Intelligent oil extraction control method and system for transformer

Abstract

The invention relates to the field of transformer oil extraction control, and discloses an intelligent oil extraction control method and system for a transformer, and the method comprises the steps: analyzing an oil extraction operation mode through collected oil extraction related operation data, detecting whether the oil extraction operation mode meets a preset standard condition or not, and carrying out the intelligent oil extraction control of the transformer according to a detection result of the oil extraction operation mode. The oil extraction method is optimized and adjusted, the oil extraction amount is monitored and analyzed in real time, the oil level descending trend during oil extraction is analyzed, the oil extraction amount is controlled to be kept higher than the lowest oil level line, the oil extraction time is planned by establishing an oil extraction time prediction model based on historical oil extraction data, and oil extraction operation is executed according to the planned oil extraction time. According to the method, the oil extraction time after compensation is analyzed and calculated based on the oil extraction environment, the oil extraction time is dynamically optimized and adjusted, the oil extraction time is kept in a standard range, finally, a control analysis result is fed back, and the oil extraction precision and the intelligent level of the transformer are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer oil sampling control, and more particularly to an intelligent transformer oil sampling control method and system. Background Art

[0002] The interior of a transformer is filled with insulating oil, which not only serves as insulation to prevent arc discharge between internal high-voltage components, but also acts as a coolant to help dissipate the heat generated during the operation of the transformer. Over time, the transformer oil ages due to thermal, electrical, chemical, and environmental influences, and its performance deteriorates. To ensure the healthy operation of the transformer, it is necessary to regularly monitor the quality of the insulating oil, including its insulation strength, moisture content, acid value, etc. Traditional transformer oil sampling usually relies on manual operation, which has problems such as safety risks, low efficiency, and environmental pollution. With the development of automation and intelligent technologies, intelligent transformer oil sampling control methods have emerged. This method aims to achieve automated and intelligent control of the transformer oil sampling process through modern sensing technologies, automatic control technologies, communication technologies, etc., to improve the safety and efficiency of the oil sampling operation, reduce human errors, and enhance the intelligent level of transformer maintenance management; As described in the Chinese patent with the publication number CN115728096A, a multi-mode hierarchical automatic oil sampling monitoring method for a transformer, the present invention provides a multi-mode automatic oil sampling monitoring method for a transformer, including: on the side of the transformer housing, an oil sampling system is installed, and the oil sampling port of the transformer is connected to a pneumatic filling device for cooperating with the oil sampling system to take oil; a controller, having a data transmission function, is triggered according to the received instructions or the modes set by itself, or the current detection data, and controls each component in the pneumatic filling device and the oil sampling system to start / stop in sequence; the method of the present invention can achieve unattended monitoring, automatically monitor the transformer to take oil samples regularly, and after taking the samples, the user can go to the site to pick them up, realizing digital intelligent monitoring.

[0003] However, the above process still has the following disadvantages: Firstly, the existing intelligent transformer oil sampling control methods adopt fixed oil sampling methods, lacking dynamic analysis and adjustment of the operation mode, and unable to optimize and adjust the oil sampling method, resulting in low efficiency and accuracy of the oil sampling operation; Secondly, the existing intelligent transformer oil sampling control methods only control the oil sampling volume through simple liquid level switches, with low control accuracy and lacking analysis of the oil level decline trend; Thirdly, the existing intelligent transformer oil sampling control methods may adopt fixed oil sampling time intervals, without fully considering the historical oil sampling rules and the influence of the oil sampling environment on the oil sampling time, resulting in ineffective oil sampling or missed inspections. Summary of the Invention

[0004] To overcome the above-mentioned defects of the prior art, the present invention provides an intelligent oil sampling control method and system for a transformer to solve the problems existing in the above-mentioned background art.

