CN116304928A - Power supply equipment fault prediction method, device, equipment and storage medium - Google Patents
Power supply equipment fault prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116304928A CN116304928A CN202310281002.1A CN202310281002A CN116304928A CN 116304928 A CN116304928 A CN 116304928A CN 202310281002 A CN202310281002 A CN 202310281002A CN 116304928 A CN116304928 A CN 116304928A
- Authority
- CN
- China
- Prior art keywords
- equipment
- fault prediction
- power supply
- data
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000003066 decision tree Methods 0.000 claims description 47
- 238000012549 training Methods 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000007257 malfunction Effects 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60M—POWER SUPPLY LINES, AND DEVICES ALONG RAILS, FOR ELECTRICALLY- PROPELLED VEHICLES
- B60M3/00—Feeding power to supply lines in contact with collector on vehicles; Arrangements for consuming regenerative power
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application relates to a power supply equipment fault prediction method, a device, equipment and a storage medium, which are applied to the field of power monitoring, wherein the method comprises the following steps: acquiring operation condition data corresponding to power supply equipment fault prediction; extracting the characteristics of the operation condition data to obtain characteristic data; inputting the characteristic data into a preset fault prediction model to obtain a fault prediction result; if the failure prediction result is equipment failure, generating a failure early warning instruction, and sending the failure early warning instruction to an equipment terminal of a worker. The technical effect that this application had is: the early prediction of the faults of the equipment in the running period is realized according to the power supply equipment fault prediction monitoring data in the PSCADA power supply equipment fault prediction system.
Description
Technical Field
The present disclosure relates to the field of power monitoring technologies, and in particular, to a power supply device fault prediction method, device, equipment, and storage medium.
Background
The power supply profession is one of the most important professions of urban rail transit intelligent operation and maintenance, and the operation stability of power supply equipment fault prediction is directly related to the safe production and safe operation of urban rail transit. Therefore, all urban rail transit enterprises provide a monitoring power supply equipment fault Prediction System (PSCADA) for the safety operation of power supply equipment fault prediction so as to remove fault hidden dangers of various power supply equipment fault predictions in time, and fundamentally guarantee the operation safety of urban rails.
The PSCADA power supply equipment fault prediction system is a track traffic power monitoring power supply equipment fault prediction system, and is an important embodiment of communication technology and computer network technology in urban track traffic application. The power supply equipment fault prediction system monitors all-line power transformation equipment, and collects and analyzes operation data of the power transformation equipment, so that scientific basis is provided for scheduling and maintenance of the power supply equipment fault prediction system. The traction power supply equipment fault prediction system and the full-line power transformation and distribution power supply equipment fault prediction system are ensured to run safely, reliably and economically.
In carrying out the present application, the inventors have found that at least the following problems exist in this technology: the existing PSCADA power supply equipment fault prediction system generally comprises a remote sub power supply equipment fault prediction system, a remote signaling sub power supply equipment fault prediction system and a remote sub power supply equipment fault prediction system, wherein each sub power supply equipment fault prediction system has real-time monitoring and recording functions, and meanwhile, the PSCADA power supply equipment fault prediction system is provided with fault classification and fault recording prompt confirmation functions, but does not provide a better fault prediction scheme. Therefore, how to realize the early prediction of the faults of the equipment in the running period according to the power supply equipment fault prediction monitoring data in the PSCADA power supply equipment fault prediction system is a common problem faced by urban rail power supply professions.
Disclosure of Invention
In order to realize early prediction of faults of equipment operation period according to power equipment fault prediction monitoring data in a PSCADA power equipment fault prediction system, the power equipment fault prediction method, device, equipment and storage medium are provided.
In a first aspect, the present application provides a power supply device fault prediction method, which adopts the following technical scheme: the method comprises the following steps: acquiring operation condition data corresponding to power supply equipment fault prediction;
extracting the characteristics of the operation condition data to obtain characteristic data;
inputting the characteristic data into a preset fault prediction model to obtain a fault prediction result, wherein the fault prediction result comprises equipment faults and equipment normal;
if the failure prediction result is equipment failure, generating a failure early warning instruction, and sending the failure early warning instruction to an equipment terminal of a worker.
