CN113591393A - Fault diagnosis method, device, equipment and storage medium of intelligent substation - Google Patents

Fault diagnosis method, device, equipment and storage medium of intelligent substation Download PDF

Info

Publication number
CN113591393A
CN113591393A CN202110913435.5A CN202110913435A CN113591393A CN 113591393 A CN113591393 A CN 113591393A CN 202110913435 A CN202110913435 A CN 202110913435A CN 113591393 A CN113591393 A CN 113591393A
Authority
CN
China
Prior art keywords
alarm information
preset
real
classification
fault
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110913435.5A
Other languages
Chinese (zh)
Inventor
李铁成
任江波
刘清泉
耿少博
孙利强
王献志
徐岩
王鸣誉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Hebei Electric Power Co Ltd
State Grid Hebei Energy Technology Service Co Ltd
Original Assignee
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Hebei Electric Power Co Ltd
State Grid Hebei Energy Technology Service Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Electric Power Research Institute of State Grid Hebei Electric Power Co Ltd, State Grid Hebei Energy Technology Service Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202110913435.5A priority Critical patent/CN113591393A/en
Publication of CN113591393A publication Critical patent/CN113591393A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/04—Power grid distribution networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]

Abstract

The invention is suitable for the technical field of power grid safety, and provides a fault diagnosis method, a fault diagnosis device, equipment and a storage medium for an intelligent substation, wherein the fault diagnosis method for the intelligent substation comprises the following steps: acquiring real-time alarm information of a secondary system; presetting the real-time alarm information to obtain preprocessed alarm information; comparing all preset classification alarm information sets in a preset C4.5 fault decision tree model with preprocessed alarm information to obtain a sub-classification alarm information set of real-time alarm information; constructing a relevance rule of a sub-classification alarm information set based on a P-growth algorithm; processing the preset association index of the association rule based on the ant lion algorithm to obtain the association index of the real-time alarm information; and obtaining the root alarm information in the real-time alarm information according to the association index and the association rule of the real-time alarm information. By adopting the invention, the accuracy of fault diagnosis can be improved.