[0005] The present invention provides the following technical solutions: An intelligent oil sampling control method for a transformer, comprising: S1: Used to collect relevant operation data for each oil sampling. When a push rod feedback signal is received, the sensor is triggered to collect the relevant operation data during oil sampling. S2: Analyze the oil sampling operation mode based on the relevant operation data for oil sampling, detect whether the oil sampling operation mode meets the preset standard conditions, and optimize and adjust the oil sampling method according to the detection result of the oil sampling operation mode. S3: Based on the real-time monitoring and analysis of the oil sampling volume, analyze the oil level drop trend during oil sampling, and control the oil sampling volume to be kept above the minimum oil level line. S4: Used to collect historical oil sampling data over a period of time, establish an oil sampling time prediction model based on the historical oil sampling data, plan the oil sampling time according to the oil sampling time prediction model, and perform the oil sampling operation according to the planned oil sampling time. S5: Based on the oil sampling environment, conduct a compensation analysis on the oil sampling time during the oil sampling operation process to obtain the compensated oil sampling time, and dynamically optimize and adjust the oil sampling time according to the compensated oil sampling time to keep the oil sampling time within the standard range. S6: Real-time feedback the control adjustment result and the entire control analysis process to the tester's terminal.

[0006] Preferably, in S1, after receiving the feedback signal of the push rod, the solenoid valve immediately sends control information to the sensor to trigger the sensor to collect the relevant operation data during oil sampling, and record the data collection time. The collected relevant operation data for oil sampling includes the ambient temperature, humidity, oil temperature, oil pressure, oil sampling flow rate, oil sampling volume, oil level, and gas content in the oil during oil sampling. The collected relevant operation data for oil sampling is classified and stored in the database according to the recorded collection time.

[0007] Preferably, in S2, by monitoring and recording the environmental conditions during the oil sampling operation and whether the sealed or semi-sealed state measures are adopted, two samples of the same oil sample are collected respectively in the fully exposed and semi-sealed states. The gas chromatography method is used to quantitatively analyze the contents of hydrogen, carbon dioxide and carbon monoxide in the two samples. Based on the results of the quantitative analysis, the mean value, standard deviation and coefficient of variation of the content of each gas in the two operation modes are calculated respectively using statistical methods. The data of the content of each gas in the oil calculated in the fully exposed and semi-sealed operation modes are subjected to differential comparison analysis, and then the overall difference evaluation value of the content of all gases is comprehensively calculated to detect whether the difference between the oil sampling operation modes meets the preset standard conditions. If it is detected that the difference between the oil sampling operation modes does not meet the preset standard conditions, the tester is prompted to dynamically adjust the oil sampling operation method according to the analysis results of the operation differences.

[0008] Preferably, in S3, based on the optimization result of the oil sampling operation mode, by analyzing the collected oil level data and calculating the oil level drop rate and the oil level drop period, the speed and trend of the oil level drop are identified. Based on the safe operation requirements of the transformer, a minimum oil level line is set. And based on the oil level drop rate, period and operation error, a safety margin is set. Then, the falling state of the oil level line is continuously monitored to always remain at a position not lower than . If the oil level approaches or is lower than , an alarm is immediately triggered and the oil sampling amount is adjusted. When the oil level approaches or is lower than , the oil level deviation is calculated. Based on the calculated oil level deviation, the control output value is calculated using the PID algorithm, and the oil sampling amount is adjusted according to the control output value to ensure that the oil level rises to or above.

[0009] Preferably, in S4, by collecting and storing the historical oil sampling data of the transformer in the past period of time, including the oil sampling time, the oil sampling amount, the oil level change and the environmental conditions, a machine learning algorithm is selected to establish an oil sampling time prediction model. The historical data is used to train the model, and the historical oil sampling data is used to train the prediction model, and the model parameters are adjusted to minimize the prediction error. Then, the currently collected oil sampling data is input into the trained prediction model, and the oil sampling prediction time is output. According to the oil sampling prediction time, the best oil sampling time point is planned to perform the oil sampling operation.

[0010] Preferably, based on the analysis result of the oil extraction time planning, the S5 analyzes the correlation between the oil extraction environmental condition parameters and the oil extraction time by using statistical methods. Based on the correlation analysis result, a mathematical model of the environmental factors and the oil extraction time is established. The current environmental conditions are input into the data model to calculate the compensated oil extraction time, and then the compensated oil extraction time is compared with the current actual oil extraction time to dynamically adjust the oil extraction time and control the oil extraction time within the standard range.

[0011] Preferably, the S6 feeds back the control adjustment results of the oil extraction operation mode, the oil extraction volume control adjustment results, and the oil extraction time control adjustment results to the tester's terminal in real time, automatically generates a regulation monitoring report based on the entire control analysis process and sends it to the terminal device of the tester, and allows the tester to perform query and confirmation operations on the terminal device.

