CN117131110A - Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis - Google Patents
Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis Download PDFInfo
- Publication number
- CN117131110A CN117131110A CN202311406243.0A CN202311406243A CN117131110A CN 117131110 A CN117131110 A CN 117131110A CN 202311406243 A CN202311406243 A CN 202311406243A CN 117131110 A CN117131110 A CN 117131110A
- Authority
- CN
- China
- Prior art keywords
- data
- dielectric loss
- association
- rule
- deviation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012544 monitoring process Methods 0.000 title claims abstract description 45
- 238000010219 correlation analysis Methods 0.000 title claims abstract description 32
- 238000005065 mining Methods 0.000 claims abstract description 14
- 238000012098 association analyses Methods 0.000 claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 13
- 230000008439 repair process Effects 0.000 claims description 12
- 230000001960 triggered effect Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000011835 investigation Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 230000007774 longterm Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 238000004393 prognosis Methods 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 241000764238 Isis Species 0.000 claims 1
- 238000004458 analytical method Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000001364 causal effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24553—Query execution of query operations
-
- 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
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
Abstract
The invention relates to the technical field of dielectric loss monitoring, and discloses a method and a system for monitoring dielectric loss of capacitive equipment based on correlation analysis, wherein the method and the system for monitoring dielectric loss of the capacitive equipment comprise the steps of collecting operation data of the capacitive equipment, and extracting characteristics of the operation data by using a self-encoder model; mining association rules on the extracted features using association analysis; when the association rule is matched, the system generates fault early warning and a corresponding strategy to inform the user. According to the method, the dielectric loss problem of the capacitive equipment can be found in real time through the data characteristics and the correlation analysis extracted from the encoder model, the accuracy and the timeliness of monitoring are ensured, and the equipment fault risk caused by the loss problem is greatly reduced. Potential safety hazards can be found and processed in time through real-time monitoring and early warning, and safety of equipment and operators is ensured.
Description
Technical Field
The invention relates to the technical field of dielectric loss monitoring, in particular to a capacitive equipment dielectric loss monitoring method and system based on correlation analysis.
Background
Capacitive devices are critical components in electrical power systems. These devices may experience increased dielectric loss during long-term operation for various reasons, thereby affecting their performance and lifetime. Therefore, it is important to monitor and pre-warn the dielectric loss of the capacitive device in real time.
Traditional capacitive device dielectric loss monitoring methods rely primarily on physical sensors and periodic manual inspection. Although these methods may provide a certain monitoring function, problems may be difficult to find in time at the early stage of loss, and a large amount of manual intervention is required, which is inefficient.
In recent years, with the development of big data, machine learning and data mining technologies, a data-based capacitive device dielectric loss monitoring method is attracting attention. The association analysis is widely applied to various application scenes, such as market basket analysis, recommendation systems and the like, as a powerful data mining technology. The main purpose of association analysis is to discover frequent patterns in the dataset and to generate association rules. These rules can help us understand the relationships between data and provide support for decisions.
In capacitive device dielectric loss monitoring, correlation analysis can help us find correlation rules between operational data (e.g., voltage, current, temperature, humidity, etc.), thereby finding potential dielectric loss problems in time. For example, when both voltage and temperature exceed a certain threshold, it may mean that the device has dielectric loss problems. Through an automatic association rule mining and early warning system, the operation safety and efficiency of the capacitive equipment can be greatly improved.
However, correlation analysis also presents some challenges. First, the number of association rules can be very large, requiring an efficient method to screen out truly useful rules. Secondly, the association rules only describe the association between data and do not directly infer causal relationships. Furthermore, in order to obtain accurate association rules, a large amount of historical data and efficient computing resources are required.
Extracting data features by using a self-encoder model, converting continuous data into discrete form using a multi-level binning method, using advanced association rule mining algorithms such as Apriori, FP-Growth, etc. The methods and techniques provide strong support for capacitive device dielectric loss monitoring based on correlation analysis.
In a word, the dielectric loss monitoring of the capacitive equipment based on the correlation analysis is a leading edge and challenging research field, and has wide application prospect and great economic value.
Disclosure of Invention
The present invention has been made in view of the above-mentioned problems occurring in the prior art.
Therefore, the invention provides a method and a system for monitoring the dielectric loss of the capacitive equipment based on correlation analysis, which can solve the problems that the traditional method for monitoring the dielectric loss of the capacitive equipment often depends on periodic physical inspection or simple sensor data, and the method is low in efficiency and can miss some initial and inconspicuous loss.
In order to solve the technical problems, the invention provides a capacitive equipment dielectric loss monitoring method based on association analysis, which comprises the following steps:
collecting operation data of the capacitive equipment, and extracting characteristics of the operation data by using a self-encoder model;
mining association rules on the extracted features using association analysis;
when the association rule is matched, the system generates fault early warning and a corresponding strategy to inform the user.
