CN118226366B - Online monitoring method, device and equipment of voltage transformer and storage medium - Google Patents
Online monitoring method, device and equipment of voltage transformer and storage medium Download PDFInfo
- Publication number
- CN118226366B CN118226366B CN202410636231.5A CN202410636231A CN118226366B CN 118226366 B CN118226366 B CN 118226366B CN 202410636231 A CN202410636231 A CN 202410636231A CN 118226366 B CN118226366 B CN 118226366B
- Authority
- CN
- China
- Prior art keywords
- data
- hardware
- temperature
- maintenance
- analysis
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/02—Testing or calibrating of apparatus covered by the other groups of this subclass of auxiliary devices, e.g. of instrument transformers according to prescribed transformation ratio, phase angle, or wattage rating
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Power Engineering (AREA)
- Protection Of Transformers (AREA)
Abstract
The invention relates to an on-line monitoring method, a device, equipment and a storage medium of a voltage transformer, wherein the method comprises the following steps: acquiring multi-element index data of the voltage transformer, and performing feature extraction on the multi-element index data to obtain hardware data and temperature data; carrying out state analysis on the hardware data through a preset state model to obtain state information, extracting historical hardware data of a multi-element database, and carrying out trend analysis by combining the state information and the historical hardware data to obtain hardware prediction data; trend analysis is carried out by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data; judging whether the hardware prediction data and the temperature prediction data reach a preset early warning threshold value, and generating corresponding maintenance suggestions according to a preset maintenance rule when any one data reach the early warning threshold value; and receiving feedback data sent by the maintenance mechanism after the maintenance advice is executed in real time, and updating the data of the early warning threshold according to the feedback data. The invention can measure the performance of the voltage transformer.
Description
Technical Field
The present invention relates to the field of power technologies, and in particular, to an online monitoring method, apparatus, device, and storage medium for a voltage transformer.
Background
With the development and popularization of power systems, voltage transformers play a vital role in power monitoring and protection systems. However, the traditional online monitoring method of the voltage transformer often depends on threshold judgment of single index data, and is difficult to comprehensively evaluate the state and performance of the voltage transformer.
Disclosure of Invention
The invention mainly aims to provide an on-line monitoring method, device, equipment and storage medium for a voltage transformer, which can acquire multi-element index data and perform feature extraction and state analysis, can comprehensively evaluate the state and performance of the voltage transformer, and improves the comprehensiveness and accuracy of monitoring
In order to achieve the above object, the present invention provides an on-line monitoring method for a voltage transformer, including:
Acquiring multi-element index data of the voltage transformer, performing feature extraction on the multi-element index data to obtain hardware data and temperature data, and storing the hardware data and the temperature data into a multi-element database;
Performing state analysis on the hardware data through a preset state model to obtain state information, extracting historical hardware data of the multi-element database, and performing trend analysis by combining the state information and the historical hardware data to obtain hardware prediction data; extracting historical temperature data of the multi-element database, and carrying out trend analysis by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data;
Judging whether the hardware prediction data and the temperature prediction data reach a preset early warning threshold value, and generating corresponding maintenance suggestions according to a preset maintenance rule when any one data reach the early warning threshold value;
And sending the maintenance advice to a corresponding maintenance mechanism, receiving feedback data sent by the maintenance mechanism after the maintenance advice is executed in real time, and updating the data of the early warning threshold according to the feedback data.
Further, the feature extraction of the multi-element index data to obtain hardware data and temperature data includes: performing feature extraction on the multi-element index data according to a preset extraction rule to obtain primary side input voltage value, secondary side output voltage value, current value and temperature feature data;
performing voltage ratio calculation based on the primary side input voltage value and the secondary side output voltage value to obtain voltage ratio characteristic data; carrying out phase analysis on the primary side input voltage value and the secondary side output voltage value to obtain phase data, extracting and combining the absolute value, the dynamic change range value and the periodic fluctuation characteristic of the phase data to obtain phase difference characteristic data; carrying out analysis on each subharmonic component of the primary side input voltage value and the secondary side output voltage value to obtain a total harmonic distortion rate and each subharmonic amplitude, and combining the total harmonic distortion rate and each subharmonic amplitude into harmonic characteristic data;
Carrying out discharge analysis on the current value to obtain the number of discharge pulses, the discharge energy, the exciting current effective value and the harmonic content, and combining the number of discharge pulses, the discharge energy, the exciting current effective value and the harmonic content into current characteristic data;
Carrying out data analysis on the temperature characteristic data to obtain key point temperature, thermal stability data and overall temperature, and combining the key point temperature, the thermal stability data and the overall temperature into temperature data;
And combining the voltage ratio characteristic data, the phase difference characteristic data, the harmonic characteristic data and the current characteristic data to obtain hardware data.
Further, performing state analysis on the hardware data through a preset state model to obtain state information, including:
Reading the hardware data through the state model, and sequentially carrying out corresponding state analysis on the read voltage ratio characteristic data, the read phase difference characteristic data, the read harmonic characteristic data and the read current characteristic data to obtain voltage ratio stability, voltage phase consistency, harmonic distortion tolerance and excitation current rationality;
And carrying out health degree analysis on the voltage ratio stability, the phase consistency, the harmonic distortion tolerance and the exciting current rationality according to a preset evaluation rule to obtain current hardware state information, carrying out risk analysis on the current hardware state information according to a preset risk evaluation rule to obtain a corresponding risk grade, and carrying out combined treatment on the risk grade and the current hardware state information to obtain state information.
