Adaptive linear neuron-based capacity regulation method and system for distribution transformer

Abstract

This application discloses a method and system for adjusting the capacity of a distribution transformer based on adaptive linear neurons, relating to the field of electrical equipment and power system automation. The method includes: inputting the secondary current to an adaptive linear neuron filter to filter out harmonic components corresponding to harmonic orders in the secondary current, and outputting the fundamental frequency component; the adaptive linear neuron filter constructs a corresponding input vector based on the harmonic order and the fundamental frequency component, the input vector including the sine and cosine components of the harmonic order, and the sine and cosine components of the fundamental frequency component; calculating the amplitude of the fundamental frequency component, comparing the amplitude of the fundamental frequency component with a preset capacity adjustment threshold, generating a switching control signal for the IGBT, and controlling the switching state of the distribution transformer windings according to the switching control signal. This application solves the technical problem that current methods using secondary current as the capacity adjustment criterion result in inaccurate estimation of the transformer's fundamental frequency capacity, leading to the transformer entering a high-capacity state prematurely or a low-capacity state too late.

Description

Technical Field

[0001] This application relates to the field of electrical equipment and power system automation, specifically to a method and system for adjusting the capacity of distribution transformers based on adaptive linear neurons. Background Technology

[0002] In the current power system, electrical energy is transmitted from power plants to users through multiple stages of transformers. Although the efficiency of individual modern transformers is already quite high, their sheer number and total capacity in the power grid lead to a significant cumulative energy consumption effect. Related research shows that the total losses of transformer systems account for approximately 10% of total power generation, and about 70% of the losses in medium- and low-voltage distribution networks originate from distribution transformers, accounting for more than 60% of the total grid losses. If distribution transformer losses could be reduced by 1%, it is estimated that over 10 billion kilowatt-hours of electricity could be saved annually. Therefore, promoting energy efficiency improvements in the distribution sector, even with limited impact, has significant energy-saving potential and economic value. With the continuous development of the economy and society and the increasingly complex electricity consumption structure, the characteristics of power grid loads are becoming more diversified and volatile. The differences in electricity consumption patterns between urban and rural areas are widening, and the peak-to-valley differences in load curves between residential, industrial, and commercial sectors are significant. Furthermore, the widespread integration of uncertain loads such as distributed photovoltaic, wind power, and electric vehicle charging facilities places higher demands on the adaptability of distribution system operation. Traditional distribution transformers, due to their fixed capacity and regulation methods, struggle to balance efficiency and power quality under varying operating conditions, resulting in significant energy waste.

[0003] As an important technological direction, adjustable-capacity distribution transformers have evolved from no-load capacity adjustment, on-load capacity adjustment, and no-load voltage adjustment to the current automatic capacity and voltage adjustment stage. Through intelligent switching between large and small capacity modes, they significantly reduce magnetic flux density and no-load losses under light loads, effectively adapting to seasonal and periodic load fluctuations. However, accurate judgment of capacity switching timing and operational stability control remain key challenges in practical applications. During transformer operation, harmonic components appear in the current due to various factors. Transformer harmonics mainly originate from the nonlinear magnetization characteristics of the core, load current distortion, and uneven winding distribution parameters. Under high magnetic flux density, the transformer core exhibits nonlinear saturation characteristics, generating a large number of odd-order harmonics in the excitation current. The third harmonic content can reach over 30% of the rated current, with the third and fifth harmonics being the dominant components. Simultaneously, the widespread use of nonlinear loads such as rectifier circuits and electric arc furnaces causes transformers to bear a large amount of harmonic current, exacerbating additional winding losses and temperature rise, and reducing service life. Taking a 12-pulse rectifier circuit as an example, its input current contains characteristic harmonics such as the 11th and 13th harmonics, with amplitudes reaching 15%-20% of the fundamental frequency. If the secondary current is directly used as the capacity adjustment criterion, the fundamental frequency capacity of the transformer will be inaccurately estimated, causing the transformer to enter the high-capacity state too early or the low-capacity state too late. Summary of the Invention

[0004] This application addresses the technical problem that current methods using secondary current as the capacity adjustment criterion result in inaccurate estimation of the transformer's fundamental frequency capacity, leading to the transformer entering a high-capacity state prematurely or a low-capacity state too late. It provides a distribution transformer capacity adjustment method and system based on adaptive linear neurons.

