CN113837535A - Method for backtracking serious accident process of nuclear power plant - Google Patents
Method for backtracking serious accident process of nuclear power plant Download PDFInfo
- Publication number
- CN113837535A CN113837535A CN202110947643.7A CN202110947643A CN113837535A CN 113837535 A CN113837535 A CN 113837535A CN 202110947643 A CN202110947643 A CN 202110947643A CN 113837535 A CN113837535 A CN 113837535A
- Authority
- CN
- China
- Prior art keywords
- accident
- event
- nuclear power
- power plant
- backtracking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 230000008569 process Effects 0.000 title claims abstract description 30
- 238000003745 diagnosis Methods 0.000 claims abstract description 26
- 230000004044 response Effects 0.000 claims abstract description 18
- 238000011161 development Methods 0.000 claims abstract description 4
- 238000002347 injection Methods 0.000 claims description 36
- 239000007924 injection Substances 0.000 claims description 36
- 238000004422 calculation algorithm Methods 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 23
- 238000013135 deep learning Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 230000000306 recurrent effect Effects 0.000 claims description 7
- 239000002826 coolant Substances 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 5
- 230000000977 initiatory effect Effects 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 241000321453 Paranthias colonus Species 0.000 claims description 2
- 238000012300 Sequence Analysis Methods 0.000 claims description 2
- 230000000116 mitigating effect Effects 0.000 claims 1
- 238000011156 evaluation Methods 0.000 abstract description 3
- 230000003111 delayed effect Effects 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000007921 spray Substances 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention relates to a method for backtracking a severe accident process of a nuclear power plant. By adopting the method provided by the invention, when a severe accident occurs in the nuclear power plant, the initial event type, the initial event parameter and the system response information of the severe accident can be rapidly diagnosed. And inputting the backtracked serious accident process diagnosis information into a serious accident integrated analysis program to obtain the prediction information of further development of the accident process, thereby providing positive and negative influence evaluation for the intervention operation of an operator. The method provided by the invention also realizes automatic diagnosis without manual intervention. Meanwhile, the method also provides the diagnosis of the head event time in the serious accident process of the accident sequence, namely the diagnosis of the system response time, and analyzes the influence of the delayed running time of each head event of the accident sequence on the serious accident process.
Description
Technical Field
The invention belongs to the field of implementation of a serious accident management guide rule of a nuclear power plant, and relates to a method for backtracking a serious accident process of the nuclear power plant.
Background
The major Accident Management Guidelines (SAMG) are guidance Management documents used by staff in a main control room and a technical support center to take measures to alleviate the consequences of a core damage Accident when a major Accident occurs in a nuclear power plant. Severe incident management guidelines A typical approach to many decisions is to evaluate the potential negative impact of the action to be taken. One of the key factors for the successful implementation of SAMG is that technical support personnel quickly diagnose a severe accident process, diagnose a severe accident initiating event, initiating event parameters, and the response of the nuclear power plant system. However, in the emergency aid decision-making system, response action information of systems in the nuclear power plant system, such as action signals of a high-pressure safety injection pump, a low-pressure safety injection pump, a safety spray pump, a main steam pipeline safety valve and the like, is lacked. This results in a serious accident in which the response of the nuclear power plant system can only be manually recorded, and automated assessment cannot be achieved.
In the prior art, some methods for backtracking the progress of a serious accident appear, which roughly include the following methods:
(1) emergency operation rules: the main method is that the operator identifies the accident reason according to the optimal recovery rule and the diagnosis rule leads the accident reason to enter the appointed accident recovery rule, thereby quickly and efficiently relieving the consequence of the specific accident.
(2) Intelligent diagnosis: the main method is to use the algorithm of machine learning to record the data of key instruments and diagnose the initial events and initial event parameters of the serious accident process according to the time sequence characteristics of the instrument data.
(3) Manual operation of the log: the main method is that an operator carries out manual recording when the operation is executed according to the emergency operation regulation, and the starting time of equipment such as a pump, a valve and the like is recorded.