Further, the trend analysis is performed by combining the state information and the historical hardware data to obtain hardware prediction data, including: reading the state information to obtain the risk level and the current hardware state information, and performing association marking on the current hardware state information and the historical hardware data to obtain hardware association data;
and carrying out preliminary trend prediction according to a preset hardware prediction algorithm by combining the risk level and the hardware associated data to obtain initial hardware prediction data, and carrying out secondary prediction analysis on the initial hardware prediction data by taking the current hardware state information as secondary input data to obtain hardware prediction data.
Further, the trend analysis is performed by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data, which comprises the following steps:
Reading the state information to obtain the risk level and the current hardware state information, and performing association marking on the historical temperature data and the temperature data to obtain temperature association data;
And carrying out primary trend prediction according to a preset temperature prediction algorithm in combination with the risk level and the temperature associated data to obtain initial temperature prediction data, and carrying out secondary prediction analysis on the initial temperature prediction data by taking the current hardware state information and the temperature data as secondary input data to obtain temperature prediction data.
Further, when any one data reaches the early warning threshold, generating a corresponding maintenance suggestion according to a preset maintenance rule, including: when the hardware prediction data reach an early warning threshold value, performing fault analysis on the hardware prediction data to obtain hardware fault information, and generating corresponding hardware maintenance suggestions based on the hardware fault information through the maintenance rules, wherein the hardware maintenance suggestions comprise replacement of elements expected to be invalid and adjustment of working parameters;
And when the temperature prediction data reach an early warning threshold value, evaluating specific overheat grade, overheat type and overheat area, carrying out safety analysis based on the overheat type and the overheat area to obtain specific hidden danger information, and carrying out maintenance analysis on the hidden danger information and the overheat grade through the maintenance rule to obtain corresponding temperature maintenance suggestions, wherein the temperature maintenance suggestions comprise cooling maintenance suggestions, load maintenance suggestions and environment maintenance suggestions.
Further, the real-time receiving maintenance mechanism executes the feedback data sent after the maintenance suggestion, and updates the data of the early warning threshold according to the feedback data:
after receiving feedback data sent by a maintenance mechanism, reading surface layer data of the feedback data, judging whether the surface layer data meets preset instruction requirements, and when the surface layer data does not meet the preset instruction requirements, acquiring the feedback data again for reading;
And when the requirement of the preset instructions is met, reversely compiling the surface layer data according to a preset compiling rule to obtain a decoding instruction packet, extracting the password of the decoding instruction packet according to a decoding instruction library to obtain an unpacking password, unpacking and analyzing the feedback data according to the unpacking password to obtain operation data of the voltage transformer after the maintenance suggestion is executed, and updating the data of the early warning threshold according to the operation data.
The invention also provides an on-line monitoring device of the voltage transformer, which comprises:
The acquisition module is used for acquiring multi-element index data of the voltage transformer, extracting characteristics of the multi-element index data to obtain hardware data and temperature data, and storing the hardware data and the temperature data into a multi-element database;
The analysis module is used for carrying out state analysis on the hardware data through a preset state model to obtain state information, extracting historical hardware data of the multi-element database, and carrying out trend analysis by combining the state information and the historical hardware data to obtain hardware prediction data; extracting historical temperature data of the multi-element database, and carrying out trend analysis by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data;
the processing module is used for judging whether the hardware prediction data and the temperature prediction data reach a preset early warning threshold value, and when any one data reach the early warning threshold value, corresponding maintenance suggestions are generated according to preset maintenance rules;
And the updating module is used for sending the maintenance suggestions to the corresponding maintenance mechanism, receiving feedback data sent by the maintenance mechanism after executing the maintenance suggestions in real time, and updating the data of the early warning threshold according to the feedback data.
The invention also provides on-line monitoring equipment of the voltage transformer, which comprises:
A memory for storing a program;
And the processor is used for executing the program and realizing the steps of the online monitoring method of the voltage transformer.
The invention also provides a storage medium storing computer instructions for causing a computer to perform the method of any one of the above.
The online monitoring method, the online monitoring device, the online monitoring equipment and the storage medium of the voltage transformer have the following beneficial effects:
The state and the performance of the voltage transformer can be comprehensively evaluated by acquiring the multi-element index data and carrying out feature extraction and state analysis, so that the comprehensiveness and the accuracy of monitoring are improved. And secondly, the hardware and temperature prediction data are obtained through trend analysis, so that the running state of the voltage transformer can be predicted, potential problems can be recognized in advance, and preventive measures can be taken, thereby improving the predictability and safety of the system. By judging whether the predicted data reach the early warning threshold value and generating the maintenance suggestion, the maintenance mechanism can take corresponding maintenance measures in time, thereby being beneficial to avoiding possible faults and damages of the voltage transformer and improving the reliability and stability of the system. In addition, the performance of the monitoring system can be continuously optimized by receiving the feedback data of the maintenance mechanism in real time and updating the early warning threshold according to the feedback data, so that the intelligence and the instantaneity of the system are improved.
Drawings
FIG. 1 is a flow chart of an on-line monitoring method of a voltage transformer provided by the invention;
FIG. 2 is a block diagram of an on-line monitoring device for a voltage transformer provided by the invention;
fig. 3 is a block diagram of an on-line monitoring device for a voltage transformer provided by the invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention will be further described with reference to the drawings and detailed description.
