Intelligent monitoring and regulation and control system for power transformer

Abstract

The invention discloses an intelligent monitoring and regulation system for a power transformer, and relates to the technical field of intelligent monitoring and regulation of power transformers. Comprising an initial automatic regulation module, a data acquisition and transmission module, a data preprocessing and feature extraction module, a feature analysis and prediction module, a load classification module, a conventional load regulation and control module and a high-frequency load adaptive regulation and control module. Load data are collected in real time through the Internet of Things, the load change type is predicted through machine learning, and for a conventional load, the initial frequency is kept to reduce abrasion; for a high-frequency load, the frequency of the tap switch is adaptively increased, rapid response of the transformer is ensured, and equipment faults caused by unstable voltage are avoided, so that efficient operation of the transformer is ensured in different load scenes, the overvoltage or undervoltage risk is reduced, reliable power supply is provided for industrial equipment and a medical system, and the stability and safety of a power grid are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring and control of power transformers, and in particular to an intelligent monitoring and control system for power transformers. Background Art

[0002] Intelligent monitoring and control of power transformers refers to real-time monitoring and data collection of key operating parameters of transformers (such as temperature, current, voltage, oil level, humidity, etc.) through sensors, Internet of Things technology and intelligent algorithms, and the use of big data analysis and machine learning models to process and predict the collected data to identify potential abnormal trends or failure risks. At the same time, the system can automatically adjust the operating parameters of the transformer according to load changes and operating status, such as through intelligent control of cooling systems, tap changers (OLTC) or load distribution strategies, to ensure that the transformer operates in an efficient and safe state, extend equipment life and reduce maintenance costs. This process not only improves the reliability of the power system, but also achieves precise control in an unattended state.

[0003] When the power transformer is intelligently monitored and regulated, the automatic adjustment of the tap changer is to control the tap position of the transformer winding under dynamic conditions such as load changes and grid voltage fluctuations to achieve accurate and stable secondary output voltage, ensuring safe and efficient operation of the grid and power-consuming equipment. This adjustment process can be carried out without power outages and is an important technical means to achieve grid voltage regulation.

[0004] The prior art has the following deficiencies: The automatic adjustment frequency of the tap changer in the prior art is usually fixed and cannot be adaptively adjusted according to the dynamic changes in the load of the power transformer. This is because the traditional system mainly relies on the preset voltage threshold and time interval to determine whether to switch, in order to avoid mechanical wear and equipment failure caused by frequent switching. When the automatic adjustment frequency of the tap changer cannot adapt to the high-frequency dynamic changes in the load of the power transformer, the secondary output voltage will fluctuate frequently and cannot be adjusted in time, causing the power supply equipment to operate in a non-rated voltage range for a long time. Overvoltage will accelerate the aging or burning of insulation materials of sensitive equipment such as motors and capacitors, increase the risk of short circuits and fires; while undervoltage will cause key equipment (such as industrial automation systems, medical equipment) to operate unstably or even suddenly shut down, directly affecting the production process and medical rescue, and seriously threatening life safety and economic operations.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent monitoring and control system for power transformers, which collects load data in real time through Internet of Things technology, and uses machine learning models to analyze and predict the type of dynamic changes in loads. For conventional dynamically changing loads, the initial adjustment frequency is maintained to reduce mechanical wear and maintenance costs; for high-frequency dynamically changing loads, the tap switch frequency is adaptively increased to ensure that the transformer responds quickly to fluctuations and avoids voltage instability causing equipment failures, thereby ensuring efficient operation of the transformer under different load scenarios, reducing the risk of overvoltage or undervoltage, providing reliable power supply support for key industrial equipment and medical systems, and improving the safety and stability of the power grid to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: an intelligent monitoring and control system for power transformers, comprising an initial automatic adjustment module, a data acquisition and transmission module, a data preprocessing and feature extraction module, a feature analysis and prediction module, a load classification module, a conventional load control module and a high-frequency load adaptive control module; Initial automatic adjustment module: In the initial stage, the tap changer is set to the initial automatic adjustment frequency to control the tap position of the transformer winding to ensure that the secondary output voltage is stable within a predetermined range; The data collection and transmission module collects the load data of the power transformer in real time during operation and transmits the collected data to the central monitoring system through the Internet of Things technology; The data preprocessing and feature extraction module preprocesses the collected load change information and extracts key features that reflect the dynamic changes of the load of the power transformer; The feature analysis and prediction module analyzes the extracted features in the monitoring window and inputs the analyzed data into a pre-trained machine learning model. The machine learning model uses the input feature data to predict the future dynamic changes of the power transformer load. The load classification module, based on the prediction results of the machine learning model, divides the load changes of the power transformer within the monitoring window into two categories: high-frequency dynamic change type and conventional dynamic change type; A conventional load control module, for load changes classified as conventional dynamic changes, continues to maintain the initial automatic adjustment of the frequency control transformer winding tap position; The high-frequency load adaptive control module adjusts the actual automatic adjustment frequency of the tap changer according to the characteristics of the current load change for load changes classified as high-frequency dynamic changes. Specifically, on the basis of the initial adjustment frequency, the adjustment frequency of the tap changer is increased so that the adjusted actual automatic adjustment frequency can respond more quickly to the high-frequency dynamic changes of the load.

[0008] Preferably, the initial automatic frequency adjustment is based on historical grid load data and control strategies, and is applicable to conventional load change scenarios.

