CN115271263A - Power equipment defect early warning method, system and medium based on improved association rule - Google Patents
Power equipment defect early warning method, system and medium based on improved association rule Download PDFInfo
- Publication number
- CN115271263A CN115271263A CN202211177619.0A CN202211177619A CN115271263A CN 115271263 A CN115271263 A CN 115271263A CN 202211177619 A CN202211177619 A CN 202211177619A CN 115271263 A CN115271263 A CN 115271263A
- Authority
- CN
- China
- Prior art keywords
- item set
- equipment
- power equipment
- association rule
- item
- 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
Links
- 230000007547 defect Effects 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 26
- 238000005065 mining Methods 0.000 claims abstract description 26
- 238000012216 screening Methods 0.000 claims abstract description 16
- 230000001364 causal effect Effects 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims description 26
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000013138 pruning Methods 0.000 claims description 5
- 230000002779 inactivation Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 description 10
- 238000007726 management method Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 238000009795 derivation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000004299 exfoliation Methods 0.000 description 1
- 238000011985 exploratory data analysis Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000012795 verification Methods 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the field of power equipment defect monitoring and early warning, and discloses a power equipment defect early warning method, a system and a medium based on an improved association rule, wherein the method comprises the following steps: acquiring and exploring each dimension data; screening out the power equipment with the defects, and constructing a multi-dimensional prediction index to form an index system; converting each dimension prediction index of the index system into each dimension equipment prediction label to form an equipment label item set predicted by the association rule model; an association rule algorithm is improved, the causal relationship of each dimension event of the power equipment is deduced through an equipment label item set, a mode mining tree is introduced to construct a frequent item set, the sequence of the occurrence time of each dimension event of the power equipment is introduced, and an association rule model is reconstructed; and predicting the defects of the power equipment to be predicted by using the association rule model. The invention solves the technical problems that the existing early warning prediction method is easy to generate a large number of candidate items and the algorithm execution efficiency is low.
Description
Technical Field
The invention belongs to the field of power equipment defect monitoring and early warning, and particularly relates to a power equipment defect early warning method, a power equipment defect early warning system and a computer storage medium.
Background
In recent years, with the deep development of the construction of intelligent transport systems, the management level of various equipment defect knowledge is improved to a certain extent, but some defects still exist when the management requirement of power grid equipment intellectualization is met. On one hand, the influence range of the defects is not visually and quickly analyzed, and the technology application for converting the existing defect knowledge into the technology for improving the equipment management level is not available; on the other hand, the data value of the same equipment and the same type of defects is not sufficiently mined due to the lack of standardized treatment and deep correlation analysis of the equipment defect information; meanwhile, there is insufficient means for analyzing familial or commonalization problems that may exist in the defect of the apparatus. Therefore, the management level of the grid equipment defects has yet to be improved as a whole.
According to the latest requirements of intelligent substation construction, the active early warning analysis of the substation main equipment is carried out by the enterprise business experts of each province level of the national grid. The data interconnection of links such as the state of the breaker equipment, the environment, the operation of a power grid and the like is completed by utilizing the current advanced information communication technology, and the full-dimensional collection of comprehensive information of the intelligent substation is realized; the intelligent algorithm model is utilized to complete the efficient processing of the state information of the mass equipment, realize the abnormal active early warning and the intelligent fault decision of the breaker equipment, form the organic fusion of the equipment data stream and the operation and maintenance service stream, and assist the operation and maintenance of the transformer equipment, so as to improve the intelligent management level of the transformer equipment.
On one hand, machine learning algorithms commonly used in the prior art, such as a neural network and a support vector machine, are black box models; the middle process of model prediction is unclear and opaque, and the principle and result of prediction output are difficult to explain and are not easy to be understood by personnel in business departments. In practical application, if problems occur, personnel in a business department are difficult to return to the source and trace the problems, technical personnel are still required to intervene for troubleshooting, and the working efficiency is reduced. Therefore, a clear and definite early warning prediction method which is easy to understand and explain is needed to predict the defects of the power equipment, improve the working efficiency and improve the intelligent management level of the equipment.
On the other hand, the conventional association rule algorithm Apriori, that is, a shopping basket analysis method, takes a set of commodities purchased at one time as a shopping basket, and is in a combined form without considering the sequence of the commodities in time of purchase. The traditional association rule algorithm uses a frequent K-1 item set to construct a candidate K item set, and the frequent K item set is generated each time; the candidate set is support-counted using data scanning and pattern matching. This will yield a large number of candidate sets, specifically: the n frequent 1 item sets will produce n (n-1)/2 candidate 2 item sets, i.e., 100 frequent 1 item sets will produce 4950 candidate 2 item sets, and 150 frequent 1 item sets will produce 11175 candidate 2 item sets, thereby occupying a large amount of computing memory space. In addition, original shopping basket data needs to be scanned for multiple times, and if the length of the longest item set is n, the original data needs to be scanned for n +1 times; scanning the original data for multiple times will cause the algorithm to execute with low efficiency, and the frequent item set output execution time is long.
Disclosure of Invention
Therefore, on one hand, the embodiment of the invention provides a power equipment defect early warning method based on an improved association rule, which improves the association rule of the traditional big data analysis algorithm and actively predicts the defect occurrence of the power equipment by combining actual business and application scenes, thereby solving the technical problems that the existing early warning prediction method is easy to generate a large number of candidate items and the algorithm execution efficiency is low.
On the other hand, based on the same inventive concept, the embodiment of the invention also provides a power equipment defect early warning system based on the improved association rule.
In still another aspect, an embodiment of the present invention further provides a computer storage medium.