Referring to fig. 1, the present invention provides an on-line monitoring method for a voltage transformer, including:
step S1: acquiring multi-element index data of the voltage transformer, performing feature extraction on the multi-element index data to obtain hardware data and temperature data, and storing the hardware data and the temperature data into a multi-element database;
Step S2: carrying out state analysis on the hardware data through a preset state model to obtain state information, extracting historical hardware data of a multi-element database, and carrying out trend analysis by combining the state information and the historical hardware data to obtain hardware prediction data; extracting historical temperature data of a multi-element database, and carrying out trend analysis by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data;
Step S3: judging whether the hardware prediction data and the temperature prediction data reach a preset early warning threshold value, and generating corresponding maintenance suggestions according to a preset maintenance rule when any one data reach the early warning threshold value;
Step S4: and sending the maintenance advice to a corresponding maintenance mechanism, receiving feedback data sent by the maintenance mechanism after the maintenance advice is executed in real time, and updating the data of the early warning threshold according to the feedback data.
Based on the above steps, the detailed procedure is as follows:
step S1: acquiring multi-element index data (including but not limited to data such as current, voltage, frequency, insulation resistance, dielectric loss factor, partial discharge capacity and the like) of a voltage transformer, extracting representative characteristic values from the original multi-element index data by using a signal processing and data analysis technology, removing noise through filtering for example, obtaining hardware data and temperature data, and storing the hardware data and the temperature data into a multi-element database;
Step S2: carrying out state analysis on the hardware data through a preset state model, judging the current working state of the voltage transformer to obtain state information, extracting historical hardware data of a multi-element database, wherein the historical hardware data comprises various key indexes of the voltage transformer in the past period of time, such as current, voltage, frequency and the like, carrying out trend analysis by combining the state information and the historical hardware data, and identifying the change trend and rule in the hardware data through technical means such as data processing, statistical analysis and the like to obtain hardware prediction data; extracting historical temperature data of a multi-element database, and carrying out trend analysis by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data; the state model uses a Markov chain model, and each state information is allocated with a unique identifier or a state code in the running process. A state transition probability matrix is constructed, each element Pij in the matrix representing the probability of transition from state i to state j. These probabilities can be derived by historical data statistics, for example, if in the past the probability of a normal operating state transitioning to a light load state is 0.7 and the probability of transitioning to a fault state is 0.05, then the values at the corresponding locations of the state transition matrix are 0.7 and 0.05, respectively.
When an initial state probability vector is determined, the system is in a probability distribution for each state. The state of the voltage transformer at a certain future point in time is predicted by using the state transition matrix and the initial state, by multiple iterations or by directly calculating the steady state distribution (for the case of infinite period).
Step S3: judging whether the hardware prediction data and the temperature prediction data reach a preset early warning threshold value or not, wherein the early warning threshold value comprises a threshold value for hardware prediction data (such as a threshold value for insulation performance reduction and a threshold value for local discharge capacity) and a threshold value for temperature prediction data (such as a maximum allowable working temperature of a winding and an average temperature rise limit value for long-term running);
when any one data reaches an early warning threshold value, marking the data as an early warning state, and generating a corresponding maintenance suggestion according to a preset maintenance rule;
and S4, after the maintenance advice is generated, the maintenance advice is sent to a corresponding maintenance mechanism, feedback data sent by the maintenance mechanism after the maintenance advice is executed are received in real time, the received feedback data are analyzed, the effect and the necessity of maintenance actions are evaluated, and the early warning threshold value is updated based on the analysis result of the feedback data.
According to the online monitoring method of the voltage transformer, provided by the invention, the state and the performance of the voltage transformer can be comprehensively evaluated by acquiring the multi-element index data and carrying out feature extraction and state analysis, so that the comprehensiveness and the accuracy of monitoring are improved. And secondly, the hardware and temperature prediction data are obtained through trend analysis, so that the running state of the voltage transformer can be predicted, potential problems can be recognized in advance, and preventive measures can be taken, thereby improving the predictability and safety of the system. By judging whether the predicted data reach the early warning threshold value and generating the maintenance suggestion, the maintenance mechanism can take corresponding maintenance measures in time, thereby being beneficial to avoiding possible faults and damages of the voltage transformer and improving the reliability and stability of the system. In addition, the performance of the monitoring system can be continuously optimized by receiving the feedback data of the maintenance mechanism in real time and updating the early warning threshold according to the feedback data, so that the intelligence and the instantaneity of the system are improved.
In one embodiment, feature extraction is performed on the multi-element index data to obtain hardware data and temperature data, including: characteristic extraction is carried out on the multi-element index data according to a preset extraction rule to obtain primary side input voltage value, secondary side output voltage value, current value and temperature characteristic data, the extracted data are cleaned, abnormal values and missing values are removed, necessary smoothing treatment is carried out, and data quality is ensured;
performing voltage ratio calculation based on the primary side input voltage value and the secondary side output voltage value to obtain voltage ratio characteristic data, wherein a calculation formula is that the voltage ratio characteristic data=the secondary side output voltage value/the primary side input voltage value;
Carrying out phase analysis on the primary side input voltage value and the secondary side output voltage value to obtain phase data, extracting the absolute value, the dynamic variation range value and the periodic fluctuation characteristic of the phase data, and merging the extracted data into phase difference characteristic data;
Carrying out analysis on each subharmonic component of the primary side input voltage value and the secondary side output voltage value to obtain a total harmonic distortion rate and each subharmonic amplitude, and combining the total harmonic distortion rate and each subharmonic amplitude into harmonic characteristic data;
Carrying out discharge analysis on the current value to obtain the number of discharge pulses, the discharge energy, the exciting current effective value and the harmonic content, and combining the number of discharge pulses, the discharge energy, the exciting current effective value and the harmonic content into current characteristic data;
Carrying out data analysis on the temperature characteristic data to obtain key point temperature, thermal stability data and overall temperature, and combining the key point temperature, the thermal stability data and the overall temperature into temperature data;
And combining the voltage ratio characteristic data, the phase difference characteristic data, the harmonic characteristic data and the current characteristic data to obtain hardware data.