According to the technical scheme, the power supply equipment fault prediction system predicts the running condition of the power supply equipment fault prediction in the future by collecting the running condition data of the power supply equipment fault prediction and inputting the running condition data into the preset fault prediction model, so that a follow-up worker can regulate and control the power supply equipment fault prediction in advance according to the predicted running condition, and the possibility of faults of the work power supply equipment fault prediction is reduced.
In a specific embodiment, after the obtaining the operation condition data corresponding to the power supply equipment failure prediction, the method further includes:
inquiring a corresponding operation data threshold value in a preset fault database according to the equipment number;
comparing the real-time operation parameters corresponding to the equipment numbers with the operation data threshold;
and if the real-time operation parameter reaches the operation data threshold value, generating an alarm signal.
According to the technical scheme, before the power supply equipment fault prediction system predicts the future running state of the power supply equipment fault prediction according to the running condition data, the running condition data is firstly utilized to judge whether the power supply equipment fault prediction has faults at the moment, so that workers can respond to the faults of the power supply equipment fault prediction in time, and economic losses caused by equipment faults are reduced.
In a specific embodiment, the inputting the feature data into a preset failure prediction model specifically includes:
inquiring a corresponding decision tree model according to the equipment number;
and inputting the real-time operation data corresponding to the equipment number into the decision tree model.
Through the technical scheme, different equipment types correspond to different fault prediction models, so that the expertise of the fault prediction models is improved, and the accuracy of a fault prediction result is improved.
In a specific embodiment, the construction of the decision tree model specifically includes:
acquiring historical working condition data in a preset historical operation database, wherein the historical working condition data at least comprises a historical equipment number and corresponding historical operation data;
classifying the historical working condition data according to the historical equipment numbers;
acquiring historical operation data under the same equipment number;
preprocessing the historical operation data to generate a training data set;
and constructing a decision tree model according to the training data set.
According to the technical scheme, the characteristic data related to the equipment faults in the historical working condition data are extracted to obtain the historical characteristic data, the historical characteristic data are classified, the historical characteristic data under the same classification category form a training data set, and classification processing operation is carried out on the historical working condition data before the decision tree model is built, so that the quality of the data for building the decision tree model is improved.
In a specific embodiment, the constructing a decision tree model according to the training dataset specifically includes:
iteratively calculating the information gain corresponding to each characteristic attribute under each node of the decision tree model;
dividing a training data set contained in the current node according to the characteristic attribute corresponding to the maximum information gain so as to form a plurality of child nodes based on the current node splitting until the category attribute can be determined according to the data set contained in the node;
and outputting a decision tree model formed according to the training data set.
According to the technical scheme, the power supply equipment fault prediction system divides the training data set by taking the characteristic attribute with the maximum information gain of the characteristic attributes as the test attribute until no redundant characteristic attribute is used for dividing the training data set, and the characteristic attribute with the optimal information gain is used for dividing the training data set as the test attribute, so that the stability of the whole decision tree model is higher, and the influence of noise is not easy.
In a specific embodiment, after the sending the fault warning instruction to the equipment terminal of the staff member, the method further includes:
inquiring downstream equipment corresponding to power supply equipment fault prediction, wherein the fault prediction result is equipment fault, in a preset equipment relation network;
and preferentially acquiring the operation condition data corresponding to the downstream equipment.
By the technical scheme, the power supply equipment fault prediction system predicts the equipment related to the power supply equipment fault prediction with the equipment fault prediction result being the equipment fault preferentially, and is beneficial to improving the efficiency of fault prediction
In a specific embodiment, the operating condition data includes at least: output voltage, input current, output current.
Through the technical scheme, the power supply equipment fault prediction system acquires the operation data related to power supply equipment fault prediction as far as possible, ensures that the data quantity for predicting the power supply equipment fault prediction operation condition is sufficient, and is beneficial to further improving the accuracy of power supply equipment fault prediction.
In a second aspect, the present application provides a power supply device fault prediction apparatus, which adopts the following technical scheme: the device comprises:
the operation condition data acquisition module is used for acquiring operation condition data corresponding to the power supply equipment fault prediction;
the characteristic data extraction module is used for carrying out characteristic extraction on the operation condition data to obtain characteristic data;
the equipment fault prediction result acquisition module is used for inputting the characteristic data into a preset fault prediction model to obtain a fault prediction result, wherein the fault prediction result comprises equipment faults and equipment normal;
and the fault early warning instruction generation module is used for generating a fault early warning instruction if the fault prediction result is equipment fault and sending the fault early warning instruction to an equipment terminal of a worker.