As a preferred embodiment of the method for monitoring dielectric loss of a capacitive device based on correlation analysis, the present invention is characterized in that: the self-encoder model includes, when the acquired operational data of the capacitive device is 24 hours of data recorded once per minute, dividing the data into a plurality of sequences of 1440 data points,
；
wherein T is a subsequence, T is a complete time sequence, the time sequence is divided into n subsequences of length m,scaling the data to between 0 and 1,
；
creating a network structure that processes time series data, the number of input layer neurons being equal to the length of each data series, capturing the time dependence using a recurrent neural network,
；
wherein,as a function of the encoder, H i For the ith subsequence T i Is hidden in T i Representing the ith subsequence;
the original sequence is reconstructed using a decoder,
；
wherein,as a function of the decoder->For the ith subsequence T i A reconstructed version of (a);
inputting the preprocessed data sequence into a model, optimizing a reconstruction error using a mean square error as a loss function,
；
inputting the new time series data into an encoder, the output of the encoder being a compressed representation of the data, capturing key features in the time series, obtaining a hidden representation,
。
as a preferred embodiment of the method for monitoring dielectric loss of a capacitive device based on correlation analysis, the present invention is characterized in that: mining association rules on extracted features using association analysis includes converting continuous hidden representations into discrete forms using multi-level binning, for each hidden representation, taking non-zero features of the hidden representation as a transaction, finding frequent sets of items using priori, for each frequent set of items, generating all possible association rules,
；
wherein,expressed as features in a hidden representation;
for each generated association rule, a degree of support is calculated,
；
wherein,for support, TC represents +.>Is a synthetic operation of (2);
when the support degree of the association rule is larger than or equal to the minimum confidence coefficient threshold value in the system, the association rule meets the confidence coefficient requirement;
for each generated association rule, a confidence level is calculated,
；
wherein,is confidence;
when the confidence coefficient of the associated rule is larger than or equal to the minimum confidence coefficient threshold value in the system, the associated rule meets the confidence coefficient requirement, and the associated rule meeting the requirements of the support coefficient and the confidence coefficient is screened out.
As a preferred embodiment of the method for monitoring dielectric loss of a capacitive device based on correlation analysis, the present invention is characterized in that: the matching to the association rule comprises that the system checks real-time data, retrieves a problem database according to the triggered association rule, automatically invokes a historical optimal processing method in the problem database if the association rule is a known problem in the problem database, and automatically records the triggered rule and the executed operation in an operation log;
when the system detects that the system does not accord with the expected mode, the system automatically marks the abnormality and records the problem database, immediately sends out an alarm, displays the triggered association rule and current data reading through an upper computer, on-site operators read the history similar problems through the system and send out overhaul operation to carry out dry prognosis, provide feedback in the system, record the result of the overhaul operation provided by the system, and continuously learn and optimize the association rule for the system according to the history data and the result of manual intervention.
As a preferred embodiment of the method for monitoring dielectric loss of a capacitive device based on correlation analysis, the present invention is characterized in that: the database of questions includes the information that,
；
wherein D is a problem database,for the ith exception event, +.>Is->Associated withTimestamp (s)/(s)>Is abnormal->Status of->And->Associated recommended solution,/->Is->And (5) associated feedback.
As a preferred embodiment of the method for monitoring dielectric loss of a capacitive device based on correlation analysis, the present invention is characterized in that: the mode which does not meet the expectations comprises the steps that when the system detects that the dielectric loss of the capacitive equipment exceeds a safety loss threshold value in a short time, the system is required to be judged to intervene, whether the internal false alarm of the system exists or not is judged, if the secondary detection system does not report the false alarm, the abnormal node is marked, the abnormal node is recorded in a problem database, an upper computer is used for notifying on-site operators to carry out maintenance and investigation, after the operator investigation is finished, the abnormal node is continuously observed, if the abnormal node continuously shows that the maintenance is higher than the normal loss for more than 24 hours, the system prompts that the equipment has long-term backlog problem, and the manual intervention is prompted to the node;
when the system detects that the capacitive equipment has dielectric loss and no corresponding association rule, the system is required to intervene, whether internal false alarm exists or not is judged, if the secondary detection system does not have false alarm, abnormal nodes are marked, the abnormal nodes are recorded in a problem database, and the abnormal nodes are prompted by an upper computer to perform manual intervention;
when the deviation level between the predicted dielectric loss value and the actual dielectric loss value is C level or S level, the system performs secondary diagnosis, checks whether the input data is abnormal or not and checks whether the model parameters change or not, if the input data is abnormal, the system performs first automatic repair, if the repair fails, prompts on-site operators to check the data and repair the data through an upper computer, if the model parameters are abnormal, the system automatically repairs the model data, if the input data and the model parameters are not abnormal, the system retrains the model, when the abnormal state is eliminated, the system secondarily calculates the deviation level between the predicted dielectric loss value and the actual dielectric loss value, if the deviation level is C level or S level, the dielectric loss of the equipment exceeds the normal range, the system gives a warning and prompts on-site operators to perform manual intervention, and if the deviation level between the secondarily calculated predicted dielectric loss value and the actual loss value is A level or B level, the system records the problem and reenters the normal operation state.