The method has the beneficial effects that through deep analysis and feature extraction of multiple indexes such as primary side voltage, secondary side voltage, current, temperature and the like of the voltage transformer, more comprehensive hardware state information and temperature state information can be obtained, potential faults and performance degradation of the voltage transformer can be accurately identified, and the accuracy and sensitivity of fault diagnosis are improved. By constructing a preset state model and analyzing trend, combining historical data and current state information, hardware performance change and temperature abnormality can be predicted in advance, early warning can be sent out timely, sudden faults can be avoided, power failure accidents caused by equipment faults can be reduced, and stable operation of a power system can be ensured.
In one embodiment, performing state analysis on hardware data through a preset state model to obtain state information includes:
Reading the hardware data through the state model, and sequentially carrying out corresponding state analysis on the read voltage ratio characteristic data, the read phase difference characteristic data, the read harmonic characteristic data and the read current characteristic data;
wherein, the state analysis process includes:
analyzing the voltage ratio characteristic data, judging whether the voltage ratio characteristic data fluctuates in a normal range, and evaluating the stability of voltage transmission to obtain voltage ratio stability;
carrying out data calculation on the phase difference characteristic data according to a preset phase range value to obtain phase consistency;
And (5) evaluating harmonic characteristic data, judging whether the harmonic content exceeds the standard, and evaluating the bearing capacity of harmonic distortion to obtain the tolerance of the harmonic distortion.
Judging whether the current characteristic data meets the preset exciting current reasonable requirement or not, and obtaining exciting current rationality.
And carrying out health degree analysis on the voltage ratio stability, the phase consistency, the harmonic distortion tolerance and the exciting current rationality according to a preset evaluation rule to obtain current hardware state information, carrying out risk analysis on the current hardware state information according to a preset risk evaluation rule to obtain a corresponding risk grade, and carrying out combined treatment on the risk grade and the current hardware state information to obtain state information.
The embodiment provides more accurate hardware state evaluation through deep analysis of key indexes such as voltage ratio, phase difference, harmonic distortion, exciting current and the like, and improves the precision and efficiency of fault detection. Potential equipment problems can be identified in advance through health and risk level evaluation, a reasonable maintenance plan is formulated according to the risk level, and the passive response fault is converted into preventive maintenance, so that the service life of the equipment is effectively prolonged, sudden faults are reduced, and the maintenance cost is reduced. The unstable state of the voltage transformer is timely identified and solved, the running stability and safety of the power system are ensured, the power interruption caused by equipment faults is reduced, and the reliability and safety of the whole system are improved.
In one embodiment, trend analysis is performed in combination with status information and historical hardware data to obtain hardware prediction data, including: and reading the state information to obtain risk level (such as normal, slight, moderate and serious) and current hardware state information, performing time sequence matching and association marking on the current hardware state information and historical hardware data to obtain hardware association data, and extracting the obtained historical hardware data including key indexes such as past voltage ratio, phase difference, harmonic characteristic, current and the like.
And carrying out preliminary trend prediction according to a preset hardware prediction algorithm by combining the risk level and the hardware associated data to obtain initial hardware prediction data.
And taking the current hardware state information as supplementary secondary input, performing secondary correction prediction analysis on the primary hardware prediction data, wherein the secondary prediction analysis comprises adjustment of the primary prediction data, and finally obtaining the hardware prediction data by considering dynamic changes of the instant state, such as recent abnormal fluctuation, new occurrence of fault symptoms and the like.
The hardware prediction algorithm adopts an autoregressive integral moving average algorithm, and combines three components of Autoregressive (AR), differential (I) and Moving Average (MA), and is formally expressed as ARIMA (p, d, q), wherein p represents the order of an autoregressive term, d represents the differential times required for stabilizing a sequence, and q is the order of a moving average term.
Autoregressive (AR): by using the historical data of the sequence itself to make predictions, the algorithm expresses the current value as a linear combination of past time values plus a random error.
Difference (I): the trend and the seasonality in the data are eliminated through the differential operation, and the sequence stabilization is realized, so that the algorithm is a key step for adapting to the non-stable time sequence.
Moving Average (MA): the sequence correlation of the error term, i.e. the model of the current error affected by the past error, is considered to be expressed as a linear combination of past error values.
Parameter estimation: parameters (e.g., autoregressive coefficients, moving average coefficients, etc.) in the model are determined using statistical methods such as maximum likelihood estimation.
Algorithm inspection and diagnosis: including residual analysis, white noise inspection, etc., ensures that the validity of the model and the residual meet statistical assumptions.
And a prediction step: based on model parameters obtained through historical data training, future data points are predicted, and the method is suitable for predicting hardware states or performance indexes with time sequence characteristics.
According to the method and the device, trend analysis is carried out by combining the current state information and the historical hardware data, so that not only is the long-term performance change trend of the device considered, but also the influence of the instant state is integrated, the prediction model is more close to the actual running state, and the accuracy and the reliability of hardware state prediction are improved. According to the obtained hardware prediction data, potential performance degradation or fault risk of the equipment can be recognized earlier, scientific basis is provided for formulating preventive maintenance strategies, sudden faults are effectively reduced, the service life of the equipment is prolonged, and maintenance cost is reduced. The accurate prediction data is beneficial to reasonably planning maintenance resources, and maintenance tasks are arranged preferentially according to the emergency degree and the importance of the prediction result, so that the maintenance efficiency and the response speed are improved.