In a third aspect, the present application provides a computer device, which adopts the following technical scheme: comprising a memory and a processor, said memory having stored thereon a computer program capable of being loaded by the processor and performing a power supply device failure prediction method as any one of the above.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical solutions: a computer program capable of being loaded by a processor and executing any one of the power supply device failure prediction methods described above is stored.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the power supply equipment fault prediction system predicts the running condition of the power supply equipment fault prediction in the future by collecting running condition data of the power supply equipment fault prediction and inputting the running condition data into a preset fault prediction model, so that a follow-up worker can regulate and control the power supply equipment fault prediction in advance according to the predicted running condition, and the possibility of faults of the working power supply equipment fault prediction is reduced;
2. and extracting the characteristic data related to the equipment faults from the historical working condition data to obtain the historical characteristic data, classifying the historical characteristic data, forming a training data set by the historical characteristic data under the same classification category, and performing classification operation on the historical working condition data before constructing the decision tree model, thereby being beneficial to improving the quality of the data used for constructing the decision tree model.
Drawings
Fig. 1 is a flowchart of a power supply apparatus failure prediction method in an embodiment of the present application.
Fig. 2 is a block diagram of a power supply apparatus failure prediction device in the embodiment of the present application.
Reference numerals: 301. an operation condition data acquisition module; 302. a feature data extraction module; 303. the equipment fault prediction result acquisition module; 304. and the fault early warning instruction generation module.
Description of the embodiments
The present application is described in further detail below in conjunction with figures 1-2.
The embodiment of the application discloses a power supply equipment fault prediction method. The method is applied to the power supply equipment fault prediction system, and the corresponding program codes of the method are stored in a control center of the power supply equipment fault prediction system.
As shown in fig. 1, the method comprises the steps of:
s10, operation condition data corresponding to power supply equipment fault prediction are obtained.
Specifically, the operation condition data refers to various operation parameter data generated in the operation process of power supply equipment fault prediction, and in this embodiment, the main content of the operation condition data is an equipment number and a corresponding real-time operation parameter. After the power supply equipment fault prediction system is started, operation condition data of the power supply equipment fault prediction are obtained at intervals of a fixed period according to a preset timing signal, wherein the power supply equipment fault prediction mainly refers to power generation equipment, in the embodiment, the power generation equipment mainly refers to a power station boiler, a steam turbine, a gas turbine, a water turbine, a generator and the like, and the operation condition data can be parameters such as output voltage, input current, output current and the like.
S20, extracting characteristics of the operation condition data.
Specifically, the power supply equipment fault prediction system extracts characteristic values of the operation condition data according to the characteristic attributes in a preset characteristic attribute database to obtain a plurality of characteristic values corresponding to the characteristic attributes, and the characteristic attributes and the corresponding characteristic values form the characteristic data for fault.
It should be noted that, the feature attribute is an attribute for describing the same type of feature value, the power supply equipment fault prediction includes different equipment types, and a plurality of feature attributes corresponding to the power supply equipment fault prediction under different equipment types have consistent feature attributes, and also have inconsistent feature attributes.
S30, inputting the characteristic data into a preset fault prediction model.
Specifically, the power supply equipment fault prediction system inputs the generated characteristic data into a preset fault prediction model, and a current fault detection result of power supply equipment fault prediction can be obtained, wherein the fault detection result comprises two states of equipment fault and equipment normal, and it is worth mentioning that the fault prediction result can be represented by simple numerical values, for example, 0 indicates that the power supply equipment fault prediction cannot occur in a time period corresponding to the prediction time, namely, the fault prediction result is the equipment normal, 1 indicates that the power supply equipment fault prediction may occur in a time period corresponding to the prediction time, namely, the fault prediction result is the equipment fault.
And S40, if the failure prediction result is equipment failure, generating a failure early warning instruction.