Description

Fault diagnosis method, device, equipment and storage medium of intelligent substation
Technical Field
The invention belongs to the technical field of power grid safety, and particularly relates to a fault diagnosis method, a fault diagnosis device, fault diagnosis equipment and a storage medium for an intelligent substation.
Background
The intelligent transformer substation adopts advanced, reliable, integrated and environment-friendly intelligent equipment to automatically complete basic functions of information acquisition, measurement, control, protection, metering, detection and the like. The intelligent substation mainly comprises a primary system and a secondary system, wherein the primary system is a system consisting of a generator, a power transmission line, a transformer, a circuit breaker and other equipment; the secondary system is a system composed of a measuring meter, an insulation monitoring device, a relay protection device, an automatic device and the like. The secondary system is used as an auxiliary system for monitoring, measuring, controlling, protecting and adjusting the primary system in the intelligent substation, and plays a significant role in the intelligent substation. If the secondary system fails during operation, the primary system cannot operate normally, so that the safety of the whole power grid is affected.
At present, the secondary system fault diagnosis of the traditional intelligent substation is mainly carried out according to the alarm information displayed by the secondary system, and a dispatcher carries out fault diagnosis by depending on work experience, so that the fault analysis of the secondary system is inaccurate and the diagnosis accuracy is low due to the lack of an effective diagnosis means.
In addition, with the continuous development of artificial intelligence, algorithms such as a neural network, a support vector machine, association rule mining and the like are widely applied to secondary system fault diagnosis, however, the algorithms are usually optimized on the complexity of fault diagnosis, and although the complexity of fault diagnosis is reduced, the diagnosis accuracy is difficult to improve and the diagnosis accuracy is low because more diagnosis data are difficult to screen.
Disclosure of Invention
In view of this, embodiments of the present invention provide a fault diagnosis method, apparatus, device and storage medium for an intelligent substation, so as to solve the problem of low diagnosis accuracy in the current fault diagnosis method.
The first aspect of the embodiment of the invention provides a fault diagnosis method for an intelligent substation, which comprises the following steps:
acquiring real-time alarm information of a secondary system of an intelligent substation;
presetting the real-time alarm information to obtain preprocessed alarm information;
comparing a preset classification alarm information set and pre-processing alarm information in a preset C4.5 fault decision tree model to obtain a sub-classification alarm information set of real-time alarm information;
constructing a relevance rule of a sub-classification alarm information set based on a P-growth algorithm;
processing the preset association index of the association rule based on the ant lion algorithm to obtain the association index of the real-time alarm information;
and obtaining the root alarm information in the real-time alarm information according to the association index and the association rule of the real-time alarm information.
In a possible implementation manner, comparing a preset classification alarm information set and a preprocessed alarm information set in a preset C4.5 fault decision tree model to obtain a sub-classification alarm information set of real-time alarm information, includes:
acquiring historical alarm information of a secondary system, wherein the historical alarm information is divided into training information and testing information according to a preset rule;
training the training information through a C4.5 decision tree algorithm to obtain a decision tree model;
verifying and pruning the decision tree model by using the test information to obtain a preset C4.5 fault decision tree model; the preset C4.5 fault decision tree model consists of a plurality of preset classification alarm information sets with different fault types;
and comparing all preset classification alarm information sets in the preset C4.5 fault decision tree model with the preset alarm information, and determining the preset classification alarm information set with the highest matching degree as a sub-classification alarm information set of the real-time alarm information.
In a possible implementation manner, before the training information is trained through the C4.5 decision tree algorithm to obtain the decision tree model, the method further includes:
constructing a fault attribute database of historical alarm information; the historical alarm information comprises secondary equipment alarm information, a GOOSE abnormal message and an SV abnormal message; the fault attribute database comprises device locking, self-checking alarm information, GOOSE alarm information, SV alarm information and fault types; storing the historical alarm information into a fault attribute database according to a preset rule;
and constructing a decision tree model based on a C4.5 decision tree algorithm and a fault attribute database.
In one possible implementation, the C4.5 decision tree algorithm employs taylor series instead of logarithmic operation;
wherein the C4.5 decision tree algorithm has an information gain ratio of
Figure BDA0003204526250000031
Gainratio (A) is selected for classificationInformation gain ratio of the type of attribute A, gain (A) being the information gain of attribute A, SplitInfoA(T) is the split information measure of the A attribute in the whole preset classification alarm information set T, T is the whole preset classification alarm information set, TjThe total data number, TC, of the jth preset classification alarm information set in the whole preset classification alarm information set TiIs that the whole preset classification alarm information set T belongs to a sub-classification alarm information set CiTotal number of data of (TC)ijThe j preset classified alarm information set in the whole preset classified alarm information set T belongs to a sub-classified alarm information set CiTotal number of data of (1).
In a possible implementation manner, based on a P-growth algorithm, an association rule of a sub-classification alarm information set is constructed, including:
performing iterative processing on the preset minimum support degree of the association rule based on the ant lion algorithm to obtain the minimum support degree of the sub-classification alarm information set;
deleting the target alarm information with the sub-classification alarm information set smaller than the minimum support degree to obtain a sub-classification alarm associated information set; wherein, the target alarm information is any one of the alarm information in the sub-classification alarm information set;
constructing a relevance rule of a sub-classification alarm relevance information set based on a P-growth algorithm;
wherein the support degree is
Figure BDA0003204526250000032
A is target alarm information, N is the number of all target alarm information, sup (A) is the support degree of the target alarm information A.
In one possible implementation, the correlation index includes a confidence and an imbalance ratio;
based on the ant lion algorithm, the preset association index of the association rule is processed to obtain the association index of the real-time alarm information, and the method comprises the following steps:
and carrying out iterative processing on the preset first confidence coefficient and the first unbalance ratio based on the ant lion algorithm to obtain a second confidence coefficient and a second unbalance ratio of the real-time alarm information.
In a possible implementation manner, obtaining root alarm information in the real-time alarm information according to the association index and the association rule of the real-time alarm information includes:
when the confidence of the target relevance rule is greater than the second confidence and the unbalance ratio of the target relevance rule is less than the second unbalance ratio, determining the front piece of the target relevance rule as the root alarm information in the real-time alarm information; wherein the target relevance rule is any one of the relevance rules;
wherein the confidence is
Figure BDA0003204526250000041
A and B are respectively any different target alarm information in the sub-classification alarm information set,
Figure BDA0003204526250000042
the probability of the occurrence of the alarm information B is under the premise of the occurrence of the alarm information of the target A;
imbalance ratio of
Figure BDA0003204526250000043
Sup (A) is the support degree of the target alarm information A, Sup (B) is the support degree of the target alarm information B, and Sup (A → B) is the support degree containing the target alarm information A and the target alarm information B at the same time.
A second aspect of an embodiment of the present invention provides a fault diagnosis device for an intelligent substation, including:
the information acquisition module is used for acquiring real-time alarm information of a secondary system of the intelligent substation;
the preset processing module is used for carrying out preset processing on the real-time alarm information to obtain preprocessed alarm information;
the information comparison module is used for comparing a preset classified alarm information set and preprocessed alarm information in a preset C4.5 fault decision tree model to obtain a sub-classified alarm information set of real-time alarm information;
the building rule module is used for building the association rule of the sub-classification alarm information set based on a P-growth algorithm;
the index optimization module is used for processing the preset association index of the association rule based on the ant lion algorithm to obtain the association index of the real-time alarm information;
and the information determining module is used for obtaining the root alarm information in the real-time alarm information according to the association index and the association rule of the real-time alarm information.
In a possible implementation manner, the information comparison module is further configured to obtain historical alarm information of the secondary system, where the historical alarm information is divided into training information and test information according to a preset rule;
training the training information through a C4.5 decision tree algorithm to obtain a decision tree model;