In one embodiment, extracting historical temperature data of the multivariate database, and performing trend analysis in combination with the state information, the historical temperature data and the temperature data to obtain temperature prediction data comprises:
Reading the state information to obtain risk level and current hardware state information, and performing time sequence pairing and association marking on the historical temperature data and the temperature data to obtain temperature association data;
And according to a preset temperature prediction algorithm, taking the risk level and the temperature related data as input data, and performing preliminary trend prediction to obtain initial temperature prediction data.
And carrying out secondary prediction analysis for refining and correcting the initial temperature prediction data by taking the current hardware state information and the temperature data as complementary secondary input data to obtain the temperature prediction data.
The temperature prediction algorithm is a long-term and short-term memory network algorithm, and the structure comprises an input gate: determining how much of the new information is updated into the temperature state; forgetting the door: determining which information in the cell state needs to be forgotten; temperature state: storing long-term dependence information, and controlling the addition and deletion of information through a gating mechanism; output door: and determining how much information to output according to the temperature state and the current input.
In the embodiment, the historical temperature data, the state information and the current hardware state are combined for multi-level analysis, so that the future temperature change is predicted more accurately, the prediction deviation caused by a single data source is reduced, and the accuracy and the reliability of the prediction are improved. Timely and accurate temperature prediction is beneficial to finding potential overheat problems in advance, and provides early warning signals for equipment maintenance, so that maintenance work can be changed from passive response to active prevention, the equipment failure rate caused by high temperature is reduced, and the service life of equipment is prolonged. Based on the temperature prediction data, the cooling resources can be allocated more reasonably, so that the energy consumption is effectively saved, and the operation cost is reduced. Through predictive analysis, the system is ensured to operate in a proper temperature range, so that performance degradation or system breakdown caused by overhigh temperature is avoided, and the high-efficiency stable operation of the system is maintained.
In one embodiment, when any one data reaches the early warning threshold, generating a corresponding maintenance suggestion according to a preset maintenance rule includes: when the hardware prediction data reach the early warning threshold value, carrying out fault analysis on the hardware prediction data to obtain hardware fault information, wherein the hardware fault information comprises potential fault identification and identification of elements to be disabled and performance reduction trend;
corresponding hardware maintenance suggestions are generated through maintenance rules based on the hardware fault information, and the hardware maintenance suggestions comprise replacement of hardware elements expected to fail soon and adjustment of working parameters.
When the temperature prediction data reach the early warning threshold value, specific overheat grades (mild, moderate and severe), overheat types (local overheat and full overheat) and overheat areas are evaluated, safety analysis is carried out based on the overheat types and the overheat areas to obtain specific hidden danger information, maintenance analysis is carried out on the hidden danger information and the overheat grades through maintenance rules to obtain corresponding temperature maintenance suggestions, and the temperature maintenance suggestions comprise cooling maintenance suggestions, load maintenance suggestions and environment maintenance suggestions.
According to the embodiment, measures can be taken before hardware faults or temperature anomalies occur through an early warning mechanism, so that the risk of system interruption caused by sudden faults is greatly reduced, and the service continuity and stability are ensured. The maintenance proposal generated based on predictive analysis can pertinently optimize hardware configuration and working parameters, thereby improving the utilization efficiency of system resources, reducing energy consumption and saving operation cost. The overheat condition is accurately evaluated and timely processed, potential safety hazards such as fire disaster and hardware damage are reduced, and the overall safety level is enhanced.
In one embodiment, feedback data sent after the maintenance mechanism executes the maintenance suggestion is received in real time, and the early warning threshold value is updated according to the feedback data:
After receiving feedback data sent by a maintenance mechanism, reading surface layer data of the feedback data, judging whether the surface layer data meets preset instruction requirements, and when the surface layer data does not meet the preset instruction requirements, acquiring the feedback data again for reading;
When the requirement of the preset instruction is met, performing inverse compiling on the surface data according to a preset compiling rule to obtain a decoding instruction packet, performing password extraction on the decoding instruction packet according to a decoding instruction library to obtain a unpacking password, performing unpacking analysis on the feedback data according to the unpacking password to obtain operation data of the voltage transformer after the maintenance suggestion is executed, and performing data updating on the early warning threshold according to the operation data. According to the embodiment, the accuracy and the credibility of the data can be improved by performing surface layer data reading, compiling, decoding, unpacking and other processing on the feedback data, and the early warning threshold value is updated after the accuracy of the data is confirmed, so that unnecessary early warning caused by errors or interference can be avoided. The feedback data is processed and analyzed in an automatic mode, so that manual intervention is reduced, processing efficiency is improved, meanwhile, the possibility of errors is reduced, and data processing is more reliable and efficient. The feedback data is unpacked and analyzed according to the unpacking password, and the early warning threshold value is updated according to the unpacking password, so that the actual running state of the voltage transformer is reflected by the early warning threshold value more accurately, the accuracy and the practicability of the monitoring system are improved, and more accurate early warning and maintenance decision making are facilitated.
