A method, device, storage medium and equipment for transformer overload warning

Abstract

An embodiment of the present invention discloses a method, device, storage medium and equipment for transformer overload warning. The method includes: building a deep learning model based on the oil chromatogram data, hot spot temperature distribution, and impedance data of different types of loads of the transformer under different load rates; collecting the current oil chromatogram data of the transformer and inputting it into the deep learning model to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer; determining the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determining the load warning threshold according to the load capacity; when the target load rate is greater than the load warning threshold, determining the load shedding information according to the target impedance data of different types of loads, and outputting the load shedding information and warning signal, so as to accurately warn the overload state of the transformer, which is beneficial to timely handle the overload situation to ensure the safe and stable operation of the transformer.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and particularly to a transformer overload warning method, device, storage medium and equipment. Background Art

[0002] In a power system, a transformer may cause large-area power rationing or power outage in the power grid due to limited load capacity or shutdown due to overload faults, resulting in large economic losses and adverse social impacts. To maintain the safe and stable operation of the power system, a series of measures need to be taken to minimize the occurrence of accidents. For example, the normal load rate of the transformer is limited to less than 80%. However, this will cause the actual load level of the transformer to be much lower than the allowable value of its load capacity, reducing the operating economic index and causing serious waste of resources. Therefore, a reasonable and effective method is needed to evaluate the load capacity of the transformer and to monitor the load rate of the transformer in real time, so as to warn of the overload state of the transformer.

[0003] Currently, generally, the load rate of the transformer is evaluated by collecting the hot spot temperature of the winding. However, due to the large error between the collected hottest winding temperature and the actual hottest temperature, and the change in the chemical properties of some winding materials, the measured load rate will have a large error, and it is impossible to accurately warn of the overload state of the transformer. Summary of the Invention

[0004] Based on this, it is necessary to address the above problems and propose a transformer overload warning method, device, storage medium and equipment to accurately warn of the overload state of the transformer, which is beneficial to timely handling of overload situations to ensure the safe and stable operation of the transformer.

[0005] To achieve the above object, the present invention provides a transformer overload warning method in a first aspect. The method includes:

[0006] Collect the oil chromatogram data of the transformer at different load rates;

[0007] Based on the finite element method and the finite element volume method, obtain the hot spot temperature distribution of the transformer at different load rates;

[0008] Obtain the impedance data of different types of loads of the transformer at different load rates;

[0009] Build a deep learning model according to the oil chromatogram data, the hot spot temperature distribution, and the impedance data of different types of loads of the transformer at different load rates;

[0010] Collect the current oil chromatographic data of the transformer, and input the current oil chromatographic data into the deep learning model to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer;

[0011] Determine the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determine the load warning threshold according to the load capacity;

[0012] If the target load rate is greater than the load warning threshold, determine the load shedding information according to the target impedance data of different types of loads, and output the load shedding information and warning signal.

[0013] Optionally, both the oil chromatographic data and the current oil chromatographic data are concentration data of characteristic gases dissolved in the transformer oil of the transformer;

[0014] The characteristic gases include one or more of hydrogen, carbon monoxide, methane, ethylene, acetylene, ethane, and carbon dioxide.

[0015] Optionally, obtaining the hot spot temperature distribution of the transformer at different load rates based on the finite element method and the finite element volume method includes:

[0016] Based on the finite element method and the finite element volume method, build a three-dimensional finite element model of the transformer at different load rates;

[0017] Input the material parameter information, temperature field, and boundary conditions of the flow field of the transformer into the three-dimensional finite element model in sequence to obtain the hot spot temperature distribution of the transformer at different load rates.

[0018] Optionally, building a deep learning model according to the oil chromatographic data, the hot spot temperature distribution, and the impedance data of different types of loads of the transformer at different load rates includes:

[0019] Determine the first functional relationship between the load rate and the oil chromatographic data according to the oil chromatographic data at different load rates;

[0020] Determine the second functional relationship between the oil chromatographic data and the hot spot temperature distribution according to the oil chromatographic data and the hot spot temperature distribution at different load rates;

[0021] Determine the third functional relationship between the load rate and the impedance data of different types of loads according to the impedance data of different types of loads at different load rates;

[0022] Build the deep learning model according to the first functional relationship, the second functional relationship, and the third functional relationship.

