Transformer monitoring and adjusting method and device, storage medium and terminal

Abstract

The invention provides a transformer monitoring and adjusting method and device, a storage medium and a terminal. The method comprises the following steps: acquiring vibration monitoring data and oil chromatography monitoring data within a preset time range before the current moment; inputting the vibration monitoring data and the oil chromatography monitoring data into a transformer fault probability prediction time sequence model to obtain a corresponding transformer fault probability value; and adjusting an oil chromatography monitoring period based on the transformer fault probability value to obtain a corresponding adjusted period. The transformer is monitored and adjusted, and the monitoring cost and the fault detection timeliness can be effectively considered.

Description

Technical Field

[0001] The present invention belongs to the technical field of transformers and relates to a monitoring and adjustment method for a transformer, and in particular to a monitoring and adjustment method and device, a storage medium and a terminal for a transformer. Background Art

[0002] Power transformers are one of the most critical core equipment in the power system, and their operational health has a significant impact on the system. According to statistics and analysis in the "2010 State Grid Corporation of China Transformer Equipment Professional Summary," as of 2010, approximately 10% of the power transformers of all voltage levels under the State Grid Corporation had been in operation for more than 15 years. Statistics from the "2013 Transformer Professional Work Summary of the Guangdong Power Grid Corporation" also show that as of 2013, nearly 11% of the power transformers of all voltage levels under the Guangdong Power Grid had been in operation for more than 15 years. However, many power transformers in my country are currently in operation for between 20 and 30 years. Consequently, a significant number of these transformers are nearing the end of their designed service life, necessitating timely monitoring and monitoring of their operational status.

[0003] Existing online monitoring methods for power transformers mainly include oil chromatography, vibration, soundprint, partial discharge, core clamp grounding current, and temperature. These monitoring methods use different principles to monitor power transformers online. However, oil chromatography is generally recognized as the most effective method for real-time monitoring of power transformers. Specifically, oil-immersed power transformers may experience latent faults such as internal overheating and partial discharge during long-term operation. Overheating and discharge can cause the insulating oil to decompose, producing trace amounts of dissolved gases such as H2, CO, CO2, CH4, C2H4, C2H2, and C2H6. Different fault phenomena and levels of deterioration produce different gas compositions and concentrations. By monitoring the concentrations of various dissolved gases in the oil using an online oil chromatography monitoring device, the transformer's operating status can be accurately understood. However, due to the lifespan of key components such as the oil pump, prolonged and high-frequency operation of the oil chromatography monitoring device significantly reduces its lifespan. To reduce monitoring costs, the oil chromatography monitoring cycle is currently set by on-site monitoring personnel at substations to record 1 to 6 data points per day (the higher the transformer voltage level, the higher the detection frequency). In fact, once a transformer fails, the deterioration rate is very fast. 1 to 6 oil chromatography data per day cannot provide timely feedback on transformer abnormalities.

[0004] In summary, in the prior art, if the oil chromatogram monitoring period is too long, the service life will be shortened, and if it is too short, the transformer fault will not be discovered in time. Therefore, it is difficult to set the oil chromatogram monitoring period to a reasonable value. Summary of the Invention

[0005] The purpose of the present invention is to provide a transformer monitoring and adjustment method and device, a storage medium and a terminal, which are used to solve the technical problem in the prior art that the oil chromatography monitoring period is difficult to set to a reasonable value.

[0006] In a first aspect, the present invention provides a transformer monitoring and adjustment method, comprising:

[0007] Obtain vibration monitoring data and oil chromatography monitoring data within a preset time range before the current moment;

[0008] Inputting the vibration monitoring data and the oil chromatogram monitoring data into a transformer fault probability prediction time series model to obtain a corresponding transformer fault probability value;

[0009] Adjusting the period of oil chromatogram monitoring based on the transformer fault probability value to obtain a corresponding adjusted period;

[0010] The adjusted period is in inverse proportion to the transformer failure probability value.