The electric power equipment defect early warning method based on the improved association rule provided by the embodiment of the invention comprises the following steps:
acquiring and exploring dimensional data for predicting the occurrence of the defects of the power equipment;
screening out power equipment with defects according to the acquired and explored dimensional data conditions, and constructing a multi-dimensional prediction index to form an index system containing multi-dimensional data;
converting each dimension prediction index of the index system into each dimension device prediction label by combining the actual data distribution condition and the operation rule of the power device to form a device label item set predicted by the association rule model;
an association rule algorithm is improved, the causal relationship of each dimension event of the power equipment is deduced through the equipment tag item set, a mode mining tree is introduced to construct a frequent item set, the sequence of the occurrence time of each dimension event of the power equipment is introduced, an association rule is deduced, and an association rule model is reconstructed;
and constructing corresponding multi-dimensional prediction indexes for each dimension data of the power equipment to be predicted, converting the multi-dimensional prediction indexes into prediction labels for each dimension equipment, and obtaining an association rule sequence containing the occurrence time sequence of each dimension event of the power equipment to be predicted by using the reconstructed association rule model so as to predict the defects of the power equipment.
In a preferred embodiment, the reconstructed association rule model includes the following stages:
in the event sorting stage, all the electric power equipment with defects are sorted according to the sequence of the occurrence time of the events in the equipment label item set to form a new equipment label item set sequence;
in the item set generation stage, scanning the new equipment label item set sequence for 2 times, counting the occurrence frequency of various events of the power equipment during the first scanning, accumulating equipment label item set sequence data in a strip-by-strip manner according to the occurrence frequency of the events during the second scanning to form a Tree-shaped counting structure, and constructing a PM-Tree mode mining Tree; mining the structure of the Tree according to the constructed PM-Tree mode, and filtering and screening by combining a given minimum support threshold to obtain a frequent item set of a certain item, wherein the frequent item set comprises a frequent 1 item set and a frequent 2 item set, \ 8230;
in the encoding and mapping stage, encoding and mapping conversion is carried out on the generated frequent 1 item set, and corresponding encoding and mapping conversion is carried out on the equipment label item set sequence of each power equipment to obtain an encoding and mapping result;
in the sequence generation stage, a minimum confidence threshold is introduced according to the frequent item set and the coding mapping result, and a frequent sequence is deduced;
and in the maximized sequence stage, pruning the generated frequent n item sets of which the last item is a certain defect event, setting a minimum lifting degree threshold value, and screening a maximized sequence meeting the conditions through the minimum lifting degree threshold value, wherein n is more than or equal to 1 and less than or equal to k.
The electric power equipment defect early warning system based on the improved association rule provided by the embodiment of the invention comprises the following components:
the data acquisition module is used for acquiring and exploring dimensional data for predicting the occurrence of the defects of the power equipment;
the index system construction module screens out the power equipment with defects according to the acquired and explored dimensional data conditions, and performs multi-dimensional prediction index construction to form an index system containing multi-dimensional data;
the equipment label item set building module is used for converting each dimension prediction index of the index system into each dimension equipment prediction label by combining the actual data distribution condition and the operation rule of the power equipment to form an equipment label item set predicted by the association rule model;
the association rule model reconstruction module is used for improving an association rule algorithm, deducing the causal relationship of each dimension event of the power equipment through the equipment tag item set, introducing a mode mining tree to construct a frequent item set, introducing the sequence of the occurrence time of each dimension event of the power equipment, deducing an association rule and reconstructing an association rule model;
and the defect prediction module constructs corresponding multi-dimensional prediction indexes for each dimensional data of the power equipment to be predicted, converts the multi-dimensional prediction indexes into prediction labels for each dimensional equipment, obtains an association rule sequence containing the occurrence time sequence of each dimensional event of the power equipment to be predicted by using the reconstructed association rule model, and predicts the defects of the power equipment.
The computer storage medium provided by the embodiment of the invention stores a computer program executed by a processor, and when the computer program is executed by the processor, the defect early warning method of the power equipment provided by the embodiment of the invention is realized.
Compared with the prior art, the invention has the following advantages and effects:
1. the application scenario of the method is the defect prediction of the electric power equipment, the electric power equipment has certain attributes by combining with an actual service scenario, and then certain events occur, so that certain defects occur. The specific attribute of the equipment and the occurrence of a specific event are reasons in chronological order, so that the occurrence of a certain type of defect is a result and is in a form of arrangement. The method fully considers the point in algorithm use, improves the traditional association rule algorithm, introduces the time sequence of event occurrence, fully considers the sequence and the causal relationship of the event occurrence time, performs rule derivation, forms a rule prediction result, and effectively warns the problem of the electric power equipment with potential defect occurrence.
2. The invention is improved based on the association rule algorithm, the intermediate process is popular and easy to understand, the result output principle is clear and clear, and the explanation is easy. The improved association rule algorithm records the support degree count of the candidate item through the PM-Tree mode mining Tree, and a large number of candidate items cannot be generated. All frequent item sets can be deduced by scanning shopping basket data for 2 times; the process of deriving a frequent item set outputs all the frequent item sets that contain a certain item at a time.
3. In a traditional association rule algorithm, namely a shopping basket analysis method, commodities of a shopping basket are all actual commodities, but external information such as the placing position of the actual commodities, a generator and the like can also influence whether the commodities are purchased. The invention takes the external information as 'virtual commodity' to be added into the shopping basket and input into the improved association rule algorithm; specifically, the invention introduces external information such as the name of a transformer substation to which the power circuit breaker belongs, a manufacturer and the like into an algorithm model, and predicts the surrounding environment of the transformer substation and the quality of equipment produced by the manufacturer, thereby influencing whether the equipment has defects or not.
Drawings
FIG. 1 is a schematic flow chart of a power circuit breaker fault warning in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a PM-Tree pattern mining Tree constructed in an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the embodiments of the present invention are not limited thereto.
Example 1
The electric power circuit breaker defect early warning takes all circuit breakers of substations governed by State grid provincial maintenance companies as objects, evaluates the operating state of the circuit breakers by utilizing data information of online monitoring, operating conditions, maintenance detection, manufacturing installation, operating environment and the like of the circuit breakers acquired by a production command center, gives out operation, maintenance strategies according to evaluation results, establishes capabilities of abnormal multi-dimensional monitoring and early warning, equipment state lean evaluation, equipment defect active prediction, equipment fault intelligent diagnosis, equipment strategy active difference management, equipment life cycle portrait and the like, systematically and deeply supports circuit breaker state maintenance services, improves the equipment intelligent operation and maintenance management and control level, improves the work effect, and provides accumulated experiences of subsequent comprehensive exploration of equipment lean management, promotion of equipment management transformation and the like.