verifying and pruning the decision tree model by using the test information to obtain a preset C4.5 fault decision tree model; the preset C4.5 fault decision tree model consists of a plurality of preset classification alarm information sets with different fault types;
and comparing all preset classification alarm information sets in the preset C4.5 fault decision tree model with the preset alarm information, and determining the preset classification alarm information set with the highest matching degree as a sub-classification alarm information set of the real-time alarm information.
In a possible implementation manner, the information comparison module is further configured to, before the training information is trained through a C4.5 decision tree algorithm to obtain the decision tree model, further include:
constructing a fault attribute database of historical alarm information; the historical alarm information comprises secondary equipment alarm information, a GOOSE abnormal message and an SV abnormal message; the fault attribute database comprises device locking, self-checking alarm information, GOOSE alarm information, SV alarm information and fault types; storing the historical alarm information into a fault attribute database according to a preset rule;
and constructing a decision tree model based on a C4.5 decision tree algorithm and a fault attribute database.
In one possible implementation, the C4.5 decision tree algorithm employs taylor series instead of logarithmic operation; wherein the C4.5 decision tree algorithm has an information gain ratio of
Figure BDA0003204526250000051
Gainratio (A) is the information gain rate of a certain attribute A selected during classification, gain (A) is the information gain of attribute A, SplitInfoA(T) is the split information measure of the A attribute in the whole preset classification alarm information set T, T is the whole preset classification alarm information set, TjThe total data number, TC, of the jth preset classification alarm information set in the whole preset classification alarm information set TiIs that the whole preset classification alarm information set T belongs to a sub-classification alarm information set CiTotal number of data of (TC)ijThe j preset classified alarm information set in the whole preset classified alarm information set T belongs to a sub-classified alarm information set CiTotal number of data of (1).
In a possible implementation manner, the construction rule module is further configured to perform iterative processing on a preset minimum support degree of the association rule based on an ant-lion algorithm to obtain a minimum support degree of the sub-classification alarm information set;
deleting the target alarm information with the sub-classification alarm information set smaller than the minimum support degree to obtain a sub-classification alarm associated information set; wherein, the target alarm information is any one of the alarm information in the sub-classification alarm information set;
constructing a relevance rule of a sub-classification alarm relevance information set based on a P-growth algorithm;
wherein the support degree is
Figure BDA0003204526250000061
A is target alarm information, N is the number of all target alarm information, sup (A) is the support degree of the target alarm information A.
In one possible implementation, the correlation index includes a confidence and an imbalance ratio;
correspondingly, the index optimization module is also used for,
and carrying out iterative processing on the preset first confidence coefficient and the first unbalance ratio based on the ant lion algorithm to obtain a second confidence coefficient and a second unbalance ratio of the real-time alarm information.
In a possible implementation manner, the information determining module is further configured to determine, when the confidence of the target association rule is greater than the second confidence and the imbalance ratio of the target association rule is smaller than the second imbalance ratio, a front piece of the target association rule as root alarm information in the real-time alarm information; wherein the target relevance rule is any one of the relevance rules;
wherein the confidence is
Figure BDA0003204526250000062
A and B are respectively any different target alarm information in the sub-classification alarm information set,
Figure BDA0003204526250000063
the probability of the occurrence of the alarm information B is under the premise of the occurrence of the alarm information of the target A;
imbalance ratio of
Figure BDA0003204526250000064
Sup (A) is the support degree of the target alarm information A, Sup (B) is the support degree of the target alarm information B, and Sup (A → B) is the support degree containing the target alarm information A and the target alarm information B at the same time.
A third aspect of embodiments of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method according to the first aspect when executing the computer program.
A fourth aspect of embodiments of the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, performs the steps of the method according to the first aspect.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, the real-time warning information of the secondary system of the intelligent substation is firstly acquired, and the real-time warning information is subjected to preset processing to obtain the pre-processing warning information; and then, comparing a preset classification alarm information set and a preprocessing alarm information set in a preset C4.5 fault decision tree model to obtain a sub-classification alarm information set of the real-time alarm information. And then, constructing a relevance rule of the sub-classification alarm information set based on a P-growth algorithm, and then processing a preset relevance index of the relevance rule based on an ant lion algorithm to obtain a relevance index of the real-time alarm information. And finally, obtaining the root alarm information in the real-time alarm information according to the association index and the association rule of the real-time alarm information. Therefore, after the real-time alarm information is processed by the preset C4.5 fault decision tree model, the P-growth algorithm and the ant lion algorithm, the root alarm information can be obtained, and the diagnosis accuracy is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flowchart illustrating steps of a fault diagnosis method for an intelligent substation according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a decision tree for protecting a device failure according to an embodiment of the present invention;
FIG. 3 is a flow chart of a C4.5 decision tree algorithm according to an embodiment of the present invention;
fig. 4 is a flow chart of an ant lion algorithm according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a fault diagnosis device of an intelligent substation according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following description is made by way of specific embodiments with reference to the accompanying drawings.
At present, the correlation analysis of the alarm information is also used in the fault diagnosis of the secondary system of the intelligent substation, but the traditional correlation analysis can generate a large amount of useless diagnosis data, so that the diagnosis accuracy is low, and a dispatcher cannot obtain an accurate fault reason.
In order to solve the problems of the prior art, the embodiment of the invention provides a fault diagnosis method, a fault diagnosis device, equipment and a storage medium for an intelligent substation. First, a fault diagnosis method for an intelligent substation provided by an embodiment of the present invention is described below.
The main body of the fault diagnosis method may be a fault diagnosis apparatus, which may be an electronic device having a processor and a memory, such as a mobile electronic device or a non-mobile electronic device. For example, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a wearable device, or the like, and the non-mobile electronic device may be a server, a network-attached storage, a personal computer, or the like, and the embodiment of the present invention is not limited in particular.
As shown in fig. 1, an embodiment of the present invention provides a fault diagnosis method for an intelligent substation, which may include the following steps:
and step S110, acquiring real-time alarm information of a secondary system of the intelligent substation.
In some embodiments, the real-time alarm information of the secondary system of the intelligent substation needs to be acquired through two parts, namely a dispatching end device and a station end device.
And the master station system of the dispatching end is deployed at the provincial dispatching end. The station end equipment can utilize the network message analysis and recording device to acquire the alarm information of the secondary system in the intelligent substation. And the station end equipment performs preprocessing such as network information collection and filtration, collects network abnormal information in time when finding abnormal conditions, and immediately reports the collected network abnormal information to the master station of the scheduling end. And the alarm information is uploaded through a scheduling system D5000 platform, interface display is carried out, and the time window of the same alarm information is set to be 8 s.
The secondary system of the intelligent substation is according to relevant standard, and the information that the secondary system of the intelligent substation output mainly includes: the method comprises the following steps of running, alarming and acting, wherein the running information mainly comprises self-checking information, fault information, message state information and the like output by the device; the action information mainly comprises the power supply working state, the measured temperature, the equipment working condition and the like of each device; the alarm information mainly refers to sampling of a secondary system, switching value abnormal alarm signals and device abnormal alarm signals, and the switching value abnormal alarm signals mainly comprise: input signal abnormality: the device sampling is abnormal, the input/output quantity is abnormal, SV/GOOSE chain breakage, SV quality is abnormal, and the like, and the device abnormal alarm signal mainly comprises a device power-off alarm, a device lock, and the like.
And step S120, performing preset processing on the real-time alarm information to obtain preprocessed alarm information.
In some embodiments, the warning information in the scheduling system D5000 may include useless warning information, such as meaningless warning information or strobe warning information, which must be removed. And performing preset processing on the alarm information, wherein the preset processing is to remove meaningless alarm information and combine stroboscopic alarm information, and the preset processing is performed to obtain preprocessed alarm information.