However, the existing backtracking methods for the serious accident processes have some disadvantages: 1) the emergency operation rules can only aim at part of specific accidents, namely the accidents of the accident reasons can be diagnosed, the application range is narrow, and the accidents of which the accident reasons cannot be identified cannot be processed; moreover, only the category of the originating event can be diagnosed, and the parameters of the originating event cannot be specifically diagnosed. 2) The intelligent diagnosis method can diagnose the type of the initial event and the parameters thereof, has stronger processing capability than emergency operation procedures, but does not diagnose the response of the nuclear power plant system. 3) Manual recording can only record system response in the process of a serious accident, and can not diagnose an initial event; moreover, since it is isolated data, it is difficult to integrate with an electronic information system.
Therefore, it is necessary to develop a method for backtracking a severe accident process of a nuclear power plant, which can quickly trace the severe accident process after the occurrence of the severe accident, provide an intervention operation suggestion in a short time, and improve the management level of the severe accident of the nuclear power plant.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method for backtracking the serious accident process of a nuclear power plant, which can be used for rapidly backtracking the serious accident process in the process of transferring from an emergency operation procedure to SAMG after the occurrence of the serious accident, and further deducing the positive and negative influences of various intervention means through computer program simulation calculation; therefore, intervention operation suggestions can be provided in a short time, and the serious accident management level of the nuclear power plant is improved.
To achieve the purpose, the invention provides a method for backtracking the progress of a serious accident of a nuclear power plant, which comprises the following steps:
s1, diagnosing the type and parameters of the initial event by adopting a deep learning algorithm, wherein the diagnosis of the type of the initial event refers to a probability safety analysis report;
s2, referring to the event tree of the probability safety analysis report, and judging the event tree corresponding to the initial event type diagnosed in the step S1;
s3, referring to the event tree of the probability safety analysis report, and diagnosing an accident sequence of the serious accident in the event tree of the probability safety analysis report by adopting a deep learning algorithm; the accident sequence comprises a plurality of head events, and the head event time diagnosis is carried out by adopting a deep learning algorithm;
and S4, automatically generating a serious accident integration program input card according to the diagnosis result of the step S3, writing the information of the diagnosis result into the input card, and calculating by the serious accident integration program to obtain the future development trend of the serious accident.
Further, in the step S1, the deep learning algorithm uses a long-short term memory network algorithm in a recurrent neural network, the long-short term memory network algorithm is good at processing the time series data, and the input data is historical data of a plurality of key instruments of the nuclear power plant.
Further, in the probabilistic security analysis report, detailed originating event analysis and classification thereof are included; for the operating power operating condition probability safety analysis report, the originating event categories include, but are not limited to, reactor coolant loss, loss of hot-traps, loss of feedwater, loss of external power, feedwater line breach, steam generator heat transfer tube rupture, steam line rupture plus steam generator heat transfer tube rupture.
Further, in the probabilistic safety analysis report, an accident sequence analysis is performed on each type of initial events, so as to determine that the nuclear power plant generates an event tree through automatic response and artificial response models after the initial events occur.
Further, in step S3, each event tree reported by the probabilistic safety analysis includes a plurality of accident sequences, where the accident sequences include accident sequences that successfully mitigate and accident sequences that cause core damage, and each accident sequence represents a progress of a serious accident.
Further, the category of the topic event includes, but is not limited to, required security function, investment of the system, occurrence of a basic event, or behavior of an operator.
Further, the subject event is a nuclear power plant system response, and the nuclear power plant system response includes, but is not limited to, the starting of a safety injection system pump, and an operation performed by an operator.
Further, in step S3, the deep learning algorithm uses a long-short term memory network algorithm in a recurrent neural network to diagnose the nuclear power plant system response in the severe accident process, and determine the accident sequence of the severe accident in the event tree reported by the probabilistic safety analysis.
Further, in step S3, the method for diagnosing the header event time includes: calculating a delay operation time data set of each topic event according with the accident sequence characteristics by using a serious accident integrated analysis program by referring to the accident sequence of the diagnosed serious accident in the event tree of the probability safety analysis report; dividing the delay operation time data set of each question head event into a training set and a testing set, and adopting a long-short term memory network algorithm in a recurrent neural network to diagnose the delay operation time of each question head event; and summarizing the delay running time of each head event together to obtain the head event time diagnosis in the serious accident process of the accident sequence.
