as to form a rule action library;
the construction process of the equipment state information base specifically comprises the following steps:
determining system design purposes, functions and structural components based on system design data input, and generating a device list of the controllable system;
according to the attribute characteristics of the discrete and continuous states of the equipment, the equipment is divided into a discrete controllable component and a continuous controllable component, so that the identification of incomplete operation and operation delay human error modes is conveniently realized;
the equipment name is encoded, and the equipment name encoding can intuitively reflect an equipment association system and tasks/subtasks;
extracting attribute characteristics of equipment, entering the attribute characteristics into an equipment state information base table through data abstraction and digital coding in a data structure format of 'equipment-attribute value', so as to generate an equipment state information base table, wherein equipment in 'equipment-attribute value' comprises equipment types and equipment names; the operation actions and the control objects are associated through the equipment actions, the equipment actions refer to the operation actions executed in the equipment attribute modification process, and the attribute values refer to the current values of the equipment attributes in the actual running environment.
Further, according to the control information base, the operation navigation of the serialization action under the given task target is realized by taking the target or the event/state as a guide, and the method specifically comprises the following steps:
for a manipulation task scene with procedure guidance, selecting an event or a state as a guide according to the procedure type, and automatically extracting a manipulation action sequence facing to an abnormal event or an abnormal state response according to the self-identification of the working condition and the admission condition of the procedure for on-line operation navigation prompt; for off-line application, an operator automatically sets an operation condition scene, a system function target and an operation task target according to the needs, and executes operation navigation prompt aiming at the specific task target;
providing constructive operation navigation guidance suggestions for random Cheng Teshu operation scenes and environments by taking system function targets as guidance and setting successful path planning or expected manipulation response configuration; wherein the successful path planning includes two methods:
based on a multi-layer flow system functional model, combining causal relationship mapping and influence propagation rules, and performing reasoning search through an anti-target 'flow' structure to obtain a successful path set of a target of a guide system function;
based on a system GO-FLOW reliability model, a system success path set guided by a task target is obtained by minimum path set analysis according to a physical signal 'FLOW' direction and a logic structure relation and by combining engineering experience feedback;
After the operation task targets under the specific operation condition scene and task requirements are determined, the operation action sequences are automatically associated and presented according to a tree structure of operation task targets, subtask targets and basic operation steps, and the operator is prompted to execute the current task process and the operation actions required to be executed subsequently according to feedback of operation supervision results.
Further, the pattern recognition starts from the requirement of the system running task and is judged by the admission condition of the procedure;
the method for realizing human error pattern recognition in the nuclear power device by combining the real-time state monitoring data of the system according to the human operation action pattern recognition algorithm specifically comprises the following steps:
judging whether the admission condition of the procedure is satisfied, if not, continuously monitoring the system operation; if yes, then:
extracting a corresponding operation action sequence, and projecting the operation action sequence to an operation navigation picture;
recording the execution time of the current action step according to the operation navigation guidance, and judging whether the operation action is completed within the specified task time or not;
according to the system running state parameters provided by the real-time state monitoring and the actual operation instructions input by operators, identifying a human error mode;
displaying the identification result of the human error mode on an operation supervision interface;
Checking whether the current action is the last step in the given task manipulation action sequence, if so:
checking whether the task manipulation action sequence has actions which are not executed, if yes, identifying a human error mode which is 'missing operation', and displaying the identification result of the current human error mode on an operation supervision interface; if not, entering the next task according to the navigation information;
if not, the method jumps to judge whether the admission condition of the procedure is satisfied, and continues to execute the subsequent operation.
Further, the identifying a human error mode according to the system running state parameter provided by the real-time state monitoring and the actual operation instruction input by the operator specifically includes:
the system running state parameters and actual operation instructions are read into a device state information base through an external data interface, read-in data are compared with default parameter settings in the device state information base, if the data are detected to be changed, an operator is considered to execute operation actions on the current device, the changed device, parameter attributes and parameter change values are recorded and integrated into operation action information, an operation action event is triggered, whether an operation object is matched or not is judged based on the operation event state mode obtained through current monitoring, and if yes, the operator is considered to execute operation actions on the current device:
Judging whether the equipment control mode and/or the operation action are matched, if not, identifying a human error mode for 'the wrong operation acts on the correct object'; if yes, jumping to S1;
if not, then:
judging whether the equipment control mode and/or the action mode are matched, if so, identifying a human error mode of 'target selection error'; if not, traversing the procedure action library, judging whether the operation action is covered in the procedure action library, and if so, jumping to S1; if not, identifying a human error mode of 'random operation';
S1：
judging whether the execution sequence of the operation actions is matched according to the standard operation action sequence defined in the standard procedure action library, if so, then:
judging whether the operation is completed within a specified task time or not by combining the execution time record of the current operation step, and if so, identifying a human error mode of 'correct operation'; if not, then: judging whether the control object is a discrete variable, if so, identifying a human error mode of 'operation delay'; if not, the operation is not complete and the human error mode is identified;
if not, then:
judging whether the operation action is advanced, if so, identifying a human error mode of 'operation advanced'; if not, the mode is identified as "operation lag" human error mode.
Further, displaying the identification result of the human error mode on an operation supervision interface specifically includes:
the executed operation action information and the identification result of the corresponding human error mode are fed back to the operation navigation window, so that an operator can know the current operation task process more conveniently;
the display of the operation supervision interface mainly comprises the backtracking of a historical operation action sequence and the identification result of the current operation action, and the potential human error possibly occurring in the task execution process of an operator is prompted by combining the warning information popup window according to the identification result of the current operation action, wherein the backtracking of the historical operation action sequence comprises the operation action actually input by the operator in the past and the identification result of the human error mode corresponding to the operation action.