Step S130, comparing all preset classified alarm information sets in the preset C4.5 fault decision tree model with the preprocessed alarm information to obtain a sub-classified alarm information set of the real-time alarm information.
In some embodiments, a preset C4.5 fault decision tree model needs to be established, so as to implement classification of alarm information.
Firstly, historical alarm information of a secondary system is obtained. The historical alarm information comprises secondary system alarm information, GOOSE abnormal messages, SV abnormal messages and other information; the secondary system alarm information mainly comprises self-checking abnormity, sampling error, power failure and the like; the GOOSE abnormal message mainly comprises GOOSE broken chain, flow abnormity, file configuration error and the like; the SV abnormal message mainly comprises SV broken link, sampling data asynchrony, message counting error and the like; and the locking information of the device is also provided, which is not described in detail herein.
And then, storing the historical alarm information into a fault attribute database according to a preset rule. The fault attribute database comprises attributes and classification results, the attributes comprise 4 types of device locking, self-checking alarm information, GOOSE alarm information and SV alarm information, and the fault types are classification results. Setting the alarm information of the secondary system in the history alarm information under the self-checking alarm information attribute, setting the device locking information under the device locking attribute, setting the GOOSE abnormal message under the GOOSE alarm information attribute, and setting the SV abnormal message under the SV alarm information attribute. The fault types are divided into 5 major categories, 19 types. The fault information is the result of manual diagnosis, wherein the fault types mainly include:
a merging unit: I/O port faults, power supply faults, program faults, configuration faults and sampling DSP faults;
protection device: I/O port failure, power failure, program failure, configuration failure;
and thirdly, the intelligent terminal: I/O port failure, power failure, program failure, configuration failure;
fourthly, the measurement and control device: I/O port failure, power failure, program failure, configuration failure;
communication link: switch failure, communication fiber failure;
specifically, the fault attribute database may be constructed according to the format of table one below, and it should be noted that the database is only an example of the format of the fault attribute database, and only a part of the alarm information and the fault category are put in the table, and not all the information in the embodiment of the present invention.
Watch 1
Figure BDA0003204526250000101
And then, dividing the historical alarm information into training information and testing information according to a preset rule. Specifically, three-fourths of the alarm information may be used as training information, and one-fourth of the alarm information may be used as test information. And training the training information through a C4.5 decision tree algorithm to obtain a decision tree model, wherein the fault type in the decision tree model is a leaf node, and the branches are device locking, self-checking alarm information, GOOSE alarm information and SV alarm information in a fault attribute database. And verifying and pruning the decision tree model by using the test information to obtain a preset C4.5 fault decision tree model. After the preset C4.5 fault decision tree model is built, each path from the root node to the leaf node corresponds to a fault classification mode. Specifically, the preset C4.5 fault decision tree model is composed of 19 preset classification alarm information sets with different fault types. Fig. 2 illustrates a partial preset C4.5 fault decision tree model established by taking four faults of the protection device as an example.
In addition, the c4.5 decision tree algorithm needs to select classified attributes by using the information gain rate of the historical alarm information, samples are classified through the classified attributes, the information entropy needs to be calculated firstly before the information gain rate is calculated, and the information entropy reflects the uncertainty degree of the information source. Here, the calculation process is not described in detail. However, it should be noted that the conventional c4.5 decision tree algorithm involves logarithmic calculation when calculating the information gain rate, and when the sample size is large, the logarithmic calculation increases the data processing time. The following was demonstrated:
Figure BDA0003204526250000111
when x is taken to be infinitely small, the formula can be simplified as:
Figure BDA0003204526250000112
specifically, as shown in the flowchart of the decision tree algorithm shown in fig. 3, the specific steps are as follows:
step l: a root node is created.
Step 2: if the training set is an empty set, the leaf nodes are empty sets.
And step 3: and calculating the information gain rate of the attributes in the attribute list.
And 4, step 4: and selecting the attribute with the highest information gain rate as a classification standard, and marking the internal node as an attribute A.
And 5: if the samples in the attribute A belong to the same label, the label is the leaf node of the current sample.
Step 6: and if the samples in the attribute A do not belong to the same label, further dividing the data in the attribute A, recalculating the information gain rate in the attribute A, and establishing a decision tree sub-tree.
And 7: and repeating the steps 5 and 6 to classify all the data in the attribute A until all the data in the attribute A are classified.
And 8: and classifying the attributes in each attribute list, and if the attribute list of the secondary fault training data in the database is empty, finishing the classification to form an initial decision tree.
And step 9: and evaluating the decision tree model from bottom to top by using the test set to judge whether leaf nodes need to be pruned.
Step 10: and pruning branches needing pruning to obtain a complete preset C4.5 fault decision tree model.
Wherein the C4.5 decision tree algorithm has an information gain ratio of
Figure BDA0003204526250000121
Gainratio (A) is the information gain rate of a certain attribute A selected during classification, gain (A) is the information gain of attribute A, SplitInfoA(T) is the split information measure of the A attribute in the whole preset classification alarm information set T, T is the whole preset classification alarm information set, TjThe total data number, TC, of the jth preset classification alarm information set in the whole preset classification alarm information set TiIs that the whole preset classification alarm information set T belongs to a sub-classification alarm information set CiTotal number of data of (TC)ijThe j preset classified alarm information set in the whole preset classified alarm information set T belongs to a sub-classified alarm information set CiTotal number of data of (1).
And finally, comparing all preset classified alarm information sets in the preset C4.5 fault decision tree model with the preset alarm information, and determining the preset classified alarm information set with the highest matching degree as a sub-classified alarm information set of the real-time alarm information.
According to the invention, a preset C4.5 fault decision tree model is constructed by utilizing a C4.5 decision tree algorithm, historical alarm information is classified according to fault types to form a preset classification alarm information set, and a path from a root node to a leaf node of each branch corresponds to a fault classification mode. Therefore, the sub-classification alarm information set of the real-time alarm information with the highest matching degree can be obtained by inputting the preset alarm information into the preset C4.5 fault decision tree model. Therefore, the diagnostic data can be reduced, judgment from a plurality of diagnostic data is not needed, and the diagnostic accuracy is improved.
And S140, constructing a relevance rule of the sub-classification alarm information set based on a P-growth algorithm.
Before performing the correlation analysis, first, a minimum support degree is determined. Specifically, the support degree refers to the probability of occurrence of a transaction, in fault analysis, namely the proportion of alarm information in total data, alarm data with excessively low occurrence times are considered to have no research value, and only information meeting the support degree counting index is mined.
In some embodiments, first, based on the ant-lion algorithm, the association rule is preset in advance to the maximumAnd carrying out iterative processing on the small support degree to obtain the minimum support degree of the sub-classification alarm information set. Specifically, the preset minimum support degree may be set to 0, and the ant lion algorithm is adopted to perform multiple iterations to obtain the optimal minimum support degree. Then, deleting the target alarm information with the sub-classification alarm information set smaller than the minimum support degree to obtain a sub-classification alarm associated information set; wherein, the target alarm information is any one of the alarm information in the sub-classification alarm information set. Before the relevance rule is constructed, part of useless target alarm information is removed, so that the constructed relevance rule data is reduced, and the diagnosis accuracy is improved. Wherein the support degree is
Figure BDA0003204526250000131
A is target alarm information, N is the number of all target alarm information, sup (A) is the support degree of the target alarm information A.
And finally, constructing the association rule of the sub-classification alarm association information set based on a P-growth algorithm.
Wherein the principle of the P-growth algorithm is as follows: the first scan records the two replacement sets of all transactions to obtain the vertex set graph. And drawing a correlation diagram after all the vertexes and the binomial displacement set are obtained. And connecting any two item permutation sets, adding 1 to a connection count when the permutation occurs again, and removing the non-frequent association according to the association diagram and the support count by the algorithm to obtain a frequent association item set. And obtaining all the two frequent item sets in the transaction set according to the frequent association item set. And obtaining three frequent item sets according to the frequent association item set.
