Intelligent processing method and system for transformer oil and electronic equipment

Abstract

The invention relates to the technical field of transformer oil intelligent processing scheme design, in particular to a transformer oil intelligent processing method and system and electronic equipment. Firstly, activated clay and reactor oil of the heating module are synchronously heated, and a reasonable stirring structure of the mixing module is adopted, so that the problems of local overheating and non-uniform mixing can be effectively avoided, full and uniform mixing of the activated clay and the reactor oil in a constant-temperature environment is ensured, and the mixing quality is improved. Secondly, the sensor module monitors various key parameters in real time, so that the mixing state is clear and visible; the processor module performs analysis and processing by means of an AI algorithm, the mixing effect can be accurately evaluated, the stirring speed is automatically controlled according to the evaluation result in combination with the control module, intelligent and dynamic process control is achieved, and the processing efficiency and stability are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent processing scheme design for transformer oil, and particularly relates to an intelligent processing method and system for transformer oil, and an electronic device. Background Art

[0002] The treatment of transformer oil requires stirring the transformer oil with activated clay. However, there are many deficiencies in the traditional mixing and stirring treatment method of transformer oil and activated clay. On the one hand, during the heating and stirring process, the heating and stirring links often lack precise synchronous control. In the preferred embodiment of the present invention, if the heating speed is too fast or the stirring is uneven, it is easy to cause poor dispersion of the activated clay in the transformer oil and local overheating problems, thereby affecting the adsorption and purification effect. On the other hand, most of the current treatment systems cannot accurately monitor various parameters during the mixing process in real time. In the preferred embodiment of the present invention, these parameters are temperature, viscosity, turbidity, and pressure changes during the stirring process. Due to the lack of effective monitoring and analysis of these key data, it is difficult to dynamically adjust the stirring speed parameters according to the actual mixing state, making it difficult for the entire treatment process to reach the best uniform mixing state, resulting in unstable quality of the treated transformer oil and being unable to fully meet the requirements for the performance restoration and improvement of transformer oil in actual applications. Therefore, there is an urgent need for an intelligent processing system and method for transformer oil that can precisely control the mixing process and perform real-time monitoring and adjustment.

[0003] Therefore, the prior art still needs to be further developed. Summary of the Invention

[0004] The purpose of the present invention is to overcome the above technical deficiencies and provide an intelligent processing method and system for transformer oil, and an electronic device to solve the problems existing in the prior art.

[0005] To achieve the above technical purpose, according to the first aspect of the present invention, the present invention provides an intelligent processing system for transformer oil, including: A heating module for synchronously heating the activated clay and the transformer oil; A mixing module for mixing the synchronously heated activated clay and the transformer oil to form a mixture; A sensor module for real-time monitoring of the mixing state of the mixture. The sensor module includes at least one sensor, and the sensor is one or more of a temperature sensor, a viscosity sensor, and a turbidity sensor; A processor module for receiving the monitoring data transmitted by the communication module and analyzing and processing the monitoring data based on an AI algorithm to obtain a mixing state evaluation result; A communication module for transmitting the monitoring data; A control module for automatically controlling the stirring speed according to the mixing state evaluation result.

[0006] Specifically, the mixing module includes: A rotating shaft, the upper end of the rotating shaft is connected to a driving motor, the lower end of the rotating shaft is fixedly connected to a horizontally arranged propeller, and the driving motor is used to drive the propeller to rotate, thereby mixing the activated clay and the transformer oil after synchronous heating to form a mixture.

[0007] According to the second aspect of the present invention, there is provided an intelligent processing method for transformer oil, including: S100. Synchronously heat the activated clay and the transformer oil; mix the synchronously heated activated clay and the transformer oil to form a mixture; S200. Real-time monitor the mixing state of the mixing system through sensors, the sensors include a temperature sensor, a viscosity sensor and a turbidity sensor, and the monitoring data is transmitted to the processor through a communication module; the processor analyzes and processes the monitoring data based on an AI algorithm to obtain a mixing state evaluation result; S300. Automatically control the stirring speed according to the mixing state evaluation result so that the mixing state of the mixture reaches a preset standard.

[0008] Specifically, the step of the processor analyzing and processing the monitoring data based on the AI algorithm includes: Establish a mixing state evaluation model, the evaluation model is trained based on the mixing experimental data of the transformer oil and the activated clay, including the mixing sample data at different temperatures, stirring speeds, and activated clay addition amounts; Input the real-time monitored temperature, viscosity and turbidity data into the evaluation model to obtain a mixing state evaluation result, and the mixing state evaluation result includes the mixing uniformity and the reaction degree index of the activated clay and the transformer oil.