[0023] Optionally, inputting the current oil chromatographic data into the deep learning model to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer includes:

[0024] Inputting the current oil chromatographic data into the deep learning model, obtaining the target load rate according to the current oil chromatographic data and the first functional relationship, obtaining the target hot spot temperature distribution according to the current oil chromatographic data and the second functional relationship, and obtaining the target impedance data of different types of loads according to the target load rate and the third functional relationship.

[0025] Optionally, the method further includes:

[0026] Obtaining historical load rate data and historical hot spot temperature distribution data of the transformer at different load rates;

[0027] Determining a critical load rate according to the historical load rate data and the historical highest temperature data;

[0028] Taking the critical load rate as the load warning threshold.

[0029] Optionally, the method further includes:

[0030] If the target load rate is less than or equal to the load warning threshold, outputting information indicating that the transformer is operating normally.

[0031] To achieve the above object, the present invention provides a transformer overload warning device in a second aspect. The device includes:

[0032] An oil chromatographic data acquisition module for acquiring oil chromatographic data of the transformer at different load rates;

[0033] A hot spot temperature acquisition module for obtaining the hot spot temperature distribution of the transformer at different load rates based on the finite element method and the finite element volume method;

[0034] An impedance data acquisition module for acquiring impedance data of different types of loads of the transformer at different load rates;

[0035] A model building module for building a deep learning model according to the oil chromatographic data, the hot spot temperature distribution, and the impedance data of different types of loads of the transformer at different load rates;

[0036] A target data acquisition module for acquiring the current oil chromatographic data of the transformer and inputting the current oil chromatographic data into the deep learning model to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer;

[0037] A threshold determination module, configured to determine the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determine a load warning threshold according to the load capacity;

[0038] An information output module, configured to, if the target load rate is greater than the load warning threshold, determine load shedding information according to the target impedance data of different types of loads, and output the load shedding information and a warning signal.

[0039] To achieve the above object, in a third aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the processor is caused to execute the steps of the method described in the first aspect.

[0040] To achieve the above object, in a fourth aspect of the present invention, there is provided a computer device including a memory and a processor, the memory storing a computer program, and when the computer program is executed by the processor, the processor is caused to execute the steps of the method described in the first aspect.

[0041] Adopting the embodiment of the present invention has the following beneficial effects: collecting the oil chromatographic data of the transformer under different load rates; obtaining the hot spot temperature distribution of the transformer under different load rates based on the finite element method and the finite element volume method; obtaining the impedance data of different types of loads of the transformer under different load rates; building a deep learning model according to the oil chromatographic data, hot spot temperature distribution, and impedance data of different types of loads of the transformer under different load rates; collecting the current oil chromatographic data of the transformer and inputting the current oil chromatographic data into the deep learning model to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer; determining the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determining the load warning threshold according to the load capacity; if the target load rate is greater than the load warning threshold, determining the load shedding information according to the target impedance data of different types of loads, and outputting the load shedding information and a warning signal. The above method builds a deep learning model according to the oil chromatographic data, hot spot temperature distribution, and impedance data of different types of loads of the transformer under different load rates, so that subsequently, only by collecting the current oil chromatographic data of the transformer and inputting the current oil chromatographic data into the deep learning model, the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer can be obtained, thereby determining the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determining the load warning threshold according to the load capacity. When the target load rate is greater than the load warning threshold, determining the load shedding information according to the target impedance data of different types of loads, and outputting the load shedding information and a warning signal to realize accurate warning of the overload state of the transformer, and by outputting the load shedding information, it is beneficial to timely process the overload situation to ensure the safe and stable operation of the transformer. Description of the Drawings

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0043] Among them:

[0044] Figure 1 is a schematic flowchart of a transformer overload warning method in an embodiment of the present application;

[0045] Figure 2 is a schematic diagram of the first functional relationship between the characteristic gas and the concentration of acetylene gas in an embodiment of the present application;

[0046] Figure 3Schematic diagram of the fourth functional relationship in the embodiments of the present application;

[0047] Figure 4 Schematic structural diagram of a transformer overload warning device in the embodiments of the present application;

[0048] Figure 5 Internal structure diagram of a computer device in one embodiment. Detailed implementation manners

[0049] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0050] Please refer to Figure 1 , which is a schematic flowchart of a transformer overload warning method in the embodiments of the present application. The method includes:

[0051] Step 110: Collect the oil chromatographic data of the transformer at different load rates.