[0009] Preferably, key features reflecting the dynamic changes in the load of the power transformer are extracted, wherein the extracted key features include the pulsation of the reactive power demand in the monitoring window and the offset degree and offset frequency of the load frequency in the monitoring window. After acquisition, the pulsation of the reactive power demand in the monitoring window and the offset degree and offset frequency of the load frequency in the monitoring window are analyzed to generate a reactive demand pulsation index and a load frequency offset index respectively. The reactive demand pulsation index is used to quantify the pulsation frequency and amplitude changes of the reactive power demand in the monitoring window, reflecting the fluctuation degree and instability of the reactive demand in the power grid. The load frequency offset index is used to quantify the offset degree and offset frequency of the load frequency in the monitoring window, reflecting the dynamic deviation between the system load and the power grid frequency.

[0010] Preferably, after obtaining the reactive power demand pulsation index and the load frequency offset index generated by analyzing the key features, the reactive power demand pulsation index and the load frequency offset index are input into a pre-trained machine learning model to generate a dynamic change coefficient, and the future dynamic load changes of the power transformer are predicted through the dynamic change coefficient.

[0011] Preferably, the dynamic change coefficient generated when predicting the future dynamic change of the load of the power transformer through the machine learning model is compared and analyzed with the preset dynamic change coefficient reference threshold, and the load change of the power transformer in the monitoring window is divided. The specific division steps are as follows: If the dynamic change coefficient is greater than the dynamic change coefficient reference threshold, the load change of the power transformer under the monitoring window is classified as a high-frequency dynamic change type; If the dynamic change coefficient is less than or equal to the dynamic change coefficient reference threshold, the load change of the power transformer under the monitoring window is classified as a conventional dynamic change type.

[0012] Preferably, the specific steps of generating a reactive power demand pulsation index after analyzing the pulsation of reactive power demand within the monitoring window are as follows: Real-time acquisition of reactive power demand within the monitoring window Time series data, represents the reactive power demand at time t; Preprocess the reactive power data and convert the preprocessed reactive power time series It will serve as the basic input for subsequent calculations; Based on the extracted reactive power demand , construct the reactive power instantaneous pulsation deviation function, which is used to quantify the deviation between the instantaneous pulsation state and the reference state at time t. The expression of the reactive power instantaneous pulsation deviation function is: , where is the reference reactive power level based on historical data, To adjust the coefficient, control the amplitude change of the reference power, is the pulsation frequency of reactive power demand, reflecting the speed of load fluctuation. is the phase angle, indicating the initial phase of the reactive power fluctuation, is the instantaneous pulsation deviation of reactive power at time t; The changing trend of the instantaneous pulsation deviation function is combined with the pulsation frequency to generate the reactive power demand pulsation index, which is used to quantitatively describe the comprehensive influence of the pulsation frequency and amplitude of reactive power. The generation expression of the reactive power demand pulsation index is: , In the formula, represents the reactive power demand pulsation index, and Respectively represent the start and end time of the monitoring window, represents the instantaneous pulsation frequency of reactive power demand at time t, is the attenuation coefficient, which suppresses the influence of small pulsation amplitude on the final result.

[0013] Preferably, the specific steps of generating the load frequency deviation index after analyzing the deviation degree and deviation frequency of the load frequency in the monitoring window are as follows: In the set monitoring window, the actual load frequency data of the power transformer and the reference frequency data of the power grid are collected. By comparing the difference between the actual load frequency and the reference frequency, the load frequency offset at each time point is calculated. The calculation expression of the load frequency offset is: , where is the actual load frequency at time t, is the base frequency of the power grid, is the load frequency offset at time t, reflecting the difference between the actual load and the reference frequency; In each monitoring window, the offset amplitude and offset frequency of the load frequency are calculated to evaluate the severity of the load fluctuation. The offset amplitude refers to the maximum offset of the load frequency in the monitoring window. The calculation expression is: , where is the load frequency deviation amplitude, indicating the maximum absolute value of the frequency deviation within the monitoring window. Indicates the maximum value of all load frequency offsets within the monitoring window; the offset frequency is used to measure the fluctuation frequency of the load frequency, that is, the number of rapid fluctuations of the load frequency within the monitoring window. Each positive or negative change of the frequency offset is defined as a fluctuation. The offset frequency calculation formula is: , In the formula, is the offset frequency of the load frequency, indicating the frequency of load frequency fluctuations within the monitoring window. T is the total time of the monitoring window, N is the number of sampling points in the monitoring window, is the Heaviside step function, which is used to determine whether the load frequency fluctuates. and represents two consecutive moments, i Represents a time index; The load frequency offset index is generated according to the calculated load frequency offset amplitude and offset frequency, which comprehensively reflects the offset degree and fluctuation frequency of the load frequency in the monitoring window. The generation expression of the load frequency offset index is: , where is the load frequency deviation index, which quantifies the degree of load frequency deviation and frequency change. and are weight coefficients, which are used to adjust the influence of the offset amplitude and offset frequency on the load frequency offset index. and is an exponential coefficient used to amplify the nonlinear effects of the offset amplitude and offset frequency.

