Dry-type transformer fault monitoring system and device based on artificial intelligence

Abstract

The invention provides a dry-type transformer fault monitoring system and device based on artificial intelligence, and relates to the technical field of dry-type transformer fault monitoring. Comprising a real-time concentration measurement module, an air circulation calculation module, a real concentration calculation module, a fault judgment module and a fault analysis module. The real-time concentration measurement module is used for acquiring measurement concentration data; the air circulation calculation module is used for calculating air circulation data; the real concentration calculation module is used for calculating real concentration data; the fault judgment module is used for judging whether the dry-type transformer has a fault or not; the fault analysis module is used for obtaining fault data. According to the method, the influence of air circulation caused by heat dissipation on the concentration of the internal gas components of the dry-type transformer is considered, the real concentration of the internal gas components is calculated, the accuracy and reliability of fault monitoring are improved, the actual condition in the transformer is reflected more accurately, and the possibility of misjudgment and missed judgment is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of dry-type transformer fault monitoring, and in particular to an artificial intelligence-based dry-type transformer fault monitoring system and an artificial intelligence-based dry-type transformer fault monitoring device. Background Art

[0002] Dry-type transformer is an important equipment widely used in power system, mainly composed of iron core, winding, insulation material, shell and other parts. The iron core is usually made of high-quality cold-rolled silicon steel sheets to reduce hysteresis loss and eddy current loss and improve the efficiency of the transformer. The winding is generally wound with copper or aluminum wire, and the number of turns and wire diameter are selected according to the capacity and voltage level of the transformer. Insulation material is a key component of dry-type transformer, and common ones include epoxy resin, etc. They can effectively isolate the winding and iron core to prevent short circuit and leakage. The shell plays the role of protecting internal components, heat dissipation and protection. The main function of dry-type transformer is to achieve voltage conversion. It can convert high voltage into low voltage for use in various electrical equipment, such as motors and lighting equipment in industrial production; it can also increase low voltage to meet the needs of long-distance power transmission and reduce line losses. In addition, dry-type transformers can also play the role of isolation and filtering, provide stable voltage output, and protect electrical equipment from voltage fluctuations and interference. Compared with traditional oil-immersed transformers, dry-type transformers have many advantages. First, it does not require the use of insulating oil, avoiding the risk of oil leakage and fire, and is more environmentally friendly and safer. Secondly, the installation and maintenance of dry-type transformers are relatively simple, with low environmental requirements, and can adapt to various harsh working environments. Furthermore, its operating noise is low and has little impact on the surrounding environment.

[0003] When a dry-type transformer fails, the concentration of its internal gas components will change significantly. When an overheating fault occurs, the insulating material will decompose at high temperature to produce gas. Among them, the concentration of hydrogen usually increases, because at lower temperatures, the thermal decomposition of the insulating material may produce hydrogen. As the temperature rises further, the concentration of methane and ethylene will gradually increase. If the overheating is serious, acetylene may even be detected, but its concentration is generally relatively low. If it is a discharge fault, the gas composition is different. In partial discharge, the concentration of hydrogen and methane may increase. In spark discharge faults, the concentration of hydrogen will increase significantly, and the concentration of carbon monoxide and carbon dioxide may also increase. In arc discharge faults, the concentration of acetylene will increase significantly, which often becomes an important sign for judging such serious faults. In addition, the concentration of ethylene and hydrogen will also increase significantly. It is worth noting that the changes in the concentration of gas components caused by faults of different types and degrees are not absolutely isolated, and there may be cross-over and superposition. For example, when long-term overheating and discharge faults exist at the same time, the concentration of various gases will have more complex changes.

[0004] By monitoring and analyzing the gas component concentration data inside the dry-type transformer, potential faults can be discovered in time, and the fault type and severity can be evaluated. Appropriate maintenance and repair measures can be taken to ensure the safe and stable operation of the dry-type transformer and reduce the losses and impacts caused by faults. However, during the operation of the dry-type transformer, it is necessary to dissipate heat. The air circulation caused by heat dissipation will dilute the concentration of gas components inside the dry-type transformer, resulting in inaccurate dry-type transformer fault monitoring, which is prone to misjudgment and missed judgment. Summary of the invention

[0005] The present invention provides a dry-type transformer fault monitoring system and device based on artificial intelligence, which are used to solve the defects of dry-type transformer fault monitoring in the prior art that is not accurate enough and prone to misjudgment and missed judgment.