[0009] Specifically, the step of automatically controlling the stirring speed according to the mixing state evaluation result includes: When the mixing state evaluation result shows that the mixing uniformity is lower than the preset value, increase the stirring speed; when the mixing state evaluation result shows that the mixing uniformity is higher than the preset value and the stirring speed is higher than the minimum maintenance speed, decrease the stirring speed.

[0010] Specifically, the sensor module further includes a pressure sensor for monitoring the pressure data during the stirring process and transmitting it to the processor module.

[0011] Specifically, the monitoring data further includes the pressure change data of the stirring material on the side wall of the stirring tank caused by the liquid flow and the change of the mixing state during the stirring process, and the processor takes the pressure change data into consideration when analyzing and processing the monitoring data based on the AI algorithm.

[0012] Specifically, the control module includes a variable frequency drive for adjusting the power supply frequency of the motor in the stirring device according to the instructions of the processor module, thereby changing the stirring speed.

[0013] Specifically, the communication module is a wired communication module or a wireless communication module, and the wireless communication module includes a Wi-Fi module, a Bluetooth module or a ZigBee module.

[0014] According to a third aspect of the present invention, there is provided an electronic device, including: a memory; and a processor, wherein computer-readable instructions are stored on the memory, and when the computer-readable instructions are executed by the processor, the above-mentioned intelligent processing method for transformer oil is implemented.

[0015] Beneficial effects: The intelligent processing system and method for transformer oil of the present invention have many significant beneficial effects.

[0016] First of all, by synchronously heating the activated clay and the transformer oil in the heating module, and the reasonable stirring structure of the mixing module, the problems of local overheating and uneven mixing can be effectively avoided, ensuring that the two are fully and evenly mixed in a constant temperature environment, and improving the mixing quality.

[0017] Secondly, the sensor module monitors a variety of key parameters in real time, making the mixing state clearly visible. The processor module analyzes and processes with the help of AI algorithms, can accurately evaluate the mixing effect, and then combines with the control module to automatically control the stirring speed according to the evaluation results, realizing intelligent and dynamic process control, and greatly improving the processing efficiency and stability.

[0018] Furthermore, the communication module enables the system to have scalability, facilitating remote monitoring and management. The electronic device, as an operation terminal, integrates multiple functions, overall optimizing the transformer oil treatment process, ensuring the stable and reliable quality of the treated transformer oil, and meeting the actual application requirements. Description of the drawings

[0019] Figure 1 is a schematic diagram of the system composition of the intelligent processing system for transformer oil provided in a specific embodiment of the present invention Figure 2 is a schematic flow chart of the intelligent processing method for transformer oil provided in a specific embodiment of the present invention; In the above-mentioned drawings, the following reference numerals are preferably used in the present invention: 1. Heating chamber; 2. Rotating shaft; 4. Driving motor; 5. Pressure sensor; 6. Propeller; 7. Turbidity sensor; 8. Viscosity sensor; 9. Temperature sensor. Detailed implementation manners

[0020] To enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the present invention. Based on the embodiments in this application, other similar embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application. In addition, the directional terms mentioned in the following embodiments, "up", "down", "left", and "right" in the preferred embodiments of the present invention are only with reference to the directions of the accompanying drawings. Therefore, the directional terms used are for illustration rather than limiting the present invention.

[0021] The present invention will be further described below in conjunction with the accompanying drawings and preferred embodiments.

[0022] Please refer to Figure 1 - Figure 2 , the present invention provides an intelligent transformer oil treatment system, including: A heating module for synchronously heating activated clay and transformer oil.

[0023] Specifically, the main function of the heating module is to synchronously heat activated clay and transformer oil. Specifically, the heating module is a special heating chamber 1, the chamber is cylindrical as a whole, and stainless steel material is used to ensure good thermal conductivity and durability during the heating process.

[0024] Inside the heating chamber 1, activated clay and transformer oil are respectively input into the chamber through different pipes. Uniformly distributed small holes with a diameter of 3 mm are provided at the connection between the pipes and the chamber, which is convenient for the two to be evenly dispersed inside the chamber. The heating devices are evenly distributed around the outer wall of the heating chamber 1 and are composed of a plurality of heating resistance wires with a total power of 2000 W. By precisely controlling the current magnitude of the heating resistance wires, the heating power is adjusted so that the temperature inside the chamber can be maintained at a preset value during the heating process.