Specifically, if the obtained fault prediction result is displayed as 1, the power supply equipment fault prediction system immediately generates a fault early warning instruction and sends the fault early warning instruction to an equipment terminal of a worker; if the obtained fault prediction result is displayed as 0, the power supply equipment fault prediction system continues to obtain operation data of next power supply equipment fault prediction, wherein the fault early warning signal comprises an equipment name, an equipment address and an equipment possible fault type, and after receiving the equipment fault early warning signal sent by the equipment fault power supply equipment fault prediction system, a worker can overhaul the equipment according to the content of the equipment fault early warning signal and the address where the equipment which is likely to be faulty is located. The power supply equipment fault prediction system predicts the future operation state of the power supply equipment fault prediction by utilizing the operation condition data corresponding to the power supply equipment fault prediction, so that staff intervenes in advance before the power supply equipment fault prediction really breaks down, and the possibility of the power supply equipment fault prediction breaking down is reduced as much as possible.
In one embodiment, after obtaining the operation condition data corresponding to the power supply equipment failure prediction, the following steps may be further performed:
the power supply equipment fault prediction system firstly queries a corresponding operation data threshold value in a preset fault database according to equipment numbers; the equipment number is mainly a series of numbers designed by the power supply equipment fault prediction system for distinguishing different equipment types and different equipment, wherein the equipment number consists of two parts, the first part is the equipment type number, and the equipment type numbers corresponding to the power supply equipment fault prediction under the same equipment type are consistent; the second part is the machine number, even the machine numbers corresponding to the fault prediction of two power supply equipment belonging to the same equipment type are not the same, for the sake of understanding, two equipment types are illustrated here, namely, a steam turbine and a gas turbine, 2 steam turbines are provided, namely, a steam turbine A, a steam turbine B and 3 gas turbines are provided, namely, a gas turbine A, a gas turbine B and a gas turbine C, respectively, so that the equipment number of the steam turbine A can be 001001, the equipment number of the steam turbine B can be 001002, the equipment number of the gas turbine A can be 002001, the equipment number of the gas turbine B can be 002002, the equipment number of the gas turbine C can be 002003, and the specific content of the equipment numbers can be freely set by a worker, so long as two conditions of distinguishing different equipment types and different equipment machines are met. The operation data threshold value refers to that when the operation state of the power supply equipment fault prediction belongs to the normal operation category, the maximum value and the minimum value which can be achieved by the corresponding operation parameter values are different from each other, and therefore the operation data threshold value corresponding to the power supply equipment fault prediction corresponding to the current fault prediction operation is required to be queried according to the equipment type number in the equipment number by the power supply equipment fault prediction system.
And then, the power supply equipment fault prediction system compares the real-time operation parameters corresponding to the equipment numbers with the corresponding operation data thresholds, if the real-time operation parameters reach the larger value in the operation data thresholds or fail to reach the smaller value in the operation data thresholds, the current power supply equipment fault prediction is in a fault state, the fault prediction is not needed any more, and the power supply equipment fault prediction system immediately generates an alarm signal. Detecting whether the equipment has failed prior to equipment failure prediction facilitates the extent to which the staff responds to equipment failure.
In one embodiment, in order to improve the accuracy of the device fault prediction result, the feature data is input into a preset fault prediction model, which may specifically be executed as the following steps:
and the power supply equipment fault prediction system queries a corresponding decision tree model according to the equipment number, and inputs real-time operation data corresponding to the equipment number into the queried decision tree model. It should be noted that, the fault prediction model includes a plurality of decision tree models, each decision tree model corresponds to a device type, the decision tree model is a classical algorithm model in the machine learning field, and is a method for approaching discrete function values, and the decision tree is a tree structure for classifying training samples based on features; for example: the power supply equipment fault prediction can be divided into a steam turbine, a gas turbine, a water turbine and the like according to equipment types; because the similarity between the operation data of the devices under each device type is higher, a decision tree model matched with the device type can be constructed according to different device types, so that the devices under each device type can share one decision tree model. Different equipment types correspond to different decision tree models, so that the matching degree between the decision tree models and the power supply equipment fault prediction is improved, and the accuracy degree of the equipment fault prediction result is improved.
In one embodiment, to ensure the accuracy of the device fault prediction data, the construction of the decision tree model may be specifically performed as the following steps:
acquiring historical working condition data in a historical operation database, wherein the historical working condition data at least comprises a historical equipment number and corresponding historical operation data; in order to enable the power supply equipment fault prediction system to more accurately predict equipment faults in a building, the historical operating condition data can be data of nearly three years.