[0014] Preferably, for a load change situation classified as a high-frequency dynamic change type, the actual automatic adjustment frequency of the tap changer is adjusted according to the characteristics of the current load change. The specific steps are as follows: In order to ensure accurate regulation, the initial regulation capacity coefficient is introduced to describe the maximum dynamic change level that can be controlled by the initial regulation frequency. The calculation expression of the initial regulation capacity coefficient is: , In the formula, is the initial adjustment frequency, reflecting the regulation capability under normal circumstances. is the initial regulation capacity coefficient, which describes the load coping capacity of the initial regulation frequency. is the fluctuation of the reference threshold value of the dynamic change coefficient, which is used to describe the deviation degree of the system load. , where Indicates the maximum dynamic change coefficient within the monitoring window, indicating the peak fluctuation of the load during the monitoring window. is the reference threshold of the dynamic change coefficient; According to the deviation between the dynamic change coefficient and the reference threshold of the dynamic change coefficient, the adjustment frequency boost coefficient is calculated, and the actual automatic adjustment frequency is calculated by the adjustment frequency boost coefficient. The calculation expression of the actual automatic adjustment frequency is: , where is the actual automatic adjustment frequency after adjustment, To adjust the frequency boost coefficient, determine the frequency increase range, adjust the frequency boost coefficient The calculation expression is: , In the formula, is the dynamic change coefficient calculated within the monitoring window, It is the sensitivity coefficient, which is used to control the degree of frequency increase to avoid equipment wear caused by excessive frequency increase.

[0015] Preferably, according to the calculated actual automatic adjustment frequency, the automatic adjustment frequency of the tap changer is adjusted in real time, and at the same time, a frequency feedback coefficient is introduced to monitor the frequency effect after adjustment in actual operation, and dynamically optimize it. The calculation expression of the frequency feedback coefficient is: , In the formula, is the frequency feedback coefficient, which is used to evaluate the regulation effect of the new frequency. is the actual automatic adjustment frequency at time t, is the dynamic change coefficient at time t; The calculated frequency feedback factor Reference threshold range with frequency feedback coefficient Compare and analyze the frequency effect after adjustment. If it meets the requirements , it indicates that the actual automatic adjustment frequency after adjustment is within a reasonable range. If it does not meet , it indicates that the actual automatic adjustment frequency after adjustment does not meet the demand, and the actual automatic adjustment frequency should be further optimized to make it within a reasonable range.

[0016] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention utilizes Internet of Things technology to collect load data in real time, and analyzes and predicts key features through machine learning models to accurately distinguish the dynamic change types of loads. For conventional dynamically changing loads, the initial adjustment frequency is maintained to avoid unnecessary frequent switching, thereby reducing mechanical wear and maintenance costs; and for high-frequency dynamically changing loads, the adjustment frequency of the tap changer is adaptively increased based on the prediction to ensure that the transformer responds quickly to load fluctuations in a short time, avoiding equipment damage and operational failures caused by unstable voltage. This not only ensures the efficient operation of power transformers in different load scenarios, but also reduces the safety risks caused by overvoltage or undervoltage, providing more reliable power supply guarantees for highly sensitive scenarios such as key industrial equipment and medical systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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 will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 The present invention is a module schematic diagram of an intelligent monitoring and control system for power transformers. DETAILED DESCRIPTION

[0019] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0020] The present invention provides Figure 1 An intelligent monitoring and control system for a power transformer is shown, comprising an initial automatic adjustment module, a data acquisition and transmission module, a data preprocessing and feature extraction module, a feature analysis and prediction module, a load classification module, a conventional load control module, and a high-frequency load adaptive control module; Initial automatic adjustment module: In the initial stage, the tap changer is set to the initial automatic adjustment frequency to control the tap position of the transformer winding to ensure that the secondary output voltage is stable within a predetermined range; This initial automatic frequency adjustment is based on the historical load data and control strategy of the power grid and is suitable for normal load change scenarios. By maintaining voltage stability, the power grid and power-consuming equipment can be ensured to operate safely and efficiently, avoiding damage to equipment caused by overvoltage and undervoltage.

[0021] The data collection and transmission module collects the load data of the power transformer in real time during operation and transmits the collected data to the central monitoring system through the Internet of Things technology; During operation, the load data of the power transformer is collected in real time through sensors and Internet of Things technology. These data mainly include the following key indicators (including but not limited to these): voltage (input and output voltage on the primary and secondary sides), current (load current through the transformer), power factor (reflecting the ratio of active power to total power), active power and reactive power (measurement of the energy actually transferred by the transformer and reflecting the balance state of power demand), frequency (change in the operating frequency of the power grid), load rate (indicating the ratio of the actual load of the transformer to its rated capacity), temperature data (including the temperature in the transformer winding and oil tank), oil level (change in the oil level in the transformer tank, used to monitor the operating status of the cooling system), harmonic content (power quality problems caused by power harmonics, mainly reflecting the degree of distortion of current and voltage). In addition, it may also include additional information such as winding insulation resistance, power grid fluctuations, and external ambient temperature. Through the Internet of Things technology, these load data are efficiently transmitted to the central monitoring system, which can analyze, store and process these real-time data, predict the load change trend of the power transformer, and generate early warning and control instructions to ensure the efficient and safe operation of the power system.