[0012] To achieve the above object, the present invention provides the following technical solution: An intelligent oil extraction control system for a transformer, implementing the above-mentioned intelligent oil extraction control method for a transformer, includes: Data collection module: used to collect relevant operation data for each oil extraction. When receiving the push rod feedback signal, trigger the sensor to collect the relevant operation data during oil extraction. Oil extraction operation control module: Analyze the oil extraction operation mode based on the relevant operation data of oil extraction, detect whether the oil extraction operation mode meets the preset standard conditions, and optimize and adjust the oil extraction method according to the detection result of the oil extraction operation mode. Oil extraction volume control module: Based on the real-time monitoring and analysis of the oil extraction volume, analyze the oil level drop trend during oil extraction, and control the oil extraction volume to be kept above the minimum oil level line. Oil extraction time planning module: used to collect historical oil extraction data within a period of time, establish an oil extraction time prediction model based on the historical oil extraction data, plan the oil extraction time according to the oil extraction time prediction model, and perform the oil extraction operation according to the planned oil extraction time. Oil extraction time control module: Based on the oil extraction environment, perform compensation analysis on the oil extraction time during the oil extraction operation process to obtain the compensated oil extraction time, and dynamically optimize and adjust the oil extraction time according to the compensated oil extraction time to keep the oil extraction time within the standard range. Control result feedback module: Feed back the control adjustment results and the entire control analysis process to the tester's terminal in real time.

[0013] The technical effects and advantages of the present invention: Based on the analysis of the relevant operation data of oil extraction, detect whether the operation mode meets the preset standard conditions, and optimize and adjust the oil extraction method according to the detection result, which can adapt to the oil extraction requirements in different situations and further improve the accuracy and efficiency of the oil extraction operation.

[0014] Based on real-time monitoring and analysis of the oil extraction volume, analyzing the oil level decline trend, it can predict in advance and control the oil extraction volume to be maintained above the minimum oil level line, avoiding the situation that the oil level is too low due to excessive oil extraction and affecting the normal operation of the transformer, and improving the safety and stability of the transformer operation.

[0015] Based on the historical oil extraction data within a period of time, establish an oil extraction time prediction model, and plan the oil extraction time according to the model, which can arrange the oil extraction operation more scientifically, avoid unnecessary frequent oil extraction or long-term non-oil extraction situations, and conduct compensation analysis on the oil extraction time according to the oil extraction environment to obtain the compensated oil extraction time, and dynamically optimize and adjust the oil extraction time according to the compensation result to ensure that the oil extraction time always remains within the standard range, further improving the accuracy and reliability of the oil extraction operation. Description of the Drawings

[0016] Figure 1 It is a method step diagram of the present invention.

[0017] Figure 2 It is a system structure block diagram of the present invention.

[0018] Figure 3 It is a transformer oil extraction control flow chart of this embodiment. Detailed Embodiment

[0019] Next, the technical solutions in the present invention will be clearly and completely described in conjunction with the drawings in the present invention. In addition, the forms of each structure described in the following embodiments are merely examples, and a transformer intelligent oil extraction control method and system involved in the present invention are not limited to the structures described in the following embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0020] As Figure 1 shown, this embodiment provides a transformer intelligent oil extraction control method, including: S1: Used to collect relevant operation data for each oil extraction. When the push rod feedback signal is received, trigger the sensor to collect the oil extraction-related operation data during oil extraction.

[0021] In this embodiment, after receiving the feedback signal of the push rod, the S1 immediately sends control information to the sensor through the solenoid valve to trigger the sensor to collect the oil extraction-related operation data during oil extraction, and record the data collection time. The collected oil extraction-related operation data includes the ambient temperature, humidity, oil temperature, oil pressure, oil extraction flow rate, oil extraction volume, oil level, and gas content in the oil during oil extraction. The collected oil extraction-related operation data is classified and stored in the database according to the recorded collection time.