[0025] In the preferred embodiment of the present invention, for different types of activated clay and transformer oil, the initial heating power is set to 1500 W, and the temperature is gradually increased to 65 °C, and the heating time is 8 minutes. Then, it is kept at a constant temperature of 65 °C for 3 minutes to ensure that the activated clay and transformer oil uniformly reach the appropriate working temperature and prepare for the subsequent mixing process.

[0026] A mixing module for mixing the synchronously heated activated clay and transformer oil to form a mixture.

[0027] A sensor module for real-time monitoring of the mixing state of the mixture. The sensor module includes at least one sensor, and the sensor is one or more of a temperature sensor 9, a viscosity sensor 8, and a turbidity sensor 7.

[0028] Preferably, the sensor module in the present invention includes: Temperature sensor 9: Multiple temperature sensors 9 are installed in the heating chamber 1. A K-type thermocouple thermometer is used. The temperature sensors 9 are evenly arranged at heights of 100 mm, 500 mm, and 900 mm from the bottom of the chamber, one on each layer, for accurately monitoring the heating temperature at different positions. The sensors are connected to the processor module through signal lines, and the signal lines are laid in metal shielded tubes inside the chamber wall to reduce external interference.

[0029] Viscosity sensor 8: The viscosity sensor 8 is a rotational viscometer, model Brookfield DV-II+Pro, installed at a position near the bottom on the side of the heating chamber 1. This position can effectively measure the viscosity of the mixed liquid during the overall flow process, with an accuracy of ±1 cP.

[0030] Turbidity sensor 7: The turbidity sensor 7 uses the principle of light scattering, model HACH 1720E, installed on the side of the chamber opposite to the viscosity sensor 8, with the same installation position parameters as the viscosity sensor 8. It mainly reflects the turbidity by detecting the degree of light scattering by activated clay particles in the mixed system, thereby judging the dispersion uniformity of activated clay in the transformer oil, with a measurement accuracy of ±1%.

[0031] Pressure sensor 5: The pressure sensor 5 is installed at the bottom position of the chamber side wall, 10 mm from the bottom, for monitoring the pressure changes caused by liquid flow and changes in the mixing state during the stirring process. A piezoresistive pressure sensor 5, model MS5611, is used, with a measurement accuracy of ±0.1 kPa.

[0032] The processor module is used to receive the monitoring data transmitted by the communication module and analyze and process the monitoring data based on the AI algorithm to obtain the mixed state evaluation result.

[0033] The communication module is used to transmit the monitoring data; The control module is used to automatically control the stirring speed according to the mixed state evaluation result.

[0034] Specifically, the mixing module includes: The rotating shaft 2, the upper end of the rotating shaft 2 is connected to the driving motor 4, the lower end of the rotating shaft 2 is fixedly connected with a horizontally arranged propeller 6, and the driving motor 4 is used to drive the propeller 6 to rotate, thereby mixing the activated clay and transformer oil after synchronous heating to form a mixture.

[0035] Specifically, the control module includes a variable frequency driver, which is used to adjust the power supply frequency of the motor in the stirring device according to the instructions of the processor module, thereby changing the stirring speed.

[0036] Specifically, the communication module is a wired communication module or a wireless communication module, and the wireless communication module includes a Wi-Fi module, a Bluetooth module, or a ZigBee module.

[0037] Please refer to Figure 2 , another embodiment is provided by the present invention. This embodiment provides an intelligent processing method for transformer oil. The intelligent processing system for transformer oil includes: S100. Synchronously heat activated clay and transformer oil; mix the synchronously heated activated clay and transformer oil to form a mixture. S200. Real-time monitor the mixing state of the mixing system through sensors. The sensors include a temperature sensor 9, a viscosity sensor 8, and a turbidity sensor 7. The monitoring data is transmitted to the processor through the communication module; the processor analyzes and processes the monitoring data based on the AI algorithm to obtain a mixing state evaluation result.

[0038] Specifically, the steps for the processor to analyze and process the monitoring data based on the AI algorithm include: Establish a mixing state evaluation model. The evaluation model is trained based on the mixing experimental data of transformer oil and activated clay, including the mixing sample data at different temperatures, stirring speeds, and activated clay addition amounts. Input the real-time monitored temperature, viscosity, and turbidity data into the evaluation model to obtain a mixing state evaluation result. The mixing state evaluation result includes the mixing uniformity and the reaction degree index of the activated clay and the transformer oil.