The power supply equipment fault prediction system classifies historical working condition data according to equipment types, correspondingly stores the historical working condition data into different equipment type databases, specifically, the number of the equipment type databases is consistent with the equipment type corresponding to the electrical equipment, namely, each equipment type corresponds to one equipment type database, all the historical working condition data corresponding to the electrical equipment under the equipment type are stored in one equipment type database, and it is required to be noted that only the historical operation data are stored in the equipment type database, and the equipment numbers corresponding to the historical operation data are not stored any more, so that the data amount in the equipment type database is reduced.
When the power supply equipment fault prediction system builds a decision tree model, firstly, historical operation data under the same equipment type are obtained, the obtained historical operation data are subjected to feature extraction to obtain corresponding historical feature data, a plurality of historical feature data form a training database corresponding to the equipment type, the feature extraction process of the historical operation data is consistent with the feature extraction process of the operation condition data, and the description is not repeated here. Specifically, the data in the pre-training database is the part of the history operation data after the pretreatment, the power supply equipment fault prediction system extracts the characteristic values of the history operation data after the pretreatment in the pre-training database according to the characteristic attributes in the preset characteristic attribute database to obtain a plurality of characteristic values corresponding to the characteristic attributes, and then the power supply equipment fault prediction system constructs a decision tree model according to the generated training data set.
In this embodiment, a method of verifying a split sample is adopted, and the power supply equipment failure prediction system uses 80% of samples as a training construction model.
In the embodiment, an ID3 algorithm is adopted to generate a decision tree model, the ID3 algorithm is a decision tree algorithm based on an information theory and taking information entropy and information gain degree as measurement standards, so that the summary classification of a data set is realized, a power supply equipment fault prediction system iteratively calculates the information gain of each characteristic attribute in the process of constructing the decision tree model according to the training data set, divides the training data set contained in a current node according to the characteristic attribute corresponding to the maximum information gain, divides the current node to form a plurality of sub-nodes until the class attribute can be determined according to the data set contained in the node, wherein the information gain is used for describing the capability of distinguishing a data sample by one characteristic attribute, each node of the decision tree model comprises an internal node and a leaf node, and the internal node represents a classification test on one characteristic attribute, so that in the process of generating the decision tree model according to the training data set, the information gain of each characteristic attribute under each node is required to be iteratively calculated, and the data set contained in the current node is divided according to the characteristic attribute corresponding to the maximum information gain; the current node may be called a parent node corresponding to the split child node, and the relationship between the connected parent node and the child node is called a branch, and is typically the output of the characteristic attribute represented by the parent node on a certain value range.
It should be noted that, the generation of the decision tree model is to learn the association between the characteristic attributes of a plurality of samples and the classification result to obtain a data model for classification, the actual process is to use the criterion meeting the characteristic selection to divide the data set formed by the characteristic values of a plurality of characteristics into optimal data subsets, so that for the generation of the decision tree model, the training data set formed by the characteristic values of a plurality of training samples under different characteristic attributes needs to be obtained, the class attribute of each training sample is known, and then the training data set is divided continuously, so that each node and branch of the decision tree model are generated correspondingly, namely, the splitting of the nodes is performed continuously until the attribute class can be determined according to the data set contained in the sub-nodes obtained by splitting, thereby finally obtaining the decision tree model with the data classification function.
In one embodiment, considering the service connection between the fault predictions of different power supply devices, the abnormal operation of the fault prediction of one power supply device may affect other devices, and after the fault early warning instruction is sent to the device terminal of the staff, the following steps may be further executed:
if the failure prediction result obtained by the power supply equipment failure prediction system in the current equipment failure prediction process is an equipment failure, the power supply equipment failure prediction system queries a downstream equipment corresponding to the power supply equipment failure prediction in a preset equipment relationship network, wherein the equipment relationship network is mainly used for describing service connections among different power supply equipment failure predictions, that is, the power supply equipment failure predictions with the service connections can affect each other, and the power supply equipment failure prediction system can preferentially obtain operation condition data corresponding to the downstream equipment, that is, the next equipment failure prediction is to predict the operation state of the downstream equipment, so that the power supply equipment failure prediction related to the power supply equipment failure prediction is detected immediately when a certain power supply equipment failure prediction possibly fails, and the failure prediction efficiency is improved.