[0022] Specifically, by installing sensors on the oil extraction equipment, it is used to monitor environmental conditions (temperature, humidity, air pressure) and operating status (whether it is sealed or semi-sealed) in real time. Before starting oil extraction, check whether all sensors (temperature sensor, humidity sensor, pressure sensor, oil level sensor, flow sensor, and gas sensor), solenoid valve, push rod, data acquisition unit, and control unit are installed in place and correctly wired, and configure the control system software to ensure that it can receive the signal of the solenoid valve and trigger the sensor data acquisition; when the operator starts the push rod and performs the oil extraction operation, the built-in sensor or limit switch generates an electrical signal as feedback and transmits it to the solenoid valve. After receiving the feedback signal of the push rod, the solenoid valve is activated and sends a control signal to the control system. After receiving the signal of the solenoid valve, the control system immediately sends a data acquisition start signal to all relevant sensors to collect environmental parameters, oil sample parameters, and gas content in the oil during oil extraction. The environmental parameters during oil extraction include the environmental temperature recorded by the temperature sensor and the environmental humidity recorded by the humidity sensor. The oil sample parameters include the oil sample temperature monitored and recorded by the oil temperature sensor, the oil pressure recorded by the pressure sensor, and the oil extraction flow measured and recorded by the flow sensor. The gas content in the oil includes the gas content such as hydrogen, carbon dioxide, and carbon monoxide in the oil monitored in real time by the gas analysis sensor. At the same time, record the current UTC time or local time as the start timestamp of data acquisition.

[0023] S2: Analyze the oil extraction operation mode based on the oil extraction-related operation data, detect whether the oil extraction operation mode meets the preset standard conditions, and optimize and adjust the oil extraction method according to the detection result of the oil extraction operation mode.

[0024] In this embodiment, S2 monitors and records the environmental conditions during the oil extraction operation and whether the measures of sealed or semi-sealed state are adopted. Two samples of the same oil sample are collected under the fully exposed and semi-sealed states respectively. The gas chromatography method is used to quantitatively analyze the contents of hydrogen, carbon dioxide, and carbon monoxide in the two samples. Based on the results of the quantitative analysis, statistical methods are used to calculate the mean, standard deviation, and coefficient of variation of the content of each gas in the two operation modes respectively. The data of the content of each gas in the oil calculated under the fully exposed and semi-sealed operation modes are compared and analyzed for differences, and then the overall difference evaluation value of all gas contents is comprehensively calculated to detect whether the differences between the oil extraction operation modes meet the preset standard conditions. If it is detected that the differences between the oil extraction operation modes do not meet the preset standard conditions, the detection personnel are prompted to dynamically adjust the oil extraction operation method according to the analysis results of the operation differences.

[0025] Specifically, prepare the sampling equipment to ensure that sampling can be carried out in both fully exposed and semi-sealed states. By collecting multiple samples of the same oil sample in the fully exposed state and sampling again using semi-sealed measures under the same environmental conditions, according to the requirements of gas chromatography analysis, perform pretreatment on the oil sample, such as degassing, filtering, etc. Then configure the gas chromatograph, set appropriate detection parameters, run the configured instrument, and conduct quantitative analysis on hydrogen, carbon dioxide, and carbon monoxide in each oil sample, so as to measure the hydrogen, carbon dioxide, and carbon monoxide contents in each sample respectively, and organize the data obtained from gas chromatography analysis into a table, including sample number, operation mode (fully exposed / semi-sealed), environmental conditions (temperature, humidity, air pressure), hydrogen content, carbon dioxide content, and carbon monoxide content; based on the data obtained from quantitative analysis, calculate the mean, standard deviation, and coefficient of variation of each gas respectively, and use an independent samples t-test to compare the differences in the content of each gas under the two operation modes. The calculation formula for the t-test is , where represents the mean content of each gas in the fully exposed state, represents the mean content of each gas in the semi-sealed state, represents the standard deviation of the gas content in the fully exposed state, represents the standard deviation of the gas content in the semi-sealed state, represents the number of samples independently collected in the fully exposed state, represents the number of samples independently collected in the semi-sealed state; Comprehensively compare and analyze the differences in the content of each gas calculated under the fully exposed and semi-sealed operation modes to calculate the overall difference evaluation value of all gas contents. The specific calculation formula is , where represents the weight coefficient of the difference in the content of each gas, and G represents the number of types of gases; determine a difference threshold based on past operation data and experimental results. By comparing the overall difference evaluation value of all gas contents with the difference threshold, if the overall difference evaluation value of all gas contents is lower than the difference threshold, it is considered that the difference between the operation modes meets the preset standard conditions and there is no need to adjust the operation steps. If the overall difference evaluation value of all gas contents is higher than the difference threshold, it indicates that the difference between the operation modes does not meet the preset standard conditions. Analyze the operation modes in this case, find out the reasons for the differences, give adjustment suggestions, and immediately send a warning prompt message to the detection personnel, prompting the detection personnel to further investigate and adjust the operation steps that cause these differences according to the adjustment suggestions.