The second object of the invention can be achieved by adopting the following technical scheme:
a human action pattern recognition device in a nuclear power plant, the device comprising:
the control information base construction module is used for respectively carrying out hierarchical analysis and decomposition on the system function structure and the control task in the system operation interaction process to construct a control information base;
the operation navigation realizing module is used for realizing the operation navigation of the serialization action under the given task target by taking the target or the event/state as the guide according to the control information base;
The personnel operation action pattern recognition algorithm design module is used for designing a personnel operation action pattern recognition algorithm based on pattern recognition according to the control information base and the operation navigation; the personnel operation action mode identification algorithm comprises a judgment basis and a judgment method of personnel operation action modes in a digital control environment of a plurality of nuclear power devices;
and the human error mode recognition module is used for realizing human error mode recognition in the nuclear power device according to the human operation action mode recognition algorithm and by combining real-time state monitoring data of the system.
The third object of the present invention can be achieved by adopting the following technical scheme:
an electronic device comprises a processor and a memory for storing a program executable by the processor, wherein when the processor executes the program stored in the memory, the method for identifying the human error pattern in the nuclear power device is realized.
The fourth object of the present invention can be achieved by adopting the following technical scheme:
a storage medium storing a program which, when executed by a processor, implements the method for identifying a human error pattern in a nuclear power plant described above.
Compared with the prior art, the invention has the following beneficial effects:
1. The method provided by the invention considers the novel man-machine interaction behavior mode and the human error mode under the digital control environment of the nuclear power device, and can realize the detection of the human error mode under various digital control environments through the construction of the control information base, the real-time information monitoring of the system operation process and the mode recognition technology.
2. The method provided by the invention is oriented to a task target, realizes strong association coupling of a system function target and an operation control process, is a further improvement and presentation of a digital interaction mode of the operation procedure of the existing nuclear power device, and can enable operators to trace back historical operation actions, monitor the current task control process and guide an operation plan expected to be executed in real time, and can realize real-time operation early warning by combining operation applicability evaluation and personnel operation action recognition, thereby protecting the safe operation of the nuclear power device.
3. The successful path planning method provided by the invention takes the task success as the guide, and can break through the non-regulation operation safety guide of the nuclear power plant in the environment of strange polar end and complex operation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for identifying a human error pattern in a nuclear power plant according to embodiment 1 of the present invention.
Fig. 2 is a schematic diagram of a human error pattern recognition method in the nuclear power plant according to embodiment 1 of the present invention.
FIG. 3 is a flow chart of a reactor boron and water make-up system according to example 1 of the present invention.
Fig. 4 is a virtual simulation platform according to embodiment 1 of the present invention.
Fig. 5 is a flowchart for implementing human error pattern recognition in a nuclear power plant according to embodiment 1 of the present invention.
Fig. 6 is a block diagram showing a configuration of a human error pattern recognition device in a nuclear power plant according to embodiment 2 of the present invention.
Fig. 7 is a block diagram showing the structure of an electronic device according to embodiment 3 of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention. It should be understood that the description of the specific embodiments is intended for purposes of illustration only and is not intended to limit the scope of the present application.
According to the invention, the operating behavior characteristics of the personnel task process under the digital operating environment are combined, and in consideration of the fact that the operating action behavior of an operator can not be singly judged according to whether the operator acts to follow the procedure like the procedure guide under the system random operation scene, whether the operator acts to be misoperation can be clearly distinguished, and whether the operator acts correctly or not is judged according to no established standard under the random operation environment, and more, the applicability and the safety evaluation are made according to the action purpose and the effect influence of the operator, namely, the behavior types of the operator are evaluated and divided from the achievable aspects of the system safety function target and the operating task target.
The invention considers the following action modes, and specifically comprises the following steps:
correct operation: refers to the operator successfully completing the specified operation action without error under the specified conditions within the specified task time according to the specified operation procedure or the successful path guidance.
Random operation: regardless of the intended protocol action, operator action behavior that is out of range of the protocol action library is broadly referred to.
Misoperation: generally refers to a human error in some sort of behavior, or to an operator action that deviates significantly from a predetermined, required, or desired criteria to fail to achieve the intended effect.
Aiming at misoperation, the invention comprehensively refers to personnel action classification systems proposed by Reason, swain and Guttman and the like, and divides personnel Unsafe Actions (Unsafe Actions) into the following two types:
operation omission (Error of Omission, EOO): the required operation is not performed, but may be a human error caused by failure to meet a system requirement or lack of time, and the omission of operation may be intentional or unintentional.
Error operation (Error of Commission, EOC): refers to an action that is not requirement dependent but is performed such that the desired requirement state is not reached.
The considered human error modes specifically include:
operation omission (E1): an operator intentionally or unintentionally misses a necessary operation in the process of executing an operation task;
target selection error (E2): the operator selects an incorrect object target in the execution process of the operation action;
operation execution error (E3): the operator performs the wrong operation action on the correct target object;
incomplete operation (E4): the operator's operation action is insufficient, for example, the valve opening is not opened or closed to a specified position;
operational delay (E5): the operator fails to complete the operation within a prescribed action task time, e.g., the valve is not open or closed within a prescribed time;
The operation is advanced: (E6): the operation action is finished before the specified step;
operational hysteresis (E7): the operation is completed later than the prescribed steps.