The method for early warning the defect of the power circuit breaker based on the improved association rule provided by the embodiment takes the power circuit breaker as an example for explanation, and the method mainly comprises the following steps:
s1, acquiring and exploring dimensional data for predicting the defect occurrence of the power circuit breaker equipment.
The dimensional data comprises equipment attribute information, equipment historical defect information, equipment operation information, equipment weather information, equipment operation information and equipment current defect information. After the data of each dimension is obtained, the quality of the data is subjected to preliminary exploratory analysis, the integrity, the uniqueness, the consistency, the missing value and the abnormal value of the data are checked, and the usability of the data is judged.
The method comprises the steps of collecting and predicting dimensional data of the defects of the power circuit breaker equipment by combining multidimensional influence factors of the defects of the power circuit breaker equipment, wherein the data source is mainly a national power grid PMS2.0 service system, and the data source specifically comprises an equipment basic information table, an equipment operation recording table, an equipment tripping recording table, an equipment alarm information table, an equipment maintenance recording table, an equipment test recording table, an equipment defect recording table, an equipment operation voltage and current table and an equipment operation environment recording table.
The step of exploring the acquired data specifically comprises the following steps:
data integrity: whether the number of the circuit breakers in the data table is the same as the number of the circuit breakers recorded by the provincial side maintenance company or not;
data uniqueness: whether the primary key field of each dimension service table of the equipment is unique or not;
data consistency: whether the service tables of all dimensions of the equipment can be normally associated and matched or not;
data missing value: important field missing rate of each dimension service table of the equipment;
data outlier: and whether the voltage, current, temperature and humidity data of the equipment operation have abnormal values or not.
And S2, constructing a prediction index to form an index system.
And (2) screening out the power circuit breaker equipment with defects according to the data conditions of all dimensions actually obtained and explored in the step (S1), and constructing a multi-dimensional prediction index to form an index system containing multi-dimensional data for predicting the defects of the power circuit breaker equipment. The constructed index system is shown as table one, wherein the index types of the index system comprise a type, a floating point type and an integer type.
And S3, constructing an equipment prediction label to form an equipment label item set predicted by the model, namely the shopping basket.
And (3) converting each dimension prediction index in the index system constructed in the step (S2) into each dimension device prediction label by utilizing a data optimal clustering method and combining the actual data distribution condition and the service rule of the operation of the power circuit breaker device, and forming a device label item set (namely a shopping basket of the device) predicted by the association rule model, wherein the device label item set is shown in a table II. Wherein, each dimension equipment label includes: the device comprises a device attribute label, a device history defect label, a device operation label, a device weather label and a device operation label.
That is, this step converts all events that occur in chronological order by a certain device into a set of tag items; the set of device tag items (shopping basket) formed is, for example, as follows:
#1 set of high switchgear label entries for main transformer:
{ company A, SF6 gas, 5-10 years of delivery, 220KV,3150A, few defects, 1 defect, 2-3 alarms, 1 overhaul, normal temperature operation, high humidity operation, light load operation, two types of defects, sound abnormity }
And S4, improving an association rule algorithm, deducing a causal relationship of each dimension event of the power equipment through the equipment tag item set, introducing a PM-Tree (Pattern Mining Tree) to construct a frequent item set, introducing the sequence of the occurrence time of each dimension event of the power equipment, deducing an association rule, and reconstructing an association rule model.
In the step, the traditional association rule algorithm is modified to predict the defects of the power equipment. On one hand, the occurrence of various events and the occurrence of defects of the power equipment in the power equipment are considered, the events have a sequence in time and cause-effect relationship, and the occurrence time of the events in all dimensions of the power equipment is introduced into an association rule model; the intrinsic factors such as the property of the power equipment and the extrinsic factors such as the area to which the power equipment belongs, a patrol and overhaul unit and the like can be considered, and the property of the power equipment comprises a manufacturer, a rated voltage, a rated current and an inactivation medium. On the other hand, the problems that the number of candidate items generated by the traditional association rule algorithm is large, the number of times of scanning original shopping basket data is large, more calculation and storage resources are occupied, the execution efficiency is low, the output of a prediction result is slow and the like are considered. Based on the above two considerations, in this embodiment, the updated association rule model is reconstructed, the power device information is simplified, and part of the simplified data of the tag item set of the power device is taken as a derivation demonstration of an improved algorithm, as shown in table three (taking a power circuit breaker as an example).
Reconstructing the updated association rule model comprises 5 stages:
stage 1: event ordering stage
Grouping the IDs of the power circuit breaker devices, and sequencing according to the sequence of event occurrence time generated by device attribute information, device historical defect information, device operation information, device weather information, device operation information and device current defect information. Events occurring at the same time may be arranged in parallel.
The occurrence time of various information events of the power circuit breaker equipment exists. The device attribute information includes: the manufacturers, the arc extinguishing medium, the rated voltage and the rated current are all the self-carried attribute information of the equipment when the equipment leaves a factory, so that the equipment attribute information events are arranged in the front during sequencing; wherein the calculated deadline for the commissioning age is the end of the last month. And recording the historical defect information event of the equipment as the last defect occurrence time of the equipment, wherein if only 1 defect occurrence time, the information event can be ignored. And recording the equipment operation information event as the last time of each operation event. The weather information event and the operation information event of the equipment can be recorded as a certain period of time before the power circuit breaker equipment has defects, and the temperature, the humidity, the voltage and the current can be monitored. And recording the current defect information event of the equipment as the time when the current defect occurs.
For all the power circuit breaker devices with defects, according to the sequence of the occurrence time of events in the device label item set (namely, shopping basket), the sequences are ordered from first to last to form a new device label item set sequence, as shown in table four.