[0005] To achieve the above objectives, this application adopts the following technical solution: The first aspect of this application is a distribution transformer capacity adjustment method based on adaptive linear neurons, comprising: Collect the secondary current of each phase of the distribution transformer; The secondary side current is input to an adaptive linear neuron filter to filter out the harmonic components corresponding to the harmonic order in the secondary side current and output the fundamental frequency component; the adaptive linear neuron filter constructs a corresponding input vector based on the harmonic order and the fundamental frequency component, the input vector including the sine and cosine components of the harmonic order, and the sine and cosine components of the fundamental frequency component. The amplitude of the fundamental frequency component is calculated and compared with a preset capacitance threshold to generate a switching control signal for the IGBT. The switching state of the distribution transformer winding is controlled according to the switching control signal.

[0006] In some embodiments, the harmonic components include at least one of the 3rd harmonic, 5th harmonic, 11th harmonic, and 13th harmonic.

[0007] In some implementations, the weight coefficients of the adaptive linear neuron filter are updated using a least mean square algorithm during each sampling period of the secondary current.

[0008] In some implementations, the preset capacity threshold includes a first threshold and a second threshold, wherein the first threshold is less than the second threshold; Controlling the switching state of the distribution transformer windings according to the switch control signal includes: If the amplitude of the fundamental frequency component is less than the first threshold, a first switch control signal is generated. The first switch control signal controls the winding to be taken out of use, and the distribution transformer enters a low-capacitance state. If the amplitude of the fundamental frequency component is greater than the second threshold, a second switch control signal is generated. The second switch control signal controls the winding to be put into use, and the distribution transformer enters a high-capacity state. If the amplitude of the fundamental frequency component is greater than or equal to the first threshold and less than or equal to the second threshold, then the current switch control signal is maintained.

[0009] In some implementations, updating the weight coefficients of the adaptive linear neuron filter using a least mean square algorithm during each sampling period of the secondary current includes: The input vector is weighted and summed with the weight coefficients at the current sampling time to obtain the estimated output of the adaptive linear neuron filter; Calculate the error signal between the estimated output and the secondary current at the current sampling time; The weight coefficients are updated using the least mean square algorithm based on the error signal to obtain the weight coefficients at the next sampling time. Repeat the above steps until the error signal converges, then use the weighted sum of the weight coefficients corresponding to the fundamental frequency component and the input vector as the fundamental frequency component output by the adaptive linear neuron filter.

[0010] In some implementations, the sine and cosine components are constructed using the following formula:

[0011]

[0012] in, For harmonic order or 1, For the power grid frequency, This represents the current sampling time.

[0013] A second aspect of this application provides a distribution transformer capacity adjustment system based on adaptive linear neurons, comprising: The secondary current acquisition module is used to acquire the secondary current of each phase of the distribution transformer. An adaptive harmonic filtering module is used to input the secondary side current to an adaptive linear neuron filter, filter out the harmonic components corresponding to the harmonic order in the secondary side current, and output the fundamental frequency component; the adaptive linear neuron filter constructs a corresponding input vector based on the harmonic order and the fundamental frequency component, the input vector including the sine and cosine components of the harmonic order, and the sine and cosine components of the fundamental frequency component; The capacity adjustment module is used to calculate the amplitude of the fundamental frequency component, compare the amplitude of the fundamental frequency component with a preset capacity adjustment threshold, generate a switching control signal for the IGBT, and control the switching state of the distribution transformer winding according to the switching control signal.