The above human error types are used only as case illustration, the human error patterns and types in the actual scene are far beyond the definition range given above.
Example 1:
as shown in fig. 1 and 2, a method for identifying a human error pattern in a nuclear power plant specifically includes the following steps:
s101, constructing a control information base, wherein the control information base comprises an equipment state information base and a procedure action base.
And constructing a system equipment state information base and a procedure action base through hierarchical analysis and decomposition of system functional structures and procedure tasks.
As shown in fig. 3, in this embodiment, the construction process of the control information base is described by taking the operation of the reactor boron and water supply system as an example and combining with the scenario of the imaginary case, and the control information base includes two parts, namely, an equipment state information base and a procedure action base, and the specific construction process is as follows:
s1011, constructing a device state information base.
The equipment state information base takes system design data as input, analyzes and distributes a system function structure by applying 'target-means' and 'part-whole' abstract thinking to obtain 'system function target-system function-means structure-basic control component' hierarchical associated function structure distribution, and forms a 'system function target-control task target-subtask-basic control action-control action object' interactive process relation model through interactive coupling of system functions and operation control tasks.
Through hierarchical analysis and decomposition of the system function structure, a system equipment state information base is constructed, and the specific steps comprise:
(1) Based on the input system design data, the system design purpose and the function decomposition are realized.
The reactor boron and water replenishing system is used as a loop important auxiliary supporting system, and mainly realizes the following functions:
reactivity control (FG 1): providing boric acid solution and desalted and deoxidized water for a loop system, and assisting in realizing boric acid concentration control;
volume control (FG 2): providing desalted and deoxygenated water to a loop system to assist in achieving volumetric fluctuation of a loop reactor coolant;
chemical control (FG 3): the oxygen content and the PH value in the coolant of the primary loop reactor are controlled in an auxiliary way by arranging and injecting chemicals such as hydrazine, lithium hydroxide and the like through the chemical adding box.
(2) And decomposing the functional structure of the system according to the functional structure diagram of the system.
The method specifically comprises the following steps:
boric acid injection line: the device consists of two boric acid tanks with redundant structures, two boric acid transport pumps and valves on branch pipelines of the two boric acid transport pumps. In normal operation, one boric acid tank and one boric acid delivery pump are used for delivering concentrated boric acid solution, and the boric acid tank and the boric acid delivery pump on the other branch pipeline are in a standby state;
Desalting and deoxidizing water injection pipeline: the device consists of two desalting and deoxidizing water tanks with redundant structures, two desalting and deoxidizing water pumps, and branch pipelines and valves thereof. In normal operation, one desalting and deoxidizing water tank and one desalting and deoxidizing water pump supply water, and the desalting and deoxidizing water tank and the desalting and deoxidizing water pump on the other branch pipeline are in a standby state;
chemical addition line: consists of a chemical adding tank and a valve on a single branch pipeline thereof. During normal operation, hydrazine and lithium hydroxide solution are added through a chemical addition tank, and chemical solvent is delivered to the reactor-loop through a charging line.
(3) According to the functional structure of the system, the device composition of the system is listed and the devices are classified.
The system specifically comprises the following components:
(3-1) steerable section: refers to devices that can be manipulated and whose control variables relate to discrete switch states, continuous process variables, and the like.
(3-1-1) discrete switching device, comprising in particular:
manual control valve: REA001HOV, REA002HOV, REA003HOV, REA004HOV, REA005HOV, REA006HOV, REA007HOV, REA008HOV, REA009HOV, REA010HOV, REA011HO;
pneumatic control valve: REA001PCV, REA002PCV, electric control valve REA002MOV;
Desalting and deoxidizing water pump: REA001PO, REA002PO;
boric acid delivery pump: REA003PO and REA004PO.
(3-1-2) continuous switch state apparatus, comprising in particular:
pneumatic isolation valve: REA001PIV, REA002PIV.
(3-1-3) a continuous process variable control device, comprising in particular:
desalting and deoxidizing water tank: REA001BA, REA002BA;
boric acid tank: REA003BA, REA004BA;
chemical adding box: REA005BA;
batching box: REA006BA;
volume control box: RCV001BA.
(3-2) an uncontrollable component: refers to a device that cannot be operated and controlled, and its device state is not affected by external operations.
Including check valve REA00CV.
(3-3) extracting attribute features of the equipment according to equipment types, wherein the attribute features specifically comprise:
control mode: automatic control and manual control;
action mode: an on-motion and an off-motion;
state mode: an on state, an off state, a valve opening value, and a process variable value;
operation action execution time: time requirements.
(4) Based on the above system function structure decomposition and distribution results, the basic attribute features of the system devices are extracted, and are sorted according to classes, so as to generate a device state information base table, and as shown in table 1, the device state information base table field comprises device classes, subclasses, device names, device numbers, device actions, device attributes (control mode, action mode, state mode), device control variable attribute values and the like.
Table 1 device status information base table
S1012, constructing a rule action library.
The construction of a rule action library takes a standard operation rule as input, and a hierarchical task analysis method is applied to analyze and decompose rule tasks to obtain a hierarchical sequence structure of 'manipulation task targets-subtasks-basic manipulation actions'; a procedure action library is generated by digitally encoding manipulation action sequence information. The protocol action library can also be obtained by importing digital operation protocols.