Stage 2: item set generation phase
Modifying a mode of generating a frequent item set by a traditional association rule Apriori algorithm, scanning the new equipment tag item set sequence for 2 times, and only counting the occurrence frequency of various events of the power equipment during the first scanning; accumulating the equipment tag item set sequence data one by one according to the number of the occurrence times of the event during the second scanning to form a Tree-shaped counting structure, and constructing a PM-Tree mode mining Tree; and mining the structure of the Tree according to the constructed PM-Tree mode, and filtering and screening by combining a given minimum support threshold to obtain all frequent item sets of a certain item.
Therefore, in the embodiment, the frequent item set can be obtained only by scanning the device label item set sequence for 2 times, and the computing resources and the storage resources are saved. The device tag item set sequence data herein specifically refers to a set of various events that each occur with a power circuit breaker device that has a defect. The frequent item set includes: a frequent 1 item set, a frequent 2 item set, \8230, a frequent k item set; several sets represent several elements in a collection.
Counting the occurrence frequency of the events of the power equipment during the first scanning, wherein the events with a large occurrence frequency are placed in front when a pattern mining tree is constructed; and during the second scanning, sequencing according to the occurrence frequency of the events, and accumulating one by one. In other words, in the process of constructing the pattern mining tree, events occurring in each power device are sorted according to the occurrence times and then accumulated, so that the events occurring in the front are overlapped as much as possible.
In the process of outputting the frequent item set, the frequent item set is generated from the bottom end to the top end of the pattern mining tree, and all frequent K item sets containing a certain item, namely the frequent (1, 2, \8230;, K) item sets of the certain item, are output each time. The process of outputting the frequent item set is specifically as follows:
the threshold value of the given minimum support degree is 40%, and the calculation formula of the support degree is as follows:
wherein: x represents an item set X, Y represents an item set Y, S (X, Y) represents the support of the item set X and the item set Y,
indicating the number of device tag item sets that contain both item set X and item set Y, and N indicating the number of all device tag item sets.
(1) Scanning the equipment tag item set sequence data for the 1 st time to obtain a candidate 1 item set count, wherein the candidate 1 item set count is shown in a table five; and screening out a set of frequent 1 items through a minimum support threshold value of 3> =7 × 40% =2.8, as shown in table six.
The frequent 1 item set can be found during the first scanning, and other frequent item sets except the frequent 1 item set can be obtained only after the pattern mining tree is built.
(2) In order to construct the simplest PM-Tree pattern mining Tree, the device tag item set sequence data is arranged in descending order according to the item set counting number, as shown in the seventh table, item sets which do not meet the minimum support degree threshold are filtered, and only frequent item sets are reserved.
For a power circuit breaker device, the order of the number of support counts for the frequent 1-item set may be: the operation is carried out for 2-3 times, such as heavy load operation, falling off, operation for more than 10 years, over-current operation, SF6 gas generation, and high-temperature operation.
(3) And scanning the equipment tag item set sequence data for the 2 nd time, constructing a PM-Tree pattern mining Tree, and accumulating and overlapping the power circuit breaker equipment tag item set sequence data after sorting and screening frequent items row by row, as shown in FIG. 2.
(4) Scanning the constructed PM-Tree mode mining Tree, and outputting all frequent item sets containing a certain item one by one according to the support degree from small to large (namely from the bottom end to the top end of the PM-Tree); at this point, the original device tag item set sequence data is no longer needed.
For the item "overhaul 2-3 times", there are 3 branch paths:
"heavy load operation", "shedding", "over-current operation", "SF6 gas", "multiple defect occurrence" (1);
the method comprises the following steps of (1) carrying out heavy-load operation, shedding and operation for more than 10 years;
"more than 10 years of shipment", "SF6 gas" (1);
{ "heavy load operation": 2}, { "shed": 2}, { "SF6 gas": 2};
{ "more than 10 years of operation": 2}, { "multiple defects occur": 1}, { "overcurrent operation": 1};
the minimum support threshold value is not met, and the frequent item set output of the item '2-3 times of overhaul' is not included.
For the term "high temperature operation", there are 3 branch paths:
the method comprises the following steps of (1) heavy load operation, shedding, overcurrent operation and multiple defects (1);
"heavy load operation", "shedding", "operation for more than 10 years" (1);
the method comprises the following steps of (1) heavy-load operation "," shedding "," operation for more than 10 years ", and" over-current operation ";
{ "heavy load operation": 3}, { "shed": 3} { "more than 10 years of operation": 2};
{ "overcurrent operation": 2, and { 'multiple defects occur {' 1};
outputting a frequent item set containing 'high-temperature operation' items:
2 items are set { "heavy load operation", "high temperature operation": 3}, { "shedding", "high temperature operation": 3};
3 item set: { "heavy-load operation", "shedding", "high-temperature operation": 3}:3.
for the item "defect occurred multiple times", there are 2 branch paths:
"heavy load operation", "shedding", "over-current operation", "SF6 gas" (2);
the method comprises the following steps of (1) heavy load operation, shedding and overcurrent operation;
{ "heavy load operation": 3}, { "shed": 3} { "overcurrent operation": 3}, { "SF6 gas": 2};
the output contains: the frequent item set of the item of 'multiple defects occur':
2, item set: { "heavy load operation", "occurrence of defects a plurality of times": 3}, { "shedding", "multiple defects occurred": 3};
{ "SF6 gas", "defect occurred a plurality of times": 3}
3 item set: { "heavy-load operation", "shedding", "multiple defects occur": 3}
{ "heavy duty operation", "SF6 gas", "occurrence of defects a plurality of times": 3}
{ "exfoliation", "SF6 gas", "occurrence of defects a plurality of times": 3};
4 item set: { "heavy-duty operation", "shedding", "SF6 gas", "occurrence of defects multiple times": 3}.
For the term "SF6 gas", there are 2 bifurcation paths:
the method comprises the following steps of (1) heavy load operation, shedding and overcurrent operation (2);
"more than 10 years of shipment" (1);
{ "heavy load operation": 2}, { "shed": 2}, { "overcurrent operation": 2}, { "more than 10 years of operation": 1}
The support degree threshold value is not met, and frequent item set output containing 'SF 6 gas' items is not provided.