[0052] Among them, the oil chromatographic data can be the concentration data of the characteristic gases dissolved in the transformer oil of the transformer, or the gas production rate data of the characteristic gases dissolved in the transformer oil of the transformer. The oil chromatographic data in the embodiments of the present application uses the concentration data of the characteristic gases dissolved in the transformer oil of the transformer. Of course, other data obtained based on the oil chromatographic data of the transformer can also be used, which is not limited here.

[0053] It should be noted that collecting the oil chromatographic data of the transformer at different load rates is to obtain the oil chromatographic data of the transformer at different load rates, so as to facilitate determining the situation of the oil chromatographic data of the transformer at different load rates.

[0054] Step 120: Obtain the hot spot temperature distribution of the transformer at different load rates based on the finite element method and the finite element volume method.

[0055] It should be noted that based on the finite element method and the finite element volume method, a three-dimensional finite element model of the transformer at different load rates can be built, and the material parameter information, temperature field and flow field boundary conditions of the transformer are input into the three-dimensional finite element model in turn, so as to obtain the hot spot temperature distribution of the transformer at different load rates. It can be understood that in the prior art, the process of establishing a three-dimensional finite element model and obtaining the hot spot temperature distribution of the transformer based on the finite element method and the finite element volume method has been introduced in detail, and will not be elaborated here.

[0056] Step 130: Obtain the impedance data of different types of loads of the transformer under different load rates.

[0057] It should be noted that the impedance data is related to the type of load, and the number of types of different loads connected to the transformer under different load rates is different. Therefore, when obtaining the load rate of the transformer, the number of types of different loads of the transformer currently can be determined, and the impedance data of the current different types of loads can be obtained.

[0058] Step 140: Build a deep learning model based on the oil chromatographic data, hot spot temperature distribution, and impedance data of different types of loads of the transformer under different load rates.

[0059] It should be noted that for the construction of the deep learning model, the first functional relationship between the load rate and the oil chromatographic data is determined according to the oil chromatographic data under different load rates, the second functional relationship between the oil chromatographic data and the hot spot temperature distribution is determined according to the oil chromatographic data and the hot spot temperature distribution under different load rates, and the third functional relationship between the load rate and the impedance data of different types of loads is determined according to the impedance data of different types of loads under different load rates. Thus, the deep learning model is built based on the first functional relationship, the second functional relationship, and the third functional relationship. Of course, various transformations can also be carried out. For example, determining the second functional relationship between the oil chromatographic data and the hot spot temperature distribution according to the oil chromatographic data and the hot spot temperature distribution under different load rates can be replaced by determining the fourth functional relationship between the load rate and the hot spot temperature distribution according to the hot spot temperature distribution under different load rates. It can be understood that since the first functional relationship between the load rate and the oil chromatographic data has been obtained, when the oil chromatographic data of the transformer is collected, the load rate can be obtained according to the oil chromatographic data and the first functional relationship, and then the hot spot temperature distribution can be obtained according to the load rate and the fourth functional relationship; determining the third functional relationship between the load rate and the impedance data of different types of loads according to the impedance data of different types of loads under different load rates can be replaced by determining the fifth functional relationship between the oil chromatographic data and the impedance data of different types of loads according to the oil chromatographic data and the impedance data of different types of loads under different load rates. It can be understood that when the oil chromatographic data of the transformer is collected, the impedance data of different types of loads can be obtained according to the oil chromatographic data and the fifth functional relationship.

[0060] Step 150: Collect the current oil chromatographic data of the transformer and input the current oil chromatographic data into the deep learning model to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer.