As a preferred embodiment of the method for monitoring dielectric loss of a capacitive device based on correlation analysis, the present invention is characterized in that: the deviation level includes, when the deviationWhen the deviation grade is A;
when the deviation isWhen the deviation grade is B grade;
when the deviation isWhen the deviation grade is C grade;
when the deviation isAnd when the deviation grade is S grade.
Another object of the present invention is to provide a system for monitoring dielectric loss of a capacitive device based on correlation analysis, which greatly improves timeliness of fault early warning by accurately monitoring an operation state of the capacitive device in real time, thereby avoiding huge economic loss caused by fault delay. And secondly, through the deep learning capability of the self-encoder model, the system can automatically extract and learn the operation characteristics of the equipment, so that the monitoring of the equipment is more accurate, and the situations of false alarm and missing report are reduced. In addition, the introduction of the association analysis enables the system to mine potential association rules in the equipment operation data, provides deeper and more detailed analysis results for operators, and helps the operators to better understand the operation states and potential problems of the equipment. Finally, when the system detects an abnormality or a potential risk, the early warning mechanism can be automatically triggered, and a targeted processing suggestion is provided for an operator, so that the efficiency of dealing with emergency is greatly improved.
As a preferred embodiment of the system for monitoring dielectric loss of a capacitive device based on correlation analysis according to the present invention, the system further comprises: the system comprises a data preprocessing module, an association rule generating module, a rule screening module and a service application module;
the data preprocessing module cleans, converts and standardizes the original data so that the original data is suitable for association rule mining;
the association rule generation module is used for generating association rules from the preprocessed data by using an Apriori algorithm;
the rule screening module screens and sorts association rules based on the minimum support and the minimum confidence;
and the service application module applies the screened association rule to the actual service scene.
A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of a method of any one of the capacitive device dielectric loss monitoring methods based on correlation analysis.
A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the steps of a method of any of the correlation analysis based capacitive device dielectric loss monitoring methods.
The invention has the beneficial effects that: the method is based on data characteristics and associated analysis extracted from the encoder model, can find the dielectric loss problem of the capacitive equipment in real time, ensures the accuracy and timeliness of monitoring, and greatly reduces the equipment fault risk caused by the loss problem. Potential safety hazards can be found and processed in time through real-time monitoring and early warning, and safety of equipment and operators is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a schematic diagram of a method and a system for monitoring dielectric loss of a capacitive device based on correlation analysis according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a capacitive device dielectric loss monitoring system based on correlation analysis according to an embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present invention have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides a method and a system for monitoring dielectric loss of a capacitive device based on correlation analysis, including:
s1, collecting operation data of the capacitive equipment, and extracting characteristics of the operation data by using a self-encoder model;
the operational data includes, but is not limited to, voltage, current, temperature, humidity, etc.
The self-encoder model includes, when the acquired operational data of the capacitive device is 24 hours of data recorded once per minute, dividing the data into a plurality of sequences of 1440 data points,
；
wherein T is a subsequence, T is a complete time sequence, the time sequence is divided into n subsequences of length m,scaling the data to between 0 and 1,
；
creating a network structure that processes time series data, the number of input layer neurons being equal to the length of each data series, capturing the time dependence using a recurrent neural network,
；
wherein,as a function of the encoder, H i For the ith subsequence T i Is hidden in T i Representing the ith subsequence;
the original sequence is reconstructed using a decoder,
；
wherein,as a function of the decoder->For the ith subsequence T i A reconstructed version of (a);
inputting the preprocessed data sequence into a model, optimizing a reconstruction error using a mean square error as a loss function,
；
feature extraction, extracting meaningful patterns from new time series data using a trained encoder, inputting the new time series data into the encoder, the output of the encoder being a compressed representation of the data, capturing key features in the time series, obtaining a hidden representation,
。
s2, mining association rules on the extracted features by using association analysis;
mining association rules on extracted features using association analysis includes converting continuous hidden representations into discrete forms using multi-level binning, for each hidden representation, taking non-zero features of the hidden representation as a transaction, finding frequent sets of items using priori, for each frequent set of items, generating all possible association rules,
；
wherein,expressed as features in a hidden representation;
for each generated association rule, a degree of support is calculated,
；
wherein,for support, TC represents +.>Is a synthetic operation of (2);
when the support degree of the association rule is larger than or equal to the minimum confidence coefficient threshold value in the system, the association rule meets the confidence coefficient requirement;
for each generated association rule, a confidence level is calculated,
；
wherein,is confidence;
when the confidence coefficient of the associated rule is larger than or equal to the minimum confidence coefficient threshold value in the system, the associated rule meets the confidence coefficient requirement, and the associated rule meeting the requirements of the support coefficient and the confidence coefficient is screened out.