Extracting an operation action sequence taking an operation task target as a guide through procedure introduction condition analysis and layering task decomposition, constructing a procedure action library as a standard reference basis for detecting and identifying the consistency of the operation action modes of personnel, and specifically comprising the following steps of:
(1) According to the operation characteristics of the boron and water supply system of the reactor, the system functional task decomposition is realized, and the method specifically comprises the following steps:
boron dilution (MG 1): replacing the reactor coolant of the first loop with equivalent desalted and deoxidized water to reduce the boric acid concentration in the coolant of the first loop, and stopping dilution when the fed desalted and deoxidized water reaches a set value; at least one line of desalination and oxygen removal water make-up lines should be added to ensure successful completion of the boron dilution task.
Boride (MG 2): replacing the reactor coolant of the first loop with an equal amount of concentrated boric acid solution to increase the boric acid concentration in the coolant of the first loop, and stopping boration when the supplied boric acid solution reaches a set value; at least one line of boric acid solution replenishment lines should be fed to ensure successful completion of the boration task.
Automatic boron replenishment (MG 3): supplementing boron-containing water with the same concentration as the primary loop reactor coolant for volume control without changing the concentration of the primary loop reactor coolant; in the replenishing process, the flow of the desalted and deoxidized water is kept constant, the flow of boric acid is given through calculation, and the boric acid and the desalted and deoxidized water are injected into an upper charging pipeline after being mixed in a mixing runner, so that automatic boron replenishing is completed; at least one line of demineralized oxygen-depleted water injection lines and one line of boric acid injection lines should be added to ensure successful completion of the automated boron replenishment task.
Manual boron replenishment (MG 4): the device is used for initially filling or supplementing water into a refueling water tank and filling and exhausting water into a container control box, replenishing boron-containing water with the same concentration as that of the coolant of the loop reactor for volume control, and not changing the concentration of the coolant of the loop reactor; in the replenishing process, the flow of the desalted and deoxidized water and the boric acid is manually set by an operator, and replenishing is manually stopped when the replenishing amount reaches a set value; at least one line of demineralized oxygen-depleted water injection lines and one line of boric acid injection lines should be added to ensure successful completion of the automated boron replenishment task.
Chemical addition (MG 5): injecting desalted and deoxidized water into a chemical adding box pipeline through a desalted and deoxidized water pump, and adding hydrazine or lithium hydroxide solution into the chemical adding box to change the content and the PH value of a loop reactor coolant, thereby achieving the purpose of chemical control; in the chemical adding process, at least one line of desalting and deoxidizing water supply pipeline and chemical adding box pipeline should be put in order to ensure successful completion of the chemical adding task.
(2) The manual boron replenishment (MG 4) is used as a manipulation task target, and the manipulation action sequence is shown in Table 2 through successful path planning, example layering task decomposition and manipulation action sequence extraction processes in a virtual random scene.
The manual boron replenishment task of the reactor boron and water replenishment system is divided into five sub-tasks, including:
opening an isolation valve: the opening of the pneumatic isolation valves REA001PIV and REA002PIV (Step-1) is a combination of unordered actions that can be simply understood as a functional level of operation.
Switching the pump from automatic to manual control mode: the desalination and deoxidation water pump REA002PO and the boric acid conveying pump REA002PO are switched from automatic mode to manual control mode (Step-2) and are also combined in a disordered action mode.
Starting a desalting and deoxidizing water pump and a boric acid conveying pump: the boric acid delivery pump REA004PO (Step-3) and the desalination and deoxidation water pump REA002PO (Step-4) are sequentially started.
Starting boron replenishment: the opening of the pneumatic control valve REA001PCV was adjusted to 80% (Step-5), the opening of the pneumatic control valve REA002PCV was adjusted to 60% (Step-6), and the electric control valve REA002MOV was opened (Step-7).
Stopping boron replenishment: sequentially closing the pneumatic control valve REA001PCV (Step-8), closing the pneumatic control valve REA002PCV (Step-9), closing the electric control valve REA002MOV (Step-10), closing the boric acid delivery pump REA004PO (Step-11), closing the desalination and deoxidation water pump REA002PO (Step-12), closing the pneumatic isolation valve REA001PIV (Step-13), and closing the pneumatic isolation valve REA002PIV (Step-14).
TABLE 2 manipulation action sequence Listing
(3) Based on the hierarchical task decomposition result, the basic operation action steps under the tree structure of 'operation task target-subtask-basic operation action steps' are organized in a form of serialization or function combination to form a rule action library, so that automatic association between task target-subtask target-basic operation actions at all levels is realized.
The procedure action library information list field includes: the method comprises the steps of working condition scene, task target, subtask target, operation action step sequence coding, operation action mode, controlled action object association coding, control variable minimum boundary value, control variable maximum boundary value, action execution time and the like.
S102, a designer operates an action pattern recognition algorithm.
Based on the state pattern recognition technology, according to the control information base and the operation navigation, a designer operates an action pattern recognition algorithm; the personnel operation action mode recognition algorithm comprises a judgment basis and a judgment method of personnel operation action modes in a digital control environment of the nuclear power device, and is used for identifying the personnel error modes in the digital control environment of the nuclear power device.
S103, real-time state monitoring data of the system comprise system running state implementation monitoring input and actual operation action instruction input.
Based on the QT virtual simulation platform, the generation, monitoring and reading of system process state parameters and manual operation instruction signals of operators are simulated.