For the item "over-current operation", there are 2 branch paths:
"heavy running", "shedding" (3);
"heavy load operation", "shedding", "operation for more than 10 years" (1);
{ "heavy load operation": 4}, { "shed": 4} { "more than 10 years of operation": 1};
the output contains: the frequent item set of the 'over-current operation' item:
2 items are set to be 'heavy-load operation', 'over-current operation': 4}, { "drop", "over-current operation": 4};
3 sets { "heavy load operation", "drop", "overcurrent operation": 4}.
For the item "more than 10 years of operation", there are 1 branch path in total:
"heavy running", "shedding" (3);
{ "heavy load operation": 3}, { "shed": 3};
the output contains: the frequent item set of items "more than 10 years of operation":
2, item set: { "heavy load operation", "more than 10 years of operation": 3}, { "fall off", "put into operation for more than 10 years": 3};
3, item set: { "heavy load operation", "shedding", "operation for more than 10 years": 3}.
For the item "drop", there are 1 branch path:
"heavy duty operation" (6);
{ "heavy load operation": 6};
the output contains: frequent item set of "shed" items:
2, item set: { "heavy-load operation", "drop": 6}.
Stage 3: code mapping phase
And performing encoding mapping conversion on the generated frequent 1 item set, as shown in table eight, and performing corresponding encoding mapping conversion on the device tag item set sequence of each device, as shown in table nine, to obtain an encoding mapping result.
And 4, a stage: sequence generation phase
And introducing a minimum confidence threshold value according to the deduced frequent item set and the coding mapping result, and deducing a frequent sequence. The core point of this embodiment is the early warning of device defects, so the last event is that some defect occurs in the device.
In a preferred embodiment, after the frequent item set is found through the minimum support threshold, a minimum confidence threshold is introduced according to the deduced frequent item set and the coding mapping result, and is used for judging the credibility of the association rule result and deducing a frequent sequence. Wherein, the confidence coefficient calculation formula is:
wherein: x represents an item set X as a leading item of the association rule, Y represents an item set Y as a trailing item of the association rule,
representing item set X derives a confidence level for item set Y,
representing the number of device tag item sets that contain both item set X and item set Y,
representing the number of device tag item sets that contain item set X.
The calculation formula of the lifting degree is as follows:
wherein: x represents an item set X as a leading item of the association rule, Y represents an item set Y as a trailing item of the association rule,
representing the set of items X deduces the degree of lifting of the set of items Y,
representing the confidence with which item set X derives item set Y,
representing the number of device tag item sets that contain both item set X and item set Y,
representing the number of device tag item sets that contain item set X,
representing the number of device tag item sets that contain item set Y.
The association rules derived are:
The operation is carried out for more than 10 years, namely falling off, high-temperature operation, and heavy-load operation;
SF6 gas, multiple defects, overcurrent operation and the like fall off;
2-3 times of maintenance are carried out, and the falling is avoided.
2 item derived defects
Heavy-load operation, over-current operation, falling off, heavy-load operation and high-temperature operation, falling off;
the operation of heavy load, SF6 gas drop, the operation of heavy load, more than 10 years of operation drop;
the operation of heavy load, the defect is more than dropped for many times, the operation of heavy load, the overhaul is more than dropped for 2-3 times;
the defects occur for many times, and the over-current operation, the over-current operation and the high-temperature operation fall off;
SF6 gas falls off after overcurrent operation, and SF6 gas falls off after multiple defects.
3 item derived defects
Heavy load operation, overcurrent operation and high temperature operation are carried out, and the operation is more than falling off;
heavy load operation, overcurrent operation, and falling-off of multiple defects;
heavy load operation, over-current operation, SF6 gas falling.
4 item derived defects
Heavy load operation and overcurrent operation, multiple defects occur, and SF6 gas drops.
Stage 5: maximum sequence stage
Pruning the generated frequent n item set sequences of which the last item is a certain defect event, setting a minimum lifting degree threshold value, and screening the maximized sequences meeting the conditions through the minimum lifting degree threshold value, wherein n is more than or equal to 1 and less than or equal to k.
Derived association rules, there is a containment relationship between the antecedents, such as:
{ 'heavy load operation', 'overcurrent operation' }
{ "heavy load operation", "over-current operation", "occurrence of multiple defects", "SF6 gas" }
{ "occurrence of multiple defects", "SF6 gas" }
{ "heavy load operation", "over-current operation", "occurrence of multiple defects", "SF6 gas" }
In order to obtain the association rule which is the simplest and has the largest coverage range, the deduced association rule result is pruned, and the subset rule is subtracted to obtain the largest association rule sequence. In this embodiment, the method specifically includes:
SF6 gas causes multiple defects, heavy-load operation and over-current operation to fall off
And S5, predicting the defects of the power circuit breaker equipment by using the reconstructed association rule model.
And constructing corresponding multi-dimensional prediction indexes for each dimensional data of the power equipment to be predicted, converting the multi-dimensional prediction indexes into prediction labels of each dimensional equipment, acquiring an association rule sequence containing the occurrence time sequence of each dimensional event of the power equipment by using the reconstructed association rule model, and predicting the time and the type of future defects of the equipment.
In this embodiment, the same statistical aperture as in step S3 is used to generate information and labels of all to-be-predicted power devices, and all to-be-predicted devices are subjected to aperture statistics to construct an index in the same manner from 5 aspects of device attribute information, device historical defect information, device operation information, device weather information, and device operation information, and are converted into event labels (the to-be-predicted power circuit breaker device does not have currently-occurring defect information, which is to-be-predicted content). If a certain device is found to satisfy the maximum sequence prefix of the association rule derived in step S4, or satisfy the subsequence with the minimum support degree, the minimum confidence degree, and the minimum promotion degree, it is considered that the device will have a defect of the association rule postamble in the future.
And S6, carrying out actual verification on the prediction result, and adjusting the iterative optimization label and the association rule model.