Fig. 1 is a flow chart of a power supply device failure prediction method in one embodiment. It should be understood that, although the steps in the flowchart of fig. 1 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows; the steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders; and at least some of the steps in fig. 1 may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, but may be performed alternately or alternately with at least some of the other steps or sub-steps of other steps.
Based on the method, the embodiment of the application also discloses a power supply equipment fault prediction device.
As shown in fig. 2, the apparatus comprises the following modules:
an operation condition data obtaining module 301, configured to obtain operation condition data corresponding to a power supply device fault prediction;
the feature data extraction module 302 is configured to perform feature extraction on the operation condition data to obtain feature data;
the device fault prediction result obtaining module 303 is configured to input the feature data into a preset fault prediction model to obtain a fault prediction result, where the fault prediction result includes a device fault and a device normal;
the fault early warning instruction generating module 304 is configured to generate a fault early warning instruction if the fault prediction result is a device fault, and send the fault early warning instruction to a device terminal of a staff.
In one embodiment, the operation condition data obtaining module 301 is further configured to query a corresponding operation data threshold in a preset failure database according to the equipment number;
comparing the real-time operation parameters corresponding to the equipment numbers with operation data thresholds;
and if the real-time operation parameter reaches the operation data threshold value, generating an alarm signal.
In one embodiment, the device failure prediction result obtaining module 303 is further configured to query a corresponding decision tree model according to the device number;
and inputting the real-time operation data corresponding to the equipment number into the decision tree model.
In one embodiment, the device fault prediction result obtaining module 303 is further configured to obtain historical operating condition data in a preset historical operating database, where the historical operating condition data at least includes a historical device number and corresponding historical operating data;
classifying the historical working condition data according to the historical equipment numbers;
acquiring historical operation data under the same equipment number;
preprocessing historical operation data to generate a training data set;
and constructing a decision tree model according to the training data set.
In one embodiment, the device fault prediction result obtaining module 303 is further configured to iteratively calculate an information gain corresponding to each feature attribute under each node of the decision tree model;
dividing a training data set contained in the current node according to the characteristic attribute corresponding to the maximum information gain so as to form a plurality of child nodes based on the current node splitting until the category attribute can be determined according to the data set contained in the node;
and outputting a decision tree model formed according to the training data set.
In one embodiment, the fault early warning instruction generating module 304 is further configured to query, in a preset device relationship network, a downstream device corresponding to a power supply device fault prediction in which a fault prediction result is a device fault;
and preferentially acquiring the operation condition data corresponding to the downstream equipment.
In one embodiment, the operation condition data obtaining module 301 is further configured to obtain operation condition data at least including: output voltage, input current, output current.
The embodiment of the application also discloses a computer device.
Specifically, the computer device includes a memory and a processor, and the memory stores thereon a computer program that can be loaded by the processor and execute the power supply device failure prediction method described above.
The embodiment of the application also discloses a computer readable storage medium.
Specifically, the computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the power supply device failure prediction method as described above, includes, for example: a U-disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
The present embodiment is only for explanation of the present invention and is not to be construed as limiting the present invention, and modifications to the present embodiment, which may not creatively contribute to the present invention as required by those skilled in the art after reading the present specification, are all protected by patent laws within the scope of claims of the present invention.
Claims (10)
1. A power supply equipment failure prediction method, characterized in that the method comprises:
acquiring operation condition data corresponding to power supply equipment fault prediction;
extracting the characteristics of the operation condition data to obtain characteristic data;
inputting the characteristic data into a preset fault prediction model to obtain a fault prediction result, wherein the fault prediction result comprises equipment faults and equipment normal;
if the failure prediction result is equipment failure, generating a failure early warning instruction, and sending the failure early warning instruction to an equipment terminal of a worker.
2. The method of claim 1, wherein the characteristic data includes at least a device number and a corresponding real-time operating parameter, and further comprising, after the obtaining the operating condition data corresponding to the power supply device failure prediction:
inquiring a corresponding operation data threshold value in a preset fault database according to the equipment number;
comparing the real-time operation parameters corresponding to the equipment numbers with the operation data threshold;
and if the real-time operation parameter reaches the operation data threshold value, generating an alarm signal.