[0026] S3: Based on the real-time monitoring and analysis of the oil extraction volume, analyze the trend of the oil level drop during oil extraction, and control the oil extraction volume to be kept above the minimum oil level line.

[0027] In this embodiment, based on the optimization result of the oil extraction operation mode, S3 analyzes the collected oil level data through the collected oil level data, calculates the oil level drop rate and the oil level drop period, identifies the speed and trend of the oil level drop, and sets a minimum oil level line based on the safe operation requirements of the transformer. And based on the oil level drop rate, period and operation error, a safety margin is set. Then, the falling state of the oil level line is continuously monitored to always remain at a position not lower than . If the oil level approaches or is lower than , an alarm is immediately triggered and an adjustment operation is performed on the oil extraction volume. When the oil level approaches or is lower than , the oil level deviation is calculated. Based on the calculated oil level deviation, the control output value is calculated using the PID algorithm, and the oil extraction volume is adjusted according to the control output value to ensure that the oil level rises to or higher.

[0028] Specifically, real-time oil level data is collected through an oil level sensor, and the timestamp of data collection is recorded. A suitable time window is selected, and the change amount of the oil level within this window is divided by the duration of the time window to calculate the oil level drop rate. The specific calculation formula is . The Fourier transform function is used to perform time series analysis on the oil level data to determine the oil level drop period , that is, the period from the highest point of the oil level to the next same height. Then, based on the oil level drop rate , the oil level drop period and the operation error (the error caused by sensor accuracy, environmental factors and human operation), the safety margin is calculated as . According to the set minimum oil level line and the safety margin , a safety oil level line threshold is defined for the oil extraction. Based on the safety oil level line threshold, it is judged whether to adjust the oil extraction volume. When the actual oil level drops and approaches , the oil level deviation is calculated, that is, the difference between the current oil level and . Based on the oil level deviation, the control output value calculated using the PID algorithm is . Among them, , represents the control output value, that is, the adjustment amount of the oil extraction volume, represents the oil level difference, represents the proportional gain, which is used to adjust the influence of the current deviation, represents the integral gain, which is used to adjust the accumulated influence of the deviation, Represents differential gain, which is used to predict the change trend of deviation. Represents the time variable, which is used to describe the change of oil level difference over time. According to Adjust the oil intake to ensure that the oil level is maintained at above, continuously monitor the oil level, and adjust the PID parameters according to the actual situation to optimize the control effect.

[0029] S4: It is used to collect historical oil intake data for a period of time, establish an oil intake time prediction model based on the historical oil intake data, plan the oil intake time according to the oil intake time prediction model, and perform the oil intake operation according to the planned oil intake time.

[0030] In this embodiment, S4 collects and stores the historical oil intake data of the transformer in the past period of time, including the oil intake time, the oil intake volume, the oil level change, and the environmental conditions, selects a machine learning algorithm to establish an oil intake time prediction model, uses the historical data to train the model, uses the historical oil intake data to train the prediction model, and adjusts the model parameters to minimize the prediction error. Then, the currently collected oil intake data is input into the trained prediction model, and the predicted oil intake time is output. According to the predicted oil intake time, the best oil intake time point is planned to perform the oil intake operation.

