CN114881419A - Automatic flow analysis method for nuclear power evaluation data - Google Patents

Automatic flow analysis method for nuclear power evaluation data Download PDF

Info

Publication number
CN114881419A
CN114881419A CN202210371581.4A CN202210371581A CN114881419A CN 114881419 A CN114881419 A CN 114881419A CN 202210371581 A CN202210371581 A CN 202210371581A CN 114881419 A CN114881419 A CN 114881419A
Authority
CN
China
Prior art keywords
nuclear power
evaluation data
flow analysis
power evaluation
analysis method
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
Application number
CN202210371581.4A
Other languages
Chinese (zh)
Inventor
徐小照
孙振
郭俊
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.)
Research Institute of Nuclear Power Operation
Original Assignee
Research Institute of Nuclear Power Operation
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 Research Institute of Nuclear Power Operation filed Critical Research Institute of Nuclear Power Operation
Priority to CN202210371581.4A priority Critical patent/CN114881419A/en
Publication of CN114881419A publication Critical patent/CN114881419A/en
Pending legal-status Critical Current

Links

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
    • G06Q10/0639—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
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Monitoring And Testing Of Nuclear Reactors (AREA)

Abstract

The invention provides an automatic flow analysis method for nuclear power evaluation data, which comprises the following steps: step S1: dividing attributes, and analyzing the driving relation between the two AFIs according to a decision tree flow; step S2: dividing the obtained sample set according to the attributes, and judging the relation between AFI-B and AFI-A by taking AFI-A as a reference; step S3: selecting an optimized attribute, selecting a partition attribute by taking information gain as a criterion, determining a root node, an internal node or a leaf node of the decision tree, and further finishing the drawing of the decision tree; step S4: and designing model basic information. The analysis method provided by the invention is faster and more efficient, can avoid the subjectivity of people, and builds the automatic flow analysis method of the nuclear power evaluation data by means of an informatization means and a decision tree model so as to supplement the defects of the existing manual flow analysis method.

