Method for predicting internal heating temperature of combined electric appliance

Abstract

The invention relates to the technical field of power equipment state detection, in particular to a combined electric appliance internal heating temperature prediction method. A prediction data set is formed by building a combined electric appliance model and recording SF6 gas pressure P, environment temperature T, environment humidity H, wind speed V1, wind direction V2, combined electric appliance shell temperature T2 and heat source temperature T1, and a prediction function is obtained through algorithm training, so that when the inside of the combined electric appliance is heated in the actual working process, the heating temperature inside the combined electric appliance can be correctly predicted, and the prediction accuracy of the combined electric appliance is improved. A basis is provided for the correctness of the defect, a power-off maintenance and defect elimination plan is reasonably made according to the heating temperature, and safe and stable operation of power equipment is ensured; the internal heating temperature of the combined electric appliance is predicted by combining the environment temperature, the wind speed, the wind direction, the SF6 gas pressure value, the shell temperature and the structure of the combined electric appliance, the severity of the defect is judged according to the heating temperature, and a basis is provided for correctly knowing the health state of equipment and making a maintenance plan.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment state detection, and in particular to a method for predicting the internal heating temperature of a combined electrical appliance. Background Art

[0002] During the operation of power equipment, heating defects are common defects, which bring great hidden dangers to the safe and stable operation of the power system. The heating of power equipment will not only cause power loss, but also cause further damage to the equipment in serious cases. For some current heating defects at the joint position, heating further leads to an increase in contact resistance, and the increase in contact resistance further stimulates the increase in temperature. The positive promotion effect will further amplify the defect, leading to damage and burning of the joint. Therefore, in the power system, various temperature measurement methods are used to regularly inspect the equipment, record the heating conditions of the equipment, and formulate a defect elimination plan based on the regulations and heating temperature, and eliminate the defects in time to ensure equipment safety.

[0003] However, in the current temperature measurement of the power system, infrared detection is very effective for open equipment. It can effectively discover common heating defects such as joints, wire clamps, contacts, screws, etc. of primary equipment, which is convenient for timely processing. However, for combined electrical equipment, since the heating position is enclosed inside the combined electrical equipment, there is no effective means to measure the internal heating temperature.

[0004] For combined electrical appliances, due to their small footprint and low failure rate, their share in the power system is increasing year by year. Therefore, for a large number of combined electrical appliances, it is impossible to measure the internal heating temperature and effectively detect their defects, which will inevitably have a great impact on the safe operation of the power system. For the temperature measurement of combined electrical appliances, when there is a heating defect inside, it can be mapped to the device casing, causing the device casing to overheat locally. This type of defect can be detected by infrared temperature measurement, and it can be predicted and processed in advance. However, this type of detection can only determine the heating inside the combined electrical appliance, and the specific hot spot temperature cannot be determined. Studies have pointed out that when the heating temperature of the combined electrical appliance shell reaches 3°C, there may be serious heating inside, and the power should be cut off for processing. Due to the operating status of the combination electrical appliance, the internal heat is mostly caused by the excessive contact resistance of the contact surface and the heat generated by the current. When the equipment is running, it cannot be disassembled to measure the internal temperature. When the combination electrical appliance is disassembled after power failure, the internal hot spots have long cooled down. There have been many cases where the combination electrical appliance has abnormal status and the internal joints have been severely heated, burned black and deformed after disassembly, making it impossible to accurately measure the heating temperature before disassembly. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of the prior art and to provide a method for predicting the internal heating temperature of a combination electrical appliance. The internal heating temperature of the combination electrical appliance is predicted by combining the ambient temperature, wind speed, wind direction, SF6 gas pressure value, shell temperature and combination electrical appliance structure. The severity of the defect is judged based on the heating temperature, providing a basis for correctly understanding the health status of the equipment and formulating a maintenance plan.