In the embodiment, the model prediction result is actually verified, the model accuracy is evaluated, and the iterative optimization model is gradually adjusted; the optimization direction comprises the following steps:
(1) Label generation rules and critical point threshold division;
(2) And setting the minimum support degree, the minimum confidence degree and the minimum promotion degree threshold of the association rule model.
Example 2
Based on the same inventive concept as embodiment 1, the present embodiment provides an electric power equipment defect early warning system based on an improved association rule, which includes the following modules:
the data acquisition module is used for acquiring and exploring dimensional data for predicting the occurrence of the defects of the power equipment;
the index system construction module screens out the power equipment with defects according to the acquired and explored dimensional data conditions, and performs multi-dimensional prediction index construction to form an index system containing multi-dimensional data;
the equipment label item set building module is used for converting each dimension prediction index of the index system into each dimension equipment prediction label by combining the actual data distribution condition and the operation rule of the power equipment to form an equipment label item set predicted by the association rule model;
the association rule model reconstruction module is used for improving an association rule algorithm, deducing the causal relationship of each dimension event of the power equipment through the equipment tag item set, introducing a mode mining tree to construct a frequent item set, introducing the sequence of the occurrence time of each dimension event of the power equipment, deducing an association rule and reconstructing an association rule model;
and the defect prediction module constructs corresponding multi-dimensional prediction indexes for each dimensional data of the power equipment to be predicted, converts the multi-dimensional prediction indexes into prediction labels for each dimensional equipment, obtains an association rule sequence containing the occurrence time sequence of each dimensional event of the power equipment to be predicted by using the reconstructed association rule model, and predicts the defects of the power equipment.
In this embodiment, the reconstructed association rule model includes the following 5 stages:
in the event sorting stage, all the electric power equipment with defects are sorted according to the sequence of the occurrence time of the events in the equipment label item set to form a new equipment label item set sequence;
in the item set generation stage, the new equipment label item set sequence is scanned for 2 times, the times of various events of the power equipment are counted during the first scanning, the equipment label item set sequence data are accumulated piece by piece according to the number of the event occurrence times during the second scanning, a Tree-shaped counting structure is formed, and a PM-Tree mode mining Tree is constructed; mining the structure of the Tree according to the constructed PM-Tree mode, and filtering and screening by combining a given minimum support threshold to obtain a frequent item set of a certain item, wherein the frequent item set comprises a frequent 1 item set, a frequent 2 item set, \ 8230and a frequent k item set;
in the encoding and mapping stage, encoding and mapping conversion is carried out on the generated frequent 1 item set, and corresponding encoding and mapping conversion is carried out on the equipment label item set sequence of each electric power equipment to obtain an encoding and mapping result;
in the sequence generation stage, a minimum confidence threshold is introduced according to the frequent item set and the coding mapping result, and a frequent sequence is deduced;
and in the maximized sequence stage, pruning the generated frequent n item sets of which the last item is a certain defect event, setting a minimum lifting degree threshold value, and screening a maximized sequence meeting the conditions through the minimum lifting degree threshold value, wherein n is more than or equal to 1 and less than or equal to k.
For a detailed description of the above stages, refer to example 1.
The power device in the defect warning system of the power device of this embodiment may also be a power circuit breaker device, and specific implementation technical means of each module are referred to in embodiment 1, which are not described herein again.
Meanwhile, the present embodiment also provides a computer storage medium, on which a computer program executed by a processor is stored, and when the computer program is executed by the processor, the steps of the power equipment defect warning method according to embodiment 1 are implemented.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
A storage medium is a machine-readable medium and may include any medium that can store or transfer information. Examples of a machine-readable medium include an electronic circuit, a semiconductor memory device, a ROM, a flash memory, an Erasable ROM (EROM), a floppy disk, a CD-ROM, an optical disk, a hard disk, an optical fiber medium, a Radio Frequency (RF) link, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments noted in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed at the same time.
Aspects of the present invention are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. A power equipment defect early warning method based on an improved association rule is characterized by comprising the following steps:
acquiring and exploring dimensional data for predicting the occurrence of the defects of the power equipment;
screening out power equipment with defects according to the obtained and explored conditions of the data of each dimension, and constructing a multi-dimensional prediction index to form an index system containing the data of each dimension;
converting each dimension prediction index of the index system into each dimension device prediction label by combining the actual data distribution condition and the operation rule of the power device to form a device label item set predicted by the association rule model;
an association rule algorithm is improved, the causal relationship of each dimension event of the power equipment is deduced through the equipment tag item set, a mode mining tree is introduced to construct a frequent item set, the sequence of the occurrence time of each dimension event of the power equipment is introduced, an association rule is deduced, and an association rule model is reconstructed;
and constructing corresponding multi-dimensional prediction indexes for each dimension data of the power equipment to be predicted, converting the multi-dimensional prediction indexes into prediction labels for each dimension equipment, and obtaining an association rule sequence containing the occurrence time sequence of each dimension event of the power equipment to be predicted by using the reconstructed association rule model so as to predict the defects of the power equipment.
2. The electric power equipment defect early warning method according to claim 1, wherein the reconstructed association rule model comprises the following stages:
in the event sorting stage, all the electric power equipment with defects are sorted according to the sequence of the occurrence time of the events in the equipment label item set to form a new equipment label item set sequence;
in the item set generation stage, scanning the new equipment label item set sequence for 2 times, counting the occurrence frequency of various events of the power equipment during the first scanning, accumulating equipment label item set sequence data in a strip-by-strip manner according to the occurrence frequency of the events during the second scanning to form a Tree-shaped counting structure, and constructing a PM-Tree mode mining Tree; mining the structure of the Tree according to the constructed PM-Tree mode, and filtering and screening by combining a given minimum support threshold to obtain a frequent item set of a certain item, wherein the frequent item set comprises a frequent 1 item set and a frequent 2 item set, \ 8230;
in the encoding and mapping stage, encoding and mapping conversion is carried out on the generated frequent 1 item set, and corresponding encoding and mapping conversion is carried out on the equipment label item set sequence of each electric power equipment to obtain an encoding and mapping result;
in the sequence generation stage, a minimum confidence threshold is introduced according to a frequent item set and a coding mapping result, and a frequent sequence is deduced;
and in the maximized sequence stage, pruning the generated frequent n item sets of which the last item is a certain defect event, setting a minimum lifting degree threshold value, and screening a maximized sequence meeting the conditions through the minimum lifting degree threshold value, wherein n is more than or equal to 1 and less than or equal to k.