[0011] In one embodiment of the present invention, the transformer fault probability prediction time series model includes a time series prediction module and a probability conversion module;

[0012] The time series prediction module is used to make predictions based on a preset AI model, wherein the preset AI model uses vibration monitoring data and oil chromatography monitoring data within a preset time range as prediction factors, and uses the transformer condition within a preset future time range as the prediction result;

[0013] The probability conversion module is used to convert the transformer status within the preset future time range into the transformer failure probability value;

[0014] The transformer status includes normal and abnormal.

[0015] In one embodiment of the present invention, converting the transformer condition within the preset future time range into the transformer failure probability value includes:

[0016] Obtaining the difference between the time when the transformer condition is abnormal for the first time in the preset future time range and the current time as the abnormality time;

[0017] The difference obtained by subtracting the abnormal time consumption from one and dividing it by the preset future time range is used as the transformer failure probability value.

[0018] In one embodiment of the present invention, the vibration monitoring data includes vibration acceleration and vibration frequency, and the oil chromatography monitoring data includes gas concentration mean, gas concentration maximum, and gas concentration minimum.

[0019] In one embodiment of the present invention, adjusting the period of oil chromatogram monitoring based on the transformer fault probability value to obtain the corresponding adjusted period includes:

[0020] Obtaining a preset maximum cycle and a preset minimum cycle of oil chromatogram monitoring, and obtaining a difference between the preset maximum cycle and the preset minimum cycle as an adjustment space value;

[0021] Obtaining the product of the adjustment space value and the transformer failure probability value as the adjustment amplitude;

[0022] The preset minimum period is added to the adjustment amplitude to obtain an adjusted period.

[0023] In one embodiment of the present invention, the preset time range is 7 days, and the preset future time range is 7 hours.

[0024] In a second aspect, the present invention further provides a transformer monitoring and adjustment device, characterized in that it includes:

[0025] A feature acquisition module is used to acquire vibration monitoring data and oil chromatography monitoring data within a preset time range before the current moment;

[0026] A probability prediction module, configured to input the vibration monitoring data and the oil chromatogram monitoring data into a transformer fault probability prediction time series model to obtain a corresponding transformer fault probability value;

[0027] A cycle adjustment module, configured to adjust the cycle of oil chromatogram monitoring based on the transformer fault probability value to obtain a corresponding adjusted cycle;

[0028] The adjusted period is in inverse proportion to the transformer failure probability value.

[0029] In a third aspect, the present invention further provides a storage medium storing a computer program, which, when executed by a processor, implements the transformer monitoring and adjustment method as described above.

[0030] In a fourth aspect, the present invention further provides a terminal, comprising a processor and a memory, wherein the memory is communicatively connected to the processor;

[0031] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the transformer monitoring and adjustment method as described above.

[0032] As described above, the transformer monitoring and adjustment method and device, storage medium, and terminal of the present invention have the following beneficial effects:

[0033] The present invention utilizes a transformer fault probability prediction time series model to predict the transformer fault probability value based on vibration and oil chromatogram data, and accordingly adjusts the oil chromatogram monitoring period based on the transformer fault probability value, thereby realizing intelligent adjustment of the oil chromatogram monitoring period. If the transformer fault probability value is high (high probability of abnormality), the monitoring period is shortened and the detection frequency is increased to detect problems more quickly. If the transformer fault probability value is low (normal operation), the monitoring period is extended to reduce unnecessary monitoring times and reduce the burden on equipment. Therefore, the present invention can balance monitoring costs and fault detection timeliness. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic flow chart of a transformer monitoring and adjustment method according to an embodiment of the present invention is shown.

[0035] Figure 2 A schematic diagram of a data flow for obtaining a transformer fault probability value based on a two-stage method in a transformer monitoring and adjustment method according to an embodiment of the present invention is shown.