[0014] A third aspect of this application is a computer device comprising: a processor and a computer-readable storage medium; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the aforementioned method for adjusting the capacity of a distribution transformer based on adaptive linear neurons.

[0015] A fourth aspect of this application is a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed by the described adaptive linear neuron-based distribution transformer capacity adjustment method.

[0016] A fifth aspect of this application is a computer program product comprising a computer program that, when executed by a processor, implements the aforementioned method for adjusting the capacity of a distribution transformer based on adaptive linear neurons.

[0017] Compared with the prior art, this application has the following beneficial effects: This application collects the secondary current of each phase of the distribution transformer and inputs it to an adaptive linear neuron filter. This filter constructs an input vector containing sine and cosine components based on the harmonic order and fundamental frequency component, thereby filtering out typical harmonic components and outputting a clean fundamental frequency component. The amplitude of the fundamental frequency component is calculated and compared with a preset capacity adjustment threshold to generate an IGBT switching control signal to control the winding switching. Through the harmonic filtering mechanism of the adaptive linear neuron filter, the capacity adjustment criterion can accurately reflect the fundamental frequency capacity level of the load, fundamentally eliminating the interference of harmonics on capacity estimation, avoiding malfunctions caused by harmonic distortion, and improving the accuracy and reliability of capacity adjustment decisions.

[0018] Furthermore, the harmonic components include at least one of the 3rd, 5th, 11th, and 13th harmonics. The 3rd and 5th harmonics primarily originate from the nonlinear saturation characteristics of the transformer core under high magnetic flux density; the 11th and 13th harmonics mainly originate from nonlinear loads, with amplitudes reaching 15%-20% of the fundamental frequency. By filtering out these typical harmonic components, the adaptive linear neuron filter can accurately suppress the main interference sources in the capacitance adjustment criterion, further improving the purity of the fundamental frequency component extraction and the accuracy of the capacitance adjustment criterion.

[0019] Furthermore, the weight coefficients of the adaptive linear neuron filter are updated using the least mean square algorithm during each sampling period of the secondary current, enabling the filter to track changes in load current in real time. When load fluctuations or harmonic components change, the weight coefficients can be quickly adjusted to adapt to the new operating conditions, ensuring that the filter is always in the best estimation state. This guarantees the continuity and accuracy of fundamental frequency component extraction, allowing the capacity adjustment criterion to dynamically respond to load changes and avoiding criterion lag or misjudgment caused by changes in operating conditions.

[0020] Furthermore, the amplitude range of the fundamental frequency component is determined by the first and second thresholds, thereby generating a switch control signal to control the switching state of the distribution transformer windings. This forms a control logic with hysteresis characteristics, avoiding frequent switching caused by current fluctuations, enabling the transformer to operate stably within the economic operating range, and balancing energy saving and equipment lifespan. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart of the distribution transformer capacity adjustment method based on adaptive linear neurons provided in the embodiments of this application; Figure 2 A structural diagram of a distribution transformer capacity adjustment system based on adaptive linear neurons provided in an embodiment of this application; Figure 3 This is a schematic diagram of the topology of a multi-winding parallel-wound distribution transformer in an embodiment of this application; Figure 4 This is a block diagram of the ADALINE filter structure in an embodiment of this application; Figure 5 This is a diagram showing the secondary current amplitude in an embodiment of this application; Figure 6 This is a schematic diagram of the computer device structure provided in an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] like Figure 1 As shown, this application provides a method for adjusting the capacity of a distribution transformer based on adaptive linear neurons, including: S1 collects the secondary current of each phase of the distribution transformer; As one embodiment, a current sensor is used to measure the load current on the secondary side of each phase of the transformer. , , ).