Further, in step S4, the serious accident integration analysis program includes, but is not limited to, MAAP developed by Fauske & Associates, MELCOR developed by Sandia national laboratory, and ASTEC developed by IRSN in france and GRS in germany.
The method for backtracking the progress of the severe accident of the nuclear power plant has the advantages that when the severe accident occurs in the nuclear power plant, the method diagnoses the type of the initial event, the parameters of the initial event and the system response information of the severe accident through the time sequence obtained by monitoring the available key instruments. And inputting the diagnosis information into a severe accident integrated analysis program to obtain the prediction information of the accident process, and diagnosing the severe accident process so as to provide positive and negative influence evaluation for the intervention operation of an operator. The method provided by the invention also realizes automatic diagnosis without manual intervention. Meanwhile, the method provided by the invention reduces the number of parameters required by diagnosis, can quickly diagnose without starting and stopping signals of the pump and the valve, and can realize the diagnosis function when the starting and stopping signals of the equipment such as the pump and the valve cannot be acquired. In addition, the method provided by the invention analyzes the influence of the starting running time of each topic header event of the accident sequence on the serious accident process, comprises a plurality of running times of each topic header event in the deep learning input data set, and considers the influence of the delay running time of the topic header event on the serious accident process.
Drawings
Fig. 1 is a main flow diagram of a method for backtracking a severe accident process of a nuclear power plant according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a time diagnosis process of an accident sequence according to an embodiment of the present invention.
FIG. 3 is a flow chart of a tree of breached reactor coolant loss (i.e., BI1A) events in the hot leg of operating power operating conditions in accordance with an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and detailed description. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a main flow diagram of an embodiment of a method for backtracking a severe accident process of a nuclear power plant provided by the present invention mainly includes the following steps:
and S1, adopting a long-short term memory network algorithm (LSTM algorithm) in the recurrent neural network to diagnose the types and parameters of the initial events. In the probabilistic safety analysis report (PSA report), some of the originating events and parameters are shown in table 1; for example, the hypothetical accident was a medium breach reactor loss of coolant accident (medium LOCA) diagnosed from the originating event in the PSA report.
S2, judging the originating event type diagnosed in the step S1 corresponds to the event tree of PSA report. For example, from the accident conclusion of LOCA diagnosed in step S1, it is determined that the accident is assumed to be a breach reactor coolant loss accident in the hot leg (i.e., BI1A), the event tree of BI1A is found from the PSA report, and the event tree of BI1A is shown in fig. 3.
And S3, adopting an LSTM algorithm to diagnose the accident sequence to which the assumed accident belongs in the event tree. As shown in FIG. 3, there are 8 accident sequences in BI1A event tree, and the assumed accident belongs to accident sequence 2 by using LSTM algorithm.
In the PSA report BI1A event tree shown in fig. 3, the head of problem events include a safety shutdown, direct containment spray, direct high-pressure safety injection pump injection via pipeline, operator execution of a1.2 protocol, safety injection tank injection, direct low-pressure safety injection pump injection via cold-leg injection pipeline, low-pressure safety injection pump injection via cold-leg pipeline recirculation, safety spray pump recirculation operation, and the like. If a header event is successfully executed, the column of the header event in fig. 3 is represented as a horizontal line; if the execution fails, the column of the header event is shown as a polyline in FIG. 3. In fig. 3, the accident sequence 1 is that after a breach accident occurs, the accident is relieved because each header event is successfully executed, and no serious accident occurs; other 7 accident sequences are all serious accidents that the execution of a certain head event fails and the damage of the reactor core occurs. And (3) diagnosing whether each header event in the event tree is successfully executed by adopting an LSTM algorithm, so that the accident sequence number causing the damage of the reactor core can be diagnosed.