[0036] Figure 3 The figure shows a flow chart of periodic adjustment in the transformer monitoring and adjustment method according to an embodiment of the present invention.

[0037] Figure 4 A schematic structural diagram of a transformer monitoring and adjustment device according to an embodiment of the present invention is shown.

[0038] Figure 5 A schematic structural diagram of a terminal according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0039] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0040] The principles and implementation methods of the transformer monitoring and adjustment method and device, storage medium and terminal of this embodiment will be described in detail below, so that those skilled in the art can understand the transformer monitoring and adjustment method, device, storage medium and terminal of this embodiment without creative work.

[0041] In order to solve the above technical problems existing in the prior art, an embodiment of the present invention provides a monitoring and adjustment method for a transformer.

[0042] Figure 1A schematic diagram of a transformer monitoring and adjustment method according to an embodiment of the present invention is shown. Figure 1 As shown, the transformer monitoring and adjustment method according to the embodiment of the present invention mainly includes the following steps:

[0043] Step S100: Acquire vibration monitoring data and oil chromatography monitoring data within a preset time range before the current moment.

[0044] Specifically, the vibration monitoring data is collected from the transformer vibration sensor, and the oil chromatography monitoring data is collected from the oil chromatography analyzer. The embodiment of the present invention collects the vibration monitoring data and oil chromatography monitoring data generated during the operation of the transformer, and ensures that the data covers a preset time range so that the subsequent time series prediction model can accurately calculate the transformer failure probability value. The vibration monitoring data and oil chromatography monitoring data within the preset time range are also the time series data of vibration monitoring and oil chromatography monitoring. For example, if the preset time range is 10 days, the embodiment of the present invention uses 10 days of vibration monitoring data and 10 days of oil chromatography monitoring data as the data basis.

[0045] Optionally, the vibration monitoring data includes vibration acceleration and vibration frequency, and the oil chromatography monitoring data includes gas concentration mean, gas concentration maximum and gas concentration minimum. Vibration monitoring is mainly used to detect mechanical faults (such as loose core, winding deformation, partial discharge, etc.). Using only vibration acceleration may not be able to distinguish different types of faults. Therefore, this embodiment adds vibration frequency to analyze the vibration characteristics of different frequency bands. The oil chromatography monitoring data mainly includes the gas concentration of each gas in H2, CH4, C2H2, and CO2. Using only a single-point measurement value of the gas concentration may not be able to fully reflect the trend change. Therefore, this embodiment also considers the mean, maximum and minimum values ​​to capture abnormal fluctuations. The above settings are conducive to making the prediction of the transformer fault probability value more accurate.

[0046] Step S200: Inputting vibration monitoring data and oil chromatogram monitoring data into a transformer fault probability prediction time series model to obtain a corresponding transformer fault probability value.

[0047] Specifically, vibration monitoring data and oil chromatography monitoring data are both time series data. The occurrence of transformer failures is closely related to the changing trends of the historical data represented by these time series data. In this embodiment of the present invention, a transformer failure probability prediction time series model is used to predict the transformer failure probability value, which is the probability of the transformer failing within a preset future time range. The time series AI models utilized in the transformer failure probability prediction time series model include LSTM, GRU, and XGBoost. Using a sigmoid activation function in the last layer of the time series AI model outputs a probability within the range [0, 1]. Using these time series AI models to predict time series data for corresponding scenarios is prior art in the art. Based on the above description of step S200, those skilled in the art can select an appropriate time series AI model and collect and annotate the corresponding training dataset to train and obtain a transformer failure probability prediction time series model. In this embodiment, the training dataset for the time series AI model includes multiple training data items, each of which includes a time value, vibration monitoring data and oil chromatography monitoring data within a preset time range before the time value, and a transformer failure probability value after the time value. It should be noted that the key improvement of the embodiment of the present invention is not the network structure of the time series AI model itself, but based on the unique technical problem of the present invention, the time series AI model is used to predict the transformer failure probability value, and the transformer failure probability value is used as the basis for adjusting the period of oil chromatography monitoring of the transformer.