[0022] The data preprocessing and feature extraction module preprocesses the collected load change information and extracts key features that reflect the dynamic changes of the load of the power transformer; The feature analysis and prediction module analyzes the extracted features in the monitoring window and inputs the analyzed data into a pre-trained machine learning model. The machine learning model uses the input feature data to predict the future dynamic changes of the power transformer load. The key features reflecting the dynamic changes of the load of the power transformer are extracted, wherein the extracted key features include the pulsation of the reactive power demand in the monitoring window and the offset degree and offset frequency of the load frequency in the monitoring window. After acquisition, the pulsation of the reactive power demand in the monitoring window and the offset degree and offset frequency of the load frequency in the monitoring window are analyzed, and then a reactive demand pulsation index and a load frequency offset index are generated respectively. The reactive demand pulsation index is used to quantify the pulsation frequency and amplitude changes of the reactive power demand in the monitoring window, reflecting the fluctuation degree and instability of the reactive demand in the power grid. The load frequency offset index is used to quantify the offset degree and offset frequency of the load frequency in the monitoring window, reflecting the dynamic deviation between the system load and the power grid frequency.

[0023] After obtaining the reactive power demand pulsation index and load frequency offset index generated by analyzing the key features, the reactive power demand pulsation index and the load frequency offset index are input into a pre-trained machine learning model to generate a dynamic change coefficient, and the future dynamic load changes of the power transformer are predicted through the dynamic change coefficient.

[0024] A pre-trained machine learning model refers to a machine learning algorithm model that has been trained and optimized with a large amount of historical data before being used in practice, so that it can accurately predict the dynamic changes in the load of power transformers. During the training phase, the model uses multi-dimensional data collected during the operation of the power transformer, including multiple features such as load fluctuations, voltage, current, reactive power demand, and frequency offset. Through the training process, the model can identify the potential complex patterns and regularities in the power system, and can extract features that are closely related to the dynamic changes in the load from high-dimensional data. The algorithms commonly used in these models include random forests, support vector machines, neural networks, LSTM (long short-term memory networks), etc. The specific algorithm to be selected depends on the nature of the data and the complexity of the problem to be solved. During the training process, the model will continuously learn and adjust internal parameters to maximize the ability to predict future load changes.

[0025] In practical applications, the role of pre-trained machine learning models is to infer and predict through real-time input feature data, such as the key features of reactive demand pulsation index and load frequency offset index. Because these models have optimized their prediction capabilities through historical data during the training phase, when real-time data is input, the model can predict the load change trend of power transformers in the future based on the existing features. For example, when the reactive demand pulsation index rises rapidly, combined with other input features such as the load frequency offset index, the machine learning model can identify the upcoming high-frequency load fluctuations or sudden load demands in the system. This enables the power control system to adjust the adjustment frequency of the tap changer in advance, maintain system stability, and avoid equipment failures, unstable power supply, and other problems caused by excessive load frequency fluctuations. In general, the pre-trained machine learning model is an intelligent prediction tool based on historical data learning and pattern recognition, which can effectively improve the control accuracy and response speed of power transformers.

[0026] If the reactive power demand fluctuates greatly within the monitoring window, it usually indicates that the load of the power transformer is in a dynamic high-frequency change state. The reason is that reactive power is mainly closely related to the inductive or capacitive loads (such as motors, capacitor banks, etc.) in the power system. The frequent start and stop or rapid changes of these loads will cause large fluctuations in reactive power demand. High-frequency load changes mean that the inductive or capacitive equipment in the system is constantly switching in or out of operation, causing pulsation of reactive power. If this pulsation is frequent and significant in amplitude, it not only reflects the characteristics of rapid fluctuations in the load in a short period of time, but may also cause problems such as voltage instability and power factor deterioration. Timely identification and adjustment of this high-frequency reactive demand fluctuation can help avoid frequent switching of transformer tap switches and instability in grid operation.

[0027] The specific steps of generating the reactive power demand pulsation index after analyzing the pulsation of reactive power demand within the monitoring window are as follows: Real-time acquisition of reactive power demand within the monitoring window Time series data, represents the reactive power demand at time t; The real-time collection of time series data of reactive power demand within the monitoring window usually adopts a combination of smart meters and power monitoring terminals. These devices integrate high-precision sensors, which can collect reactive power, current, voltage and other parameters at the millisecond or even microsecond level, and transmit the data to the monitoring system in real time through communication protocols such as Modbus, IEC61850, DL / T645. In addition, the SCADA system can also be used to uniformly collect and aggregate the status of power equipment and reactive power demand data distributed in different areas to the central control room through the network to achieve remote real-time monitoring. If more sophisticated monitoring is required, power quality analyzers can be deployed, combined with edge computing technology to perform preliminary data processing and storage locally to reduce network latency. This multi-level data collection method can ensure high-precision and low-latency monitoring of reactive power demand, and provide a stable data foundation for real-time analysis and regulation.

[0028] In order to ensure the accuracy and effectiveness of the data, the reactive power data needs to be preprocessed, including noise removal, outlier detection and time series normalization. It will serve as the basic input for subsequent calculations.

[0029] Based on the extracted reactive power demand , construct the reactive power instantaneous pulsation deviation function, which is used to quantify the deviation between the instantaneous pulsation state and the reference state at time t. The expression of the reactive power instantaneous pulsation deviation function is: , where is the reference reactive power level based on historical data, To adjust the coefficient, control the amplitude change of the reference power, is the pulsation frequency of reactive power demand, reflecting the speed of load fluctuation. is the phase angle, indicating the initial phase of the reactive power fluctuation, is the instantaneous pulsation deviation of reactive power at time t; By calculating the instantaneous pulsation deviation of reactive power, the instantaneous fluctuation intensity of reactive power can be captured, reflecting whether the load is in a high-frequency dynamic change state within the monitoring window.