[0039] Specifically, an AI algorithm based on deep learning is used to analyze and process the monitoring data. The specific steps are preferably as follows in the present invention: Data preprocessing: First, receive multiple groups of sensor data of temperature, viscosity, turbidity (and pressure) transmitted by the communication module, clean these data to remove outliers (preferably unreasonable maximum or minimum values caused by sensor failures or external interferences in the present invention), and then normalize the data and map it to the [0, 1] interval to improve the efficiency and accuracy of subsequent model training and processing.

[0040] AI Model Training: Construct a hybrid state evaluation model with a deep neural network (DNN) structure. The training data is sourced from a large number of experimental data, collecting no less than 800 sets of mixed sample data under different transformer oil types, different activated clay addition amounts (ranging from 1 kg to 10 kg), different initial temperatures (40°C - 75°C), and stirring speeds (300 revolutions per minute - 1200 revolutions per minute). Through feature engineering, temperature, viscosity, turbidity (and pressure) features are extracted as input layer nodes, and the mixing uniformity and the reaction degree index of activated clay and transformer oil are used as output layer nodes. 25 nodes are set in the middle hidden layer, ReLU is used as the activation function, and the cross-entropy loss function and Adam optimization algorithm are used for model training to finally obtain the trained evaluation model.

[0041] Specifically, the specific steps of AI model training include: 1. Data Collection and Preparation Experimental Design: Design multiple groups of experiments covering different transformer oil types, activated clay addition amounts, initial temperatures, and stirring speed variables.

[0042] Each group of experiments records the following data: Temperature (temperature sensor data distributed at different heights in the chamber).

[0043] Viscosity (viscosity of the mixed liquid measured by a viscosity sensor).

[0044] Turbidity (turbidity of the mixed liquid measured by a turbidity sensor).

[0045] Pressure (pressure change of the tank wall during stirring measured by a pressure sensor).

[0046] Mixing Uniformity (mixing uniformity percentage obtained by sampling and analysis after the experiment).

[0047] Reaction Degree (quantification index of the chemical reaction degree between activated clay and transformer oil, preferably the adsorption rate or reaction time in the present invention).

[0048] Data Scale: Collect no less than 800 sets of experimental data to ensure data diversity and coverage.

[0049] The data sources include different types of transformer oils (preferably No. 25 transformer oil and No. 45 transformer oil in the present invention) and different proportions of activated clay addition amounts (ranging from 1 kg to 10 kg).

[0050] Data Annotation: Annotate each group of experimental data, and the annotation content includes: Mixing Uniformity (preferably 75%, 80% in the present invention).

[0051] Degree of reaction index (preferably 80% and 85% in the present invention).

[0052] The annotation is completed by the experimenter according to the actual measurement results to ensure the accuracy of the data.

[0053] Data cleaning: Removing outliers: Eliminating unreasonable data caused by sensor failures or external interferences (preferably sudden temperature rises and abnormal viscosities in the present invention).

[0054] Handling missing values: Interpolating or deleting missing data to ensure data integrity.

[0055] Data normalization: Mapping the characteristic values of temperature, viscosity, turbidity, and pressure to the interval [0, 1]. The formula is preferably as follows in the present invention: where x is the original data, x′ is the normalized data, x min and x max are the minimum and maximum values of the feature, respectively.

[0056] 2. Model construction Model selection: Using a deep neural network (DNN) as the basic model, which is suitable for modeling non-linear relationships with multiple inputs and outputs.

[0057] Model structure: Input layer: Consisting of 4 nodes (temperature, viscosity, turbidity, pressure).

[0058] Hidden layer: Setting 25 nodes, using the ReLU (Rectified Linear Unit) activation function, and the formula is: f(x) = max(0, x) Output layer: Consisting of 2 nodes (mixing uniformity, degree of reaction index).

[0059] Loss function: Using the cross-entropy loss function to measure the difference between the predicted value and the true value.

[0060] Optimization algorithm: Using the Adam optimizer, combining momentum and adaptive learning rate adjustment to improve the convergence speed.

[0061] Model initialization: Initializing the weights using the He initialization method, and the formula is: where n in is the number of input nodes.