[0006] On the one hand, the present invention provides a dry-type transformer fault monitoring system based on artificial intelligence, comprising: The acquisition module is used to obtain temperature data and parameter data of the dry-type transformer and to collect gas samples inside the dry-type transformer in real time.

[0007] The real-time concentration measurement module is used to perform component analysis on a gas sample by gas chromatography to obtain gas component measurement concentration data.

[0008] The air circulation calculation module is used to calculate the total heat dissipation of the dry-type transformer within a preset time period, and calculate the air circulation data inside the dry-type transformer based on the total heat dissipation.

[0009] The real concentration calculation module is used to combine the air circulation data with the measured concentration data to calculate the real concentration data of the gas components inside the dry-type transformer.

[0010] The fault judgment module is used to compare the actual concentration data with the preset normal concentration threshold range. If the actual concentration data exceeds the normal concentration threshold range, it is marked as fault concentration data, indicating that the dry-type transformer is faulty.

[0011] The fault analysis module is used to build a fault analysis model based on a convolutional neural network, input fault concentration data, and output fault data of the dry-type transformer. The fault data includes fault type, fault location, and fault degree.

[0012] The fault reporting module is used to send fault data to maintenance personnel.

[0013] According to the dry-type transformer fault monitoring system based on artificial intelligence provided by the present invention, the parameter data includes the volume of gas inside the dry-type transformer and the surface area of ​​the dry-type transformer. The temperature data includes the surface temperature of the dry-type transformer and the ambient temperature.

[0014] According to a dry-type transformer fault monitoring system based on artificial intelligence provided by the present invention, the process of analyzing the composition of a gas sample includes: The gas sample is injected into the gas chromatograph, and a corresponding chromatographic column is selected according to the gas composition of the gas sample.

[0015] The thermal conductivity detector is used to detect the gas component state data of the gas sample at the outlet of the chromatographic column. The gas component state data includes the retention time and peak area of ​​the gas component at the outlet of the chromatographic column.

[0016] According to the gas component state data, gas component measurement concentration data of the gas sample is obtained.

[0017] According to an artificial intelligence-based dry-type transformer fault monitoring system provided by the present invention, the air circulation calculation module includes a heat dissipation calculation unit, which is used to obtain the total heat dissipation by calculating the heat dissipation by thermal radiation and the heat dissipation by thermal convection. The calculation formula for the heat dissipation by thermal radiation is expressed as:

[0018] The calculation formula for heat dissipation by convection is expressed as:

[0019] The total heat dissipation calculation formula is expressed as:

[0020] In the formula, Indicates the surface emissivity of the dry-type transformer, represents the Stefan-Boltzmann constant, A represents the heat dissipation area, T 1 Indicates the surface temperature of dry-type transformer, T 0 represents the ambient temperature, and h represents the convection heat transfer coefficient.

[0021] According to an artificial intelligence-based dry-type transformer fault monitoring system provided by the present invention, the air circulation calculation module also includes an air flow calculation unit, which is used to calculate the air flow inside the dry-type transformer according to the total heat dissipation. The formula is expressed as:

[0022] In the formula, represents the constant pressure specific heat capacity of air, Indicates the air density.

[0023] According to a dry-type transformer fault monitoring system based on artificial intelligence provided by the present invention, the calculation formula of the real concentration data is expressed as:

[0024] In the formula, represents the measured concentration data of the i-th gas component, V represents the volume of the internal space of the dry-type transformer, and t represents the air flow rate inside the dry-type transformer. The time that has passed.

[0025] According to a dry-type transformer fault monitoring system based on artificial intelligence provided by the present invention, the process of setting a normal concentration threshold range includes: The historical data of gas component concentration during normal operation of dry-type transformers are collected as sample data.

[0026] Calculate the average value of the concentration data for each gas component and standard deviation .

[0027] According to the mean value and standard deviation, the normal concentration threshold range of each gas cost is set, and the formula is expressed as follows:

[0028] In the formula, A i B i represents the normal concentration threshold range of the i-th gas component, and k represents the confidence coefficient.

[0029] According to a dry-type transformer fault monitoring system based on artificial intelligence provided by the present invention, the process of building a fault analysis model based on a convolutional neural network includes: Collect historical fault case data, which includes gas composition concentration data, temperature data and operating parameters of dry-type transformers.

[0030] The historical fault case data is standardized and annotated with the fault type, fault location and fault severity to obtain label data.

[0031] Construct a convolutional neural network basic model, which includes convolutional layer, pooling layer and fully connected layer. The convolutional layer is used to extract features from label data to obtain feature data. The pooling layer is used to reduce the feature dimension of feature data to obtain distinct features. The fully connected layer is used to flatten distinct features and output fault data.

[0032] Use labeled data to train the basic model and iteratively update the parameters of the basic model.

[0033] The accuracy of the output fault data is calculated, and the basic model that reaches the preset accuracy is used as the fault analysis model.

[0034] According to a dry-type transformer fault monitoring system based on artificial intelligence provided by the present invention, the fault reporting module includes a fault receiving unit, a report generating unit and a report sending unit, wherein the fault receiving unit is used to receive fault data. The report generating unit is used to perform structured processing on the fault data to obtain a fault report. The report sending unit is used to send the fault report to relevant maintenance personnel.

[0035] On the other hand, the present invention also provides a dry-type transformer fault monitoring device based on artificial intelligence, the fault monitoring device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. Each functional module in the fault monitoring device is deployed in the manner of the above-mentioned dry-type transformer fault monitoring system based on artificial intelligence, and when the processor executes the computer program, the fault monitoring of the dry-type transformer is realized, thereby improving the accuracy and reliability of the fault monitoring.

[0036] The artificial intelligence-based dry-type transformer fault monitoring system and device provided by the present invention considers the influence of air circulation caused by heat dissipation on the concentration of gas components inside the dry-type transformer and calculates the true concentration of the internal gas components, thereby bringing many significant beneficial effects to the fault monitoring of the dry-type transformer. In the early stage of a transformer failure, internal chemical reactions and physical changes will lead to the generation and concentration changes of specific gas components. By accurately calculating the true concentration, these subtle changes can be captured before the fault develops to a serious degree, and precious time can be gained for timely maintenance and protection measures, effectively avoiding power outages and equipment damage caused by sudden faults. Secondly, the accuracy and reliability of fault monitoring are improved. Traditional monitoring methods may be interfered by environmental factors, measurement errors, etc., but by comprehensively considering the dynamic changes of air circulation and gas component concentration, some external interference factors can be eliminated, and the actual situation inside the transformer can be more accurately reflected, reducing the possibility of misjudgment and missed judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 It is a structural schematic diagram of an artificial intelligence-based dry-type transformer fault monitoring system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Combine the following Figure 1 The present invention describes an artificial intelligence-based dry-type transformer fault monitoring system and device.

[0041] Figure 1 It is a structural schematic diagram of an artificial intelligence-based dry-type transformer fault monitoring system provided in an embodiment of the present invention.

[0042] like Figure 1 As shown, the artificial intelligence-based dry-type transformer fault monitoring system and device provided in the embodiment of the present invention, the execution subject can be an artificial intelligence-based dry-type transformer fault monitoring system, including an acquisition module, a real-time concentration measurement module, an air circulation calculation module, a real concentration calculation module, a fault judgment module, a fault analysis module and a fault reporting module.

[0043] The acquisition module is used to obtain temperature data and parameter data of the dry-type transformer, and to collect gas samples inside the dry-type transformer in real time.

[0044] The parameter data include the volume of gas inside the dry-type transformer and the surface area of ​​the dry-type transformer. The temperature data include the surface temperature of the dry-type transformer and the ambient temperature.

[0045] In this embodiment, the acquisition module can obtain the key data of the dry-type transformer comprehensively and in real time. By acquiring temperature data and parameter data, basic information is provided for subsequent analysis. Real-time collection of internal gas samples helps to timely discover potential fault signs and achieve early warning, thereby avoiding further deterioration of the fault and reducing maintenance costs and possible power outage losses.

[0046] The real-time concentration measurement module is used to perform component analysis on a gas sample through gas chromatography to obtain gas component measurement concentration data.

[0047] The process of analyzing the composition of a gas sample includes: The gas sample is injected into the gas chromatograph, and a corresponding chromatographic column is selected according to the gas composition of the gas sample.

[0048] The thermal conductivity detector is used to detect the gas component state data of the gas sample at the outlet of the chromatographic column. The gas component state data includes the retention time and peak area of ​​the gas component at the outlet of the chromatographic column.

[0049] According to the gas component state data, gas component measurement concentration data of the gas sample is obtained.

[0050] In this embodiment, the gas sample will be separated in the chromatographic column, and different components will flow out at the outlet of the chromatographic column with different retention times. The outflowing gas components are detected using a thermal conductivity detector to obtain the chromatographic peak shape data of each component, including retention time and peak area. The retention time reflects the characteristics of the gas components, and the retention time values ​​of different gas components are different. The peak area is proportional to the concentration of the gas component and can be used to calculate the concentration value.

[0051] According to the known retention time and peak area of ​​the standard gas sample, a calibration curve of gas component concentration and peak area is established. The formula is expressed as:

[0052] In the formula, C i represents the measured concentration of the i-th gas component, k 1 is the correction factor, A i Represents the peak area of ​​the i-th gas component.

[0053] In this embodiment, the real-time concentration measurement module performs component analysis through gas chromatography to obtain gas component measurement concentration data, which can accurately detect the concentration of various components in the gas sample. This helps to accurately determine the chemical changes inside the transformer, provides key quantitative indicators for fault diagnosis, and improves the accuracy and reliability of fault diagnosis.

[0054] The air circulation calculation module is used to calculate the total heat dissipation of the dry-type transformer within a preset time period, and calculate the air circulation data inside the dry-type transformer based on the total heat dissipation.

[0055] The air circulation calculation module includes a heat dissipation calculation unit, which is used to obtain the total heat dissipation by calculating the heat dissipation by thermal radiation and heat dissipation by thermal convection. The calculation formula for the heat dissipation by thermal radiation is expressed as:

[0056] The calculation formula for heat dissipation by convection is expressed as:

[0057] The total heat dissipation calculation formula is expressed as:

[0058] In the formula, Indicates the surface emissivity of the dry-type transformer, represents the Stefan-Boltzmann constant, A represents the heat dissipation area, T 1 Indicates the surface temperature of dry-type transformer, T 0represents the ambient temperature, and h represents the convection heat transfer coefficient.

[0059] The air circulation calculation module also includes an air flow calculation unit, which is used to calculate the air flow inside the dry-type transformer according to the total heat dissipation.

[0060] According to the law of conservation of energy, the total heat dissipation is equal to the heat absorbed by the air. The heat calculation formula is expressed as:

[0061] Where m represents the air quality.

[0062] And because mass equals density times volume, the formula for air mass is:

[0063] In the formula, Q a represents the air flow rate during time t, Indicates the air density.

[0064] Substituting m into the heat calculation formula, the heat calculation formula is expressed as:

[0065] The formula for the air flow rate in time t is:

[0066] In the formula, represents the constant pressure specific heat capacity of air, Indicates the air density.

[0067] In this embodiment, the air circulation calculation module helps to more accurately evaluate the operating status of the transformer by calculating the total heat dissipation and internal air circulation data within a preset time period. Considering the air circulation factor, the interference of the external environment on the gas concentration measurement can be eliminated, making the judgment of the real situation inside the transformer more accurate, providing a more reliable basis for subsequent fault analysis.

[0068] The real concentration calculation module is used to combine the air circulation data with the measured concentration data to calculate the real concentration data of the gas components inside the dry-type transformer.

[0069] In this embodiment, we consider that the air volume flow rate caused by heat dissipation within a period of time t is , the volume of the internal space of the transformer is V.

[0070] Assume that the measured concentration of gas component is , in the absence of air circulation, after time t, the amount of gas components remains unchanged and the concentration remains .

[0071] However, due to air circulation, the volume of fresh air entering the transformer within time t is Q a *t.

[0072] The entry of this fresh air will dilute the original gas components.

[0073] Considering this process as a continuous dilution process, for a small time interval , the change in concentration can be expressed as:

[0074] Arrange the above formula and separate the variables to get:

[0075] Integrate both sides:

[0076] Integrating the left side gives:

[0077] Right now:

[0078] After finishing, we can get:

[0079] The calculation formula of the true concentration data is expressed as:

[0080] In the formula, represents the measured concentration data of the i-th gas component, V represents the volume of the internal space of the dry-type transformer, and t represents the air flow rate inside the dry-type transformer. The time that has passed.

[0081] In this embodiment, the real concentration calculation module calculates the real concentration data by combining the air circulation data and the measured concentration data, which can eliminate the influence of environmental factors and obtain a concentration value that better reflects the actual condition inside the transformer. This helps to more accurately determine whether there is a fault, reduce the possibility of misjudgment, and improve the sensitivity and specificity of fault monitoring.

[0082] The fault judgment module is used to compare the actual concentration data with the preset normal concentration threshold range. If the actual concentration data exceeds the normal concentration threshold range, it is marked as fault concentration data, indicating that the dry-type transformer is faulty.

[0083] The process for setting normal concentration threshold ranges includes: The historical data of gas component concentration during normal operation of dry-type transformers are collected as sample data.

[0084] Calculate the mean value and standard deviation of the concentration data of each gas component. The formula for calculating the mean value is expressed as:

[0085] The formula for calculating the standard deviation is:

[0086] In the formula, x j represents the jth sample value, and n represents the number of samples.

[0087] According to the mean value and standard deviation, the normal concentration threshold range of each gas cost is set, and the formula is expressed as follows:

[0088] In the formula, A i B i represents the normal concentration threshold range of the i-th gas component, and k represents the confidence coefficient.

[0089] In this embodiment, the fault judgment module judges the fault by comparing the real concentration data with the normal concentration threshold range, which can quickly and intuitively determine whether the transformer has a fault. This clear judgment standard helps to improve the efficiency and accuracy of fault monitoring, discover problems in time, and buy valuable time for subsequent maintenance and processing.

[0090] The fault analysis module is used to build a fault analysis model based on convolutional neural network, input fault concentration data, and output fault data of dry-type transformer. The fault data includes fault type, fault location and fault degree.

[0091] The process of building a convolutional neural network-based fault analysis model includes: Collect historical fault case data, which includes gas composition concentration data, temperature data and operating parameters of dry-type transformers.

[0092] The historical fault case data is standardized and annotated with the fault type, fault location and fault severity to obtain label data.

[0093] Construct a convolutional neural network basic model, which includes convolutional layer, pooling layer and fully connected layer. The convolutional layer is used to extract features from label data to obtain feature data. The pooling layer is used to reduce the feature dimension of feature data to obtain distinct features. The fully connected layer is used to flatten distinct features and output fault data.

[0094] Use labeled data to train the basic model and iteratively update the parameters of the basic model.

[0095] The accuracy of the output fault data is calculated, and the basic model that reaches the preset accuracy is used as the fault analysis model.

[0096] In this embodiment, the fault analysis module can deeply mine the hidden information in the real concentration data and accurately output the fault type, location and degree by constructing a fault analysis model based on a convolutional neural network. This provides maintenance personnel with detailed and accurate fault information, which helps to improve the pertinence and efficiency of maintenance and reduce maintenance time and cost.

[0097] The fault reporting module is used to send fault data to maintenance personnel.

[0098] The fault reporting module includes a fault receiving unit, a report generating unit and a report sending unit. The fault receiving unit is used to receive fault data. The report generating unit is used to perform structured processing on the fault data to obtain a fault report. The report sending unit is used to send the fault report to relevant maintenance personnel.

[0099] In this embodiment, the fault reporting module can ensure that the maintenance personnel can obtain fault information in time and respond quickly by sending fault data to the maintenance personnel. This helps to shorten the time interval for fault handling, improve the stability and reliability of the power system, and reduce the impact of power outages caused by faults on production and life.

[0100] In summary, this embodiment provides a dry-type transformer fault monitoring system based on artificial intelligence. Through the collaborative work of multiple modules, data is obtained from multiple dimensions such as temperature, parameters, and gas samples, and in-depth analysis is performed, which can timely and accurately discover potential faults and improve the accuracy and reliability of fault diagnosis. The air circulation factor is comprehensively considered, and advanced analysis methods and models are used to reduce the risk of misjudgment and missed judgment, and significantly improve the maintenance efficiency and quality. By considering the impact of air circulation caused by heat dissipation on the concentration of gas components inside the dry-type transformer and calculating the true concentration of the internal gas components, many significant beneficial effects are brought to the fault monitoring of the dry-type transformer. In the early stage of a transformer failure, internal chemical reactions and physical changes will cause the generation and concentration changes of specific gas components. By accurately calculating the true concentration, these subtle changes can be captured before the fault develops to a serious level, and precious time can be gained for timely maintenance and protection measures, effectively avoiding power outages and equipment damage caused by sudden failures. Secondly, the accuracy and reliability of fault monitoring are improved. Traditional monitoring methods may be interfered by environmental factors, measurement errors, etc., but by comprehensively considering the dynamic changes of air circulation and gas component concentration, some external interference factors can be eliminated, the actual situation inside the transformer can be more accurately reflected, and the possibility of misjudgment and missed judgment can be reduced. Furthermore, it helps to optimize the maintenance strategy of the transformer. According to the gas component concentration calculated in real time, a maintenance plan can be formulated more scientifically, maintenance time and resources can be reasonably arranged, over-maintenance or under-maintenance can be avoided, maintenance costs can be reduced, and the service life of the transformer can be extended. In addition, the stability and reliability of the power system can be enhanced. Potential faults of the transformer can be discovered and handled in a timely manner to ensure the normal operation of the transformer and reduce power supply interruptions caused by transformer faults, thereby improving the power supply quality and stability of the entire power system and meeting users' continuous and stable demand for electricity. Finally, it promotes the development and innovation of dry-type transformer monitoring technology. This fault monitoring method based on gas component concentration calculation provides new ideas and directions for related research, promotes the continuous improvement and progress of monitoring technology, and provides strong support for the intelligent and digital development of the power industry.

[0101] It can also provide maintenance personnel with detailed fault data, making maintenance work more targeted, shortening maintenance time, reducing maintenance costs, and enhancing the stability and reliability of the power system. Timely detection and handling of faults reduces power outages caused by transformer failures and ensures a continuous and stable supply of electricity, which is of great significance to industrial production, residents' lives, and the normal operation of society. In addition, the system has a high degree of intelligence and automation, which reduces manual intervention, reduces the errors and risks that may be caused by manual monitoring, and improves the efficiency and safety of monitoring work.

[0102] In order to realize the above-mentioned dry-type transformer fault monitoring system based on artificial intelligence and apply it to the existing dry-type transformer fault monitoring, so as to simplify the fault monitoring process of practical application and improve the accuracy and reliability of dry-type transformer fault monitoring, this embodiment also provides a dry-type transformer fault monitoring device based on artificial intelligence. The fault monitoring device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the fault monitoring of the existing dry-type transformer is realized, and the accuracy and reliability of the fault monitoring are improved.

[0103] The computer device may be a smart phone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server or cabinet server (including an independent server or a server cluster composed of multiple servers) that can execute programs. The computer device of this embodiment includes at least but is not limited to: a memory and a processor that can communicate with each other through a system bus.

[0104] In this embodiment, the memory (i.e., readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), etc. equipped on the computer device. Of course, the memory may also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the memory is generally used to store an operating system and various application software installed on the computer device. In addition, the memory may also be used to temporarily store various types of data that have been output or are to be output.

[0105] The processor may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor is generally used to control the overall operation of a computer device. In this embodiment, the processor is used to run the program code stored in the memory or process data, thereby realizing fault monitoring of an existing dry-type transformer and improving the accuracy and reliability of fault detection.

[0106] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The dry-type transformer fault monitoring system based on artificial intelligence is characterized by: include: A collection module, used to obtain temperature data and parameter data of the dry-type transformer, and collect gas samples inside the dry-type transformer in real time; A real-time concentration measurement module, used to perform component analysis on the gas sample by gas chromatography to obtain gas component measurement concentration data; An air circulation calculation module, used to calculate the total heat dissipation of the dry-type transformer within a preset time period, and calculate the air circulation data inside the dry-type transformer according to the total heat dissipation; A real concentration calculation module, used to combine the air circulation data with the measured concentration data to calculate the real concentration data of the gas components inside the dry-type transformer; A fault judgment module is used to compare the real concentration data with a preset normal concentration threshold range. If the real concentration data exceeds the normal concentration threshold range, it is marked as fault concentration data, indicating that the dry-type transformer is faulty; A fault analysis module, used to construct a fault analysis model based on a convolutional neural network, input the fault concentration data, and output the fault data of the dry-type transformer, wherein the fault data includes the fault type, fault location, and fault degree; The fault reporting module is used to send the fault data to maintenance personnel.

2. The dry-type transformer fault monitoring system based on artificial intelligence according to claim 1 is characterized in that: The parameter data includes the volume of gas inside the dry-type transformer and the surface area of ​​the dry-type transformer; the temperature data includes the surface temperature and ambient temperature of the dry-type transformer.

3. The dry-type transformer fault monitoring system based on artificial intelligence according to claim 1 is characterized in that: The process of analyzing the composition of the gas sample includes: Injecting the gas sample into a gas chromatograph, and selecting a corresponding chromatographic column for the gas components of the gas sample; Using a thermal conductivity detector to detect gas component state data of the gas sample at the outlet of the chromatographic column, the gas component state data including the retention time and peak area of ​​the gas component at the outlet of the chromatographic column; According to the gas component state data, gas component measurement concentration data of the gas sample is obtained.

4. The dry-type transformer fault monitoring system based on artificial intelligence according to claim 1 is characterized in that: The air circulation calculation module includes a heat dissipation calculation unit, which is used to obtain the total heat dissipation by calculating the heat dissipation by thermal radiation and the heat dissipation by thermal convection. The calculation formula of the heat dissipation by thermal radiation is expressed as: The calculation formula of the heat convection heat dissipation is expressed as: The calculation formula of the total heat dissipation is expressed as: In the formula, Indicates the surface emissivity of the dry-type transformer, represents the Stefan-Boltzmann constant, A represents the heat dissipation area, T1 represents the surface temperature of the dry-type transformer, T0 represents the ambient temperature, and h represents the convection heat transfer coefficient.

5. The dry-type transformer fault monitoring system based on artificial intelligence according to claim 4 is characterized in that: The air circulation calculation module further includes an air flow calculation unit, which is used to calculate the air flow inside the dry-type transformer according to the total heat dissipation, and the formula is expressed as: In the formula, represents the constant pressure specific heat capacity of air, Indicates the air density.

6. The artificial intelligence-based dry-type transformer fault monitoring system according to claim 1 is characterized in that: The calculation formula of the true concentration data is expressed as: In the formula, represents the measured concentration data of the i-th gas component, V represents the volume of the internal space of the dry-type transformer, and t represents the air flow rate inside the dry-type transformer. The time that has passed.

7. The dry-type transformer fault monitoring system based on artificial intelligence according to claim 1 is characterized in that: The process of setting the normal concentration threshold range includes: Collecting historical data of gas component concentration during normal operation of the dry-type transformer as sample data; Calculate the average value of the concentration data for each gas component and standard deviation ; According to the average value and the standard deviation, the normal concentration threshold range of each gas cost is set, and the formula is expressed as follows: In the formula, A i B i represents the normal concentration threshold range of the i-th gas component, and k represents the confidence coefficient.

8. The dry-type transformer fault monitoring system based on artificial intelligence according to claim 1 is characterized in that: The process of constructing the fault analysis model based on convolutional neural network includes: Collecting historical fault case data, wherein the historical fault case data includes gas component concentration data, temperature data, and operating parameters of the dry-type transformer; Standardizing the historical fault case data, and marking the fault type, fault location, and fault severity to obtain label data; Constructing a convolutional neural network basic model, the basic model includes a convolution layer, a pooling layer and a fully connected layer, the convolution layer is used to extract features from the label data to obtain feature data; the pooling layer is used to reduce the feature dimension of the feature data to obtain distinct features; the fully connected layer is used to flatten the distinct features and output fault data; Using the label data to train the basic model, and iteratively updating the parameters of the basic model; The accuracy of the output fault data is calculated, and the basic model that achieves the preset accuracy is used as the fault analysis model.

9. The artificial intelligence-based dry-type transformer fault monitoring system according to claim 1 is characterized in that: The fault reporting module includes a fault receiving unit, a report generating unit and a report sending unit. The fault receiving unit is used to receive the fault data; the report generating unit is used to perform structured processing on the fault data to obtain a fault report; and the report sending unit is used to send the fault report to relevant maintenance personnel.

10. A dry-type transformer fault monitoring device based on artificial intelligence, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: Each functional module in the artificial intelligence-based dry-type transformer fault monitoring device is deployed in the manner of an artificial intelligence-based dry-type transformer fault monitoring system as described in any one of claims 1 to 9.

Images