[0030] The changing trend of the instantaneous pulsation deviation function is combined with the pulsation frequency to generate the reactive power demand pulsation index, which is used to quantitatively describe the comprehensive influence of the pulsation frequency and amplitude of reactive power. The generation expression of the reactive power demand pulsation index is: , In the formula, represents the reactive power demand pulsation index, and Respectively represent the start and end time of the monitoring window, represents the instantaneous pulsation frequency of reactive power demand at time t, is the attenuation coefficient, which suppresses the influence of small pulsation amplitude on the final result; By multiplying the pulsation deviation function and the instantaneous pulsation frequency and combining the attenuation coefficient, the excessive impact of small-amplitude pulsations on the index can be avoided. The resulting reactive demand pulsation index can accurately quantify the changes in reactive power frequency and amplitude within the monitoring window, providing an important reference for predicting high-frequency dynamic loads.

[0031] It can be seen from the reactive demand pulsation index that the larger the performance value of the reactive demand pulsation index generated after analyzing the pulsation of reactive power demand within the monitoring window, the higher the frequency of dynamic load changes of the power transformer. This is because the reactive demand pulsation index quantifies the pulsation frequency and amplitude changes of reactive power demand within the monitoring window, reflecting the drastic fluctuations of the load in a short period of time. When the reactive demand pulsation index is high, it means that the reactive power fluctuates frequently and the fluctuation amplitude is large, suggesting that the load of the transformer is frequently switched or started and stopped, which is usually related to high-frequency dynamic load changes. On the contrary, when the performance value of the reactive demand pulsation index is low, it means that the fluctuation of reactive demand is small and the change is stable, reflecting that the load of the transformer is relatively stable.

[0032] If the load frequency has a large degree of deviation and a large frequency of deviation within the monitoring window, it usually indicates that the load of the power transformer is undergoing dynamic high-frequency changes. This is because the frequency deviation reflects that the power balance between the load and the grid in the system is frequently broken, and frequent load switching, startup of high-power equipment, or instantaneous changes in nonlinear loads can cause rapid fluctuations in the system frequency. Frequent deviations in load frequency mean that power demand increases sharply in a short period of time, requiring the transformer to constantly adjust its output to maintain grid stability. This high-frequency dynamic change not only increases the regulation burden of the transformer, but also aggravates the mechanical wear of the equipment and the instability of the power system.

[0033] The specific steps of generating the load frequency deviation index after analyzing the deviation degree and deviation frequency of the load frequency in the monitoring window are as follows: In the set monitoring window, the actual load frequency data of the power transformer and the reference frequency data of the power grid are collected. By comparing the difference between the actual load frequency and the reference frequency, the load frequency offset at each time point is calculated. The calculation expression of the load frequency offset is: , where is the actual load frequency at time t, in Hz, is the base frequency of the power grid, usually 50Hz or 60Hz, is the load frequency offset at time t, reflecting the difference between the actual load and the reference frequency.

[0034] In each monitoring window, the offset amplitude and offset frequency of the load frequency are calculated to evaluate the severity of the load fluctuation. The offset amplitude refers to the maximum offset of the load frequency in the monitoring window. The calculation expression is: , where is the load frequency deviation amplitude, indicating the maximum absolute value of the frequency deviation within the monitoring window. Indicates the maximum value of all load frequency offsets within the monitoring window; the offset frequency is used to measure the fluctuation frequency of the load frequency, that is, the number of rapid fluctuations of the load frequency within the monitoring window. Each positive or negative change of the frequency offset is defined as a fluctuation. The offset frequency calculation formula is: , In the formula, is the offset frequency of the load frequency, indicating the frequency of load frequency fluctuations within the monitoring window. T is the total time of the monitoring window, N is the number of sampling points in the monitoring window, is the Heaviside step function, which is used to determine whether the load frequency fluctuates. and represents two consecutive moments,i Represents a time index; If the load frequency changes positively or negatively between two consecutive moments, then The output is 1 if yes, otherwise the output is 0.

[0035] The load frequency offset index is generated according to the calculated load frequency offset amplitude and offset frequency, which comprehensively reflects the offset degree and fluctuation frequency of the load frequency in the monitoring window. The generation expression of the load frequency offset index is: , where is the load frequency deviation index, which quantifies the degree of load frequency deviation and frequency change. and are weight coefficients, which are used to adjust the influence of the offset amplitude and offset frequency on the load frequency offset index. and is an exponential coefficient used to amplify the nonlinear effects of the offset amplitude and offset frequency.

[0036] It can be seen from the load frequency offset index that the larger the performance value of the load frequency offset index generated after analyzing the offset degree and offset frequency of the load frequency within the monitoring window, the more frequent and drastic the dynamic changes of the load of the power transformer are, and vice versa. The load frequency offset index quantifies the amplitude of the frequency offset and the frequency of fluctuations. When the load frequency offset index is high, it means that the load frequency has shifted significantly and frequently within the monitoring window, which is usually related to the access of nonlinear loads, frequent startup of high-power equipment, or drastic changes in load demand. These high-frequency changes will put greater pressure on the transformer's control system and increase the risk of voltage instability and equipment wear. Conversely, when the load frequency offset index is low, it means that the load frequency changes are small and stable, and the power transformer is in a relatively stable operating state, which helps to extend the life of the equipment and ensure the reliability of the power supply of the power grid.

[0037] The machine learning model is not specifically limited here, and can realize the reactive power demand pulsation index and load frequency deviation index Perform comprehensive analysis to generate dynamic coefficient of change In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; the dynamic change coefficient The resulting calculation formula is: , In the formula, , Reactive power demand pulsation index and load frequency deviation index The preset scaling factor of , Both are greater than 0.