The expression of accident sequence 2 in the PSA report is: after a breach loss of coolant accident occurs in a hot section under a power operation working condition, emergency shutdown succeeds, containment vessel is directly sprayed successfully, a high-pressure safety injection pump is directly injected successfully through a pipeline, an operator executes A1.2 procedure to quickly cool and depressurize a primary circuit successfully, a safety injection box is injected successfully, a low-pressure safety injection system succeeds later, and under the condition that the safety injection system and the safety injection box are operated successfully, reactor core waste heat can be taken away through the breach, but the safety injection pump fails in recycling operation, so that the reactor core fails to take heat for a long time, and finally the reactor core is damaged.
In addition to diagnosing the head events, the LSTM algorithm is also used for diagnosing the head event time. For example, diagnosis of high pressure safety injection pump in BI1A accident sequence 2 via line direct injection start time.
More specific embodiments of event header event time diagnostics in PSA reports are as follows:
step P1, referring to the LOCA event tree in the PSA report, adopting the deep learning LSTM algorithm to diagnose the accident sequence which occurs to belong to the accident sequence 2 in the LOCA event tree;
step P2, referring to the PSA report accident sequence 2, a header event delay runtime dataset conforming to the accident sequence 2 characteristics is calculated using the MAAP. For example, for the direct injection of the high-pressure safety injection pump through the pipeline, the delay time of the actual injection behavior of the high-pressure safety injection pump through the pipeline in various situations such as 0 minute, 2 minutes, 5 minutes, 10 minutes and the like after the high-pressure safety injection pump reaches the high-pressure safety injection starting condition is calculated, and the calculated data is used as a delay running time data set for the direct injection of the high-pressure safety injection pump through the pipeline of the LSTM algorithm.
And for other question head events, such as failure of the injection stage of a safety injection box and the recycling injection stage of a low-pressure safety injection pump through a cold section pipeline, the MAAP calculation is also adopted by the same method to obtain a corresponding question head event delay operation time data set.
And step P3, dividing the subject event delay running time data set obtained in the step P2 into a training set and a testing set, and diagnosing the injection time of the direct injection of the high-pressure safety injection by adopting an LSTM algorithm of deep learning. And summarizing the delay running times of the head events diagnosed in the step P2 together to obtain the head event time diagnosis in the serious accident process of the accident sequence 2, namely the system response time diagnosis.
And S4, automatically generating an MAAP input card of the serious accident integrated analysis program according to the diagnosis result of the steps, writing diagnosis information into the MAAP input card, generating the MAAP input card which accords with the BI1A accident sequence 2, obtaining the development trend of the serious accident process through MAAP calculation, and diagnosing the serious accident process, thereby providing positive and negative influence evaluation for the intervention operation of an operator.
TABLE 1 originating event type and parameter Table
The above-described embodiments are merely illustrative of the present invention, and those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for backtracking the progress of a severe accident in a nuclear power plant, the method comprising the steps of:
s1, diagnosing the type and parameters of the initiating event by adopting a deep learning algorithm, wherein the type of the initiating event refers to a probability safety analysis report;
s2, referring to the event tree of the probability safety analysis report, and judging the event tree corresponding to the initial event type diagnosed in the step S1;
s3, referring to the event tree of the probability safety analysis report, and diagnosing an accident sequence of the serious accident in the event tree of the probability safety analysis report by adopting a deep learning algorithm; the accident sequence comprises a plurality of head events, and the head event time diagnosis is carried out by adopting a deep learning algorithm;
and S4, automatically generating a serious accident integration program input card according to the diagnosis result of the step S3, writing the information of the diagnosis result into the input card, and calculating by the serious accident integration program to obtain the future development trend of the serious accident.
2. The method for backtracking the progress of the severe accident of nuclear power plant according to claim 1, wherein in the step S1, the deep learning algorithm uses a long-short term memory network algorithm in a recurrent neural network, the long-short term memory network algorithm is good at processing time series data, and the input data is historical data of a plurality of key instruments of the nuclear power plant.