[0048] In a specific implementation of step S200, a two-stage approach is adopted to obtain the transformer fault probability value. Specifically, the transformer fault probability prediction time series model includes a time series prediction module and a probability conversion module. Figure 2 A schematic diagram of the data flow for obtaining a transformer failure probability value based on a two-stage method in the transformer monitoring and adjustment method described in an embodiment of the present invention is shown, wherein time represents a timestamp, vibration_data represents vibration monitoring data, oil_data represents oil chromatogram monitoring data, trans_condition represents the transformer condition (where 1 represents abnormality and 0 represents normal), and probability represents the transformer failure probability value. This embodiment first obtains the transformer condition corresponding to a preset future time range (multiple future time points) based on the vibration monitoring data and oil chromatogram monitoring data within a preset time range, and then generates a transformer failure probability value based on all transformer conditions.

[0049] Specifically, the transformer fault probability prediction time series model includes:

[0050] The time series prediction module is used to make predictions based on a preset AI model. The preset AI model uses vibration monitoring data and oil chromatography monitoring data within a preset time range as prediction factors, and uses the transformer condition within a preset future time range as the prediction result. The transformer condition can be normal or abnormal.

[0051] Specifically, a preset AI model is used to learn the trends of historical detection data to predict the future operation of the transformer, and the transformer status within a preset future time range is obtained as a prediction result. The preset AI model includes LSTM and XGBoost. In this embodiment, the transformer status within the preset future time range is first obtained. For example, the prediction result of the preset AI model is "normal" in the first hour of the future, "normal" in the second hour of the future, and "abnormal" in the third hour of the future. The transformer status within the preset future time range is specifically expressed as the transformer status per time unit.

[0052] The probability conversion module is used to convert the transformer status within a preset future time range into a transformer failure probability value.

[0053] Specifically, in the probability conversion module, the transformer condition within a preset future time range is analyzed. The closer the time point at which the transformer condition first appears abnormal is to the current moment, the greater the transformer failure probability value. The further the time point at which the transformer condition first appears abnormal is from the current moment, the smaller the transformer failure probability value. As long as the relationship between the time point at which the abnormality first appears and the transformer failure probability value is satisfied, those skilled in the art can construct corresponding probability conversion modules based on a variety of different functional relationships to convert the transformer condition within the preset future time range into a transformer failure probability value. This embodiment does not impose any specific limitations on this.

[0054] It should be noted that the advantage of the two-stage method of this embodiment is that it does not directly predict the transformer failure probability end-to-end, but first predicts the transformer status (normal or abnormal) at each specific time in the future based on the preset AI model, and then quantifies the prediction results through the probability conversion module. The output transformer failure probability value is a more fine-grained fault risk assessment, which can effectively improve the accuracy of the transformer failure probability.

[0055] In a specific probability conversion construction method, converting the transformer condition within a preset future time range into a transformer failure probability value includes:

[0056] The difference between the time when the transformer condition first became abnormal within the preset future time range and the current moment is obtained as the abnormality time. Specifically, all transformer conditions within the preset future time range are obtained. For example, if the preset future time range is 10 hours, and the next hour is normal, the next two hours are normal, the next three hours are normal, the next four hours are normal, and the next five hours are abnormal, then the difference between the time when the transformer condition first became abnormal and the current moment is 5 hours, and the abnormality time is 5 hours. It should be noted that if the transformer condition remains abnormal throughout the preset future time range, then the abnormality occurred outside the preset future time range. In other words, the abnormality time is equal to the preset future time range.

[0057] The transformer failure probability is calculated by subtracting the difference between the abnormal duration and the preset future time range. For example, if the abnormal duration is 1 hour and the preset future time range is 10 hours, the transformer failure probability is 1 minus 1 / 10, or 0.9. This method for obtaining transformer failure probability provides a more dynamic fault risk assessment, reduces false alarms, and allows for more refined adjustments to the monitoring cycle.