[0062] 3. Model Training Division of Training Set and Validation Set: The dataset is divided into a training set and a validation set in a ratio of 8:2.

[0063] The training set is used for learning model parameters, and the validation set is used to evaluate the generalization ability of the model.

[0064] Hyperparameter Settings: Batch Size: Set to 32 or 64 to ensure an appropriate amount of data for each training.

[0065] Learning Rate: Initially set to 0.001 and can be dynamically adjusted according to the training situation later.

[0066] Epochs: Set to 200 to ensure that the model converges sufficiently.

[0067] Training Process: Forward Propagation: Input the normalized sensor data (temperature, viscosity, turbidity, pressure).

[0068] Calculate the feature representation through the ReLU activation function in the hidden layer.

[0069] The output layer calculates the predicted values of the mixing uniformity and reaction degree indicators.

[0070] Loss Calculation: Use the cross-entropy loss function to calculate the difference between the predicted value and the true value.

[0071] The formula is: where N is the number of samples, C is the number of output classes, y ij is the true label, and p ij is the predicted probability.

[0072] Backward Propagation: Use the chain rule to calculate the gradient of the loss function with respect to the model parameters.

[0073] Update the weights and biases, and the formula is: where η is the learning rate.

[0074] Model Validation: After each training epoch, use the validation set to evaluate the model performance.

[0075] Calculate the mean squared error (MSE) and mean absolute error (MAE) on the validation set. The formula of the present invention is preferably as follows: Among them, y i is the true value, and

[0076] Early stopping mechanism: Preferably, if the MSE on the validation set does not decrease for 10 consecutive epochs, the training is stopped to prevent overfitting.

[0077] 4. Model testing and optimization Test set evaluation: Use an independent test set (data not involved in training and validation) to evaluate the model performance.

[0078] Calculate the MSE, MAE, and R² (coefficient of determination) on the test set to ensure the generalization ability of the model.

[0079] Model optimization: Preferably, if the model performance does not meet the standard, adjust the hyperparameters (preferably the learning rate and the number of hidden layer nodes) or increase the amount of data.

[0080] Use the cross-validation method to further optimize the model.

[0081] Model saving: Save the trained model as a file (preferably in HDF5 format) for subsequent real-time data processing.

[0082] 5. Model deployment and application Model loading: Load the trained model in the processor module for real-time data processing.

[0083] Real-time inference: Input the temperature, viscosity, turbidity, and pressure data collected by the sensor into the model to obtain the prediction results of the mixing uniformity and reaction degree indicators.

[0084] Model update: Regularly collect new experimental data and retrain the model to improve the adaptability and accuracy of the model.

[0085] Real-time data processing and evaluation: When processing actual mixing data, input the preprocessed real-time monitoring data into the trained model, and obtain the mixing state evaluation results through forward propagation calculation, including the mixing uniformity (preferably the calculated value is 75%, indicating a mixing uniformity of 75%) and the reaction degree indicator of activated clay and oil (preferably 80%) information.

[0086] S300. Automatically control the stirring speed according to the evaluation result of the mixing state so that the mixing state of the mixture reaches a preset standard.

[0087] Specifically, the step of automatically controlling the stirring speed according to the evaluation result of the mixing state includes: When the evaluation result of the mixing state shows that the mixing uniformity is lower than the preset value, increase the stirring speed; when the evaluation result of the mixing state shows that the mixing uniformity is higher than the preset value and the stirring speed is higher than the minimum maintenance speed, decrease the stirring speed.

[0088] Specifically, the method includes: The variable frequency drive accurately adjusts the power supply frequency of the drive motor 4 in the stirring device according to the control instruction transmitted from the processor module, thereby changing the stirring speed. In a preferred embodiment of the present invention, when the evaluation result of the mixing state indicates that the mixing uniformity is lower than 60%, the variable frequency drive increases the motor power supply frequency from the current 50 Hz to 60 Hz according to the preset control strategy to increase the stirring speed; when the mixing uniformity is higher than 85% and the stirring speed is higher than 400 revolutions per minute (the minimum maintenance speed), the variable frequency drive reduces the power supply frequency to 40 Hz to reduce the stirring speed, save energy and avoid over-stirring.

[0089] Specifically, the sensor module further includes a pressure sensor 5 for monitoring the pressure data during the stirring process and transmitting it to the processor module.