[0061] Among them, the current oil chromatographic data can be the concentration data of characteristic gases dissolved in the transformer oil of the transformer, or the gas production rate data of the characteristic gases dissolved in the transformer oil of the transformer. In the embodiments of the present application, the current oil chromatographic data adopted is the concentration data of the characteristic gases dissolved in the transformer oil of the transformer. Of course, other data obtained based on the current oil chromatographic data of the transformer can also be adopted, which is not limited here.

[0062] It should be noted that since the established deep learning model has a first functional relationship between the load rate and the oil chromatographic data, a second functional relationship between the oil chromatographic data and the hot spot temperature distribution, and a third functional relationship between the load rate and the impedance data of different types of loads, when the current oil chromatographic data is input into the deep learning model, the target load rate can be obtained according to the current oil chromatographic data and the first functional relationship, the target hot spot temperature distribution can be obtained according to the current oil chromatographic data and the second functional relationship, and the target impedance data of different types of loads can be obtained according to the target load rate and the third functional relationship.

[0063] Step 160: Determine the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determine the load warning threshold according to the load capacity.

[0064] Among them, the standard temperature index of the transformer is related to the national standard regulations and industry standard regulations. That is to say, it can be understood that the standard temperature index of the transformer can be the national standard regulations or the industry standard regulations.

[0065] It should be noted that according to the target hot spot temperature distribution and the standard temperature index of the transformer, the load capacity of the transformer can be evaluated, and thus the load warning threshold can be determined according to the evaluated load capacity. Generally, if the load capacity is L, the value range of the obtained load warning threshold is 0.8L to 0.9L.

[0066] Step 170: If the target load rate is greater than the load warning threshold, determine the load shedding information according to the target impedance data of different types of loads, and output the load shedding information and the warning signal.

[0067] It should be noted that when the target load rate is greater than the load warning threshold, it indicates that the transformer is in an overloaded state at this time. Therefore, a warning signal needs to be output to prompt the operator; further, in addition to outputting the warning signal, load shedding information also needs to be given. It can be understood that when the operator receives the warning signal, they do not know which loads need to be shed, but they cannot directly shut down the transformer. Therefore, the load shedding information needs to be determined according to the target impedance data of different types of loads, so that when the warning signal is output, the load shedding information is output together. Among them, the warning signal and the load shedding information can be displayed through a display screen or voice prompted through a speaker, etc.

[0068] In an embodiment of the present application, a deep learning model is built based on the oil chromatographic data, hot spot temperature distribution, and impedance data of different types of loads of a transformer under different load rates. Subsequently, only by collecting the current oil chromatographic data of the transformer and inputting the current oil chromatographic data into the deep learning model, the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer can be obtained. Then, the load capacity of the transformer is determined based on the target hot spot temperature distribution and the standard temperature index of the transformer, and the load warning threshold is determined based on the load capacity. When the target load rate is greater than the load warning threshold, the load shedding information is determined based on the target impedance data of different types of loads, and the load shedding information and warning signal are output to accurately warn the overload state of the transformer. Moreover, by outputting the load shedding information, it is beneficial to promptly handle the overload situation to ensure the safe and stable operation of the transformer.

[0069] In a feasible implementation manner, in steps 110 and 150, both the oil chromatographic data and the current oil chromatographic data are the concentration data of the characteristic gases dissolved in the transformer oil of the transformer; the characteristic gases include one or more of hydrogen, carbon monoxide, methane, ethylene, acetylene, ethane, and carbon dioxide.

[0070] It should be noted that the oil chromatographic data and the current oil chromatographic data can be the concentration data of the characteristic gases dissolved in the transformer oil of the transformer, or the gas production rate data of the characteristic gases dissolved in the transformer oil of the transformer. In the embodiments of the present application, the oil chromatographic data and the current oil chromatographic data adopt the concentration data of the characteristic gases dissolved in the transformer oil of the transformer. Of course, other data obtained based on the oil chromatographic data and the current oil chromatographic data of the transformer can also be adopted, which is not limited herein.