When the minimum support is set to be 5%, it is indicated that at least 5% of factor combinations appear in the observation as usable rules, when the minimum confidence is set to be 70%, the factor combinations needing attention have at least 70% of confidence rules, and when the support of the rules is greater than 5% and the confidence is greater than 70%, the rules are usable in the detection of dielectric loss of the capacitive device.
And S3, when the association rule is matched, the system generates fault early warning and a corresponding strategy to inform a user.
The matching to the association rule comprises that the system checks real-time data, retrieves a problem database according to the triggered association rule, automatically invokes a historical optimal processing method in the problem database if the association rule is a known problem in the problem database, and automatically records the triggered rule and the executed operation in an operation log;
when the system detects that the system does not accord with the expected mode, the system automatically marks the abnormality and records the problem database, immediately sends out an alarm, displays the triggered association rule and current data reading through an upper computer, on-site operators read the history similar problems through the system and send out overhaul operation to carry out dry prognosis, provide feedback in the system, record the result of the overhaul operation provided by the system, and continuously learn and optimize the association rule for the system according to the history data and the result of manual intervention.
The database of questions includes the information that,
；
wherein D is a problem database,for the ith exception event, +.>Is->Associated timestamp, ">Is abnormal->Status of->And->Associated recommended solution,/->Is->And (5) associated feedback.
The mode which does not meet the expectations comprises the steps that when the system detects that the dielectric loss of the capacitive equipment exceeds a safety loss threshold value in a short time, the system is required to be judged to intervene, whether the internal false alarm of the system exists or not is judged, if the secondary detection system does not report the false alarm, the abnormal node is marked, the abnormal node is recorded in a problem database, an upper computer is used for notifying on-site operators to carry out maintenance and investigation, after the operator investigation is finished, the abnormal node is continuously observed, if the abnormal node continuously shows that the maintenance is higher than the normal loss for more than 24 hours, the system prompts that the equipment has long-term backlog problem, and the manual intervention is prompted to the node;
when the system detects that the capacitive equipment has dielectric loss and no corresponding association rule, the system is required to intervene, whether internal false alarm exists or not is judged, if the secondary detection system does not have false alarm, abnormal nodes are marked, the abnormal nodes are recorded in a problem database, and the abnormal nodes are prompted by an upper computer to perform manual intervention;
when the deviation level between the predicted dielectric loss value and the actual dielectric loss value is C level or S level, the system performs secondary diagnosis, checks whether the input data is abnormal or not and checks whether the model parameters change or not, if the input data is abnormal, the system performs first automatic repair, if the repair fails, prompts on-site operators to check the data and repair the data through an upper computer, if the model parameters are abnormal, the system automatically repairs the model data, if the input data and the model parameters are not abnormal, the system retrains the model, when the abnormal state is eliminated, the system secondarily calculates the deviation level between the predicted dielectric loss value and the actual dielectric loss value, if the deviation level is C level or S level, the dielectric loss of the equipment exceeds the normal range, the system gives a warning and prompts on-site operators to perform manual intervention, and if the deviation level between the secondarily calculated predicted dielectric loss value and the actual loss value is A level or B level, the system records the problem and reenters the normal operation state.
The deviation level includes, when the deviationWhen the deviation level is A, if the deviation level is A, the system confirms that the prediction is accurate and is close to the actual value, and the system is allowed to use;
when the deviation isWhen the deviation grade is B, the system confirms that slight deviation exists between the deviation grade and the actual value, and the system is allowed to use after screening;
when the deviation isWhen the deviation grade is C, the deviation between the prediction and the actual value is obvious, and the data needs to be processed;
when the deviation isWhen the deviation level is S level, the deviation between the prediction and the actual value is very large, and the data needs to be processed.
Example 2
For the second embodiment of the invention, a method and a system for monitoring the dielectric loss of the capacitive equipment based on correlation analysis are provided, and in order to verify the beneficial effects of the invention, scientific demonstration is carried out through experiments.
The prediction results were classified using different thresholds, and for each threshold, the prediction accuracy, false positive rate, and false negative rate were calculated as shown in table 1.