Description

Automatic flow analysis method for nuclear power evaluation data
Technical Field
The invention relates to the technical field of analysis and evaluation of nuclear power simultaneous assessment data, in particular to an automatic flow analysis method of nuclear power assessment data.
Background
Since the united states initiated the peer evaluation in the nuclear power field in 1979, the nuclear power evaluation has become an effective means for pursuing excellence and continuously improving the nuclear power operation management level in the global nuclear power industry. With the continuous development of nuclear power evaluation activities, how to effectively utilize data generated by evaluation and how to really implement the evaluation as a tool for improving the performance of a nuclear power plant are problems which are long-term addressed by nuclear power organizations at home and abroad and are fundamental requirements of power companies and nuclear power plants.
At present, a flow Analysis (Stream Analysis) method is adopted internationally to find out deep assessment reasons, and the operation mode is a method for finding out deep management reasons of a nuclear power plant by establishing a manual Analysis group, analyzing nuclear power assessment data, drawing an enabling relationship and a mutual relation among the nuclear power assessment data.
The method for analyzing the artificial flow cannot automatically generate a driving relationship graph among evaluation data quickly and effectively to identify driving factors, and in addition, the method needs to rely on human subjectivity in the analysis process, such as division of driving relationships and decision of high-order leaders when different opinions of participants are met. Therefore, two short plates exist in the practical application process of the method, and one is that the labor and the time are consumed; secondly, human subjectivity participates in the analysis process too much, and uncertainty may exist.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a nuclear power evaluation data automatic flow analysis method which is quicker and more efficient and can avoid the subjectivity of people.
In order to achieve the above purpose, the invention provides the following technical scheme:
a nuclear power evaluation data automatic flow analysis method comprises the following steps:
step S1: dividing attributes, and analyzing the driving relation between the two AFIs according to a decision tree flow;
step S2: dividing the obtained sample set according to the attributes, and judging the relation between AFI-B and AFI-A by taking AFI-A as a reference;
step S3: selecting an optimized attribute, selecting a partition attribute by taking information gain as a criterion, determining a root node, an internal node or a leaf node of the decision tree, and further finishing the drawing of the decision tree;
step S4: and designing model basic information.
In step S1, the method includes four attributes including a domain association degree, a domain dimension, a keyword association degree, and a keyword dimension.
The domain association degree comprises four nodes, the domain dimension comprises three nodes, and the keyword association degree comprises three nodes; the keyword dimension includes three nodes.
In step S2, the a/B relationship includes three types: the A drive B, B drives A or A has no drive relationship with B.
The step S3 specifically includes:
step S31: calculating the information entropy of each node according to the proportion of different results in the sample;
step S32: calculating information gain according to the information entropy of the nodes;
step S33: and drawing a decision tree model.
By the step S31
Figure BDA0003588787110000021
And calculating the information entropy of each node.
The step S4 specifically includes:
step S41: dividing according to three aspects of high, low and no correlation of common keywords in nuclear power evaluation, and dividing three types of high, low and no correlation of the relationship among the keywords;
step S42: designing the dimension basic information of the field, and sequencing the dimension relation of the sub-fields in the evaluation criterion;
step S43: and designing the dimensionality of the keywords of the nuclear power evaluation, and sequencing the dimensionality relation of the keywords commonly seen in the evaluation data.
Compared with the prior art, the automatic flow analysis method for nuclear power evaluation data provided by the invention has the following beneficial effects:
the automatic flow analysis method for the nuclear power evaluation data is quicker and more efficient, can avoid the subjectivity of people, and is built by means of an informatization means and a decision tree model so as to supplement the defects of the existing manual flow analysis method. In addition, automatic flow analysis is carried out on the nuclear power evaluation data through the decision tree model, the mutual driving relation of the nuclear power evaluation data can be analyzed through one key of a tool, core driving factors are automatically identified, the analysis efficiency of the evaluation data is greatly improved, and subjective factors caused by a conventional manual analysis method can be avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of an automatic analysis sample set of nuclear power evaluation data provided by an embodiment of the present invention;
fig. 2 is a schematic diagram of root node division based on a domain relevance attribute according to an embodiment of the present invention.
Detailed Description
The following is a more detailed description of the present invention by way of specific embodiments.
As shown in fig. 1 and fig. 2, the present invention provides an automatic flow analysis method for nuclear power evaluation data, which comprises the following steps:
step S1: dividing attributes, and analyzing the driving relation between the two AFIs according to a decision tree flow;
step S2: judging the relation between the AFI-B and the AFI-A by taking the AFI-A as a reference according to a sample set obtained by attribute division;
step S3: selecting an optimized attribute, selecting a partition attribute by taking information gain as a criterion, determining a root node, an internal node or a leaf node of the decision tree, and further finishing the drawing of the decision tree;
step S4: and designing model basic information.
Specifically, the invention mainly designs an automatic analysis mechanism of nuclear power evaluation data based on a decision tree model, and the main technical steps are as follows:
(1) attribute partition selection
The basic element of decision tree model building is partition attribute. According to the flow of evaluation data flow analysis, the scheme assumes that the driving relation between two AFIs (A, B) is analyzed according to a decision tree flow, and four attributes of 'field association degree', 'field dimension', 'keyword association degree' and 'keyword dimension' are designed in the scheme.
Wherein, four nodes of high, middle, low and no are designed according to the field association degree; three nodes of 'high', 'low' and 'same' are designed in the field dimension; three nodes of high, low and no are designed according to the keyword association degree; three nodes of 'high', 'low' and 'same' are designed in the keyword dimension.
(2) Determining a set of examples
The obtained sample set (Y) is divided according to 4 attributes, and the relationship between AFI-B and AFI-A is judged by taking AFI-A as a reference, so that the total number of the samples is 108, and the result is shown in Table 1. Wherein the A/B relationship comprises three types: a → B (A drives B), B → A (B drives A) or A ≠ B (A has no driving relation with B).
TABLE 1
Figure BDA0003588787110000041
Figure BDA0003588787110000051
Figure BDA0003588787110000061
Figure BDA0003588787110000071
Figure BDA0003588787110000081
Figure BDA0003588787110000091
(3) Selection of optimized attributes
After the attribute division and the determination of the sample set are completed, the key of establishing the decision tree model is to select the optimized attribute, select the division attribute by taking the information gain as a criterion, determine the root node (the first optimized attribute), the internal node (the branch node except the root node) or the leaf node (the node without the child node) of the decision tree, and further complete the drawing of the decision tree.
31) Calculation of information entropy
According to the proportion of different results in the sample, the information entropy of each node is calculated by the formula