Referring to fig. 2, the present invention further provides an on-line monitoring device for a voltage transformer, including:
The acquisition module is used for acquiring multi-element index data of the voltage transformer, extracting characteristics of the multi-element index data to obtain hardware data and temperature data, and storing the hardware data and the temperature data into a multi-element database;
The analysis module is used for carrying out state analysis on the hardware data through a preset state model to obtain state information, extracting historical hardware data of the multi-element database, and carrying out trend analysis by combining the state information and the historical hardware data to obtain hardware prediction data; extracting historical temperature data of a multi-element database, and carrying out trend analysis by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data;
the processing module is used for judging whether the hardware prediction data and the temperature prediction data reach a preset early warning threshold value, and when any one data reach the early warning threshold value, corresponding maintenance suggestions are generated according to a preset maintenance rule;
the updating module is used for sending the maintenance suggestions to the corresponding maintenance mechanism, receiving feedback data sent by the maintenance mechanism after the maintenance mechanism executes the maintenance suggestions in real time, and updating the data of the early warning threshold according to the feedback data.
According to the online monitoring method of the voltage transformer, provided by the invention, the state and the performance of the voltage transformer can be comprehensively evaluated by acquiring the multi-element index data and carrying out feature extraction and state analysis, so that the comprehensiveness and the accuracy of monitoring are improved. And secondly, the hardware and temperature prediction data are obtained through trend analysis, so that the running state of the voltage transformer can be predicted, potential problems can be recognized in advance, and preventive measures can be taken, thereby improving the predictability and safety of the system. By judging whether the predicted data reach the early warning threshold value and generating the maintenance suggestion, the maintenance mechanism can take corresponding maintenance measures in time, thereby being beneficial to avoiding possible faults and damages of the voltage transformer and improving the reliability and stability of the system. In addition, the performance of the monitoring system can be continuously optimized by receiving the feedback data of the maintenance mechanism in real time and updating the early warning threshold according to the feedback data, so that the intelligence and the instantaneity of the system are improved.
Referring to fig. 3, the present invention further provides an on-line monitoring device for a voltage transformer, including:
A memory for storing a program;
And the processor is used for executing a program and realizing the steps of the online monitoring method of the voltage transformer.
In this embodiment, the processor and the memory may be connected by a bus or other means. The memory may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk. The processor may be a general-purpose processor, such as a central processing unit, a digital signal processor, an application specific integrated circuit, or one or more integrated circuits configured to implement embodiments of the present invention.
The invention also provides a storage medium storing computer instructions for causing a computer to perform the method of any one of the above.
It should be noted that, for convenience and brevity of description, the specific working process of the above-described system and each module may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (9)
1. An on-line monitoring method of a voltage transformer is characterized by comprising the following steps:
Acquiring multi-element index data of the voltage transformer, performing feature extraction on the multi-element index data to obtain hardware data and temperature data, and storing the hardware data and the temperature data into a multi-element database;
Performing state analysis on the hardware data through a preset state model to obtain state information, extracting historical hardware data of the multi-element database, and performing trend analysis by combining the state information and the historical hardware data to obtain hardware prediction data; extracting historical temperature data of the multi-element database, and carrying out trend analysis by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data;
Judging whether the hardware prediction data and the temperature prediction data reach a preset early warning threshold value, and generating corresponding maintenance suggestions according to a preset maintenance rule when any one data reach the early warning threshold value;
The maintenance advice is sent to a corresponding maintenance mechanism, feedback data sent by the maintenance mechanism after the maintenance advice is executed are received in real time, and the early warning threshold value is updated according to the feedback data;
Performing feature extraction on the multi-element index data according to a preset extraction rule to obtain primary side input voltage value, secondary side output voltage value, current value and temperature feature data;
performing voltage ratio calculation based on the primary side input voltage value and the secondary side output voltage value to obtain voltage ratio characteristic data; carrying out phase analysis on the primary side input voltage value and the secondary side output voltage value to obtain phase data, extracting and combining the absolute value, the dynamic change range value and the periodic fluctuation characteristic of the phase data to obtain phase difference characteristic data; carrying out analysis on each subharmonic component of the primary side input voltage value and the secondary side output voltage value to obtain a total harmonic distortion rate and each subharmonic amplitude, and combining the total harmonic distortion rate and each subharmonic amplitude into harmonic characteristic data;
Carrying out discharge analysis on the current value to obtain the number of discharge pulses, the discharge energy, the exciting current effective value and the harmonic content, and combining the number of discharge pulses, the discharge energy, the exciting current effective value and the harmonic content into current characteristic data;
Carrying out data analysis on the temperature characteristic data to obtain key point temperature, thermal stability data and overall temperature, and combining the key point temperature, the thermal stability data and the overall temperature into temperature data;
And combining the voltage ratio characteristic data, the phase difference characteristic data, the harmonic characteristic data and the current characteristic data to obtain hardware data.
2. The method for on-line monitoring of a voltage transformer according to claim 1, wherein the performing a state analysis on the hardware data through a preset state model to obtain state information comprises:
Reading the hardware data through the state model, and sequentially carrying out corresponding state analysis on the read voltage ratio characteristic data, the read phase difference characteristic data, the read harmonic characteristic data and the read current characteristic data to obtain voltage ratio stability, voltage phase consistency, harmonic distortion tolerance and excitation current rationality;
And carrying out health degree analysis on the voltage ratio stability, the phase consistency, the harmonic distortion tolerance and the exciting current rationality according to a preset evaluation rule to obtain current hardware state information, carrying out risk analysis on the current hardware state information according to a preset risk evaluation rule to obtain a corresponding risk grade, and carrying out combined treatment on the risk grade and the current hardware state information to obtain state information.
3. The method for online monitoring of a voltage transformer according to claim 2, wherein the combining the state information and the historical hardware data for trend analysis to obtain hardware prediction data comprises:
Reading the state information to obtain the risk level and the current hardware state information, and performing association marking on the current hardware state information and the historical hardware data to obtain hardware association data;
and carrying out preliminary trend prediction according to a preset hardware prediction algorithm by combining the risk level and the hardware associated data to obtain initial hardware prediction data, and carrying out secondary prediction analysis on the initial hardware prediction data by taking the current hardware state information as secondary input data to obtain hardware prediction data.