3. The electric power equipment defect early warning method according to claim 2, wherein the calculation formula of the support degree is as follows:
wherein: x represents an item set X, Y represents an item set Y, S (X, Y) represents the support of the item set X and the item set Y,
indicating the number of device tag item sets that contain both item set X and item set Y, and N indicating the number of all device tag item sets.
4. The power equipment defect early warning method according to claim 2, wherein a minimum confidence threshold is used for judging the credibility of the result of the association rule, and the confidence is calculated by the following formula:
wherein: x represents an item set X as a leading item of the association rule, Y represents an item set Y as a trailing item of the association rule,
representing the confidence with which item set X derives item set Y,
representing the number of device tag item sets that contain both item set X and item set Y,
representing the number of device tag item sets that contain item set X.
5. The electric power equipment defect early warning method according to claim 2, wherein the calculation formula of the lifting degree is as follows:
wherein: x represents an item set X as a leading item of the association rule, Y represents an item set Y as a trailing item of the association rule,
representing the set of items X deduces the degree of lifting of the set of items Y,
representing item set X derives a confidence level for item set Y,
representing the number of device tag item sets that contain both item set X and item set Y,
representing the number of device tag item sets that contain item set X,
representing the number of device tag item sets that contain item set Y.
6. The electric power equipment defect early warning method according to claim 1, wherein when the association rule model is reconstructed, the internal factors and external factors of the electric power equipment are also considered, wherein the internal factors comprise manufacturers, rated voltages, rated currents and inactivation media, and the external factors comprise areas to which the electric power equipment belongs and patrol and overhaul units.
7. The electric power equipment defect early warning method according to claim 1, wherein the dimensional data comprises an equipment basic information table, an equipment operation record table, an equipment trip record table, an equipment alarm information table, an equipment overhaul record table, an equipment test record table, an equipment defect record table, an equipment operation voltage and current table and an equipment operation environment record table.
8. An electric power equipment defect early warning system based on improved association rules is characterized by comprising:
the data acquisition module is used for acquiring and exploring dimensional data for predicting the occurrence of the defects of the power equipment;
the index system construction module screens out the power equipment with defects according to the acquired and explored data conditions of each dimension, and performs multi-dimensional prediction index construction to form an index system containing multi-dimensional data;
the equipment label item set building module is used for converting each dimension prediction index of the index system into each dimension equipment prediction label by combining the actual data distribution condition and the operation rule of the power equipment to form an equipment label item set predicted by the association rule model;
the association rule model reconstruction module is used for improving an association rule algorithm, deducing the causal relationship of each dimension event of the power equipment through the equipment tag item set, introducing a mode mining tree to construct a frequent item set, introducing the sequence of the occurrence time of each dimension event of the power equipment, deducing an association rule and reconstructing an association rule model;
and the defect prediction module constructs corresponding multi-dimensional prediction indexes for each dimensional data of the power equipment to be predicted, converts the multi-dimensional prediction indexes into prediction labels for each dimensional equipment, obtains an association rule sequence containing the occurrence time sequence of each dimensional event of the power equipment to be predicted by using the reconstructed association rule model, and predicts the defects of the power equipment.
9. The power equipment defect pre-warning system of claim 8, wherein the reconstructed association rule model comprises the following stages:
in the event sorting stage, all the electric power equipment with defects are sorted according to the sequence of the occurrence time of the events in the equipment label item set to form a new equipment label item set sequence;
in the item set generation stage, the new equipment label item set sequence is scanned for 2 times, the times of various events of the power equipment are counted during the first scanning, the equipment label item set sequence data are accumulated piece by piece according to the number of the event occurrence times during the second scanning, a Tree-shaped counting structure is formed, and a PM-Tree mode mining Tree is constructed; mining the structure of the Tree according to the constructed PM-Tree mode, and filtering and screening by combining a given minimum support threshold to obtain a frequent item set of a certain item, wherein the frequent item set comprises a frequent 1 item set and a frequent 2 item set, \ 8230;
in the encoding and mapping stage, encoding and mapping conversion is carried out on the generated frequent 1 item set, and corresponding encoding and mapping conversion is carried out on the equipment label item set sequence of each electric power equipment to obtain an encoding and mapping result;
in the sequence generation stage, a minimum confidence threshold is introduced according to the frequent item set and the coding mapping result, and a frequent sequence is deduced;
and in the maximized sequence stage, pruning the generated frequent n item sets of which the last item is a certain defect event, setting a minimum lifting degree threshold value, and screening a maximized sequence meeting the conditions through the minimum lifting degree threshold value, wherein n is more than or equal to 1 and less than or equal to k.