[0031] Specifically, by performing feature selection on the collected historical oil intake data, key factors affecting the oil intake volume are selected, such as time, the oil level drop rate, environmental conditions, etc., and a time series analysis algorithm is selected to establish an oil intake time prediction model. The historical oil intake data is used to train the established oil intake time prediction model. The specific formula is as follows: , where F represents the predicted oil intake time, X represents the selected feature vector, represents the model parameters, and the accuracy of the model prediction is evaluated through a loss function. The specific formula is as follows: , where represents the actual oil intake time, represents the predicted oil intake time, represents the number of data points collected, and at the same time, an optimization algorithm is used to adjust the model parameters to minimize the loss function, and then the cross-validation method is used to evaluate the performance of the model. Adjust the model parameters until a satisfactory prediction accuracy is achieved; The currently collected oil intake data is used as the input feature vector and input into the already trained model. The model is used for prediction, and the predicted oil intake time is output. Based on the predicted oil intake time output by the prediction model, combined with the operation window and the buffer time, the best oil intake time point is calculated. The specific calculation formula is , where F represents the predicted oil intake time, represents the start time of the operation window, represents the end time of the operation window. Indicates the buffering time.

[0032] S5: Based on the oil extraction environment, perform compensation analysis on the oil extraction time during the oil extraction operation process to obtain the compensated oil extraction time, and dynamically optimize and adjust the oil extraction time according to the compensated oil extraction time to keep the oil extraction time within the standard range.

[0033] In this embodiment, S5 is based on the analysis result of the oil extraction time planning. By using statistical methods to analyze the correlation between the oil extraction environment condition parameters and the oil extraction time, based on the correlation analysis result, establish a mathematical model of the environmental factors and the oil extraction time, input the current environmental conditions into the data model, calculate the compensated oil extraction time, and then compare the compensated oil extraction time with the current actual oil extraction time to dynamically adjust the oil extraction time and control the oil extraction time within the standard range.

[0034] It should be specifically noted that the Pearson correlation coefficient is used to analyze the correlation between the environmental condition parameters and the oil extraction time. The specific analysis calculation formula is , where represents the correlation coefficient, and respectively represent the observed values of the environmental parameters and the observed values of the oil extraction time. and respectively represent the average values of the observed values of the environmental parameters and the observed values of the oil extraction time. Then, based on the correlation analysis result, establish a mathematical model of the environmental factors and the oil extraction time, calculate the compensated oil extraction time. For example, if there is a linear relationship between the environmental condition parameters and the oil extraction time, a linear regression model can be used as the mathematical model for constructing the environmental factors and the oil extraction time. Take the collected environmental condition parameters as the characteristic parameters input into the linear regression model to calculate the compensated oil extraction time. The specific calculation formula is , where T represents the compensated oil extraction time, represents the model parameter, represents the temperature, represents the humidity, represents the oil viscosity. Then compare the compensated oil extraction time with the current actual oil extraction time, and dynamically adjust the oil extraction time to , where represents the lower limit of the oil extraction time, represents the upper limit of the oil extraction time, and perform the oil extraction operation according to the final oil extraction time .

[0035] S6: Real-time feedback the control adjustment result and the entire control analysis process to the tester's terminal.

[0036] In this embodiment, S6 feeds back the control adjustment results of the oil extraction operation mode, the control adjustment results of the oil extraction amount, and the control adjustment results of the oil extraction time to the tester's terminal in real time, automatically generates a regulation monitoring report based on the entire control analysis process, and sends it to the terminal device of the tester, and allows the tester to perform query and confirmation operations on the terminal device.

[0037] As Figure 2 shown, this embodiment provides an implementation system corresponding to an article anti-counterfeiting method based on local feature visual information, including a data collection module, an oil extraction operation control module, an oil extraction amount control module, an oil extraction time planning module, an oil extraction time control module, and a control result feedback module. The data collection module is connected to the oil extraction operation control module, the oil extraction operation control module is connected to the oil extraction amount control module, the oil extraction operation control module is connected to the oil extraction time planning module, the oil extraction time planning module is connected to the oil extraction time control module, and the oil extraction operation control module, the oil extraction amount control module, and the oil extraction time control module are connected to the control result feedback module.