[0090] Specifically, the monitoring data further includes the pressure change data of the stirring material on the side wall of the stirring tank caused by the liquid flow and the change of the mixing state during the stirring process. When the processor analyzes and processes the monitoring data based on the AI algorithm, the pressure change data is taken into consideration.

[0091] The following illustrates the working process of the present invention through a specific example: Data acquisition and transmission (corresponding to part of S100): Each sensor in the sensor module real-time collects temperature, viscosity, turbidity (and pressure) data, and transmits the data to the processor module through the communication module (which can choose wired, Wi-Fi, Bluetooth or ZigBee).

[0092] Data analysis and evaluation (corresponding to part of S200): Model Application: The data received by the processor module is first simply verified and then transmitted to the processor in the electronic device. After the computer-readable instructions in the electronic device load the data, the pre-stored AI-based hybrid state evaluation model is called to analyze and process the data. Taking a specific data sample as an example, assuming the input temperature is 62 °C, viscosity is 35 cP, turbidity is 6%, and pressure is 1.2 kPa. After processing, through the calculation of multiple neural networks in the model, the final hybrid state evaluation results are a mixing uniformity of 78% and a reaction degree of 82%.

[0093] Result Judgment: The evaluation result is compared with the preset mixing standard (preferably, the preset standard for mixing uniformity in the present invention is that above 80% is considered uniform) to determine whether the mixing state meets the preset standard.

[0094] Speed Control (corresponding to part S300): Adjustment Strategy: Preferably, if the hybrid state evaluation result is lower than the preset value, and in the preferred embodiment of the present invention, the mixing uniformity is lower than 80%, the computer-readable instructions in the electronic device generate instructions to increase the stirring speed according to the preset control strategy and send them to the variable frequency driver in the control module; if the hybrid state evaluation result shows that the mixing uniformity is higher than the preset value (preferably 85% in the present invention) and the stirring speed is higher than the minimum maintenance speed (preferably 400 revolutions per minute), then instructions to reduce the stirring speed are generated.

[0095] Speed Adjustment Execution: After receiving the instructions, the variable frequency driver changes the power supply frequency of the motor in the stirring device according to a certain frequency adjustment rule (preferably, according to the difference value of the control instructions, gradually adjusts in steps of 5 Hz per step), thereby changing the stirring speed until the mixing state reaches or approaches the preset standard.

[0096] Specific Application Scenario Example: In an actual transformer oil treatment workshop, a batch of 900 L of No. 25 transformer oil and 50 kg of activated clay are mixed and processed according to the system and method of the present invention. Both are synchronously heated to 65 °C through the heating module, and then stirred and mixed using the mixing module. During the mixing process, the sensor module real-time collects data on temperature, viscosity, turbidity, and pressure, and transmits it to the processor module through the communication module. After analysis and processing by the processor module using the AI algorithm, it is found that the mixing uniformity is 70%, lower than the preset standard of 80%. Therefore, instructions to increase the stirring speed are generated, and the variable frequency driver in the control module increases the stirring motor speed from 600 revolutions per minute to 700 revolutions per minute. After stirring for a period of time, data is collected again, and the mixing uniformity increases to 83%, reaching the preset standard. The control system maintains the current stirring speed until the entire processing process is completed, ensuring the quality and efficiency of the mixing treatment of transformer oil and activated clay.

[0097] In a preferred embodiment, the present application further provides an electronic device, which includes: a memory; and a processor, wherein computer-readable instructions are stored on the memory, and when the computer-readable instructions are executed by the processor, the intelligent processing method of transformer oil is implemented. This computer device can be broadly a server, a terminal, or any other electronic device with necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, a memory, a network interface, and a communication interface connected through a system bus. The processor of the computer device can be used to provide necessary computing, processing, and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system and a computer program may be stored in or on the non-volatile storage medium. The internal memory can provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the computer device can be used to connect and communicate with external devices through a network. The computer program, when executed by the processor, performs the steps of the method of the present invention.

[0098] The present invention can be implemented as a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method of the embodiments of the present invention are caused to be executed. In one embodiment, the computer program is distributed on a plurality of network-coupled computer devices or processors, so that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, can be executed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations can be executed by one or more computer devices or processors, and one or more other method steps / operations can be executed by one or more other computer devices or processors. One or more computer devices or processors can execute a single method step / operation, or execute two or more method steps / operations.