Figure BDA0003588787110000092
(hereinafter, referred to as formula 1),
the root node contains all the samples in the sample set (Y), where A → B holds
Figure BDA0003588787110000093
B → A takes
Figure BDA0003588787110000094
A ≠ B
Figure BDA0003588787110000095
The information entropy of the root node can be calculated according to the above formula 1 as follows:
Figure BDA0003588787110000096
subsequently, the information gain of each attribute in the current attribute set { domain association degree (LG), keyword association degree (GG), domain dimension (LW), keyword dimension (GW) } is calculated.
For example, the attribute "domain association" has 4 possible values: { high domain association, medium domain association, low domain association, no domain association }. If the attribute is used to divide the sample set, 4 subsets can be obtained, and are respectively recorded as: LG1 (domain association degree is high domain association degree), LG2 (domain association degree is medium domain association degree), LG3 (domain association degree is low domain association degree), and LG4 (domain association degree is no domain association degree).
Subset LG1 contains 27 samples numbered {1, 2, 3, … …, 37}, where A → B holds
Figure BDA0003588787110000097
B → A takes
Figure BDA0003588787110000101
A ≠ B
Figure BDA0003588787110000102
LG2 contains 27 samples numbered {17, 18, 19, … …, 56}, where A → B holds
Figure BDA0003588787110000103
B → A occupation
Figure BDA0003588787110000104
A is not equal to B
Figure BDA0003588787110000105
LG3 contains 27 samples numbered {25, 26, 57, … …, 81}, where A → B holds
Figure BDA0003588787110000106
B → A takes
Figure BDA0003588787110000107
A ≠ B
Figure BDA0003588787110000108
LG4 contains 27 samples numbered {25, 26, 57, … …, 81}, where A → B holds
Figure BDA0003588787110000109
B → A takes
Figure BDA00035887871100001010
A ≠ B
Figure BDA00035887871100001011
The entropy of the information of the 4 internal nodes obtained after the division by the domain association degree can be calculated according to the formula 1 as follows:
Figure BDA00035887871100001012
Figure BDA00035887871100001013
Figure BDA00035887871100001014
Figure BDA00035887871100001015
32) information gain calculation
The principle of the information gain criterion is to judge the optimized attribute by comparing the magnitude of each attribute information gain value, generally speaking, the larger the information gain is, the larger the "purity" obtained by dividing the sample by the attribute is, and the attribute is the optimized attribute.
According to the information entropy of the nodes, calculating the 'information gain' obtained by dividing the sample set D by the attribute a, wherein the calculation formula is
Figure BDA00035887871100001016
(hereinafter, referred to as the formula 2),
where V represents the possible value of the attribute a, i.e. the number of subsets into which the attribute a will divide the sample set D.
The information gain of the attribute "domain association degree" can be calculated according to the above formula 2 as follows:
Figure BDA0003588787110000111
similarly, the information gain for other attributes can be calculated:
Gain(Y,GG)＝0.208；Gain(Y,LW)＝0.197；Gain(Y,GW)＝0.033
obviously, the information gain of the attribute "domain association degree" is the largest, and therefore, the attribute is selected as the partition attribute, that is, the root node of the decision tree, and the decision tree after partitioning is as shown in fig. 1.
33) Rendering of decision tree models
After the attribute 'domain association degree' is divided into root nodes of a decision tree, samples in the sample set (Y) are divided into 4 subsets of 'high domain association degree (LG1),' middle domain association degree (LG2), 'low domain association degree (LG3) and' no domain association degree (LG4), and for the 4 subsets, the following attributes are further divided according to an information gain criterion.
The information entropy calculation result of the value 'non-domain correlation degree' in the attribute 'domain correlation degree' is 0, the smaller the information entropy calculation result is, the higher the purity of the sample in the subset is, and compared with the 'non-domain correlation degree' sample in which A is not equal to B (A and B have no driving relation), it can be known that all samples in the subset are non-correlated, so that the 'non-domain correlation degree' is divided into leaf nodes, and the attribute does not need to be further divided.
Taking "high domain association degree" as an example, the branch node is further attribute-divided, and the node includes 27 samples numbered {1, 2, 3, … …, 37} in a sample set LG1, and the available attribute set is { keyword association degree (GG), domain dimension (LW), keyword dimension (GW) }.
The information gains of the field association degree, the field dimension and the keyword dimension can be calculated as follows:
Gain(LG1，GG)＝0.640；Gain(LG1，LW)＝0.477；Gain(LG1，GW)＝0.033
obviously, the information gain of the attribute "keyword association degree" is the largest, so the "keyword association degree" is selected as the division attribute, i.e., the internal node of the branch.
By analogy, a flow analysis logic diagram is obtained, and a decision tree model generated based on information gain is shown in fig. 2. The degree of association and the dimension information in fig. 2 are shown in table 2.
TABLE 2
Figure BDA0003588787110000121
(4) Design of model base information
The method is mainly divided according to three aspects of high, low and no association of 21 common keywords in nuclear power evaluation, wherein the 21 keywords (actually 20 keywords and 21 keywords 'other' keywords) are divided according to categories of problems found in evaluation of the past, and the relationship among the keywords is divided according to three types of high, low and no association according to the principle.
Then, the dimension basic information of the fields is designed, the invention mainly ranks the dimension relations of 47 sub-fields in the evaluation criterion, the representative field with large dimension coefficient has high dimension, and in the flow analysis decision tree criterion, the high dimension coefficient mostly drives related elements, as shown in table 3.
TABLE 3
Figure BDA0003588787110000131
Figure BDA0003588787110000141
Finally, designing the dimensionality of the keywords of nuclear power evaluation, the invention mainly ranks the dimensionality relations of 20 common keywords (no keyword is 'other', and in the keyword relevance logic, the keywords compared with 'other' are all unrelated and do not form the conclusion of a driving relation) in the evaluation data, and the representative keyword with a large dimensionality coefficient has a high dimensionality. The details are shown in Table 4.
TABLE 4
Figure BDA0003588787110000151
Figure BDA0003588787110000161
The following description takes the automatic analysis of certain nuclear power evaluation data as an example:
firstly, nuclear power evaluation data to be analyzed is classified, the nuclear power evaluation data is divided according to data flow categories (expectation, flow, execution and responsibility), and related fields and keywords are selected.
After the work is finished, nuclear power evaluation data to be analyzed are formed, and the data can be displayed in a classified manner according to different data stream types.
And secondly, realizing an automatic flow analysis function, wherein the model can automatically analyze the mutual driving relationship of the current nuclear power evaluation data according to information such as the field, the keyword, the field association degree and the keyword association degree and according to a decision flow shown in FIG. 2, the automatic analysis is to compare each piece of data with all other pieces of data one by one, determine the driving relationship between the two pieces of data through a decision tree model, and draw an automatic flow analysis relationship graph of the nuclear power evaluation data according to the driving relationship graph.
And finally, extracting an analysis conclusion from an automatic flow analysis result page, wherein the driving factors, the intermediate factors, the symptom factors and the independent factors are automatically identified by a system. The driving factor is the core content of nuclear power evaluation data analysis, and more attention and improvement are required to be paid to the nuclear power plant or the electric power company.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are also within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims (7)

