CN116629120A - Heat dissipation evaluation method and system for dry type power transformer - Google Patents
Heat dissipation evaluation method and system for dry type power transformer Download PDFInfo
- Publication number
- CN116629120A CN116629120A CN202310593419.1A CN202310593419A CN116629120A CN 116629120 A CN116629120 A CN 116629120A CN 202310593419 A CN202310593419 A CN 202310593419A CN 116629120 A CN116629120 A CN 116629120A
- Authority
- CN
- China
- Prior art keywords
- average value
- temperature
- heat dissipation
- fan
- result
- 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
- 230000017525 heat dissipation Effects 0.000 title claims abstract description 71
- 238000011156 evaluation Methods 0.000 title claims abstract description 48
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 238000013210 evaluation model Methods 0.000 claims abstract description 23
- 230000003245 working effect Effects 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 43
- 238000012549 training Methods 0.000 claims description 34
- 238000000034 method Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 12
- 230000005855 radiation Effects 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012417 linear regression Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000011217 control strategy Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000011810 insulating material Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000000540 analysis of variance Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 239000012774 insulation material Substances 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000191 radiation effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04D—NON-POSITIVE-DISPLACEMENT PUMPS
- F04D27/00—Control, e.g. regulation, of pumps, pumping installations or pumping systems specially adapted for elastic fluids
- F04D27/001—Testing thereof; Determination or simulation of flow characteristics; Stall or surge detection, e.g. condition monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
Abstract
The application relates to the technical field of data monitoring and application, in particular to a heat dissipation evaluation method and a heat dissipation evaluation system of a dry type power transformer, wherein the heat dissipation evaluation method comprises the following steps: s100, determining a plurality of temperature monitoring parameters for a dry type power transformer; s200, synchronously collecting each temperature monitoring parameter according to a set time interval to obtain a plurality of temperature monitoring results, and calculating the average value of each temperature monitoring result to obtain a temperature average value; s300, obtaining a plurality of temperature parameter variation degrees, calculating an average value of the temperature parameter variation degrees, and obtaining a variation degree average value; s400, inputting the temperature average value and the variation degree average value into a temperature analysis control module, and outputting control parameters of a fan; s500, inputting the operation parameter acquisition result, the temperature average value and the variation degree average value into a heat dissipation evaluation model, and evaluating the working effect of the fan. According to the application, the heat dissipation condition of the dry-type power transformer is monitored and evaluated in real time, the fan control parameters are timely adjusted, the heat dissipation efficiency is improved, and the energy is saved.
Description
Technical Field
The application relates to the technical field of data monitoring and application, in particular to a heat dissipation evaluation method and a heat dissipation evaluation system for a dry type power transformer.
Background
Load loss and no-load loss in the operation of the dry power transformer are converted into heat energy to be outwards dispersed, so that the transformer is continuously heated and the temperature is increased, and in general, the larger the load of the transformer is, the higher the temperature rise of the transformer is; under the same load, the temperature rise level of the transformer directly determines the load carrying capacity of the transformer.
In general, the temperature rise of the transformer causes the following problems:
the life of the transformer is shortened: excessive temperature can accelerate the aging and failure of the insulating material of the transformer, thereby shortening the service life of the transformer; the energy consumption is increased: the rise of the temperature of the transformer can lead to the rise of the internal resistance of the transformer, thereby leading to the reduction of transmission power, and simultaneously, the induction current can also be increased, so that the energy consumption of the transformer is increased; security risk increases: excessive temperature easily causes safety accidents such as fire disaster and the like, and immeasurable losses are caused to human bodies and equipment.
Therefore, for the dry power transformer, the temperature rise level of the dry power transformer must be strictly controlled, and the transformer is ensured to run in a normal working range through reasonable measures such as heat dissipation design, temperature monitoring and timely maintenance of the transformer. In the current control mode, a fan is adopted to cool the transformer, for example, when the temperature of the overload low-voltage coil of the transformer reaches a set high temperature, the fan is automatically started to cool the transformer; when the temperature of the low-voltage coil of the transformer reaches the set low temperature, the fan is automatically controlled to stop.
In the control mode, the temperature can reach the safe range through the operation of the fan, but the system and the method for evaluating the heat dissipation effect after the operation of the fan are not available, so that the operation of the fan may have overload, high energy consumption and other conditions.
Disclosure of Invention
The application provides a heat dissipation evaluation method and a heat dissipation evaluation system for a dry type power transformer, so that the problems pointed out in the background technology are effectively solved.
In order to achieve the above purpose, the technical scheme adopted by the application is as follows:
a heat dissipation evaluation method of a dry type power transformer comprises the following steps:
s100, determining a plurality of temperature monitoring parameters for the dry-type power transformer;
s200, synchronously collecting each temperature monitoring parameter according to a set time interval to obtain a plurality of temperature monitoring results, and calculating the average value of each temperature monitoring result to obtain a temperature average value;
s300, calculating the change degree of the current result relative to the previous result according to each temperature monitoring result respectively to obtain a plurality of temperature parameter change degrees, and calculating the average value of the temperature parameter change degrees to obtain a change degree average value;
s400, inputting the temperature average value and the variation degree average value into a temperature analysis control module, and outputting control parameters of a fan; after the fan is started, the operation parameters of the fan are collected, an operation parameter collection result is obtained, and calculation of a temperature average value and a change degree average value is continuously carried out;
s500, inputting the operation parameter acquisition result, the temperature average value and the variation degree average value into a heat dissipation evaluation model, and evaluating the working effect of the fan.
Further, the heat dissipation evaluation model is established, which comprises the following steps:
s010: determining a historical sample data set, wherein the historical sample data set comprises a corresponding operation parameter acquisition result, a temperature average value and a change degree average value;
s020: determining a heat dissipation evaluation value, and marking a historical sample data set according to the heat dissipation evaluation value;
s030: determining a modeling method, and dividing data into a training set and a testing set;
s040: training the model using the training set, and validating and optimizing the model according to the test set.
Further, the working effect of the fan is evaluated by adopting a linear regression model, and the training steps comprise:
s041: extracting and selecting characteristics according to the operation parameter acquisition result to determine the most relevant and important characteristics to participate in model training;
s042: training the linear regression model by adopting a gradient descent algorithm, and setting super parameters during training;
s043: the performance of the model is evaluated and the best combination of model parameters and hyper-parameters is selected.
Further, feature extraction is performed on the operation parameter acquisition result, and the method comprises the following steps:
s0411: determining variables and grouping modes to be analyzed aiming at an operation parameter acquisition result of the fan;
s0412: grouping the obtained data in a grouping mode, and then calculating the average value and variance of each group;
s0413: calculating a variance ratio by adopting F statistics;
s0414: determining variables which have important influence on the difference of the average values according to the size and the significance level of the F statistic;
s0415: and taking the determined variable as a characteristic factor to perform characteristic extraction.
Further, the feature selection performed after feature extraction includes the following steps:
s0416: evaluating the importance of the extracted features;
s0417: according to the result of the importance assessment, the extracted features are ranked in order of importance from high to low;
s0418: and selecting a plurality of top-ranked bit features according to the set selection criteria.
Further, the operation parameter acquisition result, the temperature average value and the variation degree average value in the historical sample data set are respectively acquired by adopting a weighted average calculation method, wherein the weight coefficient is smaller as the distance interval time is longer.
A heat dissipation evaluation system of a dry power transformer, comprising:
the temperature acquisition module is used for synchronously acquiring each temperature monitoring parameter according to a set time interval to obtain a plurality of temperature monitoring results, and calculating the average value of each temperature monitoring result to obtain a temperature average value;
the temperature change acquisition module is used for respectively calculating the change degree of the current result relative to the previous result aiming at each temperature monitoring result to obtain a plurality of temperature parameter change degrees, calculating the average value of the temperature parameter change degrees and obtaining a change degree average value;
the control parameter generation module inputs the temperature average value and the variation degree average value into the temperature analysis control module, and outputs control parameters of the fan, wherein after the fan is started, the operation parameters of the fan are collected, an operation parameter collection result is obtained, and calculation of the temperature average value and the variation degree average value is continuously carried out;
and the heat radiation evaluation module inputs the operation parameter acquisition result, the temperature average value and the variation degree average value into a heat radiation evaluation model to evaluate the working effect of the fan.
Further, the heat dissipation evaluation module further comprises a heat dissipation evaluation training unit, and the heat dissipation evaluation model is trained, verified and optimized.
Further, the heat dissipation evaluation module further comprises a history storage unit, and the history sample data set of the heat dissipation evaluation model is stored, wherein the history sample data set comprises a corresponding operation parameter acquisition result, a temperature average value and a change degree average value.
By the technical scheme of the application, the following technical effects can be realized:
according to the application, the heat dissipation condition of the dry-type power transformer can be monitored and evaluated in real time, and the fan control parameters can be adjusted in time, so that the heat dissipation efficiency is improved and the energy is saved; through synchronous acquisition and calculation of a plurality of temperature monitoring parameters, a more accurate temperature average value and a change degree average value can be obtained, so that the working effect of the fan can be estimated more accurately; the whole method can realize marking of a historical sample data set and training, verification and optimization of the model by establishing a heat dissipation evaluation model, so that the accuracy and generalization capability of the evaluation model are improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
Fig. 1 is a flow chart diagram of a method for evaluating heat dissipation of a dry power transformer;
FIG. 2 is a schematic flow chart of establishing the heat dissipation evaluation model;
FIG. 3 is a schematic flow chart for evaluating the working effect of the fan;
FIG. 4 is a flow chart of feature extraction from the result of the operation parameter acquisition;
FIG. 5 is a schematic flow chart of feature selection performed after feature extraction;
fig. 6 is a schematic diagram of a heat dissipation evaluation system of a dry power transformer.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
As shown in fig. 1, a heat dissipation evaluation method for a dry-type power transformer includes:
s100, determining a plurality of temperature monitoring parameters for a dry type power transformer;
s200, synchronously collecting each temperature monitoring parameter according to a set time interval to obtain a plurality of temperature monitoring results, and calculating the average value of each temperature monitoring result to obtain a temperature average value;
s300, respectively calculating the change degree of the current result relative to the previous result aiming at each temperature monitoring result to obtain a plurality of temperature parameter change degrees, and calculating the average value of the temperature parameter change degrees to obtain a change degree average value;
s400, inputting the temperature average value and the variation degree average value into a temperature analysis control module, and outputting control parameters of a fan; after the fan is started, the operation parameters of the fan are collected, an operation parameter collection result is obtained, and calculation of a temperature average value and a change degree average value is continuously carried out;
s500, inputting the operation parameter acquisition result, the temperature average value and the variation degree average value into a heat dissipation evaluation model, and evaluating the working effect of the fan.
In the embodiment, in step S100, the busbar junction temperature of the dry-type power transformer generally refers to the temperature of the copper busbar junction inside the transformer, and the coil temperature refers to the temperature of the coil inside the transformer. The busbar junction temperature and the coil temperature are important parameters to be monitored and controlled in the operation process of the transformer, because the performance, the service life and the safety of the transformer are affected by the excessive temperature. In general, the busbar junction temperature of the transformer should be controlled below 60 ℃ and the coil temperature should be controlled within a temperature range that the transformer insulation material can withstand. The specific temperature depends on the rated power of the transformer, the use environment, the insulating material and other factors, and generally, the coil temperature of the dry-type power transformer is controlled below 155 ℃.
In this embodiment, the plurality of temperature monitoring results include a busbar junction temperature monitoring result, a coil temperature monitoring result and an environmental temperature monitoring result, and in step S200, the temperature average value of the three monitoring results is obtained correspondingly in real time, that is, after each acquisition, the average value of the busbar junction temperature monitoring result, the coil temperature monitoring result and the environmental temperature monitoring result is obtained as the temperature average value.
In the above-described scheme, the temperature average value and the variation degree average value are calculated, and the following benefits are obtained in the heat dissipation evaluation of the dry-type power transformer:
clearly reflects the temperature change trend: the temperature average value and the change degree average value are calculated, so that the change trend and the amplitude of the temperature can be clearly reflected, and the monitoring and the control are convenient;
reducing the influence of single-point abnormality on the evaluation result: because the temperature distribution inside the dry power transformer is uneven, the temperature abnormality of a certain point or area is likely to be higher, if only single-point temperature data is concerned, larger errors are generated on the evaluation result, and the temperature conditions of all points can be comprehensively considered by calculating the temperature average value and the change degree average value, so that the influence of single-point abnormality on the evaluation result is reduced.
In step S400, the control parameters of the fan may specifically include:
and (3) start-stop control: the start and stop of the fan are controlled according to the heat dissipation condition calculated by the temperature average value and the change degree average value so as to ensure the normal heat dissipation of the transformer;
and (3) rotating speed control: according to the calculation results of the temperature average value and the variation degree average value, the rotating speed of the fan is adjusted to adapt to the actual heat dissipation requirement of the transformer;
and (3) air quantity control: the air quantity of the fan is controlled to meet the heat dissipation requirements of the transformer under different load working conditions.
The running state of the fan can be adjusted according to the real-time monitoring data through outputting the control parameters of the fan, so that the fan can run in the optimal state, the heat dissipation efficiency of the equipment is improved, and the stable running of the equipment is ensured; the operation parameters of the fan are collected, so that the actual operation condition of the fan can be known, the failure or performance reduction of the fan can be found in time, the normal operation of equipment is ensured, and the maintenance cost is reduced. In addition, the heat radiation evaluation model can comprehensively evaluate the heat radiation effect of the equipment according to the acquired temperature average value, variation degree average value and operation parameter data, discover the poor heat radiation condition, take measures in time to improve the heat radiation efficiency and ensure the normal operation of the equipment. By the above mode, the following purposes can be achieved:
effectively judge fan running state: by acquiring the operation parameter acquisition result after the fan is started and continuously calculating the temperature average value and the variation degree average value, the operation state of the fan can be judged and evaluated in real time, so that a corresponding control strategy is adopted in time.
Helping to optimize the control strategy: according to the calculation results of the temperature average value and the variation degree average value, control parameters of the fan can be output to realize start-stop and rotation speed control of the fan, and a control strategy is continuously optimized according to the evaluation result, so that the heat dissipation efficiency is improved, and the energy is saved.
In summary, the method can monitor and evaluate the heat dissipation condition of the dry power transformer in real time, and can adjust the fan control parameters in time so as to improve the heat dissipation efficiency and save energy.
Further, as shown in fig. 2, the heat dissipation evaluation model is built, and includes the following steps:
s010: determining a historical sample data set, wherein the historical sample data set comprises a corresponding operation parameter acquisition result, a temperature average value and a change degree average value;
s020: determining a heat dissipation evaluation value, and marking a historical sample data set according to the heat dissipation evaluation value;
s030: determining a modeling method, and dividing data into a training set and a testing set;
s040: training the model using the training set, and validating and optimizing the model according to the test set.
Specifically, in step S010, by collecting historical fan operation data, changes in the fan operation state and performance performances of the fan under different working conditions can be known; these data can be used to train and optimize machine learning models and provide important information about fan health; in the step S020, a heat dissipation evaluation value is marked, and a heat dissipation evaluation value is allocated to each sample in the historical data set, so that the data can be converted into a format which can be used for training a machine learning model; after the modeling method is determined, dividing the data into a training set and a testing set is one of key steps for establishing a heat dissipation evaluation model, and by dividing the data into the training set and the testing set, the model can be ensured to obtain good prediction performance on the training data and realize good generalization performance on the testing data; the heat dissipation evaluation model is established to be combined with other intelligent technologies, such as the Internet of things, cloud computing and the like, so that intelligent management and control of equipment are realized, and the running efficiency and management level of the equipment are improved.
Further, as shown in fig. 3, a linear regression model is used to evaluate the working effect of the fan, and the training steps include:
s041: feature extraction and selection are carried out on the operation parameter acquisition result so as to determine the most relevant and important features to participate in model training; for example, in the present application, assuming that the operation parameters of the blower are collected, the most important features include the rotation speed and the air volume of the blower;
s042: training a linear regression model by adopting a gradient descent algorithm, and setting super parameters during training;
s043: the performance of the model is evaluated and the best combination of model parameters and hyper-parameters is selected.
Specifically, the gradient descent algorithm is a commonly used machine learning algorithm for training a model and optimizing model parameters; when the model is trained by using a gradient descent algorithm, some super parameters are required to be set so as to control the training process and result of the model; specifically, the super-parameters refer to parameters which are not determined by training data and need to be set manually; in the linear regression model, common super parameters include learning rate, iteration number, regularization parameters, and the like. The linear regression model is adopted in fan evaluation, so that the advantages of simplicity, easiness in interpretation, stability, high efficiency and the like can be fully utilized, and the performance and the operation effect of the fan can be accurately evaluated and predicted. Meanwhile, when the performance of the model is evaluated, the performance of the model can be evaluated more comprehensively and objectively by adopting cross verification and other evaluation indexes, and the optimal combination of model parameters and super parameters is selected, so that the prediction precision and stability of the model are further improved, and more accurate fan working effect evaluation is realized.
Further, as shown in fig. 4, feature extraction is performed for the operation parameter acquisition result, which includes the following steps:
s0411: determining variables and grouping modes to be analyzed aiming at an operation parameter acquisition result of the fan;
in this step, it is necessary to determine the variables to be analyzed, which should be able to describe the results of the acquisition of the operating parameters of the blower, such as blower speed, air volume, local temperature, current, voltage, power, etc. Meanwhile, a grouping mode needs to be determined, and the grouping mode can be selected according to actual conditions, for example, grouping is performed according to different running states, different working conditions, different time periods and the like;
s0412: grouping the obtained data in a grouping mode, and then calculating the average value and variance of each group;
s0413: calculating a variance ratio by adopting F statistics;
s0414: determining variables which have important influence on the difference of the average values according to the size and the significance level of the F statistic;
s0415: and taking the determined variable as a characteristic factor to perform characteristic extraction.
Specifically, the grouping mode can be selected according to actual conditions, the degree of difference between each group can be known by calculating variance, and the influence of each variable on the average value is determined; in analysis of variance, the F statistic is used to compare the degree of difference of the average values between different groups, and determine whether each variable has significance to the difference of the average values, and the calculation method of the F statistic is as follows:
f=mean square error (group)/mean square error (inner)
Wherein the mean square error (group) represents the variance between groups and the mean square error (inner) represents the variance inside each group. The larger the value of the F statistic, the smaller the intra-group variance, and the larger the inter-group variance, i.e. the larger the degree of average difference between different groups; thus, the larger the F value, the more significant the difference is explained; when the variance analysis is carried out, if the F value is larger than the critical value, the variance can be considered to have a significant effect on the difference of the average value, and the variance can be further analyzed; the characteristic factors in step S0415 may be used to perform model training and prediction to achieve evaluation and optimization of the fan operation effect.
Further, as shown in fig. 5, the feature selection performed after feature extraction includes the following steps:
s0416: evaluating the importance of the extracted features;
s0417: according to the result of the importance assessment, the extracted features are ranked in order of importance from high to low;
s0418: and selecting a plurality of top-ranked bit features according to the set selection criteria.
The model is trained using the selected features and evaluated. If the performance of the model is good, it is useful to state that the selected feature, it should be noted that feature selection is an iterative process that requires multiple evaluations and adjustments. In selecting features, correlation between features also needs to be considered to avoid selecting similar features too much. At the same time, feature selection needs to be performed in conjunction with specific application scenarios and data sets.
Further, the operation parameter collection result, the temperature average value and the variation degree average value in the historical sample data set are respectively collected by adopting a weighted average calculation method, wherein the weight coefficient is smaller as the distance interval time is longer.
Specifically, this weighted average calculation method has an advantage in that it can take timeliness of the history data into consideration, and attach more importance to recent data by giving different weights to the data in different time periods, thereby reflecting the current state more accurately. The method can also avoid over-dependence on past data to a certain extent, and ensure the updating property and real-time property of the data. In addition, by adopting a weighted average method, the interference of data noise on a calculation result can be effectively reduced, and the reliability and accuracy of data are improved. When the number of the historical data is large and the distribution is scattered, the weighted average method can better reflect the overall trend of the historical data, so that the establishment and optimization of a model are better supported.
As shown in fig. 6, a heat dissipation evaluation system for a dry-type power transformer includes:
the temperature acquisition module is used for synchronously acquiring each temperature monitoring parameter according to a set time interval to obtain a plurality of temperature monitoring results, and calculating the average value of each temperature monitoring result to obtain a temperature average value;
the temperature change acquisition module is used for respectively calculating the change degree of the current result relative to the previous result aiming at each temperature monitoring result to obtain a plurality of temperature parameter change degrees, calculating the average value of each temperature parameter change degree and obtaining a change degree average value;
the control parameter generation module inputs the temperature average value and the variation degree average value into the temperature analysis control module, and outputs control parameters of the fan, wherein after the fan is started, the operation parameters of the fan are collected, an operation parameter collection result is obtained, and calculation of the temperature average value and the variation degree average value is continuously carried out;
and the heat radiation evaluation module inputs the operation parameter acquisition result, the temperature average value and the variation degree average value into a heat radiation evaluation model to evaluate the working effect of the fan.
Furthermore, the heat dissipation evaluation module further comprises a heat dissipation evaluation training unit for training the heat dissipation evaluation model and verifying and optimizing the heat dissipation evaluation model.
Furthermore, the heat dissipation evaluation module further comprises a history storage unit for storing a history sample data set of the heat dissipation evaluation model, wherein the history sample data set comprises a corresponding operation parameter acquisition result, a temperature average value and a change degree average value.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course by means of special purpose hardware including application specific integrated circuits, special purpose CPUs, special purpose memories, special purpose components, etc. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. However, a software program implementation is a preferred embodiment for many more of the cases of the present application. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., comprising several instructions for causing a computer device to execute the method of the embodiments of the present application.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.
The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with the present application are fully or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from a computer-readable storage medium, and the usable medium may be a magnetic medium, (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), etc.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, appear throughout the specification
"in one embodiment" or "in an embodiment" does not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present application, the sequence number of each process described above does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the present application.
In addition, the terms "system" and "network" are often used interchangeably herein. The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
It should be understood that in the present application, "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In summary, the above embodiments are only preferred embodiments of the present application, and are not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (9)
1. A heat dissipation evaluation method for a dry-type power transformer is characterized by comprising the following steps:
determining a plurality of temperature monitoring parameters for the dry power transformer;
synchronously collecting each temperature monitoring parameter according to a set time interval to obtain a plurality of temperature monitoring results, and calculating the average value of each temperature monitoring result to obtain a temperature average value;
calculating the change degree of the current result relative to the previous result according to each temperature monitoring result respectively to obtain a plurality of temperature parameter change degrees, and calculating the average value of each temperature parameter change degree to obtain a change degree average value;
inputting the temperature average value and the variation average value into a temperature analysis control module, and outputting control parameters of a fan; after the fan is started, the operation parameters of the fan are collected, an operation parameter collection result is obtained, and calculation of a temperature average value and a change degree average value is continuously carried out;
and inputting the operation parameter acquisition result, the temperature average value and the variation degree average value into a heat dissipation evaluation model, and evaluating the working effect of the fan.
2. The heat dissipation evaluation method of a dry-type power transformer according to claim 1, wherein establishing the heat dissipation evaluation model comprises the steps of:
s010: determining a historical sample data set, wherein the historical sample data set comprises a corresponding operation parameter acquisition result, a temperature average value and a change degree average value;
s020: determining a heat dissipation evaluation value, and marking a historical sample data set according to the heat dissipation evaluation value;
s030: determining a modeling method, and dividing data into a training set and a testing set;
s040: training the model using the training set, and validating and optimizing the model according to the test set.
3. The method for evaluating heat dissipation of a dry power transformer according to claim 2, wherein the fan operation effect is evaluated by using a linear regression model, and the training step includes:
s041: extracting and selecting characteristics according to the operation parameter acquisition result to determine the most relevant and important characteristics to participate in model training;
s042: training the linear regression model by adopting a gradient descent algorithm, and setting super parameters during training;
s043: the performance of the model is evaluated and the best combination of model parameters and hyper-parameters is selected.
4. A heat radiation evaluation method of a dry type power transformer according to claim 3, wherein the feature extraction is performed for the operation parameter acquisition result, comprising the steps of:
s0411: determining variables and grouping modes to be analyzed aiming at an operation parameter acquisition result of the fan;
s0412: grouping the obtained data in a grouping mode, and then calculating the average value and variance of each group;
s0413: calculating a variance ratio by adopting F statistics;
s0414: determining variables which have important influence on the difference of the average values according to the size and the significance level of the F statistic;
s0415: and taking the determined variable as a characteristic factor to perform characteristic extraction.
5. The method for evaluating heat dissipation of a dry power transformer according to claim 4, wherein the feature selection performed after the feature extraction comprises the steps of:
s0416: evaluating the importance of the extracted features;
s0417: according to the result of the importance assessment, the extracted features are ranked in order of importance from high to low;
s0418: and selecting a plurality of top-ranked bit features according to the set selection criteria.
6. The method for evaluating heat dissipation of a dry power transformer according to claim 2, wherein the operation parameter collection result, the temperature average value and the variation degree average value in the historical sample data set are collected by a weighted average calculation method, respectively, and the weight coefficient is smaller as the distance interval is longer.
7. A heat dissipation evaluation system for a dry power transformer, comprising:
the temperature acquisition module is used for synchronously acquiring a plurality of temperature monitoring parameters determined for the dry-type power transformer according to a set time interval to obtain a plurality of temperature monitoring results, and calculating the average value of the temperature monitoring results to obtain a temperature average value;
the temperature change acquisition module is used for respectively calculating the change degree of the current result relative to the previous result aiming at each temperature monitoring result to obtain a plurality of temperature parameter change degrees, calculating the average value of the temperature parameter change degrees and obtaining a change degree average value;
the temperature analysis control module outputs control parameters of the fan according to the input temperature average value and the variation degree average value;
the operation parameter acquisition module acquires operation parameters of the fan after the fan is started to obtain an operation parameter acquisition result, and in the acquisition process, the temperature acquisition module and the temperature change acquisition module continuously calculate a temperature average value and a change degree average value;
and the heat radiation evaluation module inputs the operation parameter acquisition result, the temperature average value and the variation degree average value into a heat radiation evaluation model to evaluate the working effect of the fan.
8. The system according to claim 7, wherein the heat dissipation evaluation module further comprises a heat dissipation evaluation training unit that trains the heat dissipation evaluation model and performs verification and optimization.
9. The system of claim 8, wherein the heat dissipation evaluation module further comprises a history storage unit for storing a history sample data set of the heat dissipation evaluation model, the history sample data set including a corresponding operation parameter acquisition result, a temperature average value, and a variation degree average value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310593419.1A CN116629120A (en) | 2023-05-23 | 2023-05-23 | Heat dissipation evaluation method and system for dry type power transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310593419.1A CN116629120A (en) | 2023-05-23 | 2023-05-23 | Heat dissipation evaluation method and system for dry type power transformer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116629120A true CN116629120A (en) | 2023-08-22 |
Family
ID=87612822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310593419.1A Pending CN116629120A (en) | 2023-05-23 | 2023-05-23 | Heat dissipation evaluation method and system for dry type power transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116629120A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117199029A (en) * | 2023-11-07 | 2023-12-08 | 瑞森半导体科技(广东)有限公司 | Power supply management chip and power supply management method |
| CN117216577A (en) * | 2023-11-07 | 2023-12-12 | 博纯材料股份有限公司 | Temperature monitoring method and system based on germane purification system |
| CN117250547A (en) * | 2023-11-20 | 2023-12-19 | 深圳市菲尼基科技有限公司 | Reliability evaluation method and system for battery energy storage system |
| CN117529070A (en) * | 2024-01-08 | 2024-02-06 | 四川建诚智造科技有限公司 | Heat dissipation control method and system for stable operation of photovoltaic inverter |
-
2023
- 2023-05-23 CN CN202310593419.1A patent/CN116629120A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117199029A (en) * | 2023-11-07 | 2023-12-08 | 瑞森半导体科技(广东)有限公司 | Power supply management chip and power supply management method |
| CN117216577A (en) * | 2023-11-07 | 2023-12-12 | 博纯材料股份有限公司 | Temperature monitoring method and system based on germane purification system |
| CN117199029B (en) * | 2023-11-07 | 2024-01-12 | 瑞森半导体科技(广东)有限公司 | Power supply management chip and power supply management method |
| CN117216577B (en) * | 2023-11-07 | 2024-02-27 | 博纯材料股份有限公司 | Temperature monitoring method and system based on germane purification system |
| CN117250547A (en) * | 2023-11-20 | 2023-12-19 | 深圳市菲尼基科技有限公司 | Reliability evaluation method and system for battery energy storage system |
| CN117250547B (en) * | 2023-11-20 | 2024-04-02 | 深圳市菲尼基科技有限公司 | Reliability evaluation method and system for battery energy storage system |
| CN117529070A (en) * | 2024-01-08 | 2024-02-06 | 四川建诚智造科技有限公司 | Heat dissipation control method and system for stable operation of photovoltaic inverter |
| CN117529070B (en) * | 2024-01-08 | 2024-03-26 | 四川建诚智造科技有限公司 | Heat dissipation control method and system for stable operation of photovoltaic inverter |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116629120A (en) | Heat dissipation evaluation method and system for dry type power transformer | |
| CN114298863B (en) | Data acquisition method and system of intelligent meter reading terminal | |
| CN113805064B (en) | Lithium ion battery pack health state prediction method based on deep learning | |
| WO2021097604A1 (en) | Multi-information fusion-based fault early warning method and device for converter | |
| CN107291991B (en) | Early defect early warning method for wind turbine generator based on dynamic network sign | |
| WO2023065580A1 (en) | Fault diagnosis method and apparatus for gearbox of wind turbine generator set | |
| CN108960492A (en) | A kind of exhaust enthalpy of turbine prediction technique based on PSO-SVR soft-sensing model | |
| CN112782499B (en) | Multi-information fusion-based converter state evaluation method and device | |
| CN113128005A (en) | Power grid node clustering and frequency safety analysis method and system based on dynamic characteristics | |
| CN116973703A (en) | Acoustic diagnosis method for discharge fault and abnormal operation state of dry type air-core reactor | |
| CN117057190A (en) | Temperature rise prediction method for brake disc of railway vehicle | |
| CN105741184A (en) | Transformer state evaluation method and apparatus | |
| CN112782614A (en) | Fault early warning method and device of converter based on multi-information fusion | |
| Luo | Application of reinforcement learning algorithm model in gas path fault intelligent diagnosis of gas turbine | |
| CN116523493A (en) | Auxiliary decision analysis method, system and storage medium for operation maintenance of power distribution network | |
| CN116307838A (en) | Accurate equivalence method, system and medium for power distribution network in power grid reliability evaluation | |
| CN112307652B (en) | Quick maintenance method for complex equipment system based on average remaining life importance | |
| Deng et al. | A fractional hilbert transform order optimization algorithm based DE for bearing health monitoring | |
| CN113537821A (en) | Rapid assessment method and system for state of power system | |
| CN111950131A (en) | Wind power plant output equivalent aggregation model construction method considering electricity limiting factors | |
| Kumar et al. | Gas turbine engine operational data analysis for anomaly detection: Statistical vs. neural network approach | |
| Zhang et al. | Optimization of wind power configuration in distribution network based on scenario clustering and power flow entropy | |
| CN113722977B (en) | Gas turbine rotor fault early warning method based on hybrid prediction | |
| Bai et al. | A Comprehensive Evaluation Method for Reliability Confidence Capacity of Renewable Energy Based on Improved DEMATEL-AHP-EWM | |
| CN115842335A (en) | New energy power system transient frequency maximum deviation prediction method based on measurement |
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 |