4. The method for online monitoring of a voltage transformer according to claim 2, wherein the trend analysis is performed by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data, comprising:
Reading the state information to obtain the risk level and the current hardware state information, and performing association marking on the historical temperature data and the temperature data to obtain temperature association data;
And carrying out primary trend prediction according to a preset temperature prediction algorithm in combination with the risk level and the temperature associated data to obtain initial temperature prediction data, and carrying out secondary prediction analysis on the initial temperature prediction data by taking the current hardware state information and the temperature data as secondary input data to obtain temperature prediction data.
5. The method for on-line monitoring of a voltage transformer according to claim 1, wherein when any one of the data reaches the early warning threshold, generating a corresponding maintenance suggestion according to a preset maintenance rule comprises:
When the hardware prediction data reach an early warning threshold value, performing fault analysis on the hardware prediction data to obtain hardware fault information, and generating corresponding hardware maintenance suggestions based on the hardware fault information through the maintenance rules, wherein the hardware maintenance suggestions comprise replacement of elements expected to be invalid and adjustment of working parameters;
And when the temperature prediction data reach an early warning threshold value, evaluating specific overheat grade, overheat type and overheat area, carrying out safety analysis based on the overheat type and the overheat area to obtain specific hidden danger information, and carrying out maintenance analysis on the hidden danger information and the overheat grade through the maintenance rule to obtain corresponding temperature maintenance suggestions, wherein the temperature maintenance suggestions comprise cooling maintenance suggestions, load maintenance suggestions and environment maintenance suggestions.
6. The method for on-line monitoring of a voltage transformer according to claim 1, wherein the real-time receiving maintenance mechanism performs the maintenance advice and then sends feedback data, and the early warning threshold is updated according to the feedback data:
After receiving feedback data sent by a maintenance mechanism, reading surface layer data of the feedback data, judging whether the surface layer data meets preset instruction requirements, and when the surface layer data does not meet the preset instruction requirements, re-acquiring the feedback data for reading;
And when the requirement of the preset instructions is met, reversely compiling the surface layer data according to a preset compiling rule to obtain a decoding instruction packet, extracting the password of the decoding instruction packet according to a decoding instruction library to obtain an unpacking password, unpacking and analyzing the feedback data according to the unpacking password to obtain operation data of the voltage transformer after the maintenance suggestion is executed, and updating the data of the early warning threshold according to the operation data.
7. An on-line monitoring device of a voltage transformer, comprising:
The acquisition module is used for acquiring multi-element index data of the voltage transformer, extracting characteristics of the multi-element index data to obtain hardware data and temperature data, and storing the hardware data and the temperature data into a multi-element database;
The analysis module is used for carrying out state analysis on the hardware data through a preset state model to obtain state information, extracting historical hardware data of the multi-element database, and carrying out trend analysis by combining the state information and the historical hardware data to obtain hardware prediction data; extracting historical temperature data of the multi-element database, and carrying out trend analysis by combining the state information, the historical temperature data and the temperature data to obtain temperature prediction data;
the processing module is used for judging whether the hardware prediction data and the temperature prediction data reach a preset early warning threshold value, and when any one data reach the early warning threshold value, corresponding maintenance suggestions are generated according to preset maintenance rules;
the updating module is used for sending the maintenance suggestions to the corresponding maintenance mechanism, receiving feedback data sent by the maintenance mechanism after executing the maintenance suggestions in real time, and updating the data of the early warning threshold according to the feedback data;
Performing feature extraction on the multi-element index data according to a preset extraction rule to obtain primary side input voltage value, secondary side output voltage value, current value and temperature feature data;
performing voltage ratio calculation based on the primary side input voltage value and the secondary side output voltage value to obtain voltage ratio characteristic data; carrying out phase analysis on the primary side input voltage value and the secondary side output voltage value to obtain phase data, extracting and combining the absolute value, the dynamic change range value and the periodic fluctuation characteristic of the phase data to obtain phase difference characteristic data; carrying out analysis on each subharmonic component of the primary side input voltage value and the secondary side output voltage value to obtain a total harmonic distortion rate and each subharmonic amplitude, and combining the total harmonic distortion rate and each subharmonic amplitude into harmonic characteristic data;
Carrying out discharge analysis on the current value to obtain the number of discharge pulses, the discharge energy, the exciting current effective value and the harmonic content, and combining the number of discharge pulses, the discharge energy, the exciting current effective value and the harmonic content into current characteristic data;
Carrying out data analysis on the temperature characteristic data to obtain key point temperature, thermal stability data and overall temperature, and combining the key point temperature, the thermal stability data and the overall temperature into temperature data;
And combining the voltage ratio characteristic data, the phase difference characteristic data, the harmonic characteristic data and the current characteristic data to obtain hardware data.
8. An on-line monitoring device for a voltage transformer, comprising:
A memory for storing a program;
a processor for executing the program to implement the steps of a method for on-line monitoring of a voltage transformer according to any one of claims 1-6.