[0038] It can be seen from the dynamic change coefficient that the larger the performance value of the reactive demand pulsation index generated after analyzing the pulsation of the reactive power demand within the monitoring window, the larger the performance value of the load frequency deviation index generated after analyzing the deviation degree and deviation frequency of the load frequency within the monitoring window. That is, the larger the performance value of the dynamic change coefficient generated when predicting the future dynamic changes of the load of the power transformer through the machine learning model, the higher the frequency of the dynamic changes in the load of the power transformer, and vice versa. It indicates that the load of the transformer is relatively stable.

[0039] The load classification module, based on the prediction results of the machine learning model, divides the load changes of the power transformer within the monitoring window into two categories: high-frequency dynamic change type and conventional dynamic change type; The dynamic change coefficient generated when predicting the future dynamic change of the load of the power transformer through the machine learning model is compared and analyzed with the preset reference threshold of the dynamic change coefficient, and the load change of the power transformer in the monitoring window is divided. The specific division steps are as follows: If the dynamic change coefficient is greater than the dynamic change coefficient reference threshold, the load change of the power transformer under the monitoring window is classified as a high-frequency dynamic change type; High-frequency dynamic change type: The load fluctuates frequently and violently in a short period of time, with a large amplitude, which is difficult to effectively control through conventional frequency adjustment.

[0040] If the dynamic change coefficient is less than or equal to the dynamic change coefficient reference threshold, the load change of the power transformer under the monitoring window is classified as a conventional dynamic change type; Conventional dynamic change type: The load changes relatively smoothly, and the fluctuation amplitude and frequency are within the controllable range. It is suitable to use the initially set adjustment frequency for control.

[0041] A conventional load control module, for load changes classified as conventional dynamic changes, continues to maintain the initial automatic adjustment of the frequency control transformer winding tap position; Since the load changes are relatively stable, the initial adjustment frequency is sufficient to maintain the stability of the secondary output voltage. This practice helps to avoid frequent operation of the tap changer, extend its service life, reduce maintenance costs, and ensure the stable operation of the power system to meet the normal power demand of users.

[0042] The high-frequency load adaptive control module adjusts the actual automatic adjustment frequency of the tap changer according to the characteristics of the current load change for load changes classified as high-frequency dynamic changes. Specifically, the adjustment frequency of the tap changer is increased on the basis of the initial adjustment frequency, so that the adjusted actual automatic adjustment frequency responds more quickly to the high-frequency dynamic changes of the load; For load changes classified as high-frequency dynamic changes, adjust the actual automatic adjustment frequency of the tap changer according to the characteristics of the current load changes. The specific steps are as follows: In order to ensure accurate regulation, the initial regulation capacity coefficient is introduced to describe the maximum dynamic change level that can be controlled by the initial regulation frequency. The calculation expression of the initial regulation capacity coefficient is: , In the formula, is the initial adjustment frequency (number of adjustments per second), reflecting the regulation capability under normal circumstances. is the initial regulation capacity coefficient, which describes the load coping capacity of the initial regulation frequency. is the fluctuation of the reference threshold value of the dynamic change coefficient, which is used to describe the deviation degree of the system load. , where Indicates the maximum dynamic change coefficient within the monitoring window, indicating the peak fluctuation of the load during the monitoring window. is the reference threshold of the dynamic change coefficient; This step is used to analyze the effectiveness of the initial frequency adjustment under the current situation and provide a benchmark for the next frequency increase.

[0043] According to the deviation between the dynamic change coefficient and the reference threshold of the dynamic change coefficient, the adjustment frequency boost coefficient is calculated, and the actual automatic adjustment frequency is calculated by the adjustment frequency boost coefficient. The calculation expression of the actual automatic adjustment frequency is: , where is the actual automatic adjustment frequency after adjustment, To adjust the frequency boost coefficient, determine the frequency increase range, adjust the frequency boost coefficient The calculation expression is: , In the formula, is the dynamic change coefficient calculated within the monitoring window, It is the sensitivity coefficient, which is used to control the degree of frequency increase to avoid excessive frequency increase and cause equipment wear; This step combines the current load change with the initial regulation capability by calculating the regulation frequency increase coefficient to ensure that the new frequency increase matches the actual demand.

[0044] According to the calculated actual automatic adjustment frequency, the automatic adjustment frequency of the tap changer is adjusted in real time. At the same time, the frequency feedback coefficient is introduced to monitor the frequency effect after adjustment in actual operation and perform dynamic optimization. The calculation expression of the frequency feedback coefficient is: , In the formula, is the frequency feedback coefficient, which is used to evaluate the regulation effect of the new frequency. is the actual automatic adjustment frequency at time t, is the dynamic change coefficient at time t; The calculated frequency feedback factor Reference threshold range with frequency feedback coefficient Compare and analyze the frequency effect after adjustment. If it meets the requirements , it indicates that the actual automatic adjustment frequency after adjustment is within a reasonable range. This actual automatic adjustment frequency after adjustment can ensure that the frequency regulation of the tap changer is both efficient and will not be excessively worn. If it does not meet , it indicates that the actual automatic adjustment frequency after adjustment does not meet the demand, and the system will further optimize the actual automatic adjustment frequency to make it within a reasonable range.