[0006] The object of the present invention is achieved by: a method for predicting the internal heating temperature of a combined electrical appliance, comprising the following steps: S1. Build a combination electrical appliance model, and set a heat source with adjustable temperature inside the combination electrical appliance. Set the heat source temperature to T1, and the closest distance between the heat source and the combination electrical appliance housing to L; S2. Fill the combined electrical model with SF6 gas and record the SF6 gas pressure as P; S3, placing the combined electrical appliance model in a closed environment, and recording the ambient temperature T, ambient humidity H, wind speed V1, and wind direction V2; S4. Measure the hottest point temperature of the combination electrical housing and record it as T2; S5. In the laboratory, by modifying the input parameters [T1, L, P, T, H, V1, V2] in sequence, the corresponding combination electrical housing temperature T2 is recorded to form a data set; S6. In the actual work site, the temperature of the combination electrical housing T2 is known, and the temperature of the internal heat source of the combination electrical appliance is an unknown variable. Set the input vector to IN, then IN=[T2, L, P, T, H, V1, V2], and the output result is OUT, then OUT=T1; S7, importing the data set in step S6 into the algorithm for training, calculating through a neural network, or obtaining a prediction function f through curve fitting; S8. At the detection site, when the combination electrical appliance shell is found to be hot, record the maximum shell temperature as t2, record the distance l between the internal conductor of the combination electrical appliance and the shell, record the combination electrical appliance pressure as p, record the ambient temperature t, record the ambient humidity h, record the wind speed v1, record the wind direction v2, and form an input vector in=[t2, l, p, t, h, v1, v2], then the internal heat source temperature t1=f(in) can be predicted.

[0007] Furthermore, in step S2, instead of charging SF6 gas into the combination electrical model, SF6 / N2 mixed gas may be charged into the combination electrical model, and the SF6 gas pressure P1 and the N2 pressure P2 are recorded, and P=[P1, P2].

[0008] Furthermore, after step S8, the method further includes: Based on the predicted internal heat source temperature, that is, the heating temperature inside the combination electrical appliance, the severity of the defect is further determined according to the regulations, the defect is graded, and according to different defect grades, power outages are carried out to eliminate the defect to ensure safe and stable operation of the equipment.

[0009] Furthermore, the defect classification includes general defects, serious defects and critical defects.

[0010] Beneficial effects of the present invention: A method for predicting the internal heating temperature of a combination electrical appliance of the present invention, by building a combination electrical appliance model, records the SF6 gas pressure P, ambient temperature T, ambient humidity H, wind speed V1, wind direction V2, the combination electrical appliance shell temperature T2 and the heat source temperature T1, to form a prediction data set, and obtains a prediction function through algorithm training, so that in the actual working process, when the combination electrical appliance is heated inside, the heating temperature inside the combination electrical appliance can be correctly predicted, providing a basis for the correct characterization of defects, and according to the heating temperature, a reasonable power outage maintenance and fault elimination plan is formulated to ensure the safe and stable operation of power equipment; A method for predicting the internal heating temperature of a combination electrical appliance of the present invention predicts the internal heating temperature of the combination electrical appliance by combining the ambient temperature, wind speed, wind direction, SF6 gas pressure value, shell temperature and combination electrical appliance structure, and judges the severity of the defect according to the heating temperature, providing a basis for correctly understanding the health status of the equipment and formulating a maintenance plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0012] Figure 1 A schematic diagram of a combined electrical appliance in an application.

[0013] Figure 2 This is a schematic diagram showing the severe internal burning of the combined electrical appliance after it was disassembled.

[0014] Figure 3 It is a schematic diagram of the combined electrical appliance model in the present invention.

[0015] Figure 4 It is a schematic diagram of the wind direction setting in the present invention. DETAILED DESCRIPTION

[0016] The present invention will be further described below in conjunction with the accompanying drawings.

[0017] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] It should be noted that all directional indications in the embodiments of the present invention (such as up-down-left-right-front-back...) are only used to explain the relative position relationship - movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. The connection can be a direct connection or an indirect connection.

[0020] like Figure 1-4 As shown, a method for predicting the internal heating temperature of a combined electrical appliance of the present invention comprises the following steps: S1. Build a combination electrical appliance model, and set a heat source with adjustable temperature inside the combination electrical appliance. Set the heat source temperature to T1, and the closest distance between the heat source and the combination electrical appliance housing to L; exist Figure 3 In the schematic diagram of the combined electrical appliance model shown, the purpose of setting the adjustable heat source temperature is to change the temperature in sequence during the test and record the temperature mapped to the shell. The distance L between the heat source and the shell is set and set to be adjustable, which can be achieved by customizing multiple groups of combined electrical appliance models with different specifications.