[0071] In this embodiment, preferably, both the oil chromatographic data and the current oil chromatographic data adopt the concentration data of the characteristic gases dissolved in the transformer oil of the transformer, and one or more of the characteristic gases such as hydrogen, carbon monoxide, methane, ethylene, acetylene, ethane, and carbon dioxide can be selected according to the actual situation, so as to facilitate warning the overload state of the transformer accurately by collecting the concentration data of the characteristic gases dissolved in the transformer oil of the transformer. Moreover, by outputting the load shedding information, it is beneficial to promptly handle the overload situation to ensure the safe and stable operation of the transformer.

[0072] In a feasible implementation manner, in step 120, based on the finite element method and the finite element volume method, the hot spot temperature distribution of the transformer under different load rates is obtained, including: based on the finite element method and the finite element volume method, a three-dimensional finite element model of the transformer under different load rates is built; the material parameter information of the transformer, and the boundary conditions of the temperature field and the flow field are sequentially input into the three-dimensional finite element model to obtain the hot spot temperature distribution of the transformer under different load rates.

[0073] It should be noted that in the prior art, the process of building a three-dimensional finite element model and obtaining the hot spot temperature distribution of the transformer based on the finite element method and the finite element volume method has been introduced in detail, and will not be elaborated here.

[0074] In the embodiment of the present application, by using the finite element method and the finite element volume method to build a three-dimensional finite element model under different load rates and obtain the hot spot temperature distribution of the transformer under different load rates, it is convenient to subsequently obtain the target hot spot temperature distribution (current hot spot temperature distribution) of the transformer through a deep learning model, so as to determine the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, so as to accurately warn the overload state of the transformer, and by outputting load shedding information, it is beneficial to timely handle the overload situation to ensure the safe and stable operation of the transformer, and the hot spot temperature distribution of the transformer under different load rates obtained by using the finite element method and the finite element volume method is accurate, and can accurately warn the overload state of the transformer.

[0075] In a feasible implementation manner, in step 140, a deep learning model is built according to the oil chromatogram data, the hot spot temperature distribution, and the impedance data of different types of loads of the transformer under different load rates, including: determining the first functional relationship between the load rate and the oil chromatogram data according to the oil chromatogram data under different load rates; determining the second functional relationship between the oil chromatogram data and the hot spot temperature distribution according to the oil chromatogram data and the hot spot temperature distribution under different load rates; determining the third functional relationship between the load rate and the impedance data of different types of loads according to the impedance data of different types of loads under different load rates; building a deep learning model according to the first functional relationship, the second functional relationship, and the third functional relationship.

[0076] It should be noted that for the construction of the deep learning model, in addition to the implementation methods in the above embodiments, various transformations can be carried out. That is, in another feasible implementation method, the first functional relationship between the load rate and the oil chromatographic data can be determined according to the oil chromatographic data at different load rates; the fourth functional relationship between the load rate and the hot spot temperature distribution can be determined according to the hot spot temperature distribution at different load rates; the fifth functional relationship between the oil chromatographic data and the impedance data of different types of loads can be determined according to the oil chromatographic data at different load rates and the impedance data of different types of loads; the deep learning model can be constructed according to the first functional relationship, the fourth functional relationship, and the fifth functional relationship. Of course, there can be other transformation methods, which will not be listed one by one here.

[0077] Furthermore, it should be noted that for another implementation method, the fourth functional relationship between the load rate and the hot spot temperature distribution is determined according to the hot spot temperature distribution at different load rates. It can be understood that since the first functional relationship between the load rate and the oil chromatographic data has been obtained, when the oil chromatographic data of the transformer is collected, the load rate can be obtained according to the oil chromatographic data and the first functional relationship, and then the hot spot temperature distribution can be obtained according to the load rate and the fourth functional relationship; the fifth functional relationship between the oil chromatographic data and the impedance data of different types of loads is determined according to the oil chromatographic data at different load rates and the impedance data of different types of loads. It can be understood that when the oil chromatographic data of the transformer is collected, the impedance data of different types of loads can be obtained according to the oil chromatographic data and the fifth functional relationship.