[0025] S2, the secondary side current is input to an adaptive linear neuron filter to filter out the harmonic components corresponding to the harmonic order in the secondary side current and output the fundamental frequency component; the adaptive linear neuron filter constructs a corresponding input vector based on the harmonic order and the fundamental frequency component, the input vector including the sine and cosine components of the harmonic order, and the sine and cosine components of the fundamental frequency component; As one example, such as Figure 4 As shown, the 3rd, 5th, 11th, and 13th harmonics of the measured current are filtered out using an Adaptive Linear Neuron (ADALINE) filter. For example, the harmonic components in the ADALINE filter are set as follows: Equation (1) in, , , , These are the 3rd, 5th, 11th, and 13th harmonic components of the secondary side current estimated by the ADALINE filter. , , , , , , , Represents the weighting coefficient. This indicates that the value is the value at the current sampling time; , , , , , , , The input vector of the ADALINE filter is expressed as: Equation (2) in: This is the power grid frequency, equal to 50Hz. This indicates the current time and is the output of the timer written into the digital controller. It is updated once every sampling period, which is typically 100 microseconds.

[0026] As one embodiment, the fundamental frequency component of the secondary current is calculated, and the estimated fundamental frequency component in the ADALINE filter is... Set to: Equation (3) in: , Represents the weighting coefficient; , The input vector is represented as: Equation (4) As one example, the weight coefficients in the ADALINE filter are updated according to the Least Mean Square (LMS) algorithm. , , , , , , , , , The specific formula is as follows: Equation (5) in: This indicates that the value is for the next sampling time.

[0027] The input vector is weighted and summed with the weight coefficients at the current sampling time to obtain the estimated output of the adaptive linear neuron filter; Calculate the error signal between the estimated output and the secondary current at the current sampling time; The weight coefficients are updated using the least mean square algorithm based on the error signal to obtain the weight coefficients at the next sampling time. Repeat the above steps until the error signal converges, then use the weighted sum of the weight coefficients corresponding to the fundamental frequency component and the input vector as the fundamental frequency component output by the adaptive linear neuron filter.

[0028] S3, calculate the amplitude of the fundamental frequency component, compare the amplitude of the fundamental frequency component with the preset capacitance threshold, generate the switching control signal of the IGBT (Insulate-Gate Bipolar Transistor), and control the switching state of the distribution transformer winding according to the switching control signal.

[0029] As one embodiment, the amplitude of the fundamental frequency component of the filtered transformer secondary current is calculated using equation (6). : Equation (6) in,: , , ..., These are the first two digits of the AC signal within this cycle. T sTime, 2 T s time,…, nT s The sampled value at time; The sampling period; It is the number of sampling points within one cycle of the AC signal.

[0030] As one embodiment, the amplitude of the fundamental frequency component of the transformer secondary current is... With the rated current amplitude of the secondary side Compare, if If the IGBT switching control signal remains unchanged, proceed to the next step: determine the amplitude of the fundamental frequency component of the transformer secondary current. Is it greater than the rated current amplitude on the secondary side? If the rated secondary current amplitude is 80%, an IGBT switching signal is generated to control the multi-winding to be put into use, and the transformer enters a high-capacitance state; otherwise, an IGBT switching signal is generated to control the multi-winding to be taken out of use, and the transformer enters a low-capacitance state. 30% of the first threshold, the rated current amplitude on the secondary side. 80% is the second threshold.

[0031] This embodiment describes a system comprising: a multi-winding parallel-wound distribution transformer, a current and voltage monitoring unit, a digital signal processor, and an IGBT drive module. The multi-winding parallel-wound distribution transformer has at least two independently switchable windings per phase on the low-voltage side. The current and voltage monitoring unit is responsible for real-time acquisition of the transformer's secondary load current signal. The digital signal processor uses the ADALINE optimization method to calculate the fundamental frequency component of the load current and generates corresponding switching commands based on the comparison between the fundamental frequency current and a preset threshold. The IGBT drive module executes the winding switching operation upon receiving a controller command. Figure 3 As shown, the basic technical parameters of the multi-winding parallel-wound distribution transformer are as follows: rated capacity of 630 kVA, rated operating frequency of 50 Hz, and primary-secondary voltage ratio of 10 kV / 400 V. This system, through a combination of structural design and control strategies, achieves dynamic and smooth adjustment of the transformer's operating capacity, ensuring its long-term efficient and economical operation.