[0021] S2. Fill the combined electrical model with SF6 gas and record the SF6 gas pressure as P; Furthermore, in one embodiment, in step S2, instead of charging SF6 gas into the combination electrical model, SF6 / N2 mixed gas may be charged into the combination electrical model, and the SF6 gas pressure P1 and the N2 pressure P2 are recorded, and P=[P1, P2].

[0022] There are two ways to read the SF6 gas pressure. One is to use a mechanical meter, and the other is to install an SF6 pressure sensor. It should be noted that the pressure value needs to be converted to the pressure value at 20°C for easy comparison. For mixed gases that are less used at present, other pressure values ​​are converted in proportion.

[0023] S3, placing the combined electrical appliance model in a closed environment, and recording the ambient temperature T, ambient humidity H, wind speed V1, and wind direction V2; The wind direction V2 can be represented by the incident angle. When the wind direction is parallel to the hottest temperature of the shell, the incident angle is 0, and when the shell is perpendicular to the shell, the incident angle is 90°. Figure 4 shown.

[0024] S4. Measure the hottest point temperature of the combination electrical housing and record it as T2; S5. In the laboratory, by modifying the input parameters [T1, L, P, T, H, V1, V2] in sequence, the corresponding combination electrical housing temperature T2 is recorded to form a data set; The input parameters [T1, L, P, T, H, V1, V2] are gridded and the shell temperature T2 of the combination appliance is recorded at different inputs.

[0025] S6. In the actual work site, the temperature of the combination electrical housing T2 is known, and the temperature of the internal heat source of the combination electrical appliance is an unknown variable. Set the input vector to IN, then IN=[T2, L, P, T, H, V1, V2], and the output result is OUT, then OUT=T1; S7, importing the data set in step S6 into the algorithm for training, calculating through a neural network, or obtaining a prediction function f through curve fitting; There are many applicable data processing algorithms, such as neural network algorithms, curve fitting, support vector machines, etc. Different algorithms have different processes. No specific algorithm is specified here because in actual applications, after conducting experiments to obtain data, predictions can be made independently through multiple algorithms, and then the prediction function with the best results can be found, or different prediction algorithms can be combined; the following is an introduction to the process of the neural network algorithm.

[0026] The neural network model prediction process generally includes the following steps: (1) Data preparation Collect and organize data sets, ensuring data quality and integrity.

[0027] Preprocess the data, such as cleaning, normalization, feature engineering, etc.

[0028] Divide the dataset into training, validation, and test sets.

[0029] (2) Model selection Choose an appropriate neural network model architecture based on the nature of the problem and the characteristics of the data.

[0030] Common neural network models include multi-layer perceptron (MLP), convolutional neural network (CNN), recurrent neural network (RNN), etc.

[0031] (3) Model training Use the training set to train the model.

[0032] Choose an appropriate optimization algorithm and loss function to minimize the prediction error.

[0033] Adjust the model's hyperparameters, such as learning rate, number of layers, number of nodes, etc., to improve the model's performance.

[0034] Monitor the loss and accuracy during training to ensure the model converges.

[0035] (4) Model evaluation Use the validation set to evaluate the trained model.

[0036] Calculate the accuracy, recall, F1 value and other indicators of the model on the validation set.

[0037] Based on the evaluation results, the model is adjusted and optimized.

[0038] (5) Model prediction Use the test set to make final predictions for the model.

[0039] Input the test data into the trained model to get the prediction results.

[0040] Analyze and interpret the forecast results.

[0041] (6) Model deployment Deploy the trained model to actual applications.

[0042] The model can be converted into a format suitable for deployment, such as TensorFlowLite, ONNX, etc.

[0043] In practical applications, models are used for real-time prediction or batch prediction.

[0044] Note: (1) Data quality has a significant impact on model performance, so it is necessary to ensure the accuracy and completeness of the data.

[0045] (2) Model selection and hyperparameter adjustment need to be based on specific problems. There is no universal method that is applicable to all situations.

[0046] (3) During the training process, we need to pay attention to the problems of overfitting and underfitting, which can be avoided through methods such as regularization and early stopping.

[0047] (4) Model evaluation requires the use of appropriate indicators and needs to be validated on multiple datasets to ensure the generalization ability of the model.

[0048] (5) Model deployment needs to consider the actual application environment and needs, such as computing resources and real-time requirements.

[0049] (6) When using a model for prediction, it is necessary to reasonably explain and analyze the prediction results to avoid over-reliance on the model.