[0078] For example, for the first functional relationship between the load rate and the oil chromatographic data in the above embodiments, taking the gas concentration of the characteristic gas as acetylene gas as an example, please refer to Figure 2 , which is a schematic diagram of the first functional relationship between the load rate and the acetylene gas concentration of the characteristic gas in the embodiments of the present application, and the fourth functional relationship between the load rate and the hot spot temperature distribution. Please refer to Figure 3 , which is a schematic diagram of the fourth functional relationship in the embodiments of the present application.

[0079] In the embodiments of the present application, by obtaining the first functional relationship between the load rate and the oil chromatographic data, the second functional relationship between the oil chromatographic data and the hot spot temperature distribution, and the third functional relationship between the load rate and the impedance data of different types of loads, and constructing a deep learning model according to the first functional relationship, the second functional relationship, and the third functional relationship, it is only necessary to collect the current oil chromatographic data of the transformer and input the current oil chromatographic data into the deep learning model in the future, so as to obtain the target hot spot temperature distribution, the target load rate, and the target impedance data of different types of loads of the transformer, so as to accurately warn the overload state of the transformer, and by outputting the load shedding information, it is beneficial to timely handle the overload situation to ensure the safe and stable operation of the transformer.

[0080] In a feasible implementation, in step 150, the current oil chromatogram data is input into the deep learning model to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer, including: inputting the current oil chromatogram data into the deep learning model, obtaining the target load rate according to the current oil chromatogram data and the first functional relationship, obtaining the target hot spot temperature distribution according to the current oil chromatogram data and the second functional relationship, and obtaining the target impedance data of different types of loads according to the target load rate and the third functional relationship.

[0081] It should be noted that since the established deep learning model has the first functional relationship between the load rate and the oil chromatogram data, the second functional relationship between the oil chromatogram data and the hot spot temperature distribution, and the third functional relationship between the load rate and the impedance data of different types of loads, when the current oil chromatogram data is input into the deep learning model, the target load rate can be obtained according to the current oil chromatogram data and the first functional relationship, the target hot spot temperature distribution can be obtained according to the current oil chromatogram data and the second functional relationship, and the target impedance data of different types of loads can be obtained according to the target load rate and the third functional relationship.

[0082] In the embodiment of the present application, by inputting the current oil chromatogram data currently collected by the transformer into the deep learning model, the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer are obtained, so as to determine the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determine the load warning threshold according to the load capacity. When the target load rate is greater than the load warning threshold, the load shedding information is determined according to the target impedance data of different types of loads, and the load shedding information and warning signal are output, so as to accurately warn the overload state of the transformer, and by outputting the load shedding information, it is beneficial to timely process the overload situation to ensure the safe and stable operation of the transformer.

[0083] In a feasible implementation, the method in the above embodiment further includes: obtaining the historical load rate data and historical hot spot temperature distribution data of the transformer at different load rates; determining the critical load rate according to the historical load rate data and historical highest temperature data; using the critical load rate as the load warning threshold.

[0084] It should be noted that the embodiment of the present application also provides another way to determine the load warning threshold, that is, the historical load rate data and historical hot spot temperature distribution data of the transformer at different load rates can also be obtained, so as to determine the critical load rate according to the historical load rate data and historical highest temperature data, and use the critical load rate as the load warning threshold.

[0085] Further, it should be noted that the historical load rate data and historical hot spot temperature distribution data of the transformer under different load rates are obtained when the transformer is between the fault state and the normal state. It can be understood that the historical load rate data and historical hot spot temperature distribution data of the transformer under different load rates can be the critical points of the transformer about to fail. Therefore, the critical load rate can be determined according to the historical load rate data and the historical highest temperature data at the critical point, and the critical load rate can be used as the load warning threshold.

[0086] In the embodiment of the present application, by providing another way to determine the load warning threshold, the backup of the load warning threshold can be realized. That is, when the load warning threshold cannot be determined according to the load capacity or in a situation where the load capacity cannot be obtained, the overloading state of the transformer in this embodiment can also be warned, so as to accurately warn the overloading state of the transformer. And by outputting the load shedding information, it is beneficial to timely handle the overloading situation to ensure the safe and stable operation of the transformer.

[0087] In a feasible implementation manner, the method in the above embodiment further includes: if the target load rate is less than or equal to the load warning threshold, output the information that the transformer is operating normally.