3. The method for backtracking the progress of the severe accident of nuclear power plants according to claim 1, wherein the probabilistic safety analysis report includes an originating event analysis and classification; for probabilistic safety analysis reporting of power operating conditions, the originating event categories include, but are not limited to, reactor coolant loss, loss of hot-traps, loss of feedwater, loss of external power, feedwater line breach, steam generator heat transfer tube rupture, steam line rupture plus steam generator heat transfer tube rupture.
4. The method for backtracking the progress of the severe accident of the nuclear power plant according to claim 1, wherein in the probabilistic safety analysis report, an accident sequence analysis is performed for each type of the initial events, so as to determine that the nuclear power plant generates the event tree through a model of automatic response and artificial response after the initial events occur.
5. The method for backtracking the progress of the severe accident in the nuclear power plant according to claim 1, wherein in the step S3, each event tree reported by the probabilistic safety analysis comprises a plurality of accident sequences, wherein the accident sequences comprise accident sequences with successful mitigation and accident sequences causing core damage, and each accident sequence represents the progress of the severe accident.
6. The method for backtracking the progress of a severe accident in a nuclear power plant according to claim 1, wherein the category of the topic event includes but is not limited to required safety functions, investment of systems, occurrence of basic events or operator's actions.
7. The method for backtracking progression of severe accident in nuclear power plants according to claim 1, wherein said heading event is a nuclear power plant system response including, but not limited to, the start of a safety injection system pump, an operator performed action.
8. The method for backtracking the progress of the severe accident of the nuclear power plant according to any one of claims 1 to 7, wherein in the step S3, the deep learning algorithm adopts a long-short term memory network algorithm in a recurrent neural network to diagnose the system response of the nuclear power plant in the progress of the severe accident and determine the accident sequence of the severe accident in the event tree reported by the probabilistic safety analysis.
9. The method for backtracking the progress of the severe accident of nuclear power plant according to claim 8, wherein in step S3, the method for diagnosing the header event time is as follows: calculating a delay operation time data set of each topic event according with the accident sequence characteristics by using a serious accident integrated analysis program by referring to the accident sequence of the diagnosed serious accident in the event tree of the probability safety analysis report; dividing the delay operation time data set of each question head event into a training set and a testing set, and adopting a long-short term memory network algorithm in a recurrent neural network to diagnose the delay operation time of each question head event; and summarizing the delay running time of each head event together to obtain the head event time diagnosis in the serious accident process of the accident sequence.
10. The method for backtracking the progress of the serious accident in nuclear power plant according to claim 9, wherein in step S4, the integrated analysis program of the serious accident includes but is not limited to MAAP developed by Fauske & Associates, MELCOR developed by Sandia national laboratory, and ASTEC developed by IRSN in france and GRS in germany.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110947643.7A CN113837535A (en) | 2021-08-18 | 2021-08-18 | Method for backtracking serious accident process of nuclear power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110947643.7A CN113837535A (en) | 2021-08-18 | 2021-08-18 | Method for backtracking serious accident process of nuclear power plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113837535A true CN113837535A (en) | 2021-12-24 |
Family
ID=78960714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110947643.7A Pending CN113837535A (en) | 2021-08-18 | 2021-08-18 | Method for backtracking serious accident process of nuclear power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837535A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103399820A (en) * | 2013-08-21 | 2013-11-20 | 中国科学院合肥物质科学研究院 | Fault diagnosis system and fault diagnosis method based on sequence and consequence analysis of event tree |