And S150, processing the preset association index of the association rule based on the ant lion algorithm to obtain the association index of the real-time alarm information.
In some embodiments, the correlation indicators include a confidence and an imbalance ratio. The confidence level refers to the probability of occurrence of one transaction on the premise that another transaction occurs. In fault diagnosis, it can be understood that the probability of occurrence of one alarm signal when another alarm signal occurs can reflect the derivative relationship between one alarm signal and another alarm signal. In order to analyze which alarm signal may reflect the root cause of the fault. In order to find the degree of correlation between two transactions, a measure of the degree of improvement is also introduced, which may reflect A, B the correlation between two transactions, i.e. whether a positive, negative or non-correlated relationship is present between two alarm signals in the fault analysis. But the degree of promotion is greatly affected by zero transactions: when the number of zero transactions irrelevant to A and B is less, the promotion degree is higher; otherwise, the lifting degree is smaller. Besides the indexes, the invention also introduces an imbalance ratio IR, has zero invariance and is suitable for databases with more data. The two indexes are used together to reflect the correlation between the transactions. The imbalance ratio index can better reflect the relation between the occurrence probability of two kinds of transactions in the rule, the closer the imbalance ratio is to zero, the higher the probability of occurrence of a back part under the condition that a front part occurs, and the opposite is true. The larger the unbalance ratio is, the more likely the front part occurs and the rear part occurs, but the opposite is not true. Wherein the confidence is
Figure BDA0003204526250000141
Figure BDA0003204526250000142
A and B are respectively any different target alarm information in the sub-classification alarm information set,
Figure BDA0003204526250000143
the probability of the occurrence of the alarm information B is under the premise of the occurrence of the alarm information of the target A; imbalance ratio of
Figure BDA0003204526250000144
Sup (A) is the support degree of the target alarm information A, Sup (B) is the support degree of the target alarm information B, and Sup (A → B) is the support degree containing the target alarm information A and the target alarm information B at the same time.
In the invention, the initial values of the confidence coefficient and the unbalance ratio are preset, and are respectively the first confidence coefficient and the first unbalance ratio. As shown in fig. 4, in the process of the ant lion algorithm, the ant lion algorithm is used for iterative processing, where the input quantity is the support degree, the confidence degree and the imbalance ratio, the weighted sum of the data coverage rate and the average imbalance ratio of all rules is used as a fitness function, and the output quantity is the support degree, the confidence degree and the imbalance ratio in the optimal state and the fitness value at that time.
The ant lion algorithm set in the invention has the following parameters: the number of ants and ant lions is set to 10, the maximum number of iterations is 100, and the parameters K1 and K2 are 0.9 and 0.1 respectively.
The fitness function set is a weighted sum of the data coverage and the average imbalance ratio of all rules:
f(x1)＝-(K1*CR-K2*IRave)；
the data coverage rate CR is the ratio of the alarm signals in all generated rules to the number of all alarm signals in the sample set, and is used to detect whether the result is successful and full coverage. IRaveRefers to the average imbalance ratio of all rules.
And after the preset first confidence coefficient and the first unbalance ratio are processed by the ant lion algorithm, obtaining the second confidence coefficient and the second unbalance ratio of the optimal real-time warning information.
Subsequently, a correlation analysis can be performed.
And S150, obtaining root alarm information in the real-time alarm information according to the association index and the association rule of the real-time alarm information.
In some embodiments, when the confidence of the target association rule is greater than the second confidence and the unbalance ratio of the target association rule is less than the second unbalance ratio, determining the antecedent of the target association rule as the root alarm information in the real-time alarm information; wherein the target association rule is any one of the association rules.
After the optimal correlation indexes of the correlation rule and the real-time alarm information are screened out, alarm signals meeting the following conditions can be found out in the correlation rule: the confidence coefficient is larger than or equal to the second confidence coefficient, the unbalance ratio is smaller than or equal to the second unbalance ratio, and the number of generated association rules is the most. The alarm signal meeting the above condition is the root alarm.
Because the diagnostic data in the conventional fault diagnosis is more and difficult to screen, the diagnosis accuracy is lower. In the embodiment of the invention, the real-time alarm information of the secondary system is firstly acquired, and the real-time alarm information is subjected to preset processing to obtain the preprocessed alarm information; and then, comparing a preset classification alarm information set and a preprocessing alarm information set in a preset C4.5 fault decision tree model to obtain a sub-classification alarm information set of the real-time alarm information. And then, constructing a relevance rule of the sub-classification alarm information set based on a P-growth algorithm, and then processing a preset relevance index of the relevance rule based on an ant lion algorithm to obtain a relevance index of the real-time alarm information. And finally, obtaining the root alarm information in the real-time alarm information according to the association index and the association rule of the real-time alarm information. Therefore, after the real-time alarm information is processed by the preset C4.5 fault decision tree model, the P-growth algorithm and the ant lion algorithm, the root alarm information can be obtained, and the diagnosis accuracy is improved.
For example: and a single-phase short circuit fault occurs in a certain intelligent station, and the protection is refused to operate. When a fault occurs, the secondary system displays the following information: the merging unit sends out a device abnormity warning signal, the merging unit samples and alarms, the protection device samples and alarms, and the merging unit communicates with the protection device and alarms. The alarm signal of the fault is: the merging unit device 11-1 alarms abnormally, the merging unit 11-1 samples abnormally, the protection device 101SV alarms, and the protection 101 samples alarms. According to the analysis result of the preset C4.5 fault decision tree model, the fault type can be determined to be the fault of the DSP of the merging unit. And comparing the alarm signals with all preset classification alarm information sets of the fault types of the categories, thereby determining the sub-classification alarm information sets of the fault types.
The preset minimum support degree is 0, the preset first confidence degree is 0, and the preset first unbalance ratio is 1. After the processing of the ant lion algorithm, the optimal minimum support degree is 0.05, the second confidence coefficient is 0.648 and the second unbalance ratio is 0.36.
Then, a P-growth algorithm is adopted to construct the relevance rule of the sub-classification alarm information set, and the result of data mining shows that: the correlation rule of the front piece, which is the merging unit sampling exception and meets the requirements of confidence degree and unbalance ratio, is the most. Wherein, the confidence of the merging unit 11-1 sampling abnormity to the merging unit device 11-1 alarm abnormity is 0.97, and the unbalance ratio is 0.35; the confidence coefficient of the abnormal sampling of the merging unit 11-1 to the warning of the SV of the protection device 101 is 0.72, and the unbalance ratio is 0.34; the confidence of the abnormal sampling of the merging unit 11-1 to the sampling alarm of the protection 101 is 0.75, and the unbalance ratio is 0.26.
The confidence of the sampling abnormality of the merging unit 11-1 to the other three alarm signals is greater than 0.648, the kulc measurement is also greater, so that the two alarm signals are closely related, and besides, the imbalance ratio is also less than 0.36, which proves that in the case of the former, the latter is more likely to occur, and vice versa. In summary, the merging unit 11-1 samples the exception as the root alarm signal of the fault, and the rest signals are derived alarm signals. The failure occurs at the merge unit sampling module.
If the association rules are not screened, more than 17 association rules are provided according to the requirement, so that a plurality of unnecessary association rules are reduced after the alarm correlation analysis is added. Therefore, the accuracy of fault diagnosis is improved, and the efficiency of fault analysis is further improved.
For example: when the relay protection of a certain intelligent station is in misoperation, the merging unit-protection device loop has communication fault, and the dispatching center receives the following alarm information: the method comprises the following steps of warning by a protection device 101GOOSE, warning by a protection device 101SV, warning by an intelligent terminal 101GOOSE and detecting line communication interruption by a switch. And comparing the analysis result of the preset fault decision tree model, and determining that the fault type is the fault of the I/O port of the protection device. Thereby determining a sub-classified set of alarm information for this fault type of real-time alarm information.
The preset minimum support degree is 0, the preset first confidence degree is 0, and the preset first unbalance ratio is 1. After the processing of the ant lion algorithm, the optimal minimum support degree is 0.03, the second confidence coefficient is 0.553, the second unbalance ratio is 0.29,