[0050] S8. At the detection site, when the combination electrical appliance shell is found to be hot, record the maximum shell temperature as t2, record the distance l between the internal conductor of the combination electrical appliance and the shell, record the combination electrical appliance pressure as p, record the ambient temperature t, record the ambient humidity h, record the wind speed v1, record the wind direction v2, and form an input vector in=[t2, l, p, t, h, v1, v2], then the internal heat source temperature t1=f(in) can be predicted.

[0051] Based on the predicted internal heat source temperature, that is, the heating temperature inside the combination electrical appliance, the severity of the defect is further determined according to the regulations, the defect is graded, and according to different defect grades, power outages are carried out to eliminate the defect to ensure safe and stable operation of the equipment.

[0052] Furthermore, in one embodiment, the defect classification includes general defects, serious defects and critical defects.

[0053] In summary, a method for predicting the internal heating temperature of a combination electrical appliance of the present invention builds a combination electrical appliance model, records the SF6 gas pressure P, the ambient temperature T, the ambient humidity H, the wind speed V1, the wind direction V2, the combination electrical appliance shell temperature T2 and the heat source temperature T1, forms a prediction data set, and obtains a prediction function through algorithm training, so that when the combination electrical appliance is heated inside during actual working, the heating temperature inside the combination electrical appliance can be correctly predicted, providing a basis for the correct characterization of defects, and according to the heating temperature, a reasonable power outage maintenance and fault elimination plan is formulated to ensure the safe and stable operation of the power equipment; a method for predicting the internal heating temperature of a combination electrical appliance of the present invention predicts the internal heating temperature of the combination electrical appliance by combining the ambient temperature, wind speed, wind direction, SF6 gas pressure value, shell temperature and combination electrical appliance structure, and judges the severity of the defect according to the heating temperature, providing a basis for correctly understanding the health status of the equipment and formulating a maintenance plan.

[0054] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0055] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A method for predicting the internal heating temperature of a combination electrical appliance, characterized in that: The following steps are involved: S1. Build a combination electrical appliance model, and set a heat source with adjustable temperature inside the combination electrical appliance. Set the heat source temperature to T1, and the closest distance between the heat source and the combination electrical appliance housing to L; S2. Fill the combined electrical model with SF6 gas and record the SF6 gas pressure as P; S3, placing the combined electrical appliance model in a closed environment, and recording the ambient temperature T, ambient humidity H, wind speed V1, and wind direction V2; S4. Measure the hottest point temperature of the combination electrical housing and record it as T2; S5. In the laboratory, by modifying the input parameters [T1, L, P, T, H, V1, V2] in sequence, the corresponding combination electrical housing temperature T2 is recorded to form a data set; S6. In the actual work site, the temperature of the combination electrical housing T2 is known, and the temperature of the internal heat source of the combination electrical appliance is an unknown variable. Set the input vector to IN, then IN=[T2, L, P, T, H, V1, V2], and the output result is OUT, then OUT=T1; S7, importing the data set in step S6 into the algorithm for training, calculating through a neural network, or obtaining a prediction function f through curve fitting; S8. At the detection site, when the combination electrical appliance shell is found to be hot, record the maximum shell temperature as t2, record the distance l between the internal conductor of the combination electrical appliance and the shell, record the combination electrical appliance pressure as p, record the ambient temperature t, record the ambient humidity h, record the wind speed v1, record the wind direction v2, and form an input vector in=[t2, l, p, t, h, v1, v2], then the internal heat source temperature t1=f(in) can be predicted.

2. A method for predicting internal heating temperature of a combined electrical appliance as claimed in claim 1, characterized in that: In the step S2, instead of charging SF6 gas into the combined electrical model, SF6 / N2 mixed gas may be charged into the combined electrical model, and the SF6 gas pressure P1 and the N2 pressure P2 are recorded, and P=[P1, P2].

3. A method for predicting internal heating temperature of a combined electrical appliance as claimed in claim 1, characterized in that: After step S8, the method further includes: Based on the predicted internal heat source temperature, that is, the internal heating temperature of the combination electrical appliance, the severity of the defect is further determined according to the regulations, the defect is graded, and power outages are carried out to eliminate the defect based on different defect grades.

4. A method for predicting internal heating temperature of a combined electrical appliance as claimed in claim 3, characterized in that: The defect classification includes general defects, serious defects and critical defects.

Images