[0032] Simulations are performed based on the method described in this embodiment, such as... Figure 5 As shown, the transformer simulation is set to simulate only phase a, with the other two phases similarly. At t = 0.1 s, the transformer load is increased, and the amplitudes of the secondary current before and after filtering are shown in the figure. It can be seen that the unfiltered current triggers a malfunction.

[0033] In one embodiment of this application, such as Figure 2 As shown, a distribution transformer capacity adjustment system based on adaptive linear neurons is provided, including: The secondary current acquisition module is used to acquire the secondary current of each phase of the distribution transformer. An adaptive harmonic filtering module is used to input the secondary side current to an adaptive linear neuron filter, filter out the harmonic components corresponding to the harmonic order in the secondary side current, and output the fundamental frequency component; the adaptive linear neuron filter constructs a corresponding input vector based on the harmonic order and the fundamental frequency component, the input vector including the sine and cosine components of the harmonic order, and the sine and cosine components of the fundamental frequency component; The capacity adjustment module is used to calculate the amplitude of the fundamental frequency component, compare the amplitude of the fundamental frequency component with a preset capacity adjustment threshold, generate a switching control signal for the IGBT, and control the switching state of the distribution transformer winding according to the switching control signal.

[0034] Specific limitations regarding the distribution transformer capacity adjustment system based on adaptive linear neurons can be found in the limitations of the distribution transformer capacity adjustment method based on adaptive linear neurons mentioned above. The corresponding technical effects are equivalent and will not be repeated here. Each module in the aforementioned distribution transformer capacity adjustment system based on adaptive linear neurons can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0035] Figure 6 An internal structural diagram of a computer device is shown in one embodiment. This computer device may specifically be a terminal or a server. Figure 6 As shown, the computer device includes a processor, memory, network interface, display, camera, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a power distribution transformer capacity adjustment method based on adaptive linear neurons. The display screen can be an LCD screen or an e-ink screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse.

[0036] As will be understood by those skilled in the art, computer equipment Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computing device may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.

[0037] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0038] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0039] In summary, the distribution transformer capacity adjustment method, system, computer equipment, and storage medium based on adaptive linear neurons provided in this application address the 3rd and 5th harmonics generated by transformer core saturation and the 11th and 13th characteristic harmonics generated by nonlinear loads. By employing an ADALINE adaptive filter to process the secondary load current in real time, it can accurately extract the fundamental component and dynamically filter out specific harmonics, effectively eliminating the interference of harmonics on the capacity adjustment criteria and solving the problem of insufficient filtering accuracy in traditional methods. The pure fundamental frequency current amplitude obtained after ADALINE filtering is used as the core parameter of the capacity adjustment criteria, replacing the traditional direct use of current amplitudes containing harmonic distortion. By accurately comparing the fundamental amplitude with a preset threshold, the load condition can be more realistically reflected, significantly improving the accuracy and reliability of capacity adjustment decisions and avoiding misjudgments caused by harmonics. Combining the above optimized criteria with the IGBT control of multi-winding parallel-wound distribution transformers allows for precise control of the IGBT switching state based on the fundamental amplitude judgment result. This technology features clear control logic and fast response speed, which not only improves the accuracy of capacity adjustment but also reduces device losses caused by frequent malfunctions, and has the outstanding advantage of being easy to implement in engineering.

[0040] The various embodiments in this specification are described in a progressive manner. For directly identical or similar parts of the embodiments, refer to each other. Each embodiment focuses on its differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0041] The above-described embodiments are merely preferred embodiments of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various improvements and substitutions without departing from the principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present invention. Therefore, the scope of protection of this invention should be determined by the scope of the claims.