[0099] Those of ordinary skill in the art can understand that the method steps of the present invention can be used to instruct relevant hardware through a computer program. The present invention is preferably implemented by a computer device or a processor. The computer program can be stored in a non-transitory computer-readable storage medium. When the computer program is executed, the steps of the present invention are caused to be executed. Depending on the circumstances, any reference herein to a memory, storage, database, or other medium may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, and solid state disk. Examples of volatile memory include random access memory (RAM) and external cache memory.

[0100] The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification as long as such a combination is not contradictory.

[0101] The specific embodiments of the present invention described above do not constitute a limitation on the protection scope of the present invention. Any other corresponding changes and deformations made according to the technical concept of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. An intelligent transformer oil processing system, characterized in that, The system includes: a heating module for synchronously heating activated clay and oil; a mixing module for mixing the synchronously heated activated clay and oil to form a mixture; a sensor module for real-time monitoring of the mixing state of the mixture, the sensor module including at least one sensor, the sensor being one or more of a temperature sensor (9), a viscosity sensor (8), and a turbidity sensor (7); a processor module for receiving the monitoring data transmitted by the communication module and analyzing and processing the monitoring data based on an AI algorithm to obtain a mixing state evaluation result; a communication module for transmitting the monitoring data; a control module for automatically controlling the stirring speed according to the mixing state evaluation result.

2. The intelligent transformer oil processing system according to claim 1, wherein The mixing module includes: a rotating shaft (2), the upper end of the rotating shaft (2) being connected to a driving motor (4), the lower end of the rotating shaft (2) being fixedly connected to a horizontally arranged propeller (6), the driving motor (4) being used to drive the propeller (6) to rotate, thereby mixing the synchronously heated activated clay and oil to form a mixture.

3. An intelligent processing method for transformer oil, characterized in that, The method includes: S100. Synchronously heating activated clay and oil; mixing the synchronously heated activated clay and oil to form a mixture; S200. Real-time monitoring of the mixing state of the mixing system through a sensor, the sensor including a temperature sensor (9), a viscosity sensor (8), and a turbidity sensor (7), the monitoring data being transmitted to the processor through the communication module; the processor analyzing and processing the monitoring data based on an AI algorithm to obtain a mixing state evaluation result; S300. Automatically controlling the stirring speed according to the mixing state evaluation result so that the mixing state of the mixture reaches a preset standard.

4. The intelligent processing method for transformer oil according to claim 3, wherein, The step of the processor analyzing and processing the monitoring data based on an AI algorithm includes: establishing a mixing state evaluation model, the evaluation model being trained based on the mixing experimental data of oil and activated clay, including the mixing sample data at different temperatures, stirring speeds, and activated clay addition amounts; inputting the real-time monitored temperature, viscosity, and turbidity data into the evaluation model to obtain a mixing state evaluation result, the mixing state evaluation result including the mixing uniformity and the reaction degree index of activated clay and oil.

5. The intelligent processing method of transformer oil according to claim 3, characterized in that The step of automatically controlling the stirring speed according to the mixing state evaluation result includes: when the mixing state evaluation result shows that the mixing uniformity is lower than the preset value, increasing the stirring speed; when the mixing state evaluation result shows that the mixing uniformity is higher than the preset value and the stirring speed is higher than the minimum maintenance speed, decreasing the stirring speed.

6. The intelligent processing method of transformer oil according to claim 3, wherein The sensor module further includes a pressure sensor (5) for monitoring the pressure data during stirring and transmitting it to the processor module.

7. The intelligent processing method of transformer oil according to claim 6, wherein The monitoring data further includes the pressure change data of the stirred material on the side wall of the stirring tank caused by the liquid flow and the change of the mixing state during stirring, and the processor takes the pressure change data into consideration when analyzing and processing the monitoring data based on an AI algorithm.

8. The intelligent processing method of transformer oil according to claim 3, characterized in that, The control module includes a variable frequency drive for adjusting the power supply frequency of the drive motor (4) in the stirring device according to the instructions of the processor module, thereby changing the stirring speed.

9. The intelligent processing method for transformer oil according to claim 3, characterized in that The communication module is a wired communication module or a wireless communication module, and the wireless communication module includes a Wi-Fi module, a Bluetooth module or a ZigBee module.

10. An electronic device, characterized in that, Comprising: A memory; And a processor, wherein computer-readable instructions are stored on the memory, and when the computer-readable instructions are executed by the processor, the intelligent processing method for transformer oil according to any one of claims 3 to 9 is implemented.

Images