then, a P-growth algorithm is adopted to construct the association rules of the sub-classification alarm information sets, and 6 association rules are generated, wherein the association rules comprise 1 line communication interruption → 101GOOSE alarm of the line protection device, 2 line communication interruption → 101SV alarm of the line protection device, 3 line communication interruption → 101GOOSE alarm of the intelligent terminal, 4 line protection device 101GOOSE alarm → 101SV alarm, 5 line protection device 101GOOSE alarm → 101GOOSE alarm, and 6 line protection device 101SV alarm → 101GOOSE alarm. Wherein the confidence of the association rule 1 is 0.578 and the imbalance ratio is 0.45; the confidence of the association rule 2 is 0.564, and the imbalance ratio is 0.46; the confidence of the association rule 3 is 0.655 and the imbalance ratio is 0.62; the confidence of the association rule 4 is 0.673, and the unbalance ratio is 0.02; the confidence of the association rule 5 is 0.603, and the imbalance ratio is 0.23; the confidence of the association rule 6 is 0.592 and the imbalance ratio is 0.24.
The confidence of each association rule is greater than 0.553, but only the imbalance ratios of the association rules numbered 4, 5, and 6 meet the index requirement, so that only the GOOSE alarm and SV alarm of the protection device 101 are root alarms.
Compared with the association analysis when the classification of the preset fault decision tree model is not performed, when the alarm information is not subjected to the classification, the alarm information of other types interferes the result of the association analysis when the confidence coefficient is calculated, for example, when the merging unit has a fault, the number of GOOSE and SV alarm signals of the protection device 101 is increased, so that the confidence coefficient of the association rule of which the two are the predecessors is reduced. So that the screening criteria are not met, resulting in the inability to find the root alarm.
Based on the fault diagnosis method for the intelligent substation provided by the embodiment, correspondingly, the invention further provides a specific implementation mode of the fault diagnosis device for the intelligent substation applied to the fault diagnosis method for the intelligent substation. Please see the examples below.
As shown in fig. 5, there is provided a fault diagnosis apparatus of an intelligent substation, the apparatus including:
an information obtaining module 510 for obtaining real-time alarm information of the secondary system;
the preset processing module 520 is used for carrying out preset processing on the real-time alarm information to obtain preprocessed alarm information;
the information comparison module 530 is used for comparing a preset classification alarm information set and a pre-processing alarm information set in a preset C4.5 fault decision tree model to obtain a sub-classification alarm information set of real-time alarm information;
the construction rule module 540 is used for constructing the association rule of the sub-classification alarm information set based on the P-growth algorithm;
the index optimization module 550 is used for processing the preset association index of the association rule based on the ant lion algorithm to obtain the association index of the real-time alarm information;
the information determining module 560 obtains root alarm information in the real-time alarm information according to the association index and the association rule of the real-time alarm information.
In a possible implementation manner, the information comparison module 530 is further configured to obtain historical alarm information of the secondary system, where the historical alarm information is divided into training information and test information according to a preset rule;
training the training information through a C4.5 decision tree algorithm to obtain a decision tree model;
verifying and pruning the decision tree model by using the test information to obtain a preset C4.5 fault decision tree model; the preset C4.5 fault decision tree model consists of a plurality of preset classification alarm information sets with different fault types;
and comparing all preset classification alarm information sets in the preset C4.5 fault decision tree model with the preset alarm information, and determining the preset classification alarm information set with the highest matching degree as a sub-classification alarm information set of the real-time alarm information.
In a possible implementation manner, the information comparison module 530 is further configured to, before the training information is trained through a C4.5 decision tree algorithm to obtain a decision tree model, the method further includes:
constructing a fault attribute database of historical alarm information; the historical alarm information comprises secondary equipment alarm information, a GOOSE abnormal message and an SV abnormal message; the fault attribute database comprises device locking, self-checking alarm information, GOOSE alarm information, SV alarm information and fault types; storing the historical alarm information into a fault attribute database according to a preset rule;
and constructing a decision tree model based on a C4.5 decision tree algorithm and a fault attribute database.
In one possible implementation, the C4.5 decision tree algorithm employs taylor series instead of logarithmic operation; wherein the C4.5 decision tree algorithm has an information gain ratio of
Figure BDA0003204526250000191
Gainratio (A) is the information gain rate of a certain attribute A selected during classification, gain (A) is the information gain of attribute A, SplitInfoA(T) is the split information measure of the A attribute in the whole preset classification alarm information set T, T is the whole preset classification alarm information set, TjThe total data number, TC, of the jth preset classification alarm information set in the whole preset classification alarm information set TiIs that the whole preset classification alarm information set T belongs to a sub-classification alarm information set CiTotal number of data of (TC)ijThe j preset classified alarm information set in the whole preset classified alarm information set T belongs to a sub-classified alarm information set CiTotal number of data of (1).
In a possible implementation manner, the construction rule module 540 is further configured to perform iterative processing on a preset minimum support degree of the association rule based on the ant lion algorithm to obtain a minimum support degree of the sub-classification alarm information set;
deleting the target alarm information with the sub-classification alarm information set smaller than the minimum support degree to obtain a sub-classification alarm associated information set; wherein, the target alarm information is any one of the alarm information in the sub-classification alarm information set; wherein the support degree is
Figure BDA0003204526250000192
A is target alarm information, N is the number of all target alarm information, sup (A) is the support degree of the target alarm information A.
And constructing the association rule of the sub-classification alarm association information set based on a P-growth algorithm.
In one possible implementation, the correlation index includes a confidence and an imbalance ratio;
accordingly, the metric optimization module 550 is further configured to,
and carrying out iterative processing on the preset first confidence coefficient and the first unbalance ratio based on the ant lion algorithm to obtain a second confidence coefficient and a second unbalance ratio of the real-time alarm information.
In a possible implementation manner, the information determining module 560 is further configured to determine, when the confidence of the target association rule is greater than the second confidence and the imbalance ratio of the target association rule is smaller than the second imbalance ratio, a front piece of the target association rule as a root alarm information in the real-time alarm information; wherein the target relevance rule is any one of the relevance rules;
wherein the confidence is
Figure BDA0003204526250000201
A and B are respectively any different target alarm information in the sub-classification alarm information set,
Figure BDA0003204526250000202
the probability of the occurrence of the alarm information B is under the premise of the occurrence of the alarm information of the target A;
imbalance ratio of
Figure BDA0003204526250000203
Sup (A) is the support degree of the target alarm information A, Sup (B) is the support degree of the target alarm information B, and Sup (A → B) is the support degree containing the target alarm information A and the target alarm information B at the same time.
Fig. 6 is a schematic diagram of an electronic device provided in an embodiment of the present invention. As shown in fig. 6, the electronic apparatus 6 of this embodiment includes: a processor 60, a memory 61 and a computer program 62 stored in said memory 61 and executable on said processor 60. The processor 60, when executing the computer program 62, implements the steps in the fault diagnosis method embodiments of the respective intelligent substations described above, such as the steps 110 to 160 shown in fig. 1. Alternatively, the processor 60, when executing the computer program 62, implements the functions of the modules/units in the above-mentioned device embodiments, such as the functions of the modules 510 to 560 shown in fig. 5.
Illustratively, the computer program 62 may be partitioned into one or more modules/units that are stored in the memory 61 and executed by the processor 60 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 62 in the electronic device 6. For example, the computer program 62 may be divided into the modules 510 to 560 shown in fig. 5.
The electronic device 6 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The electronic device 6 may include, but is not limited to, a processor 60, a memory 61. It will be appreciated by those skilled in the art that fig. 6 is merely an example of the electronic device 6 and does not constitute a limitation of the electronic device 6 and may include more or less components than those shown, or some components may be combined, or different components, e.g. the terminal may also include input output devices, network access devices, buses, etc.
The Processor 60 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 61 may be an internal storage unit of the electronic device 6, such as a hard disk or a memory of the electronic device 6. The memory 51 may also be an external storage device of the electronic device 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the electronic device 6. The memory 61 is used for storing the computer program and other programs and data required by the terminal. The memory 61 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal and method may be implemented in other ways. For example, the above-described apparatus/terminal embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the above embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of the fault diagnosis method embodiments of each intelligent substation may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims (10)