9. A storage medium having stored thereon computer instructions for causing a computer to perform the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410636231.5A CN118226366B (en) | 2024-05-22 | 2024-05-22 | Online monitoring method, device and equipment of voltage transformer and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410636231.5A CN118226366B (en) | 2024-05-22 | 2024-05-22 | Online monitoring method, device and equipment of voltage transformer and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118226366A CN118226366A (en) | 2024-06-21 |
| CN118226366B true CN118226366B (en) | 2024-08-06 |
Family
ID=91498091
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410636231.5A Active CN118226366B (en) | 2024-05-22 | 2024-05-22 | Online monitoring method, device and equipment of voltage transformer and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118226366B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118376869B (en) * | 2024-06-27 | 2024-10-11 | 山西迎润新能源有限公司 | Power system fault diagnosis method, device, equipment and medium |
| CN118625244B (en) * | 2024-07-04 | 2025-05-16 | 深圳友讯达科技股份有限公司 | Performance evaluation method and system of current transformer |
| CN118837808A (en) * | 2024-08-12 | 2024-10-25 | 深圳友讯达科技股份有限公司 | Current transformer state monitoring method and system |
| CN118818407B (en) * | 2024-09-19 | 2024-12-03 | 常州顺创电气科技有限公司 | High-voltage transformer performance monitoring system and method based on artificial intelligence |
| CN119355615B (en) * | 2024-12-25 | 2025-05-09 | 河北鑫环通变压器制造有限公司 | On-line monitoring method for running state of voltage transformer |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109116285A (en) * | 2018-08-22 | 2019-01-01 | 国网江苏省电力有限公司盐城供电分公司 | A kind of capacitance type potential transformer measuring device with electricity based on multi-signal acquisition |
| CN110261809A (en) * | 2019-06-27 | 2019-09-20 | 中国电力科学研究院有限公司 | A system and method for determining the operating state of a capacitive voltage transformer |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113899968B (en) * | 2021-09-23 | 2024-05-10 | 成都高斯电子技术有限公司 | Voltage transformer monitoring method |
| CN115574867A (en) * | 2022-10-31 | 2023-01-06 | 云南电网有限责任公司电力科学研究院 | Mutual inductor fault detection method and device, electronic equipment and storage medium |
| CN117349613A (en) * | 2023-09-15 | 2024-01-05 | 国网重庆市电力公司营销服务中心 | A method, device, storage medium and computer equipment for predicting the life of a transformer |
| CN117491935A (en) * | 2023-10-30 | 2024-02-02 | 国网河南省电力公司营销服务中心 | Evaluation method of voltage transformer operating status based on multi-source data |
| CN117538811A (en) * | 2023-11-13 | 2024-02-09 | 内蒙古电力(集团)有限责任公司电能计量分公司 | Mutual inductor detection system and method |
| CN117826058A (en) * | 2024-01-10 | 2024-04-05 | 国网河北省电力有限公司营销服务中心 | A method and device for online monitoring of operating status of a gateway capacitor voltage transformer |
-
2024
- 2024-05-22 CN CN202410636231.5A patent/CN118226366B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109116285A (en) * | 2018-08-22 | 2019-01-01 | 国网江苏省电力有限公司盐城供电分公司 | A kind of capacitance type potential transformer measuring device with electricity based on multi-signal acquisition |
| CN110261809A (en) * | 2019-06-27 | 2019-09-20 | 中国电力科学研究院有限公司 | A system and method for determining the operating state of a capacitive voltage transformer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118226366A (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118226366B (en) | Online monitoring method, device and equipment of voltage transformer and storage medium | |
| EP3979080A1 (en) | Methods and systems for predicting time of server failure using server logs and time-series data | |
| CN117114454B (en) | DC sleeve state evaluation method and system based on Apriori algorithm | |
| CN117689214B (en) | Dynamic safety assessment method for energy router of flexible direct-current traction power supply system | |
| CN112598172A (en) | Wind turbine bearing temperature early warning method | |
| CN118395358A (en) | Intelligent anti-misoperation topology analysis method for transformer substation | |
| CN118312923B (en) | Intelligent park-oriented equipment measurement method and computer equipment | |
| CN119577659B (en) | A method, system, medium and program product for generating an operation and maintenance mode analysis model | |
| Aranizadeh et al. | Prioritizing CBs maintenance and identifying mandatory maintenance at higher priorities | |
| CN114168375A (en) | Method for quickly positioning and eliminating database system abnormity | |
| CN118278911A (en) | Power distribution defect intelligent diagnosis center system | |
| CN119741003A (en) | Hydropower station remote fault early warning method and system based on big data analysis | |
| CN119494467A (en) | A method for energy system fault prediction based on knowledge graph | |
| CN118861682A (en) | Disconnector fault risk assessment method, system and storage medium based on logistic regression | |
| CN117536798A (en) | Wind driven generator fault early warning method, system, equipment and storage medium | |
| CN117824854A (en) | Transformer body temperature rise abnormal warning method and device | |
| CN116183227B (en) | Bearing two-stage service life prediction method and system | |
| CN119167778A (en) | A method for predicting the remaining useful life of aircraft engines based on hybrid data and model drive | |
| CN119273143A (en) | A method and system for evaluating the probability risk of urban power grid scenarios under the influence of natural disasters | |
| Cheng et al. | Early Warning of Energy Storage Battery Fault Based on Improved Autoformer and Adaptive Threshold | |
| CN118033344A (en) | On-line monitoring method and system for insulation state of converter transformer valve side sleeve | |
| McCalley et al. | Computation of contingency probabilities for electric transmission decision problems | |
| CN116149971A (en) | Equipment fault prediction method and device, electronic equipment and storage medium | |
| CN118983470B (en) | Online hydrogen energy UPS intelligent control method and related equipment | |
| CN119373769B (en) | Pressure regulation and control method and system applied to hydraulic energy storage starting device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |