Capacity adjusting method, system and equipment of transformer and storage medium

The method addresses the issue of inaccurate capacity switching in on-load transformers by predicting load conditions and using a fuzzy priority matrix to optimize capacity adjustments, improving transformer longevity and grid stability.

CN119066957APending Publication Date: 2024-12-03YUNNAN POWER GRID CO LTD ELECTRIC POWER RES INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411074616.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

On-load capacity-adjusting transformers lack learning ability for future load conditions, leading to inaccurate capacity mode switching, which affects the transformer's operating life and reduces the safety and stability of the power grid.

Method used

A capacity adjustment method that sets different schemes based on predicted load conditions, using a fuzzy priority relationship matrix to determine a comprehensive optimization value, considering factors like switching times, power loss, and operating costs to select the optimal capacity adjustment scheme.

Benefits of technology

Accurately switches the transformer capacity mode to avoid overload or underload states, extending the transformer's operating life and enhancing power grid safety and stability by reducing losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066957A_ABST
    Figure CN119066957A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a capacity regulating method, system and equipment for a transformer and a storage medium. Different capacity regulating schemes are set according to the predicted load condition of the transformer; obtaining a comprehensive goodness value of each capacity regulating scheme according to the fuzzy priority relation matrix between the operation indexes of the transformer and the capacity regulating schemes; and according to the comprehensive goodness value, obtaining an optimal capacitance regulation scheme in different capacitance regulation schemes. By selecting the optimal capacity regulating scheme with the maximum comprehensive goodness value from different capacity regulating schemes according to the predicted load condition, the capacity mode of the transformer can be accurately switched, the transformer is prevented from being in an overload or light load state for a long time, the loss is reduced, the service life of the on-load capacity regulating transformer is prolonged, and the power consumption of the on-load capacity regulating transformer is reduced. And the safety and the stability of the power grid are improved.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to the field of transformer capacity adjustment, and in particular to a transformer capacity adjustment method, system, device and storage medium. [Background technology]

[0002] During the operation of the transformer, affected by frequent load fluctuations, the transformer is often in an overload or no-load or light-load state. The former will accelerate the aging process of the transformer and may even cause serious consequences such as transformer overheating and damage. The latter will cause a large power loss and fail to meet the safety and economy requirements of the distribution network.

[0003] To solve the above problems, on-load capacity-adjusting transformers are widely used. They have two states: large and small capacity. When the load is lower than the capacity-adjusting node, they are adjusted to a small capacity state to reduce the large power loss caused by no-load and light load; when the load is greater than the capacity-adjusting node, they are adjusted to a large capacity state to reduce the risk of transformer overload. However, this type of on-load capacity-adjusting transformer has a strong dependence on real-time data, has no learning ability for data, has no advance knowledge of the load conditions in the next period, and cannot accurately switch the transformer's capacity mode, which affects the transformer's operating life and reduces the safety and stability of the power grid system. [Summary of the invention]

[0004] In view of this, the present invention provides a capacity adjustment method, system, device and storage medium for a transformer.

[0005] The specific technical scheme of the first embodiment of the present invention is: a capacity adjustment method for a transformer, the method comprising: setting different capacity adjustment schemes according to the predicted load conditions of the transformer; obtaining a comprehensive optimization value of each capacity adjustment scheme according to a fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme; the operating indicators include the number of switching times, power loss and operating costs; and obtaining the optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive optimization value.

[0006] Preferably, the method of obtaining the comprehensive merit value of each capacity adjustment scheme based on the fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme includes: determining the merit value of the operating indicator by using the hierarchical analysis method; determining the weight of the operating indicator according to the merit value of the operating indicator and the number of operating indicators; and obtaining the comprehensive merit value of each capacity adjustment scheme according to the fuzzy priority relationship matrix, the importance of different capacity adjustment schemes and the weight of the operating indicators.

[0007] Preferably, the method of obtaining a comprehensive goodness value of each capacity adjustment scheme according to the fuzzy priority relationship matrix, the importance of different capacity adjustment schemes and the weight of the operating indicators includes: constructing a fuzzy consistency matrix according to the fuzzy priority relationship matrix and the importance of different capacity adjustment schemes; obtaining the goodness value of each capacity adjustment scheme according to the fuzzy consistency matrix, the number of capacity adjustment schemes and the number of operating indicators; obtaining a comprehensive goodness value of each capacity adjustment scheme according to the goodness value of each capacity adjustment scheme and the weight of the operating indicators.

[0008] Preferably, the goodness value of the operating index is obtained using the following formula:

[0009]

[0010] Among them, m i is the goodness value of the operating index, n is the number of operating indicators, a ij It is the ratio of the influence of operating index i and operating index j in the criterion layer.

[0011] Preferably, the weight of the operating index is obtained using the following formula:

[0012]

[0013] Among them, ω i is the weight of operation index i, m i is the goodness value of operating index i, and n is the number of operating indicators.

[0014] Preferably, the merit value of each capacity adjustment scheme is obtained using the following formula:

[0015]

[0016] Among them, s i is the optimality value of capacity adjustment scheme i, b is the number of capacity adjustment schemes, n is the number of operating indicators, r ik is the value of the i-th row and k-th column in the fuzzy consistent matrix.

[0017] Preferably, the method also includes: obtaining the real-time capacity of the transformer; judging the size of the optimal capacity in the optimal capacity adjustment scheme and the real-time capacity; if the real-time capacity is greater than or equal to the optimal capacity, adjusting the capacity mode of the transformer to a large capacity mode; if the real-time capacity is less than the optimal capacity, adjusting the capacity mode of the transformer to a small capacity mode.

[0018] The specific technical scheme of the second embodiment of the present invention is: a capacity adjustment system for a transformer, the system comprising: a capacity adjustment scheme setting module, a comprehensive excellence value acquisition module and an optimal capacity adjustment scheme determination module; the capacity adjustment scheme setting module is used to set different capacity adjustment schemes according to the predicted load conditions of the transformer; the comprehensive excellence value acquisition module is used to obtain the comprehensive excellence value of each capacity adjustment scheme according to the fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme; the operating indicators include the number of switching times, power loss and operating costs; the optimal capacity adjustment scheme determination module is used to obtain the optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive excellence value.

[0019] The specific technical solution of the third embodiment of the present invention is: a transformer capacity adjustment device, including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of the first embodiments of the present application.

[0020] The specific technical solution of the fourth embodiment of the present invention is: a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the method described in any one of the first embodiments of the present application.

[0021] Implementing the embodiments of the present invention will have the following beneficial effects:

[0022] The present invention sets different capacity adjustment schemes according to the predicted load conditions of the transformer; obtains the comprehensive merit value of each capacity adjustment scheme according to the fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme; and obtains the optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive merit value.

[0023] By selecting the optimal capacity adjustment scheme with the largest comprehensive merit value from different capacity adjustment schemes according to the predicted load conditions, the transformer capacity mode can be switched accurately to avoid the transformer being in an overload or underload state for a long time. While reducing losses, the operating life of the on-load capacity adjustment transformer is extended, and the safety and stability of the power grid are improved.

Brief Description of the Drawings

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 The present invention is a flowchart of the steps of the capacity adjustment method of the transformer;

[0026] Figure 2 A flowchart of the steps for obtaining the comprehensive merit value of each capacity adjustment scheme;

[0027] Figure 3 A flowchart of the steps for obtaining the comprehensive merit value of each capacity adjustment scheme;

[0028] Figure 4 A flow chart of the steps for adjusting capacity according to real-time capacity;

[0029] Figure 5 It is a schematic diagram of the circuit model of the on-load capacity-changing transformer;

[0030] Figure 6 It is a schematic diagram of the circuit model under load forecasting and fuzzy decision control;

[0031] Figure 7 The schematic diagram of the voltage waveform of loads 1, 3, and 5 under fuzzy control;

[0032] Figure 8 The schematic diagram of the current waveform of loads 1, 3, and 5 under fuzzy control;

[0033] Fig. 9 It is a comparison chart between actual load and predicted load;

[0034] Fig.10 It is a structural schematic diagram of the capacity adjustment system of the transformer;

[0035] Among them, 501 is a capacity adjustment plan setting module; 502 is a comprehensive excellence value acquisition module; 503 is an optimal capacity adjustment plan determination module. [Specific implementation method]

[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] The terms "first", "second", etc. in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally includes steps or modules that are not listed, or optionally includes other steps or modules that are inherent to these processes, methods, products or devices.

[0038] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0039] Transformer capacity adjustment refers to adjusting the size of the transformer to accommodate different power demands. This usually involves a change in the capacity of the transformer to accommodate changes in load, thereby improving energy efficiency and reducing costs. Capacity adjustment can be achieved in two main ways: replacing the transformer or using a capacity adjustment transformer. Replacing the transformer means replacing the existing transformer with a new transformer with a different rated capacity. This method is suitable when the load changes are large and the capacity needs to be significantly changed. Using a capacity adjustment transformer is a more flexible method that allows capacity adjustment without replacing the entire transformer. This transformer has an adjustable feature that allows capacity adjustment according to changes in load. The use of a capacity adjustment transformer can improve energy efficiency, reduce energy waste, and reduce operating costs. In addition, it also helps improve the reliability and stability of the power system. When implementing transformer capacity adjustment, multiple factors need to be considered, including load change trends, energy efficiency requirements, cost-benefit analysis, and the guarantee of safe system operation. By comprehensively considering these factors, the most suitable capacity adjustment plan can be selected to achieve optimized operation of the power system.

[0040] See also Figure 1 , is a flowchart of a method for adjusting the capacity of a transformer in the first embodiment of the present application, thereby extending the operating life of the on-load capacity-adjusting transformer, the method comprising:

[0041] Step 101, setting different capacity adjustment schemes according to the predicted load conditions of the transformer;

[0042] Step 102: Obtaining a comprehensive merit value of each capacity adjustment scheme according to a fuzzy priority relationship matrix between the operation index of the transformer and the capacity adjustment scheme; the operation index includes the number of switching times, power loss and operation cost;

[0043] Step 103: Obtain an optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive merit value.

[0044] Specifically, samples of the transformer for a certain period of time (including three-phase current and voltage, hot spot temperature, active and reactive power, load, etc.) are obtained, and the neural network CNN-LSTM is used for training to predict the load conditions within a preset time period, such as the load conditions within 24 hours. In general, the training set, validation set, and test set account for 70%, 15%, and 15% of the total sample data; based on the number of switching times, power loss, and operating costs of the transformer, as well as the fuzzy priority relationship matrix between different capacity adjustment schemes, the comprehensive merit value of each capacity adjustment scheme is obtained, and the optimal capacity adjustment is determined.

[0045] The method in this embodiment sets different capacity adjustment schemes according to the predicted load conditions of the transformer; obtains the comprehensive merit value of each capacity adjustment scheme according to the fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme; obtains the optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive merit value. By selecting the optimal capacity adjustment scheme with the largest comprehensive merit value from different capacity adjustment schemes according to the predicted load conditions, the transformer capacity mode can be accurately switched to avoid the transformer being in an overload or underload state for a long time, while reducing losses, extending the operating life of the on-load capacity adjustment transformer, and improving the safety and stability of the power grid.

[0046] In the specific embodiments, see Figure 2 In step 102, the comprehensive merit value of each capacity adjustment scheme is obtained according to the fuzzy priority relationship matrix between the operation index of the transformer and the capacity adjustment scheme, including:

[0047] Step 201, using the analytic hierarchy process to determine the goodness value of the operating index;

[0048] Step 202: Determine the weight of the operating indicator according to the goodness value of the operating indicator and the number of the operating indicators;

[0049] Step 203: Obtain a comprehensive merit value of each capacity adjustment scheme according to the fuzzy priority relationship matrix, the importance of different capacity adjustment schemes and the weight of the operation index.

[0050] Specifically, different capacity adjustment schemes are set according to the predicted load conditions for fuzzy decision-making, including calculating the weight ratio of the number of switching times, power loss, and operating costs according to the hierarchical analysis method, and obtaining the optimality values ​​of the number of capacity adjustment switching times, power loss, and operating costs respectively, and then weighting them to obtain the comprehensive optimality value of each scheme to determine the optimal capacity adjustment scheme.

[0051] In the specific embodiments, see Figure 3 In step 203, the comprehensive merit value of each capacity adjustment scheme is obtained according to the fuzzy priority relationship matrix, the importance of different capacity adjustment schemes and the weight of the operation index, including:

[0052] Step 301: construct a fuzzy consistency matrix according to the fuzzy priority relationship matrix and the importance of different capacity adjustment schemes;

[0053] Step 302: Obtaining the merit value of each capacity adjustment scheme according to the fuzzy consistent matrix, the number of capacity adjustment schemes and the number of operating indicators;

[0054] Step 303: Obtain a comprehensive optimality value of each capacity adjustment scheme according to the optimality value of each capacity adjustment scheme and the weight of the operation index.

[0055] Specifically, the fuzzy priority relationship matrix is ​​obtained using the following formula:

[0056] A=(a ij ) b×b

[0057] Where A is the fuzzy priority relationship matrix, b is the number of capacity adjustment schemes, and a ij For a capacity adjustment plan x under a certain operating index i Comparison of capacity adjustment scheme x j The degree of excellence is expressed as follows:

[0058]

[0059] The fuzzy consistency matrix P is obtained using the following formula:

[0060] P=(r ij ) b×b

[0061] In the formula, r ij =(r i -r j ) / (2b)+0.5, r ij is the relative importance between the i-th capacity adjustment scheme and the j-th capacity adjustment scheme, r i is the relative importance of the i-th capacity adjustment scheme to the overall situation, r j is the relative importance of the jth capacity adjustment scheme to the overall, a ik is the value of the i-th row and k-th column in the fuzzy priority relation matrix.

[0062] In a specific embodiment, the goodness value of the operating index is obtained using the following formula:

[0063]

[0064] Among them, m i is the goodness value of the operating index, n is the number of operating indicators, a ij It is the ratio of the influence of operating index i and operating index j in the criterion layer.

[0065] In a specific embodiment, the weight of the operating index is obtained using the following formula:

[0066]

[0067] Among them, ω i is the weight of operation index i, m i is the goodness value of operating index i, and n is the number of operating indicators.

[0068] In a specific embodiment, the merit value of each capacity adjustment scheme is obtained using the following formula:

[0069]

[0070] Among them, s i is the optimality value of capacity adjustment scheme i, b is the number of capacity adjustment schemes, n is the number of operating indicators, r ik is the value of the i-th row and k-th column in the fuzzy consistent matrix.

[0071] In a specific embodiment, the comprehensive merit value is obtained using the following formula:

[0072]

[0073] Among them, (s i ) 总 is the comprehensive merit value of capacity adjustment scheme i, ω k is the weight of the operating index, s i(k) is the optimality value of capacity adjustment scheme i.

[0074] In the specific embodiments, see Figure 4 , the method further comprises:

[0075] Step 401: Obtain the real-time capacity of the transformer;

[0076] Step 402: Determine the size of the optimal capacity in the optimal capacity adjustment solution and the real-time capacity;

[0077] Step 403: If the real-time capacity is greater than or equal to the optimal capacity, the capacity mode of the transformer is adjusted to a large capacity mode;

[0078] Step 404: If the real-time capacity is smaller than the optimal capacity, the capacity mode of the transformer is adjusted to a small capacity mode.

[0079] Specifically, the capacity adjustment switch is controlled in the form of a step wave signal. When the capacity is greater than the optimal capacity adjustment node, the signal is assigned a value of 1; when the capacity is less than the optimal capacity adjustment node, the signal is assigned a value of 0. A signal receiving unit is connected to the transformer. If the real-time signal is 1, it switches to the large capacity mode; if the real-time signal is 0, it switches to the small capacity model. In addition, the 24-hour load data is fed back and added to the database for a new round of CNN-LSTM prediction to ensure the real-time and accuracy of subsequent prediction results.

[0080] Specifically, samples of the transformer for a certain period of time (including three-phase current and voltage, hot spot temperature, active and reactive power, and load) are obtained, and the neural network CNN-LSTM is used for training to predict the load situation within the next 24 hours. In general, the training set, validation set, and test set account for 70%, 15%, and 15% of the total sample data. Different capacity adjustment schemes are set according to the prediction results for fuzzy decision-making. The weight ratio of the number of switches, power loss, and operating costs is calculated according to the hierarchical analysis method. The optimality values ​​of the number of capacity adjustment switches, power loss, and operating costs are obtained respectively, and then the comprehensive optimality values ​​of each scheme are obtained by weighting to determine the optimal capacity adjustment node. The hierarchical analysis method (AHP) is used to determine the relationship between the various operating indicators to obtain the weight of each indicator.

[0081]

[0082] In the formula, ω i is the weight of the operating index i; a ij represents the influence ratio of operating indicators i and j in the criterion layer; n is the number of operating indicators, m i is the goodness value of each operating indicator, n is the number of operating indicators.

[0083] If there are b solutions in total, the fuzzy priority relation matrix of the b solutions is:

[0084] A=(a ij ) b×b

[0085] In the formula, a ij For the solution x under this indicator i Comparison plan x j The degree of excellence is expressed as follows:

[0086]

[0087] The fuzzy consistency matrix P is as follows:

[0088] P=(r ij ) b×b

[0089] In the formula, r ij=(r i -r j ) / (2b)+0.5, r ij is the relative importance between the i-th solution and the j-th solution, r i is the relative importance of the ith solution to the whole, r j is the relative importance of the jth solution to the whole, a ik is the value of the i-th row and k-th column in the fuzzy priority relation matrix.

[0090] The merits of each solution are:

[0091]

[0092] The comprehensive merits of each scheme are:

[0093]

[0094] In the formula, ω k is the weight of the kth operating indicator; s i(k) is the optimality value of scheme i under the kth operating index, and the scheme with the largest comprehensive optimality value is the optimal scheme.

[0095] The capacity adjustment switch is controlled in the form of a step wave signal. When the capacity is greater than the optimal capacity adjustment node, the signal is assigned a value of 1 (for the switch in the simulink simulation, the wave signal on the line assigns a value of 1 to the switch, then the switch is closed, and the switch is assigned a value of 0, then the switch is open); when the capacity is less than the optimal capacity adjustment node, the signal is assigned a value of 0. A signal receiving unit is connected to the transformer. If the real-time signal is 1, it switches to the large capacity mode; if the real-time signal is 0, it switches to the small capacity model. In addition, the 24h load data is fed back and added to the database for a new round of CNN-LSTM prediction to ensure the real-time and accuracy of subsequent prediction results. Among them, the purpose of the optimal solution is to select the optimal capacity adjustment node, and each solution selects a capacity adjustment node. Finally, the optimal solution, that is, the optimal capacity adjustment node, is calculated and selected.

[0096] In a specific embodiment, a circuit model of a load-capacitance-adjusting transformer is established. The circuit model of the load-capacitance-adjusting transformer is as follows: Figure 5 As shown. The circuit model consists of a transformer model, a power module, a load module, a switch module, and a switch control module. Based on the on-load capacity-adjusting transformer circuit model, a circuit model of the on-load capacity-adjusting transformer under load prediction and fuzzy decision control is constructed. The circuit model of the on-load capacity-adjusting transformer under load prediction and fuzzy decision control is as shown in Figure 6 This embodiment has a simple structure and is easy to operate, and can accurately and quickly switch the on-load capacity adjustment switch. Figure 5There are three current sources AC1-AC3, with a phase difference of 120°. Three single-phase transformers are used to form a three-phase transformer. Switches K1-K15 are capacity adjustment switches, and load1-load6 are loads. When the transformer is in a small capacity state, switches K2, K4, K6, K8, K11, and K14 are in a closed state, and other switches are in an open state; when the transformer is in a large capacity state, switches K2, K4, K6, K8, K11, and K14 are in an open state, and other switches are in a closed state. Figure 5 The model adopts the traditional on-load capacity adjustment strategy to detect the electrical quantity on the transformer side, and controls the switch by sending a "1" or "0" signal through the logic judgment element to determine in real time whether capacity switching is required; Figure 6 The model adopts load forecasting and fuzzy control strategies, and switches the capacity according to the capacity adjustment node selected by fuzzy control. Samples of the transformer for a certain period of time (including three-phase current and voltage, hot spot temperature, active and reactive power, and load) are obtained, and the neural network CNN-LSTM is used for training to predict the load situation within the next 24 hours. The training set, validation set, and test set account for 70%, 15%, and 15% of the total sample data. Different capacity adjustment schemes are set according to the prediction results for fuzzy decision-making. The weight ratio of the number of switches, power loss, and operating costs is calculated according to the hierarchical analysis method. The optimality values ​​of the number of capacity adjustment switches, power loss, and operating costs are obtained respectively, and then the comprehensive optimality values ​​of each scheme are obtained by weighting to determine the optimal capacity adjustment node. The capacity adjustment switch is controlled by a signal. In addition, the 24-hour load data is fed back and added to the database for a new round of CNN-LSTM prediction to ensure the real-time and accuracy of subsequent prediction results.

[0097] After simulation analysis, Figure 7 , Figure 8 As shown in the figure, the circuit model of the on-load capacity-adjusting transformer under load forecasting and fuzzy decision control reduces the number of switches while ensuring low power loss and low operating costs. The frequent switching of the capacity-adjusting switch shortens its service life and affects the stability of the system. Figure 7 and Figure 8 It can be seen that when switching the capacity state, the voltage and current on loads 1, 3, and 5 did not fluctuate greatly, indicating that after the capacity is switched, the voltage and current output on the secondary side of the capacity-adjusting transformer are relatively stable. This shows that the effect of load prediction is very good, and the capacity-adjusting transformer controlled by load prediction can accurately and quickly switch between large and small capacities.

[0098] On the basis of load forecasting, through fuzzy decision making, the number of switch switching, power loss and operating cost are used as the operating indicators of fuzzy decision making, the comprehensive merit values ​​of multiple schemes are calculated, and the optimal capacity adjustment scheme is selected. After being brought into the simulation, the voltage and current waveforms of loads 1, 3 and 5 are obtained, as shown in Figure 8 , Fig. 9 As shown in the figure, under the premise of reasonably adjusting the capacity, the switching times of the transformer capacity adjustment switch are reduced from 8 times to 4 times, avoiding frequent operation of the switch and achieving the goal of fuzzy decision-making.

[0099] By using the method in this embodiment, the transformer capacity mode can be accurately switched to avoid the transformer being in an overload or light load state for a long time. While reducing the loss, the operating life of the on-load capacity-adjusting transformer is extended, and the safety and stability of the power grid are improved. Fuzzy decision-making is used to select the capacity-adjusting node, and the three factors of switch switching times, power loss and operating costs are comprehensively considered. While ensuring low power loss and low operating costs, the switch switching times are reduced, and the service life of the transformer capacity-adjusting switch is avoided from being shortened due to frequent switching.

[0100] In a specific embodiment, the actual load of the transformer is compared with the predicted load. Fig. 9 As shown. Fig.10 It can be seen that the difference between the predicted load and the actual load is smaller.

[0101] In the specific embodiments, see Fig.10 As shown, the second embodiment of the present application provides a structural schematic diagram of a transformer capacity adjustment system, and the system includes: a capacity adjustment scheme setting module 501, a comprehensive excellence value acquisition module 502 and an optimal capacity adjustment scheme determination module 503; the capacity adjustment scheme setting module 501 is used to set different capacity adjustment schemes according to the predicted load conditions of the transformer; the comprehensive excellence value acquisition module 502 is used to obtain the comprehensive excellence value of each capacity adjustment scheme according to the fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme; the operating indicators include the number of switching times, power loss and operating costs; the optimal capacity adjustment scheme determination module 503 is used to obtain the optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive excellence value.

[0102] The system in this embodiment sets different capacity adjustment schemes according to the predicted load conditions of the transformer; obtains the comprehensive merit value of each capacity adjustment scheme according to the fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme; obtains the optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive merit value. By selecting the optimal capacity adjustment scheme with the largest comprehensive merit value from different capacity adjustment schemes according to the predicted load conditions, the transformer capacity mode can be accurately switched to avoid the transformer being in an overload or underload state for a long time, while reducing losses, extending the operating life of the on-load capacity adjustment transformer, and improving the safety and stability of the power grid.

[0103] Specifically, the on-load capacity-adjusting transformer is highly dependent on real-time data, has no prediction of the load conditions in the next time period, cannot provide early warning for subsequent working conditions, and has no limit on the number of times the switch can be opened and closed. In response to the above problems, this embodiment combines load prediction, fuzzy control and on-load capacity-adjusting transformers. Load samples of the transformer for a certain period of time are selected, and a neural network is used to train the samples to predict the load conditions in the next time period. Fuzzy decisions are made using the number of switches, power loss, and operating costs as evaluation indicators for fuzzy decisions. Through this embodiment, the most suitable capacity-adjusting node can be selected, avoiding the problem of no early warning for subsequent working conditions and frequent switch switching.

[0104] In a specific embodiment, the third embodiment of the present application provides a capacity adjustment device for a transformer, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of the first embodiments of the present application. The device in this embodiment sets different capacity adjustment schemes according to the predicted load conditions of the transformer; obtains the comprehensive merit value of each capacity adjustment scheme according to the fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme; and obtains the optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive merit value. By selecting the optimal capacity adjustment scheme with the largest comprehensive merit value from different capacity adjustment schemes according to the predicted load conditions, the transformer capacity mode can be accurately switched to avoid the transformer being in an overload or underload state for a long time, while reducing losses, extending the operating life of the on-load capacity adjustment transformer, and improving the safety and stability of the power grid.

[0105] In a specific embodiment, the fourth embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the processor executes the steps of the method described in any one of the first embodiments of the present application. The storage medium in this embodiment sets different capacity adjustment schemes according to the predicted load conditions of the transformer; obtains the comprehensive merit value of each capacity adjustment scheme according to the fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme; and obtains the optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive merit value. By selecting the optimal capacity adjustment scheme with the largest comprehensive merit value from different capacity adjustment schemes according to the predicted load conditions, the transformer capacity mode can be accurately switched to avoid the transformer being in an overload or underload state for a long time. While reducing losses, the operating life of the on-load capacity adjustment transformer is extended, and the safety and stability of the power grid are improved.

[0106] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0107] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

[0108] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for adjusting the capacity of a transformer, It is characterized in that The method comprises: Set different capacity adjustment plans according to the predicted load conditions of the transformer; Obtaining a comprehensive merit value of each capacity adjustment scheme according to a fuzzy priority relationship matrix between the operating indicators of the transformer and the capacity adjustment scheme; the operating indicators include the number of switching times, power loss and operating cost; An optimal capacity adjustment scheme is obtained from different capacity adjustment schemes according to the comprehensive merit value.

2. The method for adjusting the capacity of a transformer according to claim 1, It is characterized in that The fuzzy priority relationship matrix between the operating index of the transformer and the capacity adjustment scheme is used to obtain each adjustment scheme. The comprehensive merit value of the solution includes: The analytic hierarchy process is used to determine the goodness of the operating indicators; Determine the weight of the operating indicator according to the goodness value of the operating indicator and the number of operating indicators; The comprehensive merit value of each capacity adjustment scheme is obtained according to the fuzzy priority relationship matrix, the importance of different capacity adjustment schemes and the weight of the operation index.

3. The capacity adjustment method of the transformer according to claim 2, It is characterized in that The step of obtaining a comprehensive merit value of each capacity adjustment scheme according to the fuzzy priority relationship matrix, the importance of different capacity adjustment schemes and the weight of the operation index comprises: Constructing a fuzzy consistency matrix according to the fuzzy priority relationship matrix and the importance of different capacity adjustment schemes; Obtaining a merit value of each capacity adjustment scheme according to the fuzzy consistent matrix, the number of capacity adjustment schemes and the number of operating indicators; The comprehensive quality value of each capacity adjustment scheme is obtained according to the quality value of each capacity adjustment scheme and the weight of the operation index.

4. The capacity adjustment method of the transformer according to claim 2, It is characterized in that The goodness value of the operating index is obtained using the following formula: Among them, m i is the goodness value of the operating index, n is the number of operating indicators, a ij It is the ratio of the influence of operating index i and operating index j in the criterion layer.

5. The capacity adjustment method of the transformer according to claim 2, It is characterized in that The weight of the operating indicators is obtained using the following formula: Among them, ω i is the weight of operation index i, m i is the goodness value of operating index i, and n is the number of operating indicators.

6. The capacity adjustment method of the transformer according to claim 3, It is characterized in that The merit value of each capacity adjustment scheme is obtained by using the following formula: Among them, s i is the optimality value of capacity adjustment scheme i, b is the number of capacity adjustment schemes, n is the number of operating indicators, r ik is the value of the i-th row and k-th column in the fuzzy consistent matrix.

7. The capacity adjustment method of a transformer as claimed in claim 1, It is characterized in that The method further comprises: Get the real-time capacity of the transformer; Determine the size of the optimal capacity in the optimal capacity adjustment solution and the real-time capacity; If the real-time capacity is greater than or equal to the optimal capacity, adjusting the capacity mode of the transformer to a large capacity mode; If the real-time capacity is smaller than the optimal capacity, the capacity mode of the transformer is adjusted to a small capacity mode.

8. A capacity adjustment system for a transformer, It is characterized in that The system comprises: a capacity adjustment scheme setting module, a comprehensive excellence value acquisition module and an optimal capacity adjustment scheme determination module; The capacity adjustment scheme setting module is used to set different capacity adjustment schemes according to the predicted load conditions of the transformer; The comprehensive merit value acquisition module is used to obtain the comprehensive merit value of each capacity adjustment scheme according to the fuzzy priority relationship matrix between the operation index of the transformer and the capacity adjustment scheme; the operation index includes the number of switching times, power loss and operation cost; The optimal capacity adjustment scheme determining module is used to obtain the optimal capacity adjustment scheme from different capacity adjustment schemes according to the comprehensive merit value.

9. A transformer capacity adjustment device, comprising a memory and a processor, It is characterized in that The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, It is characterized in that When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.