As shown in fig. 4, through the QT Designer virtual simulation environment, human-computer interaction, system running state parameters, and operator operation action instructions in the manual boron replenishment process under the refueling shutdown condition are simulated, and specific simulation data include:
real-time monitoring and inputting of the running state of the system: including system device status, control mode, process variable monitoring values, etc.; for example, boric acid transfer pump REA004PO is in manual control mode and is in an on state, and boric acid concentration is 1300ppm or the like.
Actual operation action command input: manual on signal, manual off signal, etc.
S104, according to a personnel operation action mode recognition algorithm, combining real-time state monitoring data of the system, and realizing personnel error mode recognition in the nuclear power plant.
As shown in fig. 5, based on real-time simulation monitoring data generated by the QT virtual simulation platform, according to a personnel operation action pattern recognition algorithm, the method for realizing human error pattern recognition in the nuclear power plant specifically includes the following steps:
operation navigation guide: based on the protocol action library, by manipulating the task target selections, the manipulating action sequences associated with the "manual boron replenishment" task will be presented in a tree structured navigation bar.
Simulation of a system operation and control process: based on the QT virtual simulation platform, system equipment state control signals and system process state monitoring parameters are simulated and generated, and the system equipment state control signals and the system process state monitoring parameters specifically comprise control modes of controllable components, state mode digital signals and continuous process variable monitoring values such as the water level of a volume control box, the oxygen content in a reactor coolant, boric acid concentration, PH value and the like.
Reading real-time monitoring data: reading real-time monitoring signals generated by a QT virtual simulation platform or a simulator into a control information base through an external data interface, updating equipment control variable attribute values in an equipment state information base, and automatically triggering associated action events according to the change of the equipment state attribute values;
Operation action consistency detection: comparing the actual operation action event generated by the state change trigger with the expected operation action in the procedure action library for analysis;
personnel action mode identification: by means of consistency detection, personnel operation action mode and potential human error mode identification are achieved, as shown in table 3. The described embodiments take into account typical patterns of actions and human errors that may occur to an operator during task execution, including in particular correct operation, irregular operation, incomplete operation, delayed operation, advanced operation, late operation, incorrect target selection, incorrect execution of operations, missing operations, etc.
TABLE 3 personnel operation action mode and potential human error pattern recognition results
And (3) displaying an operation supervision interface: according to the personnel action mode identification result, the warning information popup window is combined to prompt potential human errors possibly occurring in the task execution process of an operator, and the executed operation action information is fed back to the operation navigation window, so that the operator can more conveniently know the current operation task progress.
The personnel action pattern recognition algorithm and the example under the digital control environment of the nuclear power device provided by the invention are not only limited to the above typical personnel action pattern recognition, in practical engineering application, practical analysts can expand the control information base according to application requirements, supplement and perfect personnel action pattern judgment basis, and realize the recognition and coverage of a larger range of personnel-caused error patterns.
Those skilled in the art will appreciate that all or part of the steps in a method implementing the above embodiments may be implemented by a program to instruct related hardware, and the corresponding program may be stored in a computer readable storage medium.
It should be noted that although the method operations of the above embodiments are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in that particular order or that all illustrated operations be performed in order to achieve desirable results. Rather, the depicted steps may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.
Example 2:
as shown in fig. 6, the present embodiment provides a human error pattern recognition device in a power device, which includes a control information base construction module 601, an operation navigation implementation module 602, a human operation action pattern recognition algorithm design module 603, and a human error pattern recognition module 604, wherein:
the control information base construction module 601 is configured to perform hierarchical analysis and decomposition on a system function structure and a control task in a system operation interaction process, respectively, so as to construct a control information base;
The operation navigation implementation module 602 is configured to implement operation navigation for a serialization action under a given task target by using a target or an event/state as a guide according to the control information base;
a personnel operation action pattern recognition algorithm design module 603, configured to design a personnel operation action pattern recognition algorithm based on pattern recognition according to the manipulation information base and the operation navigation; the personnel operation action mode identification algorithm comprises a judgment basis and a judgment method of personnel operation action modes in a digital control environment of a plurality of nuclear power devices;
the human error pattern recognition module 604 is configured to implement human error pattern recognition in the nuclear power device according to the human operation action pattern recognition algorithm and in combination with real-time state monitoring data of the system;
the human error mode recognition module 604 includes an operation supervision interface display unit, which is configured to display an interface of a human error mode recognition result, through designs such as an early warning information popup window, prompt an operator of potential or executing possible dangerous actions in time, improve safety and situational awareness, and feed back the executed operation action information to an operation navigation window, so that the operator can more conveniently know the current operation task progress.
Specific implementation of each module in this embodiment may be referred to embodiment 1 above, and will not be described in detail herein; it should be noted that, the apparatus provided in this embodiment is only exemplified by the division of the above functional modules, and in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure is divided into different functional modules, so as to perform all or part of the functions described above.
Example 3:
the present embodiment provides an electronic device, which may be a computer, as shown in fig. 7, and is connected to a processor 702, a memory, an input device 703, a display 704 and a network interface 705 through a system bus 701, where the processor is configured to provide computing and control capabilities, the memory includes a nonvolatile storage medium 706 and an internal memory 707, where the nonvolatile storage medium 706 stores an operating system, a computer program and a database, the internal memory 707 provides an environment for the operating system and the computer program in the nonvolatile storage medium, and when the processor 702 executes the computer program stored in the memory, the method for identifying a human error pattern in the nuclear power plant of the above embodiment 1 is implemented as follows:
Respectively carrying out hierarchical analysis and decomposition on a system function structure and an operation task in the system operation interaction process, and constructing an operation information base;
according to the control information base, the operation navigation of the serialization action under the given task target is realized by taking the target or the event/state as the guide;
according to the control information base and the operation navigation, designing a personnel operation action mode recognition algorithm based on mode recognition; the personnel operation action mode identification algorithm comprises a judgment basis and a judgment method of personnel operation action modes in a digital control environment of a plurality of nuclear power devices;
and according to the personnel operation action mode recognition algorithm, combining real-time state monitoring data of the system to realize the human error mode recognition in the nuclear power device.