Claims

1. A method for adjusting the capacity of a distribution transformer based on adaptive linear neurons, characterized in that, include: Collect the secondary current of each phase of the distribution transformer; The secondary side current is input to an adaptive linear neuron filter to filter out the harmonic components corresponding to the harmonic order in the secondary side current and output the fundamental frequency component. The adaptive linear neuron filter constructs a corresponding input vector based on the harmonic order and the fundamental frequency component. The input vector includes the sine and cosine components of the harmonic order, as well as the sine and cosine components of the fundamental frequency component. The amplitude of the fundamental frequency component is calculated and compared with a preset capacitance threshold to generate a switching control signal for the IGBT. The switching state of the distribution transformer winding is controlled according to the switching control signal.

2. The distribution transformer capacity adjustment method based on adaptive linear neurons according to claim 1, characterized in that, The harmonic components include at least one of the 3rd, 5th, 11th, and 13th harmonics.

3. The distribution transformer capacity adjustment method based on adaptive linear neurons according to claim 1, characterized in that, The weight coefficients of the adaptive linear neuron filter are updated using the least mean square algorithm during each sampling period of the secondary current.

4. The distribution transformer capacity adjustment method based on adaptive linear neurons according to claim 1, characterized in that, The preset capacity adjustment threshold includes a first threshold and a second threshold, wherein the first threshold is less than the second threshold; Controlling the switching state of the distribution transformer windings according to the switch control signal includes: If the amplitude of the fundamental frequency component is less than the first threshold, a first switch control signal is generated. The first switch control signal controls the winding to be taken out of use, and the distribution transformer enters a low-capacity state. If the amplitude of the fundamental frequency component is greater than the second threshold, a second switch control signal is generated. The second switch control signal controls the winding to be put into use, and the distribution transformer enters a high-capacity state. If the amplitude of the fundamental frequency component is greater than or equal to the first threshold and less than or equal to the second threshold, then the current switch control signal is maintained.

5. The distribution transformer capacity adjustment method based on adaptive linear neurons according to claim 3, characterized in that, The weight coefficients of the adaptive linear neuron filter are updated using the least mean square algorithm during each sampling period of the secondary current, including: The input vector is weighted and summed with the weight coefficients at the current sampling time to obtain the estimated output of the adaptive linear neuron filter; Calculate the error signal between the estimated output and the secondary current at the current sampling time; The weight coefficients are updated using the least mean square algorithm based on the error signal to obtain the weight coefficients at the next sampling time. Repeat the above steps until the error signal converges, then use the weighted sum of the weight coefficients corresponding to the fundamental frequency component and the input vector as the fundamental frequency component output by the adaptive linear neuron filter.

6. The distribution transformer capacity adjustment method based on adaptive linear neurons according to claim 1, characterized in that, The sine and cosine components are constructed using the following formula: in, For harmonic order or 1, For the power grid frequency, This represents the current sampling time.

7. A distribution transformer capacity adjustment system based on adaptive linear neurons, characterized in that, include: The secondary current acquisition module is used to acquire the secondary current of each phase of the distribution transformer. An adaptive harmonic filtering module is used to input the secondary side current to an adaptive linear neuron filter, filter out the harmonic components corresponding to the harmonic order in the secondary side current, and output the fundamental frequency component. The adaptive linear neuron filter constructs a corresponding input vector based on the harmonic order and the fundamental frequency component. The input vector includes the sine and cosine components of the harmonic order, as well as the sine and cosine components of the fundamental frequency component. The capacity adjustment module is used to calculate the amplitude of the fundamental frequency component, compare the amplitude of the fundamental frequency component with a preset capacity adjustment threshold, generate a switching control signal for the IGBT, and control the switching state of the distribution transformer winding according to the switching control signal.

8. A computer device, characterized in that, include: Processor and computer-readable storage media; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the distribution transformer capacity adjustment method based on adaptive linear neurons as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed as described in any one of claims 1 to 6, for adjusting the capacity of a distribution transformer based on adaptive linear neurons.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the distribution transformer capacity adjustment method based on adaptive linear neurons as described in any one of claims 1 to 6.

Images