1. A nuclear power evaluation data automatic flow analysis method is characterized by comprising the following steps:
step S1: dividing attributes, and analyzing the driving relation between the two AFIs according to a decision tree flow;
step S2: dividing the obtained sample set according to the attributes, and judging the relation between AFI-B and AFI-A by taking AFI-A as a reference;
step S3: selecting an optimized attribute, selecting a partition attribute by taking information gain as a criterion, determining a root node, an internal node or a leaf node of the decision tree, and further finishing the drawing of the decision tree;
step S4: and designing model basic information.
2. The automatic flow analysis method for nuclear power evaluation data of claim 1, wherein in step S1, the method includes four attributes including domain relevance, domain dimension, keyword relevance, and keyword dimension.
3. The automatic flow analysis method for nuclear power evaluation data according to claim 2, wherein the domain association comprises four nodes, the domain dimension comprises three nodes, and the keyword association comprises three nodes; the keyword dimension includes three nodes.
4. The method for automatic flow analysis of nuclear power evaluation data of claim 1, wherein in step S2, the a/B relationship includes three types: the A drive B, B drives A or A has no drive relationship with B.
5. The automatic flow analysis method for nuclear power evaluation data of claim 1, wherein step S3 specifically includes:
step S31: calculating the information entropy of each node according to the proportion of different results in the sample;
step S32: calculating information gain according to the information entropy of the nodes;
step S33: and drawing a decision tree model.
6. The method for automatic flow analysis of nuclear power evaluation data of claim 5 wherein step S31 is performed by
Figure FDA0003588787100000011
And calculating the information entropy of each node.
7. The automatic flow analysis method for nuclear power evaluation data of claim 1, wherein step S4 specifically includes:
step S41: dividing according to the common keywords in nuclear power evaluation according to three aspects of high, low and no correlation, and dividing the relationship among the keywords into three types of high, low and no correlation;
step S42: designing the dimension basic information of the field, and sequencing the dimension relation of the sub-fields in the evaluation criterion;
step S43: designing the dimensionality of the keywords of nuclear power evaluation, and sequencing the dimensionality relation of the keywords commonly seen in the evaluation data.
CN202210371581.4A 2022-04-11 2022-04-11 Automatic flow analysis method for nuclear power evaluation data Pending CN114881419A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210371581.4A CN114881419A (en) 2022-04-11 2022-04-11 Automatic flow analysis method for nuclear power evaluation data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210371581.4A CN114881419A (en) 2022-04-11 2022-04-11 Automatic flow analysis method for nuclear power evaluation data