Example 4:
the present embodiment provides a storage medium, which is a computer readable storage medium storing a computer program, where the computer program when executed by a processor implements the method for identifying a human error pattern in a nuclear power plant according to embodiment 1, as follows:
respectively carrying out hierarchical analysis and decomposition on a system function structure and an operation task in the system operation interaction process, and constructing an operation information base;
According to the control information base, the operation navigation of the serialization action under the given task target is realized by taking the target or the event/state as the guide;
according to the control information base and the operation navigation, designing a personnel operation action mode recognition algorithm based on mode recognition; the personnel operation action mode identification algorithm comprises a judgment basis and a judgment method of personnel operation action modes in a digital control environment of a plurality of nuclear power devices;
and according to the personnel operation action mode recognition algorithm, combining real-time state monitoring data of the system to realize the human error mode recognition in the nuclear power device.
The computer readable storage medium of the present embodiment may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In summary, the method for identifying the human error mode in the nuclear power plant provided by the invention surrounds the system function target and the manipulation task target, is based on analysis, decomposition and layering task analysis of the system function structure, and builds a manipulation information base through extracting the state attribute characteristics and the manipulation action sequence of the controllable system equipment, and a personnel operation action mode identification algorithm designed on the basis is used for realizing the effective identification of the human error mode in the novel digital manipulation environment.
The above-mentioned embodiments are only preferred embodiments of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can make equivalent substitutions or modifications according to the technical solution and the inventive concept of the present invention within the scope of the present invention disclosed in the present invention patent, and all those skilled in the art belong to the protection scope of the present invention.
Claims (7)
1. A method for identifying a human error pattern in a nuclear power plant, the method comprising:
respectively carrying out hierarchical analysis and decomposition on a system function structure and an operation task in the system operation interaction process, and constructing an operation information base; the control information base comprises a procedure action base and an equipment state information base, wherein the procedure action base is imported through a digital procedure or is obtained based on hierarchical task analysis of a standardized operation procedure, and the equipment state information base is obtained through hierarchical functional structure decomposition construction; forming an interactive process relation model of 'system function target-manipulation task target-subtask-basic manipulation action-manipulation action object' through interactive coupling of system functions and operation manipulation tasks;
according to the control information base, the operation navigation of the serialization action under the given task target is realized by taking the target or the event/state as the guide;
according to the control information base and the operation navigation, designing a personnel operation action mode recognition algorithm based on mode recognition; the personnel operation action mode identification algorithm comprises a judgment basis and a judgment method of personnel operation action modes in a digital control environment of a plurality of nuclear power devices;
According to the personnel operation action pattern recognition algorithm, combining real-time state monitoring data of a system, if the admission condition of a rule is met, extracting a corresponding operation action sequence, and projecting the operation action sequence to an operation navigation picture; according to the system running state parameters provided by the real-time state monitoring and the actual operation instructions input by operators, the human error mode identification in the nuclear power device is realized, and the identification result of the human error mode is displayed on an operation supervision interface;
the system running state parameters provided according to real-time state monitoring and actual operation instructions input by operators realize human error pattern recognition in the nuclear power device, and specifically comprises the following steps:
reading the system running state parameters and actual operation instructions into an equipment state information base, comparing and analyzing the read data with default parameter settings in the equipment state information base, if the data change is detected, considering that an operator executes operation actions on the current equipment, recording the equipment with the changed parameters, parameter attributes and parameter change values and integrating the equipment, the parameter attributes and the parameter change values into one piece of operation action information, triggering an operation action event, judging whether an operation object is matched or not based on the operation event state mode obtained by current monitoring, and if yes, judging whether the operation object is matched or not: judging whether the equipment control mode and/or the operation action are matched, if not, identifying a human error mode for 'the wrong operation acts on the correct object'; if yes, jumping to S1;
If not, then: judging whether the equipment control mode and/or the operation action are matched, if so, identifying a human error mode of 'target selection error'; if not: traversing the procedure action library, judging whether the operation action is covered in the procedure action library, and if so, jumping to S1; if not, identifying a human error mode of 'random operation';
S1：
judging whether the execution sequence of the operation actions is matched according to the standard operation action sequence defined in the standard procedure action library, if so, then: judging whether the operation is completed within a specified task time or not by combining the execution time record of the current operation step, and if so, identifying a human error mode of 'correct operation'; if not, then: judging whether the control object is a discrete variable, if so, identifying a human error mode of 'operation delay'; if not, the operation is not complete and the human error mode is identified;
if not, then: judging whether the operation action is advanced, if so, identifying a human error mode of 'operation advanced'; if not, the mode is identified as "operation lag" human error mode.