TABLE 1
As the threshold increases from 0.5% to 1%, the prediction accuracy tends to increase, reaching the highest 92.56%. But as the threshold continues to increase to 5% and 20%, the accuracy begins to decrease. This suggests that too low or too high a threshold may lead to inaccurate predictions, with false positive rates being minimized at a threshold of 1%. When a threshold of 1% is used, only 4.09% of the normal cases are falsely marked as abnormal. The false negative rate remained relatively stable throughout the experiment, but there was a clear upward trend at a threshold of 10%. A higher threshold may result in some real anomalies being missed.
Example 3
A third embodiment of the present invention, which is different from the first two embodiments, is:
the functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, randomAccess Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Example 4
Referring to fig. 2, a fourth embodiment of the present invention provides a system for a capacitive device dielectric loss monitoring method based on correlation analysis, which is characterized in that: the system comprises a data preprocessing module, an association rule generating module, a rule screening module and a service application module;
the data preprocessing module cleans, converts and standardizes the original data, so that the data preprocessing module is suitable for association rule mining and data cleaning: the missing values, outliers, and duplicate values are processed. Data conversion: the data is converted into a format suitable for association rule mining. Data normalization: all data is scaled to a uniform range.
The association rule generation module generates association rules from the preprocessed data by using an Apriori algorithm, and frequent item set mining is performed: combinations of items frequently occurring in the data are found out. Rule generation: an association rule is generated based on the frequent item set. Rule evaluation: the generated rule is evaluated using indicators of support, confidence, etc.
The rule screening module screens and sorts the association rules based on the minimum support and the minimum confidence, and the rule screening: and deleting rules which do not meet the minimum support and confidence requirements. Rule ordering: and ordering the rules according to the support and the confidence. Rule visualization: an intuitive interface is provided for the user, and the rules after screening and sorting are displayed.
The service application module applies the screened association rule to an actual service scene, and applies the rule: recommendations or predictions are provided to the user based on the association rules. User feedback: user feedback on the recommendations or predictions is collected to further optimize the rules. Continuous learning: based on the new data and user feedback, the association rules are continuously updated and optimized.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered by the scope of the claims of the present invention.
Claims (10)
1. A capacitive equipment dielectric loss monitoring method based on association analysis is characterized in that: comprising the steps of (a) a step of,
collecting operation data of the capacitive equipment, and extracting characteristics of the operation data by using a self-encoder model;
mining association rules on the extracted features using association analysis;
when the association rule is matched, the system generates fault early warning and a corresponding strategy to inform the user.
2. The method for monitoring dielectric loss of capacitive device based on correlation analysis as claimed in claim 1, wherein: the self-encoder model includes, when the acquired operational data of the capacitive device is 24 hours of data recorded once per minute, dividing the data into a plurality of sequences of 1440 data points,
；
wherein T is a subsequence, T is a complete time sequence, the time sequence is divided into n subsequences of length m,scaling the data to between 0 and 1,
；
creating a network structure that processes time series data, the number of input layer neurons being equal to the length of each data series, capturing the time dependence using a recurrent neural network,
；
wherein,as a function of the encoder, H i For the ith subsequence T i Is hidden in T i Representing the ith subsequence;
the original sequence is reconstructed using a decoder,
；
wherein,as a function of the decoder->For the ith subsequence T i A reconstructed version of (a);
inputting the preprocessed data sequence into a model, optimizing a reconstruction error using a mean square error as a loss function,
；
inputting the new time series data into an encoder, the output of the encoder being a compressed representation of the data, capturing key features in the time series, obtaining a hidden representation,
。
3. a method for monitoring dielectric loss of a capacitive device based on correlation analysis as claimed in claim 2 wherein: mining association rules on extracted features using association analysis includes converting continuous hidden representations into discrete forms using multi-level binning, for each hidden representation, taking non-zero features of the hidden representation as a transaction, finding frequent sets of items using priori, for each frequent set of items, generating all possible association rules,
；
wherein,expressed as features in a hidden representation;
for each generated association rule, a degree of support is calculated,
；
when the support degree of the association rule is greater than or equal to the minimum confidence threshold value inside the system, the association rule meets the confidence requirement, and TC representsIs a synthetic operation of (2);
for each generated association rule, a confidence level is calculated,
；
when the confidence coefficient of the associated rule is larger than or equal to the minimum confidence coefficient threshold value in the system, the associated rule meets the confidence coefficient requirement, and the associated rule meeting the requirements of the support coefficient and the confidence coefficient is screened out.
4. A method for monitoring dielectric loss of a capacitive device based on correlation analysis as claimed in claim 3 wherein: the matching to the association rule comprises that the system checks real-time data, retrieves a problem database according to the triggered association rule, automatically invokes a historical optimal processing method in the problem database if the association rule is a known problem in the problem database, and automatically records the triggered rule and the executed operation in an operation log;
when the system detects that the system does not accord with the expected mode, the system automatically marks the abnormality and records the problem database, immediately sends out an alarm, displays the triggered association rule and current data reading through an upper computer, on-site operators read the history similar problems through the system and send out overhaul operation to carry out dry prognosis, provide feedback in the system, record the result of the overhaul operation provided by the system, and continuously learn and optimize the association rule for the system according to the history data and the result of manual intervention.
5. The method for monitoring dielectric loss of capacitive device based on correlation analysis as claimed in claim 4, wherein: the database of questions includes the information that,
；
wherein D is a problem database,for the ith exception event, +.>Is->Associated timestamp, ">Is abnormal->Status of->And->Associated recommended solution,/->Is->And (5) associated feedback.
6. The method for monitoring dielectric loss of capacitive device based on correlation analysis as claimed in claim 5, wherein: the mode which does not meet the expectations comprises the steps that when the system detects that the dielectric loss of the capacitive equipment exceeds a safety loss threshold value within the safety time, the system is required to be judged to intervene, whether the internal false alarm of the system exists or not is judged, if the secondary detection system does not report the false alarm, the abnormal node is marked, the abnormal node is recorded in a problem database, an upper computer is used for notifying on-site operators to carry out maintenance and investigation, after the operator investigation is finished, the abnormal node is continuously observed, if the abnormal node continuously shows that the abnormal node is higher than the normal loss after the maintenance for more than 24 hours, the system prompts that the equipment has long-term backlog problem, and the manual intervention is prompted to the node;
when the system detects that the capacitive equipment has dielectric loss and no corresponding association rule, the system is required to intervene, whether internal false alarm exists or not is judged, if the secondary detection system does not have false alarm, abnormal nodes are marked, the abnormal nodes are recorded in a problem database, and the abnormal nodes are prompted by an upper computer to perform manual intervention;
when the deviation level between the predicted dielectric loss value and the actual dielectric loss value is C level or S level, the system performs secondary diagnosis, checks whether the input data is abnormal or not and checks whether the model parameters change or not, if the input data is abnormal, the system performs first automatic repair, if the repair fails, prompts on-site operators to check the data and repair the data through an upper computer, if the model parameters are abnormal, the system automatically repairs the model data, if the input data and the model parameters are not abnormal, the system retrains the model, when the abnormal state is eliminated, the system secondarily calculates the deviation level between the predicted dielectric loss value and the actual dielectric loss value, if the deviation level is C level or S level, the dielectric loss of the equipment exceeds the normal range, the system gives a warning and prompts on-site operators to perform manual intervention, and if the deviation level between the secondarily calculated predicted dielectric loss value and the actual loss value is A level or B level, the system records the problem and reenters the normal operation state.
7. The method for monitoring dielectric loss of capacitive device based on correlation analysis as claimed in claim 6, wherein: the deviation level includes, when the deviationWhen the deviation grade is A;
when the deviation isWhen the deviation grade is B grade;
when the deviation isWhen the deviation grade is C grade;
when the deviation isIs thatAnd when the deviation grade is S grade.
8. A system based on the correlation analysis-based capacitive device dielectric loss monitoring method of any one of claims 1-7, characterized in that: the system comprises a data preprocessing module, an association rule generating module, a rule screening module and a service application module;
the data preprocessing module cleans, converts and standardizes the original data so that the original data is suitable for association rule mining;