[0045] By speeding up the operation of the tap changer, timely adjusting the tap position of the transformer winding, stabilizing the secondary output voltage, preventing overvoltage or undervoltage, and ensuring the safe operation of the power grid and power equipment. This adaptive control strategy can effectively solve the problem that traditional fixed frequency regulation cannot meet the needs of high-frequency load changes, and improve the reliability and safety of the power system.

[0046] The present invention utilizes Internet of Things technology to collect load data in real time, and analyzes and predicts key features through machine learning models to accurately distinguish the dynamic change types of loads. For conventional dynamically changing loads, the initial adjustment frequency is maintained to avoid unnecessary frequent switching, thereby reducing mechanical wear and maintenance costs; and for high-frequency dynamically changing loads, the adjustment frequency of the tap changer is adaptively increased based on the prediction to ensure that the transformer responds quickly to load fluctuations in a short time to avoid equipment damage and operational failures caused by unstable voltage. This intelligent and adaptive control strategy not only ensures the efficient operation of power transformers under different load scenarios, but also reduces the safety risks caused by overvoltage or undervoltage, providing more reliable power supply guarantees for highly sensitive scenarios such as key industrial equipment and medical systems.

[0047] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0048] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0049] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An intelligent monitoring and control system for power transformers, characterized in that: It includes an initial automatic adjustment module, a data acquisition and transmission module, a data preprocessing and feature extraction module, a feature analysis and prediction module, a load classification module, a conventional load control module, and a high-frequency load adaptive control module; Initial automatic adjustment module: In the initial stage, the tap changer is set to the initial automatic adjustment frequency to control the tap position of the transformer winding to ensure that the secondary output voltage is stable within a predetermined range; The data collection and transmission module collects the load data of the power transformer in real time during operation and transmits the collected data to the central monitoring system through the Internet of Things technology; The data preprocessing and feature extraction module preprocesses the collected load change information and extracts key features that reflect the dynamic changes of the load of the power transformer; The feature analysis and prediction module analyzes the extracted features in the monitoring window and inputs the analyzed data into a pre-trained machine learning model. The machine learning model uses the input feature data to predict the future dynamic changes of the power transformer load. The load classification module, based on the prediction results of the machine learning model, divides the load changes of the power transformer within the monitoring window into two categories: high-frequency dynamic change type and conventional dynamic change type; A conventional load control module, for load changes classified as conventional dynamic changes, continues to maintain the initial automatic adjustment of the frequency control transformer winding tap position; The high-frequency load adaptive control module adjusts the actual automatic adjustment frequency of the tap changer according to the characteristics of the current load change for load changes classified as high-frequency dynamic changes. Specifically, on the basis of the initial adjustment frequency, the adjustment frequency of the tap changer is increased so that the adjusted actual automatic adjustment frequency can respond more quickly to the high-frequency dynamic changes of the load.

2. The intelligent monitoring and control system for power transformers according to claim 1 is characterized in that: The initial automatic frequency adjustment is based on the historical load data and control strategy of the power grid and is suitable for conventional load change scenarios.

3. The intelligent monitoring and control system for power transformers according to claim 1 is characterized in that: The key features reflecting the dynamic changes of the load of the power transformer are extracted, wherein the extracted key features include the pulsation of the reactive power demand in the monitoring window and the offset degree and offset frequency of the load frequency in the monitoring window. After acquisition, the pulsation of the reactive power demand in the monitoring window and the offset degree and offset frequency of the load frequency in the monitoring window are analyzed, and then a reactive demand pulsation index and a load frequency offset index are generated respectively. The reactive demand pulsation index is used to quantify the pulsation frequency and amplitude changes of the reactive power demand in the monitoring window, reflecting the fluctuation degree and instability of the reactive demand in the power grid. The load frequency offset index is used to quantify the offset degree and offset frequency of the load frequency in the monitoring window, reflecting the dynamic deviation between the system load and the power grid frequency.

4. The intelligent monitoring and control system for power transformers according to claim 3 is characterized in that: After obtaining the reactive power demand pulsation index and load frequency offset index generated by analyzing the key features, the reactive power demand pulsation index and the load frequency offset index are input into a pre-trained machine learning model to generate a dynamic change coefficient, and the future dynamic load changes of the power transformer are predicted through the dynamic change coefficient.

5. The intelligent monitoring and control system for power transformers according to claim 4 is characterized in that: The dynamic change coefficient generated when predicting the future dynamic change of the load of the power transformer through the machine learning model is compared and analyzed with the preset reference threshold of the dynamic change coefficient, and the load change of the power transformer in the monitoring window is divided. The specific division steps are as follows: If the dynamic change coefficient is greater than the dynamic change coefficient reference threshold, the load change of the power transformer under the monitoring window is classified as a high-frequency dynamic change type; If the dynamic change coefficient is less than or equal to the dynamic change coefficient reference threshold, the load change of the power transformer under the monitoring window is classified as a conventional dynamic change type.

