CN114462735A - Intelligent pushing method for quality defect report of nuclear power plant - Google Patents

Intelligent pushing method for quality defect report of nuclear power plant Download PDF

Info

Publication number
CN114462735A
CN114462735A CN202011240380.8A CN202011240380A CN114462735A CN 114462735 A CN114462735 A CN 114462735A CN 202011240380 A CN202011240380 A CN 202011240380A CN 114462735 A CN114462735 A CN 114462735A
Authority
CN
China
Prior art keywords
score
equipment
qdr
code
field
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.)
Granted
Application number
CN202011240380.8A
Other languages
Chinese (zh)
Other versions
CN114462735B (en
Inventor
张冀兰
杨逗
杨加东
张廉
汤奔
刘华
吴宝华
富会佳
胡文勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CNNC Nuclear Power Operation Management Co Ltd
Original Assignee
CNNC Nuclear Power Operation Management Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by CNNC Nuclear Power Operation Management Co Ltd filed Critical CNNC Nuclear Power Operation Management Co Ltd
Priority to CN202011240380.8A priority Critical patent/CN114462735B/en
Publication of CN114462735A publication Critical patent/CN114462735A/en
Application granted granted Critical
Publication of CN114462735B publication Critical patent/CN114462735B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Operations Research (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The invention discloses an intelligent pushing method for quality defect reports of a nuclear power plant, which comprises the following steps: step 1: preparing data; step 2: matching rules; and step 3: a correction factor; and 4, step 4: and (6) outputting data. The invention has the beneficial effects that: by the method, how to process the defects can be accurately worked out in daily work, and the running safety of the nuclear power plant is further guaranteed. During major repairs, time can be saved and the burden on equipment responsibility engineers reduced-. The method can match the QDR of the nuclear power plant with the related QDR and push the QDR to a filler, so that the filler can quickly know the defects of the same type, required tools and instruments and problems possibly encountered in the defect treatment process, and an optimal treatment method is worked out.