1. A fault diagnosis method of an intelligent substation is characterized by comprising the following steps:
acquiring real-time alarm information of a secondary system of an intelligent substation;
presetting the real-time alarm information to obtain preprocessed alarm information;
comparing all preset classification alarm information sets in a preset C4.5 fault decision tree model with the preprocessed alarm information to obtain a sub-classification alarm information set of the real-time alarm information;
constructing a relevance rule of the sub-classification alarm information set based on a P-growth algorithm;
processing a preset association index of the association rule based on an ant lion algorithm to obtain an association index of the real-time alarm information;
and obtaining root alarm information in the real-time alarm information according to the association index of the real-time alarm information and the association rule.
2. The method for diagnosing the fault of the intelligent substation according to claim 1, wherein the step of comparing all preset classification alarm information sets in a preset C4.5 fault decision tree model with the pre-processed alarm information to obtain a sub-classification alarm information set of the real-time alarm information comprises:
acquiring historical alarm information of a secondary system, wherein the historical alarm information is divided into training information and testing information according to a preset rule;
training the training information through a C4.5 decision tree algorithm to obtain a decision tree model;
verifying and pruning the decision tree model by using the test information to obtain the preset C4.5 fault decision tree model; the preset C4.5 fault decision tree model is composed of a plurality of preset classification alarm information sets with different fault types;
and comparing all the preset classified alarm information sets in the preset C4.5 fault decision tree model with the preset alarm information, and determining the preset classified alarm information set with the highest matching degree as a sub-classified alarm information set of the real-time alarm information.
3. The method for fault diagnosis of an intelligent substation according to claim 2, wherein before the training information is trained by a C4.5 decision tree algorithm to obtain a decision tree model, the method further comprises:
constructing a fault attribute database of the historical alarm information; the historical alarm information comprises secondary equipment alarm information, a GOOSE abnormal message and an SV abnormal message; the fault attribute database comprises device locking, self-checking alarm information, GOOSE alarm information, SV alarm information and fault types; the historical alarm information is stored in the fault attribute database according to a preset rule;
and constructing the decision tree model based on the C4.5 decision tree algorithm and the fault attribute database.
4. The fault diagnosis method of an intelligent substation of claim 2 or 3, wherein the C4.5 decision tree algorithm employs Taylor series instead of logarithmic operation;
wherein the C4.5 decision tree algorithm has an information gain ratio of
Figure FDA0003204526240000021
Gainratio is the information Gain rate of a certain attribute A selected during classification, Gain is the information Gain of the attribute A, SplitInfoAMeasure the split information of the A attribute in the whole preset classification alarm information set T, T is the whole preset classification alarm information set, TjThe total data number, TC, of the jth preset classification alarm information set in the whole preset classification alarm information set TiIs that the whole preset classification alarm information set T belongs to a sub-classification alarm information set CiTotal number of data of (TC)ijThe j preset classified alarm information set in the whole preset classified alarm information set T belongs to a sub-classified alarm information set CiTotal number of data of (1).
5. The method for diagnosing the fault of the intelligent substation according to claim 1, wherein the constructing the association rule of the sub-classification alarm information set based on the P-growth algorithm includes:
performing iterative processing on the preset minimum support degree of the association rule based on the ant lion algorithm to obtain the minimum support degree of the sub-classification alarm information set;
deleting the target alarm information with the sub-classification alarm information set smaller than the minimum support degree to obtain a sub-classification alarm associated information set; wherein, the target alarm information is any one alarm information in the sub-classification alarm information set;
constructing an association rule of the sub-classification alarm association information set based on a P-growth algorithm;
wherein the support degree is
Figure FDA0003204526240000031
A is target alarm information, N is the number of all target alarm information, sup (A) is the support degree of the target alarm information A.
6. The method of fault diagnosis of an intelligent substation of claim 5, wherein the correlation index includes a confidence and an imbalance ratio;
the processing of the preset association index of the association rule based on the ant lion algorithm to obtain the association index of the real-time alarm information comprises the following steps:
performing iterative processing on a preset first confidence coefficient and a first imbalance ratio based on an ant lion algorithm to obtain a second confidence coefficient and a second imbalance ratio of the real-time alarm information;
wherein the confidence is
Figure FDA0003204526240000032
A and B are respectively any different target alarm information in the sub-classification alarm information set,
Figure FDA0003204526240000034
the probability of the occurrence of the alarm information B is under the premise of the occurrence of the alarm information of the target A;
the unbalance ratio is
Figure FDA0003204526240000033
Sup (A) is the support degree of the target alarm information A, Sup (B) is the support degree of the target alarm information B, and Sup (A → B) is the support degree containing the target alarm information A and the target alarm information B at the same time.
7. The method for diagnosing the fault of the intelligent substation according to claim 6, wherein the obtaining of the root alarm information in the real-time alarm information according to the correlation index of the real-time alarm information and the correlation rule comprises:
when the confidence of the target relevance rule is greater than the second confidence and the unbalance ratio of the target relevance rule is less than the second unbalance ratio, determining the front piece of the target relevance rule as the root alarm information in the real-time alarm information; wherein the target association rule is any one of the association rules.
8. A fault diagnosis device of an intelligent substation is characterized by comprising:
the information acquisition module is used for acquiring real-time alarm information of a secondary system of the intelligent substation;
the preset processing module is used for carrying out preset processing on the real-time alarm information to obtain preprocessed alarm information;
the information comparison module is used for comparing a preset classified alarm information set in a preset C4.5 fault decision tree model with the preprocessed alarm information to obtain a sub-classified alarm information set of the real-time alarm information;
the building rule module is used for building the association rule of the sub-classification alarm information set based on a P-growth algorithm;
the index optimization module is used for processing the preset association index of the association rule based on the ant lion algorithm to obtain the association index of the real-time alarm information;
and the information determining module is used for obtaining the root alarm information in the real-time alarm information according to the correlation index of the real-time alarm information and the correlation rule.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
CN202110913435.5A 2021-08-10 2021-08-10 Fault diagnosis method, device, equipment and storage medium of intelligent substation Pending CN113591393A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110913435.5A CN113591393A (en) 2021-08-10 2021-08-10 Fault diagnosis method, device, equipment and storage medium of intelligent substation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110913435.5A CN113591393A (en) 2021-08-10 2021-08-10 Fault diagnosis method, device, equipment and storage medium of intelligent substation