6. The intelligent monitoring and control system for power transformers according to claim 3 is characterized in that: The specific steps of generating the reactive power demand pulsation index after analyzing the pulsation of reactive power demand within the monitoring window are as follows: Real-time acquisition of reactive power demand within the monitoring window Time series data, represents the reactive power demand at time t; Preprocess the reactive power data and convert the preprocessed reactive power time series It will serve as the basic input for subsequent calculations; Based on the extracted reactive power demand , construct the reactive power instantaneous pulsation deviation function, which is used to quantify the deviation between the instantaneous pulsation state and the reference state at time t. The expression of the reactive power instantaneous pulsation deviation function is: , where is the reference reactive power level based on historical data, To adjust the coefficient, control the amplitude change of the reference power, is the pulsation frequency of reactive power demand, reflecting the speed of load fluctuation. is the phase angle, indicating the initial phase of the reactive power fluctuation, is the instantaneous pulsation deviation of reactive power at time t; The changing trend of the instantaneous pulsation deviation function is combined with the pulsation frequency to generate the reactive power demand pulsation index, which is used to quantitatively describe the comprehensive influence of the pulsation frequency and amplitude of reactive power. The generation expression of the reactive power demand pulsation index is: , In the formula, represents the reactive power demand pulsation index, and Respectively represent the start and end time of the monitoring window, represents the instantaneous pulsation frequency of reactive power demand at time t, is the attenuation coefficient, which suppresses the influence of small pulsation amplitude on the final result.

7. The intelligent monitoring and control system for power transformers according to claim 5 is characterized in that: The specific steps of generating the load frequency deviation index after analyzing the deviation degree and deviation frequency of the load frequency in the monitoring window are as follows: In the set monitoring window, the actual load frequency data of the power transformer and the reference frequency data of the power grid are collected. By comparing the difference between the actual load frequency and the reference frequency, the load frequency offset at each time point is calculated. The calculation expression of the load frequency offset is: , where is the actual load frequency at time t, is the base frequency of the power grid, is the load frequency offset at time t, reflecting the difference between the actual load and the reference frequency; In each monitoring window, the offset amplitude and offset frequency of the load frequency are calculated to evaluate the severity of the load fluctuation. The offset amplitude refers to the maximum offset of the load frequency in the monitoring window. The calculation expression is: , where is the load frequency deviation amplitude, indicating the maximum absolute value of the frequency deviation within the monitoring window. Indicates the maximum value of all load frequency offsets within the monitoring window; The offset frequency is used to measure the fluctuation frequency of the load frequency, that is, the number of rapid fluctuations of the load frequency within the monitoring window. Each positive or negative change of the frequency offset is defined as a fluctuation. The calculation formula for the offset frequency is: ， In the formula, is the offset frequency of the load frequency, indicating the frequency of load frequency fluctuations within the monitoring window. T is the total time of the monitoring window, N is the number of sampling points in the monitoring window, is the Heaviside step function, which is used to determine whether the load frequency fluctuates. and represents two consecutive moments, i Represents a time index; The load frequency offset index is generated according to the calculated load frequency offset amplitude and offset frequency, which comprehensively reflects the offset degree and fluctuation frequency of the load frequency in the monitoring window. The generation expression of the load frequency offset index is: , where is the load frequency deviation index, which quantifies the degree of load frequency deviation and frequency change. and are weight coefficients, which are used to adjust the influence of the offset amplitude and offset frequency on the load frequency offset index. and is an exponential coefficient used to amplify the nonlinear effects of the offset amplitude and offset frequency.

8. The intelligent monitoring and control system for power transformers according to claim 7 is characterized in that: For load changes classified as high-frequency dynamic changes, adjust the actual automatic adjustment frequency of the tap changer according to the characteristics of the current load changes. The specific steps are as follows: In order to ensure accurate regulation, the initial regulation capacity coefficient is introduced to describe the maximum dynamic change level that can be controlled by the initial regulation frequency. The calculation expression of the initial regulation capacity coefficient is: ， In the formula, is the initial adjustment frequency, reflecting the regulation capability under normal circumstances. is the initial regulation capacity coefficient, which describes the load coping capacity of the initial regulation frequency. is the fluctuation of the reference threshold value of the dynamic change coefficient, which is used to describe the deviation degree of the system load. ， In the formula, Indicates the maximum dynamic change coefficient within the monitoring window, indicating the peak fluctuation of the load during the monitoring window. is the reference threshold of the dynamic change coefficient; According to the deviation between the dynamic change coefficient and the reference threshold of the dynamic change coefficient, the adjustment frequency boost coefficient is calculated, and the actual automatic adjustment frequency is calculated by the adjustment frequency boost coefficient. The calculation expression of the actual automatic adjustment frequency is: , where is the actual automatic adjustment frequency after adjustment, To adjust the frequency boost coefficient, determine the frequency increase range, adjust the frequency boost coefficient The calculation expression is: ， In the formula, is the dynamic change coefficient calculated within the monitoring window, is the sensitivity coefficient, which is used to control the degree of frequency boost.

9. The intelligent monitoring and control system for power transformers according to claim 8, characterized in that: According to the calculated actual automatic adjustment frequency, the automatic adjustment frequency of the tap changer is adjusted in real time. At the same time, the frequency feedback coefficient is introduced to monitor the frequency effect after adjustment in actual operation and perform dynamic optimization. The calculation expression of the frequency feedback coefficient is: ， In the formula, is the frequency feedback coefficient, which is used to evaluate the regulation effect of the new frequency. is the actual automatic adjustment frequency at time t, is the dynamic change coefficient at time t; The calculated frequency feedback factor Reference threshold range with frequency feedback coefficient Compare and analyze the frequency effect after adjustment. If it meets the requirements , it indicates that the actual automatic adjustment frequency after adjustment is within a reasonable range. If it does not meet , it indicates that the actual automatic adjustment frequency after adjustment does not meet the demand, and the actual automatic adjustment frequency should be further optimized to make it within a reasonable range.

Images