| CN104915768A (en) * | 2015-06-02 | 2015-09-16 | 中科华核电技术研究院有限公司 | Method and system for diagnosing and responding and supporting nuclear power plant severe accident |
| CN107548497A (en) * | 2015-03-10 | 2018-01-05 | 医科达有限公司 | Adapted treatments management system with Workflow Management engine |
| CN110348969A (en) * | 2019-07-16 | 2019-10-18 | 哈尔滨工程大学 | Taxi based on deep learning and big data analysis seeks objective policy recommendation method |
| US20210042634A1 (en) * | 2019-08-07 | 2021-02-11 | Saudi Arabian Oil Company | Representation learning in massive petroleum network systems |
| US20210042633A1 (en) * | 2019-08-07 | 2021-02-11 | Saudi Arabian Oil Company | Aggregation functions for nodes in ontological frameworks in representation learning for massive petroleum network systems |
-
2021
- 2021-08-18 CN CN202110947643.7A patent/CN113837535A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103399820A (en) * | 2013-08-21 | 2013-11-20 | 中国科学院合肥物质科学研究院 | Fault diagnosis system and fault diagnosis method based on sequence and consequence analysis of event tree |
| CN107548497A (en) * | 2015-03-10 | 2018-01-05 | 医科达有限公司 | Adapted treatments management system with Workflow Management engine |
| CN104915768A (en) * | 2015-06-02 | 2015-09-16 | 中科华核电技术研究院有限公司 | Method and system for diagnosing and responding and supporting nuclear power plant severe accident |
| CN110348969A (en) * | 2019-07-16 | 2019-10-18 | 哈尔滨工程大学 | Taxi based on deep learning and big data analysis seeks objective policy recommendation method |
| US20210042634A1 (en) * | 2019-08-07 | 2021-02-11 | Saudi Arabian Oil Company | Representation learning in massive petroleum network systems |
| US20210042633A1 (en) * | 2019-08-07 | 2021-02-11 | Saudi Arabian Oil Company | Aggregation functions for nodes in ontological frameworks in representation learning for massive petroleum network systems |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shen et al. | A methodology for collection and analysis of human error data based on a cognitive model: IDA | |
| Kang et al. | Concept of an intelligent operator support system for initial emergency responses in nuclear power plants | |
| Kim et al. | SACADA and HuREX part 2: The use of SACADA and HuREX data to estimate human error probabilities | |
| CN113837535A (en) | Method for backtracking serious accident process of nuclear power plant | |
| CN115564247A (en) | Intelligent identification and decision-making method and system for nuclear power plant accidents | |
| Park et al. | System and component anomaly detection using lstm-vae | |
| Choi et al. | A study for Unsafe Act classification under crew interaction during procedure-driven operation | |
| Solberg et al. | Situation awareness in outage work–A study of events occurring in US nuclear power plants between 2016 and 2020 | |
| Lew et al. | Computerized operator support system for nuclear power plant hybrid main control room | |
| Burgazzi | Comparative assessment of passive and active systems for the development of advanced reactors | |
| Park et al. | An experimental analysis on the CNS simulator comparing human performance between operators and students | |
| Yang et al. | Analysis of errors of commission for a CE type plant with the advanced control room in the full power condition | |
| Jung et al. | A framework of HRA data collection in nuclear power plants | |
| Kim et al. | Estimating Human Error Probabilities in Off-normal Situations from Full-Scope Simulator Data | |
| Kim et al. | Estimating recovery failure probabilities in off-normal situations from full-scope simulator data | |
| Lee et al. | Analysis of fukushima accident in resilience engineering perspective using the FRAM (Functional Resonance Analysis Method) | |
| JPS62170994A (en) | Errors decision unit | |
| Heo et al. | Characterization of Recovery Human Action Mechanisms in Nuclear Power Plants | |
| Kim et al. | Consistency check algorithm for validation and re-diagnosis to improve the accuracy of abnormality diagnosis in nuclear power plants | |
| Kim et al. | Validation and Re-diagnosis Using Consistency Check Algorithm to Improve Accuracy of Abnormality Diagnosis | |
| Laumann et al. | A study on how time pressure and information load affects operators performance in accident scenarios | |
| Yu et al. | Level 1 Probabilistic Safety Analysis (PSA) of TNPP Units 3 and 4 | |
| Choi et al. | The manipulation of time-varying dynamic variables using the rule modification method and performance-index in NPP accident diagnostic expert systems | |
| Oh et al. | Remaining Trip Time Prediction Using Light Gradient Boosting Machine in Nuclear Power Plants | |
| Ruiz-Sánchez et al. | Application of the ATHEANA methodology for the HRA of a PSA scenario for a BWR nuclear power plant |
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 |