[0088] It should be noted that outputting the information that the transformer is operating normally is also to prompt the operator, which can prompt the operator that the overloading warning of the transformer is normal and the transformer is in a normal operating state. Among them, the information that the transformer is operating normally can be displayed through a display screen or prompted by voice through a speaker, etc. Of course, in order not to affect the warning of the transformer during overloading, generally the information that the transformer is operating normally is prompted by an indicator light.

[0089] In the embodiment of the present application, by outputting the information that the transformer is operating normally when the target load rate is less than or equal to the load warning threshold, the operator can be prompted that the overloading warning of the transformer is normal and the transformer is in a normal operating state.

[0090] Please refer to Figure 4 , which is a schematic structural diagram of a transformer overloading warning device in the embodiment of the present application. The device 410 includes:

[0091] An oil chromatogram data acquisition module 411, configured to acquire the oil chromatogram data of the transformer under different load rates;

[0092] A hot spot temperature acquisition module 412, configured to obtain the hot spot temperature distribution of the transformer under different load rates based on the finite element method and the finite element volume method;

[0093] An impedance data acquisition module 413 is configured to acquire impedance data of different types of loads of a transformer under different load rates;

[0094] A model construction module 414 is configured to construct a deep learning model based on the oil chromatogram data, hot spot temperature distribution, and impedance data of different types of loads of the transformer under different load rates;

[0095] A target data acquisition module 415 is configured to collect the current oil chromatogram data of the transformer and input the current oil chromatogram data into the deep learning model to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer;

[0096] A threshold determination module 416 is configured to determine the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determine the load warning threshold according to the load capacity;

[0097] An information output module 417 is configured to, if the target load rate is greater than the load warning threshold, determine the load shedding information according to the target impedance data of different types of loads, and output the load shedding information and a warning signal.

[0098] In the embodiment of the present application, the relevant content of the above-mentioned oil chromatogram data acquisition module 411, hot spot temperature acquisition module 412, impedance data acquisition module 413, model construction module 414, target data acquisition module 415, threshold determination module 416, and information output module 417 can be referred to Figure 1 the content in the shown embodiment, and details are not described herein.

[0099] In the embodiment of the present application, by constructing a deep learning model based on the oil chromatogram data, hot spot temperature distribution, and impedance data of different types of loads of the transformer under different load rates, it is only necessary to collect the current oil chromatogram data of the transformer and input the current oil chromatogram data into the deep learning model in the follow-up, so as to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer, thereby determining the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determining the load warning threshold according to the load capacity. When the target load rate is greater than the load warning threshold, determine the load shedding information according to the target impedance data of different types of loads, and output the load shedding information and a warning signal, so as to accurately warn the overload state of the transformer, and by outputting the load shedding information, it is beneficial to timely process the overload situation to ensure the safe and stable operation of the transformer.

[0100] In the embodiment of the present application, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the processor is caused to execute a transformer overload warning method in the above method embodiment.

[0101] In one embodiment, a device is proposed, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to execute a transformer overload warning method in the above method embodiment.

[0102] Figure 5 The internal structure diagram of a computer device in one embodiment is shown. The computer device may specifically be a terminal, a server, or a gateway. As Figure 5 shown, the computer device includes a processor, a memory, and a network interface connected through a system bus.

[0103] Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can be caused to implement each step in the above method embodiment. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can be caused to execute each step in the above method embodiment. Those skilled in the art can understand that Figure 5 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0104] Those of ordinary skill in the art can understand that all or part of the processes of implementing the above method embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it may include the processes of the above method embodiments.

[0105] Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application may include non-volatile and / or volatile memories. The non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. The volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0106] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0107] The above-described embodiments merely represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for warning of transformer overload, characterized in that, The method includes: Collecting oil chromatographic data of a transformer at different load rates; Obtaining the hot spot temperature distribution of the transformer at different load rates based on the finite element method and the finite element volume method; Obtaining impedance data of different types of loads of the transformer at different load rates; Constructing a deep learning model according to the oil chromatographic data, the hot spot temperature distribution, and the impedance data of different types of loads of the transformer at different load rates; Collecting the current oil chromatographic data of the transformer and inputting the current oil chromatographic data into the deep learning model to obtain the target hot spot temperature distribution, the target load rate, and the target impedance data of different types of loads of the transformer; Determining the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determining a load warning threshold according to the load capacity; If the target load rate is greater than the load warning threshold, determining load shedding information according to the target impedance data of different types of loads, and outputting the load shedding information and a warning signal.