2. The method for identifying a human error pattern in a nuclear power plant according to claim 1, wherein the process of constructing the protocol action library specifically comprises:
Taking a standard operation rule as input, and extracting the admission conditions of the rules under different operation working conditions and scenes based on rule response analysis; wherein, the different operation conditions and the protocols under the scene comprise a diagnosis protocol, a response protocol and a system protocol;
taking a standard operation rule as input, extracting an operation task target based on hierarchical task analysis, and decomposing an operation action sequence according to the requirement of the operation task target to obtain an operation task target-subtask-basic operation step serialization structure;
abstracting basic operation steps in the serialization structure into equipment actions aiming at equipment state change, and establishing coupling association between the operation actions and the controlled objects;
extracting attribute characteristics of the operation action according to the coupling association between the operation action and the controlled object, wherein the attribute characteristics comprise the controlled object, the starting/ending time of the operation action and the task execution time, and encoding according to the action execution sequence, and storing the attribute characteristics into a database table in a data format of 'belonging to an operation task target-belonging to a subtask-operation action-task time', so as to form a rule action library;
the construction process of the equipment state information base specifically comprises the following steps:
Determining system design purposes, functions and structural components based on system design data input, and generating a device list of the controllable system;
according to the attribute characteristics of the discrete and continuous states of the equipment, the equipment is divided into a discrete controllable component and a continuous controllable component, so that the identification of incomplete operation and operation delay human error modes is conveniently realized;
the equipment name is encoded, and the equipment name encoding can intuitively reflect an equipment association system and tasks/subtasks;
extracting attribute characteristics of equipment, and inputting the attribute characteristics into an equipment state information base table through data abstraction and digital coding in an equipment-attribute value data structure format so as to generate an equipment state information base table; wherein the device in the "device-attribute value" includes a device type and a device name.
3. The method for identifying a human error pattern in a nuclear power plant according to claim 1, wherein the operation navigation of the serialized actions under the given task target is realized by taking the target or the event/state as a guide according to the control information base, and specifically comprises the following steps:
for a manipulation task scene with procedure guidance, selecting an event or a state as a guide according to the procedure type, and automatically extracting a manipulation action sequence facing to an abnormal event or an abnormal state response according to the self-identification of the working condition and the admission condition of the procedure for on-line operation navigation prompt; for off-line application, an operator automatically sets an operation condition scene, a system function target and an operation task target according to the needs, and executes operation navigation prompt aiming at the specific task target;
Providing constructive operation navigation guidance suggestions for random Cheng Teshu operation scenes and environments by taking system function targets as guidance and setting successful path planning or expected manipulation response configuration; wherein the successful path planning includes two methods:
based on a multi-layer flow system functional model, combining causal relationship mapping and influence propagation rules, and performing reasoning search through an anti-target 'flow' structure to obtain a successful path set of a target of a guide system function;
based on a system GO-FLOW reliability model, a system success path set guided by a task target is obtained by minimum path set analysis according to a physical signal 'FLOW' direction and a logic structure relation and by combining engineering experience feedback;
after the operation task targets under the specific operation condition scene and task requirements are determined, the operation action sequences are automatically associated and presented according to a tree structure of operation task targets, subtask targets and basic operation steps, and the operator is prompted to execute the current task process and the operation actions required to be executed subsequently according to feedback of operation supervision results.
4. The method for identifying a human action pattern in nuclear power according to claim 1, wherein the step of displaying the identification result of the human error pattern on an operation supervision interface specifically comprises:
The executed operation action information and the identification result of the corresponding human error mode are fed back to the operation navigation window, so that an operator can know the current operation task process more conveniently;
the display of the operation supervision interface mainly comprises the backtracking of a historical operation action sequence and the identification result of the current operation action, and the potential human error possibly occurring in the task execution process of an operator is prompted by combining the warning information popup window according to the identification result of the current operation action, wherein the backtracking of the historical operation action sequence comprises the operation action actually input by the operator in the past and the identification result of the human error mode corresponding to the operation action.
5. A human error pattern recognition device in a nuclear power plant, the device comprising:
the control information base construction module is used for respectively carrying out hierarchical analysis and decomposition on the system function structure and the control task in the system operation interaction process to construct a control information base; the control information base comprises a procedure action base and an equipment state information base, wherein the procedure action base is imported through a digital procedure or is obtained based on hierarchical task analysis of a standardized operation procedure, and the equipment state information base is obtained through hierarchical functional structure decomposition construction; forming an interactive process relation model of 'system function target-manipulation task target-subtask-basic manipulation action-manipulation action object' through interactive coupling of system functions and operation manipulation tasks;
The operation navigation realizing module is used for realizing the operation navigation of the serialization action under the given task target by taking the target or the event/state as the guide according to the control information base;
the personnel operation action pattern recognition algorithm design module is used for designing a personnel operation action pattern recognition algorithm based on pattern recognition according to the control information base and the operation navigation; the personnel operation action mode identification algorithm comprises a judgment basis and a judgment method of personnel operation action modes in a digital control environment of a plurality of nuclear power devices;
the human error pattern recognition module is used for extracting a corresponding manipulation action sequence according to the human operation action pattern recognition algorithm and combining real-time state monitoring data of the system, and projecting the manipulation action sequence to an operation navigation picture if the manipulation action sequence meets the admission condition of a rule; according to the system running state parameters provided by the real-time state monitoring and the actual operation instructions input by an operator, the human error mode identification in the nuclear power device is realized, the human error mode identification result is displayed on an operation supervision interface, the system running state parameters provided by the real-time state monitoring and the actual operation instructions input by the operator are realized, and the human error mode identification in the nuclear power device is realized specifically comprising:
Reading the system running state parameters and actual operation instructions into an equipment state information base, comparing and analyzing the read data with default parameter settings in the equipment state information base, if the data change is detected, considering that an operator executes operation actions on the current equipment, recording the equipment with the changed parameters, parameter attributes and parameter change values and integrating the equipment, the parameter attributes and the parameter change values into one piece of operation action information, triggering an operation action event, judging whether an operation object is matched or not based on the operation event state mode obtained by current monitoring, and if yes, judging whether the operation object is matched or not: judging whether the equipment control mode and/or the operation action are matched, if not, identifying a human error mode for 'the wrong operation acts on the correct object'; if yes, jumping to S1;
if not, then: judging whether the equipment control mode and/or the operation action are matched, if so, identifying a human error mode of 'target selection error'; if not: traversing the procedure action library, judging whether the operation action is covered in the procedure action library, and if so, jumping to S1; if not, identifying a human error mode of 'random operation';
S1：
judging whether the execution sequence of the operation actions is matched according to the standard operation action sequence defined in the standard procedure action library, if so, then: judging whether the operation is completed within a specified task time or not by combining the execution time record of the current operation step, and if so, identifying a human error mode of 'correct operation'; if not, then: judging whether the control object is a discrete variable, if so, identifying a human error mode of 'operation delay'; if not, the operation is not complete and the human error mode is identified;
If not, then: judging whether the operation action is advanced, if so, identifying a human error mode of 'operation advanced'; if not, the mode is identified as "operation lag" human error mode.