3. The method according to claim 2, wherein the fault prediction model at least includes a plurality of decision tree models, and the inputting the feature data into a preset fault prediction model specifically includes:
inquiring a corresponding decision tree model according to the equipment number;
and inputting the real-time operation data corresponding to the equipment number into the decision tree model.
4. A method according to claim 3, characterized in that the construction of the decision tree model comprises in particular:
acquiring historical working condition data in a preset historical operation database, wherein the historical working condition data at least comprises a historical equipment number and corresponding historical operation data;
classifying the historical working condition data according to the historical equipment numbers;
acquiring historical operation data under the same equipment number;
preprocessing the historical operation data to generate a training data set;
and constructing a decision tree model according to the training data set.
5. The method according to claim 4, wherein said constructing a decision tree model from said training dataset comprises in particular:
iteratively calculating the information gain corresponding to each characteristic attribute under each node of the decision tree model;
dividing a training data set contained in the current node according to the characteristic attribute corresponding to the maximum information gain so as to form a plurality of child nodes based on the current node splitting until the category attribute can be determined according to the data set contained in the node;
and outputting a decision tree model formed according to the training data set.
6. The method according to claim 1, further comprising, after said sending the malfunction early warning command to the equipment terminal of the worker:
inquiring downstream equipment corresponding to power supply equipment fault prediction, wherein the fault prediction result is equipment fault, in a preset equipment relation network;
and preferentially acquiring the operation condition data corresponding to the downstream equipment.
7. The method of claim 1, wherein the operating condition data comprises at least: output voltage, input current, output current.
8. A power supply equipment failure prediction apparatus, characterized in that the apparatus comprises:
an operation condition data acquisition module (301) for acquiring operation condition data corresponding to power supply equipment fault prediction;
the characteristic data extraction module (302) is used for carrying out characteristic extraction on the operation condition data to obtain characteristic data;
the equipment fault prediction result acquisition module (303) is used for inputting the characteristic data into a preset fault prediction model to obtain a fault prediction result, wherein the fault prediction result comprises equipment faults and equipment normal;
and the fault early warning instruction generation module (304) is used for generating a fault early warning instruction if the fault prediction result is equipment fault and sending the fault early warning instruction to an equipment terminal of a worker.
9. A computer device comprising a memory and a processor, the memory having stored thereon a computer program capable of being loaded by the processor and performing the method according to any of claims 1 to 7.
10. A computer readable storage medium, characterized in that a computer program is stored which can be loaded by a processor and which performs the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310281002.1A CN116304928A (en) | 2023-03-21 | 2023-03-21 | Power supply equipment fault prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310281002.1A CN116304928A (en) | 2023-03-21 | 2023-03-21 | Power supply equipment fault prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116304928A true CN116304928A (en) | 2023-06-23 |
Family
ID=86832094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310281002.1A Pending CN116304928A (en) | 2023-03-21 | 2023-03-21 | Power supply equipment fault prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116304928A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116860538A (en) * | 2023-07-18 | 2023-10-10 | 深圳唱刻科技有限公司 | Game paddle fault prediction method and game paddle operation and maintenance system |
| CN117250942A (en) * | 2023-11-15 | 2023-12-19 | 成都态坦测试科技有限公司 | Fault prediction method, device, equipment and storage medium for determining model |
| CN117289143A (en) * | 2023-11-27 | 2023-12-26 | 宁德时代新能源科技股份有限公司 | Fault prediction method, device, equipment, system and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866634A (en) * | 2019-10-25 | 2020-03-06 | 袁茂银 | Underground cable fault early warning method and device based on model selection |
| CN113494428A (en) * | 2020-03-20 | 2021-10-12 | 新疆金风科技股份有限公司 | Fault detection method and device of wind generating set |