the association rule generation module is used for generating association rules from the preprocessed data by using an Apriori algorithm;
the rule screening module screens and sorts association rules based on the minimum support and the minimum confidence;
and the service application module applies the screened association rule to the actual service scene.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311406243.0A CN117131110B (en) | 2023-10-27 | 2023-10-27 | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311406243.0A CN117131110B (en) | 2023-10-27 | 2023-10-27 | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117131110A true CN117131110A (en) | 2023-11-28 |
| CN117131110B CN117131110B (en) | 2024-01-23 |
Family
ID=88861406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311406243.0A Active CN117131110B (en) | 2023-10-27 | 2023-10-27 | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117131110B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117517908A (en) * | 2024-01-08 | 2024-02-06 | 南京中鑫智电科技有限公司 | Insulating integrated monitoring system of full station capacitive equipment of transformer substation |
| CN117591542A (en) * | 2024-01-18 | 2024-02-23 | 准检河北检测技术服务有限公司 | Intelligent detection method for database software data security |
| CN117668677A (en) * | 2023-11-30 | 2024-03-08 | 北京安领可信网络科技有限公司 | Data detection method |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819411A (en) * | 2010-03-17 | 2010-09-01 | 燕山大学 | GPU-based equipment fault early-warning and diagnosis method for improving weighted association rules |
| EP2523150A1 (en) * | 2011-05-11 | 2012-11-14 | General Electric Company | System and Method for Optimizing Plant Operations |
| EP3557816A1 (en) * | 2017-01-24 | 2019-10-23 | China Techenergy Co., Ltd | Self-diagnosis method for communication protocol of security-level instrumentation and control system of nuclear power plant |
| CN110991668A (en) * | 2019-11-29 | 2020-04-10 | 合肥国轩高科动力能源有限公司 | Electric vehicle power battery monitoring data analysis method based on association rule |
| CN112925806A (en) * | 2021-04-14 | 2021-06-08 | 中国人民解放军海军航空大学岸防兵学院 | Association rule-based performance degradation characteristic parameter extraction method, system, medium, and device |
| CN113091817A (en) * | 2021-04-06 | 2021-07-09 | 重庆大学 | Triethylene glycol dewatering device state monitoring and fault diagnosis system |
| CN113297272A (en) * | 2021-05-30 | 2021-08-24 | 福建中锐网络股份有限公司 | Bridge monitoring data association rule mining and health early warning method and system |
| CN114168409A (en) * | 2021-11-26 | 2022-03-11 | 上海蒙帕信息技术有限公司 | Service system running state monitoring and early warning method and system |
| WO2022083576A1 (en) * | 2020-10-22 | 2022-04-28 | 中兴通讯股份有限公司 | Analysis method and apparatus for operating data of network function virtualization device |
| CN114994441A (en) * | 2022-06-06 | 2022-09-02 | 重庆伏特猫科技有限公司 | Intelligent electric power efficiency monitoring device |
| CN115271263A (en) * | 2022-09-27 | 2022-11-01 | 佰聆数据股份有限公司 | Power equipment defect early warning method, system and medium based on improved association rule |
| CN115688961A (en) * | 2022-04-28 | 2023-02-03 | 国网湖北省电力有限公司黄石供电公司 | Power equipment fault prediction method and system based on deep learning |
| CN115878421A (en) * | 2022-12-09 | 2023-03-31 | 国网湖北省电力有限公司信息通信公司 | Data center equipment-level fault prediction method, system and medium based on log time sequence correlation characteristic mining |
| WO2023158044A1 (en) * | 2022-02-17 | 2023-08-24 | 주식회사 디엠테크컨설팅 | Method for facility malfunction predictive maintenance using artificial intelligence based on empirical shared knowledge |
| CN116796043A (en) * | 2023-08-29 | 2023-09-22 | 山东通维信息工程有限公司 | Intelligent park data visualization method and system |
| CN116823226A (en) * | 2023-07-06 | 2023-09-29 | 湖南鑫能实业有限公司 | Electric power district fault monitoring system based on big data |
-
2023
- 2023-10-27 CN CN202311406243.0A patent/CN117131110B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101819411A (en) * | 2010-03-17 | 2010-09-01 | 燕山大学 | GPU-based equipment fault early-warning and diagnosis method for improving weighted association rules |
| EP2523150A1 (en) * | 2011-05-11 | 2012-11-14 | General Electric Company | System and Method for Optimizing Plant Operations |
| EP3557816A1 (en) * | 2017-01-24 | 2019-10-23 | China Techenergy Co., Ltd | Self-diagnosis method for communication protocol of security-level instrumentation and control system of nuclear power plant |
| CN110991668A (en) * | 2019-11-29 | 2020-04-10 | 合肥国轩高科动力能源有限公司 | Electric vehicle power battery monitoring data analysis method based on association rule |
| WO2022083576A1 (en) * | 2020-10-22 | 2022-04-28 | 中兴通讯股份有限公司 | Analysis method and apparatus for operating data of network function virtualization device |
| CN113091817A (en) * | 2021-04-06 | 2021-07-09 | 重庆大学 | Triethylene glycol dewatering device state monitoring and fault diagnosis system |
| CN112925806A (en) * | 2021-04-14 | 2021-06-08 | 中国人民解放军海军航空大学岸防兵学院 | Association rule-based performance degradation characteristic parameter extraction method, system, medium, and device |