10. A computer storage medium storing a computer program for execution by a processor, wherein the computer program, when executed by the processor, implements the electric power equipment defect warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211177619.0A CN115271263B (en) | 2022-09-27 | 2022-09-27 | Power equipment defect early warning method, system and medium based on improved association rule |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211177619.0A CN115271263B (en) | 2022-09-27 | 2022-09-27 | Power equipment defect early warning method, system and medium based on improved association rule |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115271263A true CN115271263A (en) | 2022-11-01 |
| CN115271263B CN115271263B (en) | 2022-12-27 |
Family
ID=83757151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211177619.0A Active CN115271263B (en) | 2022-09-27 | 2022-09-27 | Power equipment defect early warning method, system and medium based on improved association rule |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115271263B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115713533A (en) * | 2023-01-10 | 2023-02-24 | 佰聆数据股份有限公司 | Method and device for detecting surface defects of electrical equipment based on machine vision |
| CN116069986A (en) * | 2023-04-04 | 2023-05-05 | 山东登远信息科技有限公司 | Alarm signal association rule analysis method and system |
| CN116451792A (en) * | 2023-06-14 | 2023-07-18 | 北京理想信息科技有限公司 | Method, system, device and storage medium for solving large-scale fault prediction problem |
| CN117131110A (en) * | 2023-10-27 | 2023-11-28 | 南京中鑫智电科技有限公司 | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180306476A1 (en) * | 2017-04-19 | 2018-10-25 | International Business Machines Corporation | Anomaly detection in a refrigeration condensor system |
| CN112183656A (en) * | 2020-10-12 | 2021-01-05 | 国网新疆电力有限公司 | SCADA data frequent item set mining method in power grid fault |
| WO2021016978A1 (en) * | 2019-08-01 | 2021-02-04 | 中国科学院深圳先进技术研究院 | Telecommunication network alarm prediction method and system |
| CN112580678A (en) * | 2019-09-29 | 2021-03-30 | 中兴通讯股份有限公司 | Method and device for constructing cloud network alarm root relation tree model |
| CN114020581A (en) * | 2021-11-23 | 2022-02-08 | 浪潮通信信息系统有限公司 | Alarm correlation method based on topological optimization FP-Growth algorithm |
| WO2022121083A1 (en) * | 2020-12-09 | 2022-06-16 | 南威软件股份有限公司 | Enterprise risk early warning method based on association analysis fp-tree algorithm |
-
2022
- 2022-09-27 CN CN202211177619.0A patent/CN115271263B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180306476A1 (en) * | 2017-04-19 | 2018-10-25 | International Business Machines Corporation | Anomaly detection in a refrigeration condensor system |
| WO2021016978A1 (en) * | 2019-08-01 | 2021-02-04 | 中国科学院深圳先进技术研究院 | Telecommunication network alarm prediction method and system |
| CN112580678A (en) * | 2019-09-29 | 2021-03-30 | 中兴通讯股份有限公司 | Method and device for constructing cloud network alarm root relation tree model |
| CN112183656A (en) * | 2020-10-12 | 2021-01-05 | 国网新疆电力有限公司 | SCADA data frequent item set mining method in power grid fault |
| WO2022121083A1 (en) * | 2020-12-09 | 2022-06-16 | 南威软件股份有限公司 | Enterprise risk early warning method based on association analysis fp-tree algorithm |
| CN114020581A (en) * | 2021-11-23 | 2022-02-08 | 浪潮通信信息系统有限公司 | Alarm correlation method based on topological optimization FP-Growth algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 肖永立等: "一种基于 FP-growth 算法的变电站二次设备缺陷分析方法", 《电测与仪表》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115713533A (en) * | 2023-01-10 | 2023-02-24 | 佰聆数据股份有限公司 | Method and device for detecting surface defects of electrical equipment based on machine vision |
| CN116069986A (en) * | 2023-04-04 | 2023-05-05 | 山东登远信息科技有限公司 | Alarm signal association rule analysis method and system |
| CN116451792A (en) * | 2023-06-14 | 2023-07-18 | 北京理想信息科技有限公司 | Method, system, device and storage medium for solving large-scale fault prediction problem |
| CN116451792B (en) * | 2023-06-14 | 2023-08-29 | 北京理想信息科技有限公司 | Method, system, device and storage medium for solving large-scale fault prediction problem |
| CN117131110A (en) * | 2023-10-27 | 2023-11-28 | 南京中鑫智电科技有限公司 | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis |
| CN117131110B (en) * | 2023-10-27 | 2024-01-23 | 南京中鑫智电科技有限公司 | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115271263B (en) | 2022-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115271263B (en) | Power equipment defect early warning method, system and medium based on improved association rule | |
| CN108376982B (en) | Load phase sequence identification method and device | |
| CN106019084B (en) | Medium-voltage power distribution network disconnection fault diagnosis method based on power distribution and utilization data correlation | |
| CN110675070B (en) | Intelligent microgrid device criticality analysis method | |
| CN110222889B (en) | Power distribution network feeder automation terminal configuration method based on multiple intelligent algorithms | |
| Jia et al. | Defect prediction of relay protection systems based on LSSVM-BNDT | |
| CN115730749B (en) | Power dispatching risk early warning method and device based on fusion power data | |
| CN116500385B (en) | Power transmission network monitoring and checking method, device, equipment and medium | |
| CN117610214B (en) | Intelligent power distribution network wiring planning method based on dynamic geographic features | |
| CN117374978B (en) | Grid-connected scheduling management method and system constructed by combining knowledge graph | |
| Anders et al. | A comprehensive study of outage rates of air blast breakers | |
| Nie et al. | Research on AHP-based Multi-factor Medium Voltage Distribution Network Line Risk Quantitative Assessment Method | |
| CN114743703A (en) | Reliability analysis method, device, equipment and storage medium for nuclear power station unit | |
| CN114168662A (en) | Power distribution network problem combing and analyzing method and system based on multiple data sources | |
| CN113609746A (en) | Power distribution network planning method based on Monte Carlo tree search and reinforcement learning algorithm | |
| Fan et al. | On backup battery data in base stations of mobile networks: Measurement, analysis, and optimization | |
| CN111292200A (en) | Distribution network typical fault studying and judging method based on operation data | |
| Dehbozorgi et al. | Association rule mining application to diagnose smart distribution power system outage root cause | |
| CN117791597B (en) | Power distribution network fault self-healing method and system based on machine learning | |
| Mahapatra et al. | Grid utility asset vulnerability assessment (GUAVA) software tool | |
| Zhao et al. | Data mining and analysis for defects of secondary equipment in power grid | |
| Gao et al. | A highly fault-tolerant distribution network fault diagnosis method based on KMP algorithm and rough set | |
| Oliveira et al. | Data-driven methodology to predict distribution lines failure location | |
| JP6719309B2 (en) | Operation support device and operation support method | |
| He et al. | Method of Equipment Fault Diagnosis Based on Frequent Itemsets Mining |
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 |