| WO2022048168A1 (en) * | 2020-09-03 | 2022-03-10 | 上海上讯信息技术股份有限公司 | Training method and device for failure prediction neural network model |
| CN115204536A (en) * | 2022-09-16 | 2022-10-18 | 苏州智能交通信息科技股份有限公司 | Building equipment fault prediction method, device, equipment and storage medium |
| CN115406483A (en) * | 2022-08-04 | 2022-11-29 | 国网湖北省电力有限公司黄龙滩水力发电厂 | Hydroelectric generating set fault identification method, device, equipment and readable storage medium |
-
2023
- 2023-03-21 CN CN202310281002.1A patent/CN116304928A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110866634A (en) * | 2019-10-25 | 2020-03-06 | 袁茂银 | Underground cable fault early warning method and device based on model selection |
| CN113494428A (en) * | 2020-03-20 | 2021-10-12 | 新疆金风科技股份有限公司 | Fault detection method and device of wind generating set |
| WO2022048168A1 (en) * | 2020-09-03 | 2022-03-10 | 上海上讯信息技术股份有限公司 | Training method and device for failure prediction neural network model |
| CN115406483A (en) * | 2022-08-04 | 2022-11-29 | 国网湖北省电力有限公司黄龙滩水力发电厂 | Hydroelectric generating set fault identification method, device, equipment and readable storage medium |
| CN115204536A (en) * | 2022-09-16 | 2022-10-18 | 苏州智能交通信息科技股份有限公司 | Building equipment fault prediction method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 施萌等: "基于SCADA数据的风电场故障预警", 电力科学与工程, no. 08 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116860538A (en) * | 2023-07-18 | 2023-10-10 | 深圳唱刻科技有限公司 | Game paddle fault prediction method and game paddle operation and maintenance system |
| CN116860538B (en) * | 2023-07-18 | 2024-03-19 | 深圳唱刻科技有限公司 | Game paddle fault prediction method and game paddle operation and maintenance system |
| CN117250942A (en) * | 2023-11-15 | 2023-12-19 | 成都态坦测试科技有限公司 | Fault prediction method, device, equipment and storage medium for determining model |
| CN117250942B (en) * | 2023-11-15 | 2024-02-27 | 成都态坦测试科技有限公司 | Fault prediction method, device, equipment and storage medium for determining model |
| CN117289143A (en) * | 2023-11-27 | 2023-12-26 | 宁德时代新能源科技股份有限公司 | Fault prediction method, device, equipment, system and medium |
| CN117289143B (en) * | 2023-11-27 | 2024-04-19 | 宁德时代新能源科技股份有限公司 | Fault prediction method, device, equipment, system and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116304928A (en) | Power supply equipment fault prediction method, device, equipment and storage medium | |
| CN107179503B (en) | Wind turbine generator fault intelligent diagnosis and early warning method based on random forest | |
| CN110825885B (en) | Power equipment knowledge graph application system | |
| CN106054104B (en) | A kind of intelligent electric meter failure real-time predicting method based on decision tree | |
| CN108153603B (en) | Database server fault handling method, device and storage medium | |
| CN109501834B (en) | Method and device for predicting fault of turnout switch machine | |
| CN111650921A (en) | Intelligent power grid regulation and control system equipment fault diagnosis method and system | |
| CN111047082A (en) | Early warning method and device for equipment, storage medium and electronic device | |
| CN101833324B (en) | Intelligent fault diagnosis system in tread extrusion process and diagnosis method thereof | |
| CN105044497B (en) | A kind of traction convertor intelligent fault analysis method | |
| CN106503439A (en) | A kind of method of the collection fault early warning system based on data mining | |
| CN111027615A (en) | Middleware fault early warning method and system based on machine learning | |
| CN112990551A (en) | Cascading failure evolution path tracing and predicting method and device based on knowledge graph | |
| CN103926490A (en) | Power transformer comprehensive diagnosis method with self-learning function | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| Shi et al. | Study of wind turbine fault diagnosis and early warning based on SCADA data | |
| Helsen et al. | Wind farm operation and maintenance optimization using big data | |
| CN116578869A (en) | Fault diagnosis method, fault diagnosis device and electronic device for power system | |
| CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
| CN110826735A (en) | Electric power SCADA intelligent multidimensional query and maintenance method | |
| CN117521498A (en) | Charging pile guide type fault diagnosis prediction method and system | |
| KR20220089853A (en) | Method for Failure prediction and prognostics and health management of renewable energy generation facilities using machine learning technology | |
| CN116389062A (en) | Industrial control system behavior monitoring method and equipment based on flow safety analysis | |
| CN115469643A (en) | Nuclear power station rotating machinery health management method, system and medium | |
| CN114238599A (en) | Information communication system fault emergency aid decision-making method and system |
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 |