Publications (1)

Publication Number Publication Date
CN113591393A true CN113591393A (en) 2021-11-02

Family

ID=78256810

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110913435.5A Pending CN113591393A (en) 2021-08-10 2021-08-10 Fault diagnosis method, device, equipment and storage medium of intelligent substation

Country Status (1)

Country Link
CN (1) CN113591393A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114615129A (en) * 2022-03-09 2022-06-10 广东电网有限责任公司 Fault diagnosis method, device and system for power communication network
CN114818387A (en) * 2022-06-20 2022-07-29 浙江大学杭州国际科创中心 Performance evaluation method of nonlinear conductive material
CN116089224A (en) * 2023-04-11 2023-05-09 宇动源(北京)信息技术有限公司 Alarm analysis method, alarm analysis device, calculation node and computer readable storage medium

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104239437A (en) * 2014-08-28 2014-12-24 国家电网公司 Power-network-dispatching-oriented intelligent warning analysis method
CN104463709A (en) * 2014-12-12 2015-03-25 国家电网公司 Substation alarm information processing method based on decision trees
CN107016507A (en) * 2017-04-07 2017-08-04 国网技术学院 Electric network fault method for tracing based on data mining technology
CN107835087A (en) * 2017-09-14 2018-03-23 北京科东电力控制系统有限责任公司 A kind of safety means alarm regulation extraction method based on Frequent Pattern Mining
CN110020967A (en) * 2019-04-18 2019-07-16 首钢京唐钢铁联合有限责任公司 The information processing method and device of a kind of dispatching of power netwoks end substation intelligent alarm
CN110674189A (en) * 2019-09-27 2020-01-10 国网四川省电力公司电力科学研究院 Method for monitoring secondary state and positioning fault of intelligent substation
CN110752942A (en) * 2019-09-06 2020-02-04 平安科技（深圳）有限公司 Alarm information decision method and device, computer equipment and storage medium
CN111208385A (en) * 2019-12-19 2020-05-29 云南电网有限责任公司玉溪供电局 Online fault layered diagnosis method for power grid
CN111612149A (en) * 2020-05-21 2020-09-01 国网湖南省电力有限公司 Main network line state detection method, system and medium based on decision tree
CN111898776A (en) * 2020-08-03 2020-11-06 贵州电网有限责任公司 Transformer substation equipment abnormity and accident handling method
CN112415331A (en) * 2020-10-27 2021-02-26 中国南方电网有限责任公司 Power grid secondary system fault diagnosis method based on multi-source fault information
CN112528458A (en) * 2020-09-16 2021-03-19 贵州电网有限责任公司 Metering master station alarm analysis model construction method based on FP-Growth algorithm
CN112749509A (en) * 2020-12-30 2021-05-04 西华大学 Intelligent substation fault diagnosis method based on LSTM neural network

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104239437A (en) * 2014-08-28 2014-12-24 国家电网公司 Power-network-dispatching-oriented intelligent warning analysis method
CN104463709A (en) * 2014-12-12 2015-03-25 国家电网公司 Substation alarm information processing method based on decision trees
CN107016507A (en) * 2017-04-07 2017-08-04 国网技术学院 Electric network fault method for tracing based on data mining technology
CN107835087A (en) * 2017-09-14 2018-03-23 北京科东电力控制系统有限责任公司 A kind of safety means alarm regulation extraction method based on Frequent Pattern Mining
CN110020967A (en) * 2019-04-18 2019-07-16 首钢京唐钢铁联合有限责任公司 The information processing method and device of a kind of dispatching of power netwoks end substation intelligent alarm
CN110752942A (en) * 2019-09-06 2020-02-04 平安科技（深圳）有限公司 Alarm information decision method and device, computer equipment and storage medium
CN110674189A (en) * 2019-09-27 2020-01-10 国网四川省电力公司电力科学研究院 Method for monitoring secondary state and positioning fault of intelligent substation
CN111208385A (en) * 2019-12-19 2020-05-29 云南电网有限责任公司玉溪供电局 Online fault layered diagnosis method for power grid
CN111612149A (en) * 2020-05-21 2020-09-01 国网湖南省电力有限公司 Main network line state detection method, system and medium based on decision tree
CN111898776A (en) * 2020-08-03 2020-11-06 贵州电网有限责任公司 Transformer substation equipment abnormity and accident handling method
CN112528458A (en) * 2020-09-16 2021-03-19 贵州电网有限责任公司 Metering master station alarm analysis model construction method based on FP-Growth algorithm
CN112415331A (en) * 2020-10-27 2021-02-26 中国南方电网有限责任公司 Power grid secondary system fault diagnosis method based on multi-source fault information
CN112749509A (en) * 2020-12-30 2021-05-04 西华大学 Intelligent substation fault diagnosis method based on LSTM neural network

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114615129A (en) * 2022-03-09 2022-06-10 广东电网有限责任公司 Fault diagnosis method, device and system for power communication network
CN114615129B (en) * 2022-03-09 2024-01-23 广东电网有限责任公司 Fault diagnosis method, device and system for power communication network
CN114818387A (en) * 2022-06-20 2022-07-29 浙江大学杭州国际科创中心 Performance evaluation method of nonlinear conductive material
CN114818387B (en) * 2022-06-20 2023-06-13 浙江大学杭州国际科创中心 Performance evaluation method of nonlinear conductive material
CN116089224A (en) * 2023-04-11 2023-05-09 宇动源(北京)信息技术有限公司 Alarm analysis method, alarm analysis device, calculation node and computer readable storage medium

Similar Documents

Publication Publication Date Title
CN109034244B (en) Line loss abnormity diagnosis method and device based on electric quantity curve characteristic model
CN113591393A (en) Fault diagnosis method, device, equipment and storage medium of intelligent substation
CN114298863B (en) Data acquisition method and system of intelligent meter reading terminal
CN113592343A (en) Fault diagnosis method, device, equipment and storage medium of secondary system
CN115170000B (en) Remote monitoring method and system based on electric energy meter communication module
CN111796957B (en) Transaction abnormal root cause analysis method and system based on application log
CN111176953B (en) Abnormality detection and model training method, computer equipment and storage medium
CN115865649B (en) Intelligent operation and maintenance management control method, system and storage medium
CN109947815B (en) Power theft identification method based on outlier algorithm
CN112528458A (en) Metering master station alarm analysis model construction method based on FP-Growth algorithm
CN113810792B (en) Edge data acquisition and analysis system based on cloud computing
CN113869721A (en) Substation equipment health state classification method and apparatus
CN111626360A (en) Method, device, equipment and storage medium for detecting fault type of boiler
CN110555619A (en) Power supply capacity evaluation method based on intelligent power distribution network
CN114138601A (en) Service alarm method, device, equipment and storage medium
CN113554361A (en) Comprehensive energy system data processing and calculating method and processing system
CN109933450A (en) A kind of method of calibration and device of intelligent substation secondary void loop configuration file
CN113835947B (en) Method and system for determining abnormality cause based on abnormality recognition result
CN115422263B (en) Multifunctional universal fault analysis method and system for electric power field
CN113391256B (en) Electric energy meter metering fault analysis method and system of field operation terminal
Pan et al. Study on intelligent anti–electricity stealing early-warning technology based on convolutional neural networks
CN115766793A (en) Based on data center computer lab basis environmental monitoring alarm device
CN115494431A (en) Transformer fault warning method, terminal equipment and computer readable storage medium
CN115146715A (en) Power utilization potential safety hazard diagnosis method, device, equipment and storage medium
CN115577927A (en) Important power consumer electricity utilization safety assessment method and device based on rough set

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