6. An electronic device comprising a processor and a memory for storing a program executable by the processor, wherein the processor, when executing the program stored in the memory, implements a method for identifying a human error pattern in a nuclear power plant as claimed in any one of claims 1 to 4.
7. A storage medium storing a program which, when executed by a processor, implements the method for identifying a human error pattern in a nuclear power plant according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111252277.XA CN113963443B (en) | 2021-10-27 | 2021-10-27 | Method, device, equipment and medium for identifying human error mode in nuclear power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111252277.XA CN113963443B (en) | 2021-10-27 | 2021-10-27 | Method, device, equipment and medium for identifying human error mode in nuclear power plant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113963443A CN113963443A (en) | 2022-01-21 |
| CN113963443B true CN113963443B (en) | 2023-06-20 |
Family
ID=79467573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111252277.XA Active CN113963443B (en) | 2021-10-27 | 2021-10-27 | Method, device, equipment and medium for identifying human error mode in nuclear power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113963443B (en) |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105023624B (en) * | 2015-06-09 | 2017-06-16 | 中广核（北京）仿真技术有限公司 | Nuclear power plant's severe accident relieving method and system |
| CN113392527B (en) * | 2021-06-17 | 2022-08-12 | 华南理工大学 | Method and device for evaluating applicability of manipulation sequence, computer equipment and storage medium |
-
2021
- 2021-10-27 CN CN202111252277.XA patent/CN113963443B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 张力 ; 陈帅 ; 青涛 ; 孙婧 ; 刘朝鹏 ; .基于认知模型与故障树的核电厂严重事故下人因失误分析.核动力工程.2020,(第03期),143-148. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113963443A (en) | 2022-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Siu | Risk assessment for dynamic systems: an overview | |
| CN107611969B (en) | Regulation and error prevention system with order regulation and constraint functions and method | |
| Kang et al. | Concept of an intelligent operator support system for initial emergency responses in nuclear power plants | |
| Li et al. | Modeling and simulation of crew to crew response variability due to problem-solving styles | |
| Dozortsev et al. | Computerized operator training: continued importance, new opportunities, and the human factor | |
| CN117350501A (en) | System and method for dispatching man-in-loop power grid driven by large language model | |
| CN114023477B (en) | Computerized regulation system and control system for nuclear power plant | |
| CN113963443B (en) | Method, device, equipment and medium for identifying human error mode in nuclear power plant | |
| CN113392527B (en) | Method and device for evaluating applicability of manipulation sequence, computer equipment and storage medium | |
| Poucet | STARS: knowledge based tools for safety and reliability analysis | |
| Bhatnagar et al. | An integrated operator advisor system for plant monitoring, procedure management, and diagnosis | |
| US20110060582A1 (en) | Diversity and Defense-In-Depth Simulation Apparatus | |
| CN115564073A (en) | Power grid power operation method and device, computer equipment and storage medium | |
| CN112433608B (en) | Automatic identification method for human-computer information interaction risk scene | |
| Mercurio | Discrete dynamic event tree modeling and analysis of nuclear power plant crews for safety assessment | |
| Kolski et al. | A process method for the design of “Intelligent” man‐machine interfaces: Case study:“The decisional module of imagery” | |
| CN114139991A (en) | Switching operation ticket forming system and method with error prevention capability | |
| Lu et al. | A new approach of modeling supervisory control for manufacturing systems based on SysML | |
| Klein et al. | Controller design for an FMS using Signal Interpreted Petri Nets and SFC: Validation of both descriptions via model-checking | |
| CN102243585B (en) | Global script program processing and analyzing method of human-machine interaction interface monitoring system | |
| Liang et al. | Identification of Human Operation Deviation Using a Conformance Checking Technique | |
| Núñez-Carrera et al. | Failure analysis of the standby liquid control system for a boiling water reactor with fuzzy cognitive maps | |
| JPH0584907B2 (en) | ||
| Liu et al. | Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents | |
| Jharko et al. | Intellectualized Operator Information Support System for NPP: Expert Systems and Dynamic Models |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |