A Transformer Thermal Fault Identification Method and System Based on Improved Relative Temperature Difference
By constructing an empirical database of absolute temperature of load current and a thermal image feature database, and combining infrared thermal imaging technology, the relative temperature difference method was improved, which solved the problem of neglecting the load current factor in transformer thermal fault analysis. This enabled automatic identification and accurate judgment of transformer thermal faults, thereby improving power supply reliability.
Patent Information
- Application Number
- CN202310594213.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-23
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-05-23
AI Technical Summary
The existing relative temperature difference method ignores the load current factor in transformer thermal fault analysis, leading to misjudgment and unnecessary power outages, thus reducing power supply reliability.
By combining the load current with the improved relative temperature difference method, an empirical database of the absolute temperature of the heating point and a thermal image feature database are constructed. Infrared thermal imaging technology is used, and the results of thermal fault judgment are corrected by the load current. A dual triggering mechanism is adopted to identify transformer thermal faults.
It enables automatic identification and accurate judgment of transformer thermal faults, avoids misjudgment, and improves the level of intelligent operation and maintenance of transformers.
Smart Images

Figure CN116626420B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of transformer thermal fault identification technology, and in particular to a transformer thermal fault identification method and system based on an improved relative temperature difference method. Background Technology
[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.
[0003] Due to the complex operating environment and long operating time, transformers can develop thermal defects of varying degrees in various equipment and lines. Non-contact infrared thermal imaging technology is the best choice for detecting thermal defects in equipment. Through temperature detection, image analysis, and intelligent diagnosis, it allows workers to promptly identify potential safety hazards and defects from a safe distance.
[0004] Currently, the commonly used method for transformer thermal fault analysis and location based on infrared thermal imaging is the relative temperature difference method. The relative temperature difference is the percentage of the temperature rise difference between two corresponding measuring points to the temperature rise of the higher temperature point. The biggest drawback of using the relative temperature difference method for transformer thermal fault analysis and location is that it ignores factors such as load current, blindly follows the criterion that "a relative temperature difference greater than 95% indicates an urgent fault," and exaggerates certain faults.
[0005] For current-heating equipment such as transformers, when the load current approaches the equipment's rated current, the hot spot temperature no longer exhibits a linear relationship with the flowing current. Therefore, under high load current conditions, the relative temperature difference method will yield a value that is larger than the actual value. This could lead to misjudgment of defects, unnecessary power outages, and reduced power supply reliability. Thus, relying solely on the relative temperature difference method, which is based on linear principles, for defect identification is overly simplistic and will produce biased results. Summary of the Invention
[0006] To address the aforementioned issues, this invention proposes a transformer thermal fault identification method and system based on an improved relative temperature difference method. By combining the load current-improved relative temperature difference method, it achieves automatic identification of transformer thermal faults and accurate determination of the defect level of transformer thermal faults.
[0007] To achieve the above objectives, the present invention adopts the following technical solution:
[0008] In a first aspect, the present invention provides a transformer thermal fault identification method based on an improved relative temperature difference method, comprising:
[0009] Based on historical transformer operating data, an empirical database of absolute temperatures of heating points corresponding to load currents and a thermal imaging feature database are constructed.
[0010] Obtain infrared thermal images of various parts of the transformer and their corresponding actual temperatures, as well as the current load current;
[0011] The actual temperature of each part is compared with the trigger temperature threshold, and the infrared thermal image of each part is compared with the thermal image feature library. When the comparison results of both meet the trigger conditions, a thermal fault warning is triggered.
[0012] The empirical value of absolute temperature is obtained from the empirical database of absolute temperature of heating point based on the current load current.
[0013] If the actual temperature is less than the absolute temperature empirical value, the initial alarm level is determined based on the absolute temperature empirical value, and the initial alarm level is corrected based on the actual temperature at the maximum load current within the set time period and the threshold corresponding to the initial alarm level.
[0014] If the actual temperature is not less than the empirical value of absolute temperature, the alarm level is determined based on the actual temperature.
[0015] As an alternative implementation, the triggering condition is: simultaneously satisfying that the actual temperature is greater than the trigger temperature threshold and that the infrared thermal image matches the corresponding data in the thermal image feature library.
[0016] As an optional implementation, the process of comparing the infrared thermal images of each part with the thermal image feature library includes: labeling the infrared thermal images in the thermal image feature library and the detected infrared thermal images with part names respectively, and matching the infrared thermal images of the corresponding parts according to the labeled names; matching the detected infrared thermal images with the infrared thermal images in the thermal image feature library one by one according to the form of individual pixels, and if the infrared thermal image matches the relevant infrared thermal image in the thermal image feature library, it means that the triggering condition is met.
[0017] As an optional implementation, the alarm levels are divided into general defects, severe defects, and emergency defects; wherein, the threshold of each alarm level is set according to the relative temperature difference. If the actual temperature is less than the empirical value of the absolute temperature, the relative temperature difference is calculated according to the empirical value of the absolute temperature of each heat point, and the relative temperature difference is compared with the threshold of each alarm level to determine the initial alarm level.
[0018] As an alternative implementation, the process of revising the initial alarm level includes: calculating the relative temperature difference based on the actual temperature at the maximum load current and comparing it with the threshold corresponding to the initial alarm level.
[0019] As an alternative implementation, the process of correcting the initial alarm level includes: if the relative temperature difference corresponding to the actual temperature at the maximum load current is within the threshold range of the initial alarm level, the final alarm level remains unchanged and is still the initial alarm level; if it exceeds the threshold of the initial alarm level, the initial alarm level is increased by 1 level.
[0020] As an alternative implementation, infrared thermograms of the transformer's tank, oil conservator, radiator, and bushing are used as key parameters for identifying transformer thermal faults.
[0021] Secondly, the present invention provides a transformer thermal fault identification system based on an improved relative temperature difference method, comprising:
[0022] The database construction module is configured to build an empirical database of absolute temperatures of heating points corresponding to load currents and a thermal imaging feature library based on historical transformer operating data.
[0023] The data acquisition module is configured to acquire infrared thermal images of various parts of the transformer and their corresponding actual temperatures, as well as the current load current.
[0024] The early warning triggering module is configured to compare the actual temperature of each part with the trigger temperature threshold, and compare the infrared thermal image of each part with the thermal image feature library. When the comparison results of both meet the triggering conditions, a thermal fault early warning is triggered.
[0025] The temperature experience value acquisition module is configured to acquire the absolute temperature experience value from the absolute temperature experience database of the heating point based on the current load current.
[0026] The first-level judgment module is configured to determine the initial alarm level based on the absolute temperature empirical value if the actual temperature is less than the absolute temperature empirical value, and to correct the initial alarm level based on the actual temperature at the maximum load current within the set time period and the threshold corresponding to the initial alarm level.
[0027] The first-level judgment module is configured to determine the alarm level based on the actual temperature if the actual temperature is not less than the absolute temperature empirical value.
[0028] Thirdly, the present invention provides an electronic device including a memory and a processor, and computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the first aspect.
[0029] Fourthly, the present invention provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in the first aspect.
[0030] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0031] This invention proposes a transformer thermal fault identification method based on an improved relative temperature difference method. It makes full use of infrared thermal imaging technology to perform infrared thermal imaging diagnosis on important parts of the transformer, such as the tank, oil conservator, radiator, and bushing. It proposes a dual triggering mechanism based on infrared thermal images and the temperature of the heating point, so as to identify the thermal fault in the transformer in a timely and proactive manner, thereby improving the intelligent level of transformer operation and maintenance.
[0032] This invention proposes a transformer thermal fault identification method based on an improved relative temperature difference method. By combining load current, the relative temperature difference method is improved to correct the thermal fault judgment results, avoid misjudgment, and realize automatic identification of transformer thermal faults and accurate determination of transformer thermal fault defect levels.
[0033] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0034] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.
[0035] Figure 1 This is a flowchart of the transformer thermal fault identification method based on the improved relative temperature difference method provided in Embodiment 1 of the present invention;
[0036] Figure 2 This is a curve of load current versus empirical value of absolute temperature of heating point provided in Embodiment 1 of the present invention;
[0037] Figure 3 This is a graph showing the relationship between load current and temperature provided in Embodiment 1 of the present invention. Detailed Implementation
[0038] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0039] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0040] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments of the invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form as well. Furthermore, it should be understood that the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0041] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.
[0042] Example 1
[0043] This embodiment provides a transformer thermal fault identification method based on an improved relative temperature difference method, such as... Figure 1 As shown, it includes:
[0044] Based on historical transformer operating data, an empirical database of absolute temperatures of heating points corresponding to load currents and a thermal imaging feature database are constructed.
[0045] Obtain infrared thermal images of various parts of the transformer and their corresponding actual temperatures, as well as the current load current;
[0046] The actual temperature of each part is compared with the trigger temperature threshold, and the infrared thermal image of each part is compared with the thermal image feature library. When the comparison results of both meet the trigger conditions, a thermal fault warning is triggered.
[0047] The empirical value of absolute temperature is obtained from the empirical database of absolute temperature of heating point based on the current load current.
[0048] If the actual temperature is less than the absolute temperature empirical value, the initial alarm level is determined based on the absolute temperature empirical value, and the initial alarm level is corrected based on the actual temperature at the maximum load current within the set time period and the threshold corresponding to the initial alarm level.
[0049] If the actual temperature is not less than the empirical value of absolute temperature, the alarm level is determined based on the actual temperature.
[0050] In this embodiment, the process of constructing a thermal image feature library based on historical transformer operating data includes:
[0051] Transformers are large and complex in structure. It is impractical and costly to perform infrared thermography on all components of a transformer. At the same time, as a current-heated device, the transformer's tank, oil conservator, radiator, and bushings are prone to significant heat generation and easy to monitor. Therefore, in this embodiment, infrared thermographic images of the transformer's tank, oil conservator, radiator, and bushings are used as key parameters for transformer thermal faults.
[0052] By combining historical operating data of transformers, a thermal image feature library is constructed for when thermal faults occur in transformers. The thermal image feature library has a memory function, and as more and more cases of transformer thermal fault handling are added, the thermal image feature library becomes richer and richer.
[0053] Some typical thermal imaging features include:
[0054] The transformer may experience localized temperature increases due to internal magnetic leakage, poor contact, blockage of oil lines, or poor insulation of the core.
[0055] Transformer bushings may experience temperature rise due to insufficient oil, poor contact, or excessive dielectric loss.
[0056] The temperature of the transformer oil conservator may rise due to insufficient oil or a false oil level.
[0057] Abnormal transformer radiator temperature can occur due to blockage or valve not being opened.
[0058] In this embodiment, the process of constructing an empirical database of the absolute temperature of the heating point corresponding to the load current based on historical transformer operating data includes: constructing an empirical database of the absolute temperature of the heating point based on empirical values of the absolute temperature of the heating point corresponding to the load current, such as... Figure 2 The figure shows a curve of load current versus empirical values of absolute temperature at the heating point.
[0059] In this embodiment, the thermal fault warning triggering conditions are set as follows: the actual temperature of the heat source is greater than the trigger temperature threshold and the infrared thermal image matches the corresponding data in the thermal image feature library at the same time.
[0060] Specifically:
[0061] (1) Method for early warning of transformer thermal fault information: Use infrared thermal imaging technology to perform infrared thermal imaging on parts such as the transformer tank, oil tank, radiator, and bushing, and extract the infrared thermal image and the actual temperature of each part.
[0062] (2) Set the trigger temperature threshold for each part. If the actual temperature in the infrared thermal image of each part exceeds the trigger temperature threshold, it means that the trigger condition is met.
[0063] (3) Intelligently compare the infrared thermal images of each part with the thermal image feature database;
[0064] The exposed surface of each part is divided into regions ABCD. To ensure that ABCD is clearly imaged on the infrared thermal imager, the focal length of the infrared thermal imager located at point O is adjusted so that each point on the object surface has a corresponding conjugate point on the image plane. However, when the thermal imager samples the optical image, this one-to-one correspondence is disrupted because each photosensitive unit on the focal plane is separated. Thus, corresponding to the resolution (M×N) of the infrared thermal imager, the surface ABCD of the high-temperature object is divided into M×N units. Let the small unit abcd be the (i,j)th unit on the ABCD plane, corresponding to the (i,j)th pixel on the focal plane of the infrared thermal imager.
[0065] The infrared thermal images in the thermal image feature library and the detected infrared thermal images are labeled with the names of the parts. Based on the labels, the infrared thermal images of the corresponding parts are first matched. Then, the detected infrared thermal images are matched one by one with the infrared thermal images in the thermal image feature library based on individual pixels. If the infrared thermal image matches the data in the thermal image feature library, it means that the trigger condition is met. The labeling algorithm is Faster R-CNN algorithm, and the target is labeled with a rectangular box.
[0066] (4) When the triggering conditions are met in both steps (2) and (3), a thermal fault warning is triggered.
[0067] In this embodiment, the alarm levels of transformer thermal faults are divided into general defects, serious defects, and emergency defects; wherein: general defects are defined as 35% ≤ δ < 50%; serious defects are defined as 50% ≤ δ < 95%; and emergency defects are defined as 95% ≤ δ.
[0068] Currently, the commonly used method for transformer thermal fault analysis and localization based on infrared thermal imaging is the relative temperature difference method. The relative temperature difference is the percentage of the temperature rise difference between two corresponding measuring points relative to the temperature rise of the higher temperature point; the relative temperature difference δ... t for:
[0069] δ t =(τ1-τ2) / τ1×100%=(T1-T2) / (T1-T0)×100%
[0070] In the formula: τ1 and T1 are the temperature rise and temperature of the heating point; τ2 and T2 are the temperature rise and temperature of the normal relative point; T0 is the ambient temperature of the device under test.
[0071] The biggest drawback of using the relative temperature difference method for transformer thermal fault analysis and localization is that it ignores factors such as load current and blindly follows the criterion that "a relative temperature difference greater than 95% indicates an urgent fault," thus exaggerating certain faults. For current-heated equipment such as transformers, when the load current approaches the equipment's rated current, the hot spot temperature no longer has a linear relationship with the flowing current. Figure 3 As shown, T'(I) and T(I) both represent the abnormal phase temperature as a function of current. The former is an ideal linear relationship, while the latter is a nonlinear relationship considering the actual situation. T0 and T1 represent the ambient temperature and the normal phase temperature of the equipment, respectively.
[0072] Therefore, when the load current is large, the value obtained by the relative temperature difference method will be larger than the actual value. This may lead to misjudgment of defects, causing unnecessary power outages and reducing the reliability of power supply. Thus, relying solely on the relative temperature difference method based on linear principles for defect identification is too simplistic and will result in biased results.
[0073] Therefore, this embodiment uses load current as a correction index for transformer thermal fault early warning information to improve the relative temperature difference method. Specifically:
[0074] The empirical value of absolute temperature is obtained from the empirical database of absolute temperature of heating point based on the current load current.
[0075] If the actual temperature is less than the absolute temperature empirical value, the relative temperature difference is calculated based on the absolute temperature empirical value of each heat point, and the relative temperature difference is compared with the set threshold of each alarm level to determine the initial alarm level.
[0076] Meanwhile, continue to monitor the set time period, select the maximum load current within the set time period, calculate the relative temperature difference based on the actual temperature at the maximum load current, and then compare it with the threshold corresponding to the initial alarm level.
[0077] If the relative temperature difference corresponding to the actual temperature at the maximum load current is within the threshold range of the initial alarm level, the final alarm level will remain unchanged and will still be the initial alarm level.
[0078] If the threshold of the initial alarm level is exceeded, the initial alarm level will be increased by 1 level. That is, if the initial alarm level is a general defect, the final alarm level will be a critical defect; if the initial alarm level is a critical defect, the final alarm level will be an urgent defect.
[0079] If the actual temperature is not less than the absolute temperature empirical value, the alarm level is determined based on the actual temperature of each heat source.
[0080] Example 2
[0081] This embodiment provides a transformer thermal fault identification system based on an improved relative temperature difference method, including:
[0082] The database construction module is configured to build an empirical database of absolute temperatures of heating points corresponding to load currents and a thermal imaging feature library based on historical transformer operating data.
[0083] The data acquisition module is configured to acquire infrared thermal images of various parts of the transformer and their corresponding actual temperatures, as well as the current load current.
[0084] The early warning triggering module is configured to compare the actual temperature of each part with the trigger temperature threshold, and compare the infrared thermal image of each part with the thermal image feature library. When the comparison results of both meet the triggering conditions, a thermal fault early warning is triggered.
[0085] The temperature experience value acquisition module is configured to acquire the absolute temperature experience value from the absolute temperature experience database of the heating point based on the current load current.
[0086] The first-level judgment module is configured to determine the initial alarm level based on the absolute temperature empirical value if the actual temperature is less than the absolute temperature empirical value, and to correct the initial alarm level based on the actual temperature at the maximum load current within the set time period and the threshold corresponding to the initial alarm level.
[0087] The first-level judgment module is configured to determine the alarm level based on the actual temperature if the actual temperature is not less than the absolute temperature empirical value.
[0088] It should be noted that the above modules correspond to the steps described in Embodiment 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should also be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer-executable instructions.
[0089] In further embodiments, the following is also provided:
[0090] An electronic device includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, wherein the computer instructions, when executed by the processor, perform the method described in Embodiment 1. For brevity, further details are omitted here.
[0091] It should be understood that in this embodiment, the processor can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.
[0092] Memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of memory may also include non-volatile random access memory. For example, memory may also store information about the device type.
[0093] A computer-readable storage medium for storing computer instructions, which, when executed by a processor, perform the method described in Embodiment 1.
[0094] The method in Example 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor. The software modules can reside in readily available storage media in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, a detailed description is not provided here.
[0095] Those skilled in the art will recognize that the units, i.e., algorithm steps, of the various examples described in connection with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0096] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.
Claims
1. A transformer thermal fault identification method based on an improved relative temperature difference method, characterized in that, include: Based on historical transformer operating data, an empirical database of absolute temperatures of heating points corresponding to load currents and a thermal imaging feature database are constructed. Obtain infrared thermal images of various parts of the transformer and their corresponding actual temperatures, as well as the current load current; The actual temperature of each part is compared with the trigger temperature threshold, and the infrared thermal image of each part is compared with the thermal image feature library. When the comparison results of both meet the trigger conditions, a thermal fault warning is triggered. The triggering condition is that the actual temperature is greater than the triggering temperature threshold and the infrared thermal image is matched with the corresponding data in the thermal image feature library at the same time. The empirical value of absolute temperature is obtained from the empirical database of absolute temperature of heating point based on the current load current. If the actual temperature is less than the absolute temperature empirical value, the initial alarm level is determined based on the absolute temperature empirical value, and the initial alarm level is corrected based on the actual temperature at the maximum load current within the set time period and the threshold corresponding to the initial alarm level. The process of revising the initial alarm level includes: calculating the relative temperature difference based on the actual temperature at the maximum load current, comparing it with the threshold corresponding to the initial alarm level, and further including: if the relative temperature difference corresponding to the actual temperature at the maximum load current is within the threshold range of the initial alarm level, the final alarm level remains unchanged and is still the initial alarm level; if it exceeds the threshold of the initial alarm level, the initial alarm level is increased by 1 level. If the actual temperature is not less than the absolute temperature empirical value, the alarm level is determined based on the actual temperature. The process of comparing infrared thermal images of various parts with the thermal image feature library includes: labeling the infrared thermal images in the thermal image feature library and the detected infrared thermal images with part names respectively, and matching the infrared thermal images of the corresponding parts according to the labeled names; matching the detected infrared thermal images with the infrared thermal images in the thermal image feature library one by one according to the form of individual pixels, and if the infrared thermal image matches the relevant infrared thermal image in the thermal image feature library, it means that the triggering condition is met.
2. The transformer thermal fault identification method based on the improved relative temperature difference method as described in claim 1, characterized in that, The alarm levels are divided into general defects, critical defects, and emergency defects. The threshold for each alarm level is set based on the relative temperature difference. If the actual temperature is less than the empirical value of the absolute temperature, the relative temperature difference is calculated based on the empirical value of the absolute temperature of each heat point. The relative temperature difference is then compared with the threshold of each alarm level to determine the initial alarm level.
3. The transformer thermal fault identification method based on the improved relative temperature difference method as described in claim 1, characterized in that, Infrared thermographic images of the transformer's enclosure, oil tank, radiator, and bushing are used as key parameters for identifying transformer thermal faults.
4. A transformer thermal fault identification system based on the improved relative temperature difference method as described in claim 1, characterized in that, include: The database construction module is configured to build an empirical database of absolute temperatures of heating points corresponding to load currents and a thermal imaging feature library based on historical transformer operating data. The data acquisition module is configured to acquire infrared thermal images of various parts of the transformer and their corresponding actual temperatures, as well as the current load current. The early warning triggering module is configured to compare the actual temperature of each part with the trigger temperature threshold, and compare the infrared thermal image of each part with the thermal image feature library. When the comparison results of both meet the triggering conditions, a thermal fault early warning is triggered. The temperature experience value acquisition module is configured to acquire the absolute temperature experience value from the absolute temperature experience database of the heating point based on the current load current. The first-level judgment module is configured to determine the initial alarm level based on the absolute temperature empirical value if the actual temperature is less than the absolute temperature empirical value, and to correct the initial alarm level based on the actual temperature at the maximum load current within the set time period and the threshold corresponding to the initial alarm level. The first-level judgment module is configured to determine the alarm level based on the actual temperature if the actual temperature is not less than the absolute temperature empirical value.
5. An electronic device, characterized in that, It includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, which, when executed by the processor, perform the method according to any one of claims 1-3.
6. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, perform the method described in any one of claims 1-3.
Citation Information
Patent Citations
Distribution transformer fault diagnosis system and method based on relation between temperature rise and load
CN103399241A
Substation power transformer overheating fault monitoring system based on thermal infrared imager
CN104165698A