| CN113297272A (en) * | 2021-05-30 | 2021-08-24 | 福建中锐网络股份有限公司 | Bridge monitoring data association rule mining and health early warning method and system |
| CN114168409A (en) * | 2021-11-26 | 2022-03-11 | 上海蒙帕信息技术有限公司 | Service system running state monitoring and early warning method and system |
| WO2023158044A1 (en) * | 2022-02-17 | 2023-08-24 | 주식회사 디엠테크컨설팅 | Method for facility malfunction predictive maintenance using artificial intelligence based on empirical shared knowledge |
| CN115688961A (en) * | 2022-04-28 | 2023-02-03 | 国网湖北省电力有限公司黄石供电公司 | Power equipment fault prediction method and system based on deep learning |
| CN114994441A (en) * | 2022-06-06 | 2022-09-02 | 重庆伏特猫科技有限公司 | Intelligent electric power efficiency monitoring device |
| CN115271263A (en) * | 2022-09-27 | 2022-11-01 | 佰聆数据股份有限公司 | Power equipment defect early warning method, system and medium based on improved association rule |
| CN115878421A (en) * | 2022-12-09 | 2023-03-31 | 国网湖北省电力有限公司信息通信公司 | Data center equipment-level fault prediction method, system and medium based on log time sequence correlation characteristic mining |
| CN116823226A (en) * | 2023-07-06 | 2023-09-29 | 湖南鑫能实业有限公司 | Electric power district fault monitoring system based on big data |
| CN116796043A (en) * | 2023-08-29 | 2023-09-22 | 山东通维信息工程有限公司 | Intelligent park data visualization method and system |
Non-Patent Citations (4)
| Title |
|---|
| 刘美;李正明;: "关联规则在企业电耗数据分析中的应用", 微计算机信息, no. 33, pages 62 - 64 * |
| 姚万业;杨金彭;: "一种基于区间划分的风机故障预警方法", 可再生能源, no. 06, pages 75 - 80 * |
| 汤敏丽;: "基于改进型Apriori算法数据挖掘技术在煤矿安全预警系统中的应用研究", 荆楚理工学院学报, no. 09, pages 36 - 39 * |
| 赵洪山;刘辉海;刘宏杨;林酉阔;: "基于堆叠自编码网络的风电机组发电机状态监测与故障诊断", 电力系统自动化, no. 11, pages 108 - 114 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117668677A (en) * | 2023-11-30 | 2024-03-08 | 北京安领可信网络科技有限公司 | Data detection method |
| CN117517908A (en) * | 2024-01-08 | 2024-02-06 | 南京中鑫智电科技有限公司 | Insulating integrated monitoring system of full station capacitive equipment of transformer substation |
| CN117517908B (en) * | 2024-01-08 | 2024-03-26 | 南京中鑫智电科技有限公司 | Insulating integrated monitoring system of full station capacitive equipment of transformer substation |
| CN117591542A (en) * | 2024-01-18 | 2024-02-23 | 准检河北检测技术服务有限公司 | Intelligent detection method for database software data security |
| CN117591542B (en) * | 2024-01-18 | 2024-03-22 | 准检河北检测技术服务有限公司 | Intelligent detection method for database software data security |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117131110B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117131110B (en) | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis | |
| Zheng et al. | A rolling bearing fault diagnosis method based on multi-scale fuzzy entropy and variable predictive model-based class discrimination | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| EP2905665B1 (en) | Information processing apparatus, diagnosis method, and program | |
| Yu | Adaptive hidden Markov model-based online learning framework for bearing faulty detection and performance degradation monitoring | |
| CN110826648B (en) | Method for realizing fault detection by utilizing time sequence clustering algorithm | |
| JP2020119605A (en) | Abnormality detection system, abnormality detection method, abnormality detection program, and method for generating learned model | |
| JP5364530B2 (en) | Equipment state monitoring method, monitoring system, and monitoring program | |
| EP3552067B1 (en) | Methods and systems for discovery of prognostic subsequences in time series | |
| JP5342708B1 (en) | Anomaly detection method and apparatus | |
| KR101948604B1 (en) | Method and device for equipment health monitoring based on sensor clustering | |
| CN112766342A (en) | Abnormity detection method for electrical equipment | |
| US20110307743A1 (en) | False alarm mitigation | |
| JP2014032455A (en) | Equipment condition monitoring method and device thereof | |
| Kamat et al. | Deep learning-based anomaly-onset aware remaining useful life estimation of bearings | |
| CN113590396A (en) | Method and system for diagnosing defect of primary device, electronic device and storage medium | |
| US20230221684A1 (en) | Explaining Machine Learning Output in Industrial Applications | |
| Amruthnath et al. | Factor analysis in fault diagnostics using random forest | |
| Leahy et al. | Cluster analysis of wind turbine alarms for characterising and classifying stoppages | |
| Liu et al. | Wind turbine anomaly detection based on SCADA: A deep autoencoder enhanced by fault instances | |
| Zhang et al. | Graph neural network-based bearing fault diagnosis using Granger causality test | |
| CN113505531B (en) | Diagnostic model construction method based on combination of traditional diagnosis and machine learning method and aiming at abnormal valve clearance faults of reciprocating machinery | |
| Han et al. | Correlation analysis based relevant variable selection for wind turbine condition monitoring and fault diagnosis | |
| CN117521800A (en) | Intelligent power transmission line inspection method based on knowledge graph | |
| CN115169650B (en) | Equipment health prediction method for big data analysis |
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 |