Description

Intelligent pushing method for quality defect report of nuclear power plant
Technical Field
The invention belongs to the field of maintenance of nuclear power plants, and particularly relates to an intelligent pushing method for quality defect reports of a nuclear power plant.
Background
The Quality Defect Report (QDR) of the nuclear power plant is an equipment quality abnormity report aiming at the condition that the quality of unexpected items in the maintenance process does not meet the original design requirements, and corrective measures must be made in time to repair equipment or the quality of the items to enable the quality of the items to meet the design requirements.
At present, when the QDR of the nuclear power plant is filled, a certain working experience of a filler is required, or a person with rich experience is required to guide, so that an optimal processing scheme can be worked out, and the QDR cannot be filled accurately and quickly. Especially during overhaul, the construction period is tight, the task is heavy, and sometimes the QDR filling delay causes other work delay.
Disclosure of Invention
The invention aims to provide an intelligent pushing method for a nuclear power plant quality defect report, which can match the QDR of a nuclear power plant with the related QDR and push the QDR to a reporter, so that the reporter can quickly know the problems possibly encountered in the defect treatment process, required tools and devices and the defect treatment process of the same type in the prior art, and an optimal treatment method is worked out.
The technical scheme of the invention is as follows: an intelligent pushing method for quality defect reports of nuclear power plants comprises the following steps:
step 1: preparing data;
step 2: matching rules;
and 3, step 3: a correction factor;
and 4, step 4: and (6) outputting the data.
The step 1 specifically comprises: past QDR data input: device encoding, QDR topic, device name, defect description, preliminary cause analysis,
the step 2 specifically comprises the following steps:
(1) when the reactor type is a pressurized water reactor, the main form of the equipment code is a set number (number), a system code (letter) and an equipment code (number and letter) matching rule:
1) if the "device code" field is normal, i.e. the code complies with the power plant device code rules, the matching rules are as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except that the first unit number and the middle number (the middle number refers to the NNNNEEEE NNNNNNNNNN, namely the number behind the unit U and the system SSS) are different in the equipment code, the other numbers are the same, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the score of the similarity is normalized, and the highest score wd；
e)wScore of＝wa/wb/wc+wdPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
2) When the 'equipment code' field is abnormal and the 'QDR theme' and the 'defect description' have normal equipment codes, the equipment codes of the 'QDR theme' and the 'defect description' field need to be extracted, and when a plurality of normal equipment codes are contained, all the equipment codes are extracted, and the equipment codes are in a one-to-many relationship, and the matching principle is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same in the equipment code, and the score is wb；
c) Except that the first unit number and the middle number (the middle number refers to the NNNNEEEE NNNNNNNNNN, namely the number behind the unit U and the system SSS) are different in the equipment code, the other numbers are the same, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the score of the similarity is normalized, and the highest score is obtainedScore value wd；
e)wScore of＝MAX(wa，wb，wc)+wdPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
3) When the equipment coding field is abnormal and no equipment coding meeting the regulation is available in the QDR theme and the defect description, the fields of the QDR theme, the equipment name and the preliminary reason analysis are learned according to the semantic similarity, and the fields higher than w are pushed through normalization processingLimiting the scoreThe data of (1).
(2) When the reactor type is a pressurized water reactor, the main form of the equipment code is a system code (letter) + "-" + equipment position number (letter, number, - + "-" + type code (letter), and the matching rule is as follows:
1) if the equipment code field is normal, namely the code conforms to the power plant equipment code rule, the matching rule is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the equipment position number, the equipment codes are all the same, and the score is wb；
c) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wc；
d)wScore of＝wa/wb+wcPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
2) When the 'equipment code' field is abnormal and the 'QDR theme' and the 'defect description' have normal equipment codes, the equipment codes of the 'QDR theme' and the 'defect description' field need to be extracted, and when a plurality of normal equipment codes are contained, all the equipment codes are extracted, and the equipment codes are in a one-to-many relationship, and the matching principle is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the equipment position number, the equipment codes are all the same, and the score is wb；
c) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wc；
d)wScore of＝MAX(wa，wb)+wcPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
3) When the 'equipment code' field is abnormal and no equipment code meeting the regulation is available in the 'QDR theme' and the 'defect description', the 'QDR theme', 'equipment name' and 'preliminary cause analysis' field are learned according to the semantic similarity, and here, the field is required to be normalized and pushed to be higher than wLimiting the scoreThe data of (1).
(3) When the heap type is a heavy water heap, the main form of the equipment code is a unit number (number) + "-" + system code (number) + "-" + equipment code, and the matching principle is as follows:
1) if the equipment code field is normal, namely the code conforms to the power plant equipment code rule, the matching rule is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except for the first unit number in the device code, if-SSSSS-EE (for example, U-SSSSS-EE-QQQ, i.e., after unit U-SSSSS-EE, i.e., "-" + system code + "-" + english letter (possibly one, two or three), and after english letter, if "-" is terminated) is the same, the other is different, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wd；
e)wScore of＝wa/wb/wc+wdPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
2) When the 'equipment code' field is abnormal and the 'QDR theme' and the 'defect description' have normal equipment codes, the equipment codes of the 'QDR theme' and the 'defect description' field need to be extracted, and when a plurality of normal equipment codes are contained, all the equipment codes are extracted, and the equipment codes are in a one-to-many relationship, and the matching principle is as follows:
a) the device codes are all identical (same device), with a score of wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except for the first unit number in the device code, if-SSSSS-EE (for example, U-SSSSS-EE-QQQ, i.e., after unit U-SSSSS-EE, i.e., "-" + system code + "-" + english letter (possibly one, two or three), and after english letter, if "-" is terminated) is the same, the other is different, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wd；
e)wScore of＝MAX(wa，wb，wc)+wdPush only wScore ofAt wLimiting the scoreAnd the data of the above scores are recorded,
3) when the 'equipment code' field is abnormal and no equipment code meeting the regulation is available in the 'QDR theme' and the 'defect description', the 'QDR theme', 'equipment name' and 'preliminary cause analysis' field are learned according to the semantic similarity, and here, the field is required to be normalized and pushed to be higher than wLimiting the scoreThe data of (1).
The step 3 specifically comprises:
the output QDR can be sorted from high to low according to the scores, if the scores of the two QDRs are the same, the QDR is judged according to fields of 'QC verification opinion' and 'equipment responsibility engineer closing opinion', and if the fields contain NCR (NCR transfer), QDR (QDR transfer) and worksheet transfer, the score of the QDR is additionally increased by wWeight scoresThe total score is: w is aTotal score＝wScore of+wWeight scores。
The step 4 specifically comprises:
the pushed QDR display fields are: QDR number, QDR theme, device code, device name, status.
The invention has the beneficial effects that: by the method, how to process the defects can be accurately worked out in daily work, and the running safety of the nuclear power plant is further guaranteed. During the overhaul period, the time can be saved, and the burden of equipment responsibility engineers is relieved.
Detailed Description
The present invention will be described in further detail with reference to specific examples.
An intelligent pushing method for quality defect reports of nuclear power plants comprises the following steps:
step 1: data preparation
The method specifically comprises the following steps: past QDR data input: device coding, QDR topic, device name, defect description, preliminary cause analysis.
Step 2: matching rules
(1) When the reactor type is a pressurized water reactor, the main form of the equipment code is a set number (number), a system code (letter) and an equipment code (number and letter) matching rule:
1) if the "equipment code" field is normal, the code conforms to the power plant equipment code rule. The matching rule is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except that the first unit number and the middle number (the middle number refers to the NNNNEEEE NNNNNNNNNN, namely the number behind the unit U and the system SSS) are different in the equipment code, the other numbers are the same, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wd；
e)wScore of＝wa/wb/wc+wdPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
2) When the device code field is abnormal and there is a normal device code in the QDR topic and the defect description, the device code of the QDR topic and the defect description field needs to be extracted. When the code contains a plurality of normal equipment codes, all the codes are extracted. Here, the relationship is one-to-many, and the matching principle is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except that the first unit number and the middle number (the middle number refers to the NNNNEEEE NNNNNNNNNN, namely the number behind the unit U and the system SSS) are different in the equipment code, the other numbers are the same, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wd；
e)wScore of＝MAX(wa，wb，wc)+wdPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
3) When the equipment coding field is abnormal and no equipment coding meeting the regulation is available in the QDR theme and the defect description, the fields of the QDR theme, the equipment name and the preliminary reason analysis are learned according to the semantic similarity, and the fields higher than w are pushed through normalization processingLimiting the scoreThe data of (1).
(2) When the reactor type is a pressurized water reactor, the main form of the equipment code is a system code (letter) + "-" + equipment position number (letter, number, - + "-" + type code (letter), and the matching rule is as follows:
1) if the equipment code field is normal, namely the code conforms to the power plant equipment code rule, the matching rule is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the equipment position number, the equipment codes are all the same, and the score is wb；
c) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wc；
d)wScore of＝wa/wb+wcPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
2) When the 'equipment code' field is abnormal and the 'QDR theme' and the 'defect description' have normal equipment codes, the equipment codes of the 'QDR theme' and the 'defect description' field need to be extracted, and when a plurality of normal equipment codes are contained, all the equipment codes are extracted, and the equipment codes are in a one-to-many relationship, and the matching principle is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the equipment position number, the equipment codes are all the same, and the score is wb；
c) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wc；
d)wScore of＝MAX(wa，wb)+wcPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
3) When the 'equipment code' field is abnormal and no equipment code meeting the regulation is available in the 'QDR theme' and the 'defect description', the 'QDR theme', 'equipment name' and 'preliminary cause analysis' field are learned according to the semantic similarity, and here, the field is required to be normalized and pushed to be higher than wLimiting the scoreThe data of (1).
(3) When the heap type is a heavy water heap, the main form of the equipment code is a unit number (number) + "-" + system code (number) + "-" + equipment code, and the matching principle is as follows:
1) if the "equipment code" field is normal, the code conforms to the power plant equipment code rule. The matching rules are as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except for the first unit number in the device code, if-SSSSS-EE (for example, U-SSSSS-EE-QQQ, i.e., after unit U-SSSSS-EE, i.e., "-" + system code + "-" + english letter (possibly one, two or three), and after english letter, if "-" is terminated) is the same, the other is different, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wd；
e)wScore of＝wa/wb/wc+wdPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
2) When the device code field is abnormal and there is a normal device code in the QDR topic and the defect description, the device code of the QDR topic and the defect description field needs to be extracted. When the code contains a plurality of normal equipment codes, all the codes are extracted. Here, the relationship is one-to-many, and the matching principle is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except for the first unit number in the device code, if-SSSSS-EE (for example, U-SSSSS-EE-QQQ, i.e., after unit U-SSSSS-EE, i.e., "-" + system code + "-" + english letter (possibly one, two or three), and after english letter, if "-" is terminated) is the same, the other is different, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score is obtainedwd；
e)wScore of＝MAX(wa，wb，wc)+wdPush only wScore ofAt wLimiting the scoreAnd data scored above.
3) When the 'equipment code' field is abnormal and no equipment code meeting the regulation is available in the 'QDR theme' and the 'defect description', the 'QDR theme', 'equipment name' and 'preliminary cause analysis' field are learned according to the semantic similarity, and here, the field is required to be normalized and pushed to be higher than wLimiting the scoreThe data of (1).
And step 3: correction factor
The output QDR can be sorted from high to low according to the scores, if the scores of the two QDRs are the same, the QDR is judged according to fields of 'QC verification opinion' and 'equipment responsibility engineer closing opinion', and if the fields contain NCR (NCR transfer), QDR (QDR transfer) and worksheet transfer, the score of the QDR is additionally increased by wWeight scoresThe total score is: w is aTotal score＝wScore of+wWeight scores。
And 4, step 4: data output
The pushed QDR display fields are: QDR number, QDR theme, device code, device name, status.

Claims (9)

1. An intelligent pushing method for quality defect reports of nuclear power plants is characterized by comprising the following steps:
step 1: preparing data;
step 2: matching rules;
and step 3: a correction factor;
and 4, step 4: and (6) outputting the data.
2. The intelligent pushing method for the quality defect report of the nuclear power plant according to claim 1, wherein the step 1 specifically comprises: past QDR data input: device coding, QDR topic, device name, defect description, preliminary cause analysis.
3. The intelligent pushing method for quality defect reports of nuclear power plants according to claim 1, wherein the step 2 specifically comprises the following steps:
(1) when the reactor type is a pressurized water reactor, the main form of the equipment code is a set number (number), a system code (letter) and an equipment code (number and letter) matching rule:
1) if the "device code" field is normal, i.e. the code complies with the power plant device code rules, the matching rules are as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except that the first unit number and the middle number (the middle number refers to the NNNNEEEE NNNNNNNNNN, namely the number behind the unit U and the system SSS) are different in the equipment code, the other numbers are the same, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wd；
e)wScore of＝wa/wb/wc+wdPush only wScore ofAt wLimiting the scoreAnd the above-scored data;
2) when the 'equipment code' field is abnormal and the 'QDR theme' and the 'defect description' have normal equipment codes, the equipment codes of the 'QDR theme' and the 'defect description' field need to be extracted, and when a plurality of normal equipment codes are contained, all the equipment codes are extracted, and the equipment codes are in a one-to-many relationship, and the matching principle is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except that the first unit number and the middle number (the middle number refers to the NNNNEEEE NNNNNNNNNN, namely the number behind the unit U and the system SSS) are different in the equipment code, the other numbers are the same, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wd；
e)wScore of＝MAX(wa，wb，wc)+wdPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
3) When the equipment coding field is abnormal and no equipment coding meeting the regulation is available in the QDR theme and the defect description, the fields of the QDR theme, the equipment name and the preliminary reason analysis are learned according to the semantic similarity, and the fields higher than w are pushed through normalization processingLimiting the scoreThe data of (a);
(2) when the reactor type is a pressurized water reactor, the main form of the equipment code is a system code (letter) + "-" + equipment position number (letter, number, - + "-" + type code (letter), and the matching rule is as follows:
1) if the equipment code field is normal, namely the code conforms to the power plant equipment code rule, the matching rule is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the equipment position number, the equipment codes are all the same, and the score is wb；
c) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wc；
d)wScore of＝wa/wb+wcPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
2) When the 'equipment code' field is abnormal and the 'QDR theme' and the 'defect description' have normal equipment codes, the equipment codes of the 'QDR theme' and the 'defect description' field need to be extracted, and when a plurality of normal equipment codes are contained, all the equipment codes are extracted, and the equipment codes are in a one-to-many relationship, and the matching principle is as follows:
a) device codes are all identical (same device), scoresIs wa；
b) Except the equipment position number, the equipment codes are all the same, and the score is wb；
c) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wc；
d)wScore of＝MAX(wa，wb)+wcPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
3) When the 'equipment code' field is abnormal and no equipment code meeting the regulation is available in the 'QDR theme' and the 'defect description', the 'QDR theme', 'equipment name' and 'preliminary cause analysis' field are learned according to the semantic similarity, and here, the field is required to be normalized and pushed to be higher than wLimiting the scoreThe data of (1).
(3) When the heap type is a heavy water heap, the main form of the equipment code is a unit number (number) + "-" + system code (number) + "-" + equipment code, and the matching principle is as follows:
1) if the equipment code field is normal, namely the code conforms to the power plant equipment code rule, the matching rule is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except for the first unit number in the device code, if-SSSSS-EE (for example, U-SSSSS-EE-QQQ, i.e., after unit U-SSSSS-EE, i.e., "-" + system code + "-" + english letter (possibly one, two or three), and after english letter, if "-" is terminated) is the same, the other is different, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wd；
e)wScore of＝wa/wb/wc+wdPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
2) When the 'equipment code' field is abnormal and the 'QDR theme' and the 'defect description' have normal equipment codes, the equipment codes of the 'QDR theme' and the 'defect description' field need to be extracted, and when a plurality of normal equipment codes are contained, all the equipment codes are extracted, and the equipment codes are in a one-to-many relationship, and the matching principle is as follows:
a) the device codes are all identical (same device), and the score is wa；
b) Except the first unit number, all the other units are the same, and the score is wb；
c) Except for the first unit number in the device code, if-SSSSSS-EE (such as U-SSSSSSSS-EE-QQQ, i.e. -SSSSSSSS-EE-behind the unit U, i.e. "-" + system code + "-" + English letter (possibly one, two or three), and digit or- "-behind English letter is terminated) is the same, the other is different, and the score is wc；
d) Other contents of the 'QDR topic' field and 'primary reason analysis' are matched through semantic similarity, the scores of the similarity are normalized, and the highest score wd；
e)wScore of＝MAX(wa，wb，wc)+wdPush only wScore ofAt wLimiting the scoreAnd the above fractional data.
3) When the 'equipment code' field is abnormal and no equipment code meeting the regulation is available in the 'QDR theme' and the 'defect description', the 'QDR theme', 'equipment name' and 'preliminary cause analysis' field are learned according to the semantic similarity, and here, the field is required to be normalized and pushed to be higher than wLimiting the scoreThe data of (1).
4. The intelligent pushing method for quality defect reports of nuclear power plants according to claim 1, wherein the step 3 specifically comprises:
the output QDRs are sorted from high to low according to the scores, if the scores of the two QDRs are the same, the opinions are verified according to QC, and equipment responsibility engineering is carried outThe teacher closes the opinion' field judgment, if the field contains NCR, QDR and worksheet, the score of QDR is additionally increased by wWeight scoresThe total score is: w is aTotal score＝wScore of+wWeight scores。
5. The intelligent pushing method for quality defect reports of nuclear power plants according to claim 1, wherein the step 4 specifically comprises:
the pushed QDR display fields are: QDR number.
6. The intelligent pushing method for quality defect reports of nuclear power plants according to claim 1, wherein the step 4 specifically comprises:
the pushed QDR display fields are: the QDR topic.
7. The intelligent pushing method for quality defect reports of nuclear power plants according to claim 1, wherein the step 4 specifically comprises:
the pushed QDR display fields are: and (5) encoding the equipment.
8. The intelligent pushing method for quality defect reports of nuclear power plants according to claim 1, wherein the step 4 specifically comprises:
the pushed QDR display fields are: the name of the device.
9. The intelligent pushing method for quality defect reports of nuclear power plants according to claim 1, wherein the step 4 specifically comprises:
the pushed QDR display fields are: the device status.
CN202011240380.8A 2020-11-09 2020-11-09 Intelligent pushing method for quality defect report of nuclear power plant Active CN114462735B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011240380.8A CN114462735B (en) 2020-11-09 2020-11-09 Intelligent pushing method for quality defect report of nuclear power plant