[0038] The data collection module is used to collect relevant operation data for each oil extraction. When a push rod feedback signal is received, the sensor is triggered to collect the relevant operation data during oil extraction. The oil extraction operation control module analyzes the oil extraction operation mode based on the relevant operation data for oil extraction, detects whether the oil extraction operation mode meets the preset standard conditions, and optimizes and adjusts the oil extraction method according to the detection result of the oil extraction operation mode. The oil extraction amount control module analyzes the real-time monitoring and analysis of the oil extraction amount, analyzes the oil level drop trend during oil extraction, and controls the oil extraction amount to be kept above the minimum oil level line. The oil extraction time planning module is used to collect historical oil extraction data within a period of time, establish an oil extraction time prediction model based on the historical oil extraction data, plan the oil extraction time according to the oil extraction time prediction model, and perform the oil extraction operation according to the planned oil extraction time. The oil extraction time control module performs compensation analysis on the oil extraction time during the oil extraction operation based on the oil extraction environment, obtains the compensated oil extraction time, dynamically optimizes and adjusts the oil extraction time according to the compensated oil extraction time, and keeps the oil extraction time within the standard range. The control result feedback module feeds back the control adjustment results and the entire control analysis process to the tester's terminal in real time.

[0039] As Figure 3 shown is the transformer oil extraction control flow of this embodiment, and the specific implementation steps include: Step 1: When a push rod feedback signal is received, the sensor is triggered to collect the relevant operation data during oil extraction. Step 2: Analyze the oil extraction operation mode by taking relevant operation data of oil extraction, and determine whether the oil extraction operation mode meets the preset standard conditions. If it does not meet, optimize and adjust the oil extraction method; Step 3: Analyze the oil level decline trend during oil extraction by the oil extraction volume, and detect whether the oil level line is close to or lower than the safety oil level line threshold. If it is close to or lower than the safety oil level line threshold, adjust the oil extraction volume to rise above the safety oil level line threshold; Step 4: Predict and plan the optimal oil extraction time point based on the oil extraction time prediction model; Step 5: Calculate the compensated oil extraction time, and compare it with the current actual oil extraction time to dynamically adjust the oil extraction time and control the oil extraction time within the standard range; Step 6: Provide real-time feedback of the control process to the tester's terminal.

[0040] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0041] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claimed rights.

Claims

1. An intelligent oil sampling control method for a transformer, characterized in that Including: S1: Used to collect relevant operation data for each oil extraction. When receiving the push rod feedback signal, trigger the sensor to collect the relevant operation data during oil extraction; S2: Analyze the oil extraction operation mode based on the relevant operation data for oil extraction, detect whether the oil extraction operation mode meets the preset standard conditions, and optimize and adjust the oil extraction method according to the detection result of the oil extraction operation mode; S3: Based on the real-time monitoring and analysis of the oil extraction volume, analyze the oil level drop trend during oil extraction, and control the oil extraction volume to be kept above the minimum oil level line; S4: Used to collect historical oil extraction data within a period of time, establish an oil extraction time prediction model based on the historical oil extraction data, plan the oil extraction time according to the oil extraction time prediction model, and perform the oil extraction operation according to the planned oil extraction time; S5: Conduct a compensation analysis on the oil extraction time during the oil extraction operation process based on the oil extraction environment, obtain the compensated oil extraction time, dynamically optimize and adjust the oil extraction time according to the compensated oil extraction time, and keep the oil extraction time within the standard range; S6: Real-time feedback the control adjustment result and the entire control analysis process to the tester's terminal.

2. The intelligent oil extraction control method for a transformer according to claim 1, wherein After receiving the feedback signal of the push rod, the S1 immediately sends control information to the sensor through the solenoid valve to trigger the sensor to collect the relevant operation data during oil extraction and record the data collection time. The collected relevant operation data for oil extraction includes the ambient temperature, humidity, oil temperature, oil pressure, oil extraction flow rate, oil extraction volume, oil level, and gas content in the oil during oil extraction. Classify and store the collected relevant operation data for oil extraction in the database according to the recorded collection time.

3. The intelligent oil extraction control method for a transformer according to claim 2, characterized in that The S2 monitors and records the environmental conditions during the oil extraction operation and whether the measures of sealed or semi-sealed state are adopted. Collect two samples of the same oil sample under the fully exposed and semi-sealed states respectively. Use the gas chromatography method to quantitatively analyze the contents of hydrogen, carbon dioxide, and carbon monoxide in the two samples. Based on the results of the quantitative analysis, use statistical methods to calculate the mean, standard deviation, and coefficient of variation of the content of each gas under the two operation modes respectively. Conduct a difference comparison analysis on the data of the content of each gas in the oil calculated under the fully exposed and semi-sealed operation modes, and then comprehensively calculate the overall difference evaluation value of all gas contents. Detect whether the difference between the oil extraction operation modes meets the preset standard conditions. If it is detected that the difference between the oil extraction operation modes does not meet the preset standard conditions, then according to the analysis result of the operation difference, prompt the tester to dynamically adjust the oil extraction operation method.