Publications (1)

Publication Number Publication Date
CN114881419A true CN114881419A (en) 2022-08-09

Family

ID=82670565

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210371581.4A Pending CN114881419A (en) 2022-04-11 2022-04-11 Automatic flow analysis method for nuclear power evaluation data

Country Status (1)

Country Link
CN (1) CN114881419A (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101257371B1 (en) * 2011-12-23 2013-04-24 한국수력원자력 주식회사 A method for evaluation of operators' diagnosis error for computer-based emergency operating procedures in nuclear power plants and using system thereof
CN105894177A (en) * 2016-03-25 2016-08-24 国家电网公司 Decision-making-tree-algorithm-based analysis and evaluation method for operation risk of power equipment
KR101670235B1 (en) * 2015-08-12 2016-11-09 한국수력원자력 주식회사 Non destructive test analysis system and method of the nuclear power plant
CN106452825A (en) * 2016-07-20 2017-02-22 国网江苏省电力公司南京供电公司 Power distribution and utilization communication network alarm correlation analysis method based on improved decision tree
US20180144258A1 (en) * 2016-11-21 2018-05-24 Nxp Usa, Inc. Network node, integrated circuit, and method for creating and processing information according to an n-ary multi output decision tree
CN110766272A (en) * 2019-09-11 2020-02-07 国网浙江省电力有限公司杭州供电公司 Power business collaborative classification method and system based on ID3 decision tree algorithm
CN111899905A (en) * 2020-08-05 2020-11-06 哈尔滨工程大学 Fault diagnosis method and system based on nuclear power device
WO2021172723A1 (en) * 2020-02-27 2021-09-02 한국수력원자력 주식회사 Method and system for intelligent monitoring of state of nuclear power plant
CN113592111A (en) * 2021-07-30 2021-11-02 上海健康医学院 Intelligent fault processing method and system for nuclear power equipment