2. The method according to claim 1, wherein Both the oil chromatographic data and the current oil chromatographic data are concentration data of characteristic gases dissolved in the transformer oil of the transformer; The characteristic gases include one or more of hydrogen, carbon monoxide, methane, ethylene, acetylene, ethane, and carbon dioxide.

3. The method according to claim 1, characterized in that, The obtaining the hot spot temperature distribution of the transformer at different load rates based on the finite element method and the finite element volume method includes: Constructing a three-dimensional finite element model of the transformer at different load rates based on the finite element method and the finite element volume method; Sequentially inputting the material parameter information of the transformer and the boundary conditions of the temperature field and the flow field into the three-dimensional finite element model to obtain the hot spot temperature distribution of the transformer at different load rates.

4. The method according to claim 1, wherein The constructing a deep learning model according to the oil chromatographic data, the hot spot temperature distribution, and the impedance data of different types of loads of the transformer at different load rates includes: Determining a first functional relationship between the load rate and the oil chromatographic data according to the oil chromatographic data at different load rates; Determining a second functional relationship between the oil chromatographic data and the hot spot temperature distribution according to the oil chromatographic data and the hot spot temperature distribution at different load rates; Determining a third functional relationship between the load rate and the impedance data of different types of loads according to the impedance data of different types of loads at different load rates; Constructing the deep learning model according to the first functional relationship, the second functional relationship, and the third functional relationship.

5. The method according to claim 4, wherein The inputting the current oil chromatographic data into the deep learning model to obtain the target hot spot temperature distribution, the target load rate, and the target impedance data of different types of loads of the transformer includes: Inputting the current oil chromatographic data into the deep learning model, obtaining the target load rate according to the current oil chromatographic data and the first functional relationship, obtaining the target hot spot temperature distribution according to the current oil chromatographic data and the second functional relationship, and obtaining the target impedance data of different types of loads according to the target load rate and the third functional relationship.

6. The method according to claim 1, characterized in that, The method further includes: Obtain the historical load rate data and historical hot spot temperature distribution data of the transformer at different load rates; Determine the critical load rate according to the historical load rate data and historical maximum temperature data; Use the critical load rate as the load warning threshold.

7. The method according to claim 1, characterized in that The method further includes: If the target load rate is less than or equal to the load warning threshold, output information indicating normal operation of the transformer.

8. An overloading early warning device for a transformer, characterized in that, The device includes: An oil chromatogram data acquisition module for acquiring the oil chromatogram data of the transformer at different load rates; A hot spot temperature acquisition module for obtaining the hot spot temperature distribution of the transformer at different load rates based on the finite element method and the finite element volume method; An impedance data acquisition module for acquiring the impedance data of different types of loads of the transformer at different load rates; A model building module for building a deep learning model according to the oil chromatogram data, the hot spot temperature distribution, and the impedance data of different types of loads of the transformer at different load rates; A target data acquisition module for acquiring the current oil chromatogram data of the transformer and inputting the current oil chromatogram data into the deep learning model to obtain the target hot spot temperature distribution, target load rate, and target impedance data of different types of loads of the transformer; A threshold determination module for determining the load capacity of the transformer according to the target hot spot temperature distribution and the standard temperature index of the transformer, and determining the load warning threshold according to the load capacity; An information output module for, if the target load rate is greater than the load warning threshold, determining load shedding information according to the target impedance data of different types of loads and outputting the load shedding information and a warning signal.

9. A computer-readable storage medium, characterized in that, Stores a computer program, which when executed by a processor causes the processor to execute the steps of the method according to any one of claims 1 to 7.

10. A computer device, characterized in that, Includes a memory and a processor, the memory stores a computer program, which when executed by the processor causes the processor to execute the steps of the method according to any one of claims 1 to 7.

Images