4. The intelligent oil extraction control method for a transformer according to claim 3, characterized in that, Based on the optimization result of the oil extraction operation mode, the S3 analyzes the collected oil level data through the collected oil level data, calculates the oil level drop rate and the oil level drop period, identifies the speed and trend of the oil level drop, and sets a minimum oil level line based on the safe operation requirements of the transformer. And based on the oil level drop rate, period, and operation error, a safety margin is set. Then, it continuously monitors that the drop state of the oil level line always remains at a position not lower than . If the oil level approaches or is lower than , an alarm is immediately triggered and an adjustment operation is performed on the oil extraction volume. When the oil level approaches or is lower than , the oil level deviation is calculated. Based on the calculated oil level deviation, the control output value is calculated using the PID algorithm, and the oil extraction volume is adjusted according to the control output value to ensure that the oil level rises above .

5. The intelligent oil extraction control method for a transformer according to claim 3, characterized in that, The S4 collects and stores the historical oil extraction data of the transformer in the past period of time, including the oil extraction time, oil extraction volume, oil level change, and environmental conditions. Select a machine learning algorithm to establish an oil extraction time prediction model, use historical data to train the model, use historical oil extraction data to train the prediction model, and adjust the model parameters to minimize the prediction error. Then input the currently collected oil extraction data into the trained prediction model and output the oil extraction prediction time. According to the oil extraction prediction time, plan the best oil extraction time point to perform the oil extraction operation.

6. The intelligent oil extraction control method for a transformer according to claim 5, wherein Based on the analysis results of the oil extraction time planning, S5 analyzes the correlation between the environmental condition parameters of oil extraction and the oil extraction time by using statistical methods. Based on the correlation analysis results, a mathematical model of environmental factors and oil extraction time is established. The current environmental conditions are input into the data model to calculate the compensated oil extraction time. Then, the compensated oil extraction time is compared with the current actual oil extraction time to dynamically adjust the oil extraction time and control the oil extraction time within the standard range.

7. A method for intelligent oil sampling control of a transformer according to claim 1, characterized in that S6 feeds back the control adjustment results of the oil extraction operation mode, the control adjustment results of the oil extraction volume, and the control adjustment results of the oil extraction time to the tester's terminal in real time, automatically generates a regulation monitoring report based on the entire control analysis process and sends it to the terminal device of the tester, and allows the tester to perform query and confirmation operations on the terminal device.

8. An intelligent oil sampling control system for a transformer, which implements an intelligent oil sampling control method for a transformer according to any one of claims 1-7, characterized in that, Including: Data collection module: used to collect relevant operation data for each oil extraction. When the push rod feedback signal is received, the sensor is triggered to collect the relevant operation data during oil extraction. Oil extraction operation control module: analyzes the oil extraction operation mode based on the relevant operation data of oil extraction, detects whether the oil extraction operation mode meets the preset standard conditions, and optimizes and adjusts the oil extraction method according to the detection results of the oil extraction operation mode. Oil extraction volume control module: based on the real-time monitoring and analysis of the oil extraction volume, analyzes the oil level drop trend during oil extraction, and controls the oil extraction volume to be kept above the minimum oil level line. Oil extraction time planning module: used to collect historical oil extraction data for a period of time, establish an oil extraction time prediction model based on the historical oil extraction data, plan the oil extraction time according to the oil extraction time prediction model, and perform the oil extraction operation according to the planned oil extraction time. Oil extraction time control module: conducts compensation analysis on the oil extraction time during the oil extraction operation based on the oil extraction environment to obtain the compensated oil extraction time, dynamically optimizes and adjusts the oil extraction time according to the compensated oil extraction time, and keeps the oil extraction time within the standard range. Control result feedback module: feeds back the control adjustment results and the entire control analysis process to the tester's terminal in real time.

Images