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101257371B1 (en) * 2011-12-23 2013-04-24 한국수력원자력 주식회사 A method for evaluation of operators' diagnosis error for computer-based emergency operating procedures in nuclear power plants and using system thereof
KR101670235B1 (en) * 2015-08-12 2016-11-09 한국수력원자력 주식회사 Non destructive test analysis system and method of the nuclear power plant
CN105894177A (en) * 2016-03-25 2016-08-24 国家电网公司 Decision-making-tree-algorithm-based analysis and evaluation method for operation risk of power equipment
CN106452825A (en) * 2016-07-20 2017-02-22 国网江苏省电力公司南京供电公司 Power distribution and utilization communication network alarm correlation analysis method based on improved decision tree
US20180144258A1 (en) * 2016-11-21 2018-05-24 Nxp Usa, Inc. Network node, integrated circuit, and method for creating and processing information according to an n-ary multi output decision tree
CN110766272A (en) * 2019-09-11 2020-02-07 国网浙江省电力有限公司杭州供电公司 Power business collaborative classification method and system based on ID3 decision tree algorithm
WO2021172723A1 (en) * 2020-02-27 2021-09-02 한국수력원자력 주식회사 Method and system for intelligent monitoring of state of nuclear power plant
CN111899905A (en) * 2020-08-05 2020-11-06 哈尔滨工程大学 Fault diagnosis method and system based on nuclear power device
CN113592111A (en) * 2021-07-30 2021-11-02 上海健康医学院 Intelligent fault processing method and system for nuclear power equipment

Similar Documents

Publication Publication Date Title
KR101130524B1 (en) Automatic data perspective generation for a target variable
Schildt et al. A dense network sub-grouping algorithm for co-citation analysis and its implementation in the software tool Sitkis
CN106779219A (en) A kind of electricity demand forecasting method and system
CN111210170A (en) Environment-friendly management and control monitoring and evaluation method based on 90% electricity distribution characteristic index
CN110781174A (en) Feature engineering modeling method and system using pca and feature intersection
CN117093407B (en) Improved S-learner-based flow anomaly cascade root cause analysis method and system
CN114881419A (en) Automatic flow analysis method for nuclear power evaluation data
CN110990907B (en) Feature-resource knowledge-based three-level optimization method for manufacturability of marine diesel engine heavy parts
Sadeghi et al. Relational pattern benchmarking on the knowledge graph link prediction task
CN108897680B (en) Software system operation profile construction method based on SOA
KR101985961B1 (en) Similarity Quantification System of National Research and Development Program and Searching Cooperative Program using same
CN108805742B (en) Method and device for evaluating electric energy substitution potential of user
CN114201635B (en) Case source clue classification method based on multi-view graph data feature learning
CN105678430A (en) Improved user recommendation method based on neighbor project slope one algorithm
CN115905188A (en) Data quality improving method based on knowledge graph
CN106598492B (en) A kind of compression optimization method applied to magnanimity deficiency of data
CN112528038B (en) Method, device and medium for ensuring communication body uniqueness identification based on multilayer graph structure
CN113610629A (en) Method and device for screening client data features from large-scale feature set
CN108062563A (en) A kind of representative sample based on classification equilibrium finds method
CN114547294A (en) Rumor detection method and system based on comprehensive information of propagation process
CN111898666A (en) Random forest algorithm and module population combined data variable selection method
Ye et al. Learning Behavior Characterization with Multi-Feature, Hierarchical Activity Sequences.
Zhang et al. Composite service selection based on dot pattern mining
Zhang et al. Research on Credit Risk Prediction Based on Cart Classification Tree
CN112836926B (en) Enterprise operation condition evaluation method based on electric power big data

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