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011240380.8A CN114462735B (en) 2020-11-09 2020-11-09 Intelligent pushing method for quality defect report of nuclear power plant

Publications (2)

Publication Number Publication Date
CN114462735A true CN114462735A (en) 2022-05-10
CN114462735B CN114462735B (en) 2024-09-10

Family

ID=81404666

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011240380.8A Active CN114462735B (en) 2020-11-09 2020-11-09 Intelligent pushing method for quality defect report of nuclear power plant

Country Status (1)

Country Link
CN (1) CN114462735B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115098624A (en) * 2022-06-10 2022-09-23 中核核电运行管理有限公司 Accurate matching method for NCR and external event information

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FI905428A0 (en) * 1989-11-02 1990-11-01 Combustion Eng FOERBAETTRAD KONTROLLENHET VID ATOMKRAFTVERK.
WO2000008577A1 (en) * 1998-07-31 2000-02-17 Westinghouse Energy Systems Europe - Wese A method for interrelating safety related documents of a production plant
KR20020030148A (en) * 2000-10-16 2002-04-24 길형보 Parts and product defect handling mathod
AU4391801A (en) * 2001-05-16 2002-11-21 Requisite Technology Inc. Method and apparatus for analyzing the quality of the content of a database
CN108256713A (en) * 2016-12-29 2018-07-06 中核核电运行管理有限公司 Nuclear power plant system measure of supervision based on ERDB
CN109492106A (en) * 2018-11-13 2019-03-19 扬州大学 Text code combined automatic classification method for defect reasons
KR102017162B1 (en) * 2018-12-05 2019-10-14 한국수력원자력 주식회사 Predictive diagnosis method and system of nuclear power plant equipment
CN111898808A (en) * 2020-07-15 2020-11-06 苏州热工研究院有限公司 Nuclear power plant in-service inspection data management and analysis method

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FI905428A0 (en) * 1989-11-02 1990-11-01 Combustion Eng FOERBAETTRAD KONTROLLENHET VID ATOMKRAFTVERK.
WO2000008577A1 (en) * 1998-07-31 2000-02-17 Westinghouse Energy Systems Europe - Wese A method for interrelating safety related documents of a production plant
KR20020030148A (en) * 2000-10-16 2002-04-24 길형보 Parts and product defect handling mathod
AU4391801A (en) * 2001-05-16 2002-11-21 Requisite Technology Inc. Method and apparatus for analyzing the quality of the content of a database
CN108256713A (en) * 2016-12-29 2018-07-06 中核核电运行管理有限公司 Nuclear power plant system measure of supervision based on ERDB
CN109492106A (en) * 2018-11-13 2019-03-19 扬州大学 Text code combined automatic classification method for defect reasons
KR102017162B1 (en) * 2018-12-05 2019-10-14 한국수력원자력 주식회사 Predictive diagnosis method and system of nuclear power plant equipment
CN111898808A (en) * 2020-07-15 2020-11-06 苏州热工研究院有限公司 Nuclear power plant in-service inspection data management and analysis method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115098624A (en) * 2022-06-10 2022-09-23 中核核电运行管理有限公司 Accurate matching method for NCR and external event information
CN115098624B (en) * 2022-06-10 2024-07-19 中核核电运行管理有限公司 NCR and external event information precise matching method

Also Published As

Publication number Publication date
CN114462735B (en) 2024-09-10

Similar Documents

Publication Publication Date Title
CN114462737B (en) Accurate matching method applied to nuclear power plant work order task and operation event report
CN110688389B (en) Cloud management system for defects of secondary equipment of transformer substation
CN114462735A (en) Intelligent pushing method for quality defect report of nuclear power plant
CN111552804B (en) Knowledge graph construction method of power grid fault handling plan
CN112383045B (en) Transient stability out-of-limit probability calculation method and device for new energy power generation uncertainty
CN109358587B (en) Hydroelectric generating set state maintenance decision method and system
CN117314142B (en) Product line process sequence optimization method
US20220277330A1 (en) Method and system for product processing price prediction based on multiple regression model
Rasmuson et al. Common-cause failure analysis in event assessment
CN116150323B (en) Text language data processing method based on artificial intelligence
Malik et al. Performability modelling and decision-making regarding maintenance priorities for power generation system of a typical thermal power plant
CN116151524A (en) Accurate matching method applied to nuclear power plant work order task
CN114077835A (en) Urban power grid dispatching operation ticket generation method
CN104408289B (en) A kind of modified opportunity maintenance method for introducing correction maintenance
CN116957369A (en) Nuclear power plant quality defect report and production non-conforming item accurate matching method
KR102668289B1 (en) Neural network-based piping and instrument diagram indexing method and apparatus
CN115098624B (en) NCR and external event information precise matching method
Musyafa et al. Hazad And Operability Study and Analysis of Safety Integrity Level Case Study: Ammonia Refrigerant Compressor at Petrocemical Plant
Tian et al. Application of Best-Estimate Plus Uncertainty Analysis Method in Nuclear Safety Evaluation
CN116522900A (en) Cost analysis data management system and method
CN116166981A (en) Nuclear power station equipment grading method
CN114661731B (en) Method for automatically updating nuclear power plant functional equipment group data
CN107341603A (en) Multi-source transmission line of electricity account based on character match corresponds to capacity checking device and method
CN109241606A (en) Emergency maneuvre Situated design method and system
CN116932690A (en) Accurate matching method applied to production non-conforming items of 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
GR01 Patent grant
GR01 Patent grant