[0058] Step S300: adjusting the period of oil chromatography monitoring based on the transformer fault probability value to obtain a corresponding adjusted period.

[0059] In this embodiment, the adjusted period is inversely proportional to the transformer failure probability. Specifically, a larger transformer failure probability indicates a greater likelihood of transformer failure, and a smaller adjusted period results. Oil chromatography monitoring at a smaller period (i.e., a higher frequency) facilitates early detection and timely detection of transformer failures, preventing serious power accidents and generating significant economic benefits. A smaller transformer failure probability indicates a lower likelihood of transformer failure, and a larger adjusted period significantly extends the service life of the oil chromatography device, improving the economic efficiency of online transformer monitoring. This also generates less monitoring data than usual, reducing the analytical workload for transformer operators.

[0060] In a specific implementation of step S300, Figure 3 The schematic diagram of the process flow of period adjustment in the transformer monitoring and adjustment method according to the embodiment of the present invention is shown. Figure 3 As shown, the oil chromatogram monitoring period is adjusted based on the transformer fault probability value to obtain the corresponding adjusted period including:

[0061] Step S301: obtaining a preset maximum period and a preset minimum period of oil chromatogram monitoring, and obtaining a difference between the preset maximum period and the preset minimum period as an adjustment space value.

[0062] Specifically, refer to the following formula:

[0063] C=Tmax-Tmin

[0064] Wherein, C represents the adjustment space value, Tmax represents the preset maximum period of oil chromatogram monitoring, and Tmin represents the preset minimum period of oil chromatogram monitoring. For example, if Tmax is 240 hours and Tmin is 5 hours, the adjustment space value is 235 hours.

[0065] Step S302: obtaining the product of the adjustment space value and the transformer failure probability value as the adjustment amplitude.

[0066] Specifically, refer to the following formula:

[0067] X=C*P

[0068] Among them, X represents the adjustment amplitude, C represents the adjustment space value, and P represents the transformer failure probability value.

[0069] Step S303: Add the preset minimum period and the adjustment amplitude to obtain the adjusted period.

[0070] That is, the sum of Tmin and X is used as the adjusted period. The oil chromatogram monitoring period is dynamically adjusted based on the transformer fault probability. The adjusted oil chromatogram monitoring period always remains between the preset maximum and minimum periods for oil chromatogram monitoring. This not only achieves dynamic period adjustment but also ensures that the period remains within a reasonable range, preventing damage to the oil chromatogram monitoring instrument if the period exceeds the range.

[0071] Optionally, the preset time range is 7 days, and the preset future time range is 7 hours. That is, using 168 hours of vibration monitoring data and oil chromatogram monitoring data to predict the transformer failure probability value for the next 7 hours is a parameter setting that achieves optimal results in this embodiment. Those skilled in the art may also set other appropriate preset time ranges and preset future time ranges based on actual circumstances.

[0072] The protection scope of the transformer monitoring and adjustment method of the embodiment of the present invention is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing, or replacing steps in the prior art based on the principles of the present invention are included in the protection scope of the present invention.

[0073] The transformer monitoring and adjustment method of the present invention utilizes a transformer fault probability prediction time series model to predict the transformer fault probability value based on vibration and oil chromatogram data. The method then adjusts the oil chromatogram monitoring period accordingly based on the transformer fault probability value. This intelligently adjusts the oil chromatogram monitoring period, balancing monitoring costs and the timeliness of fault detection. Furthermore, a fault risk assessment model is provided that first predicts the transformer condition (normal or abnormal) at each specific time in the future based on a preset AI model, and then probabilistically quantifies the prediction results through a probability conversion module. This allows for more granular assessments to effectively improve the accuracy of transformer fault probabilities.

[0074] In order to solve the above technical problems existing in the prior art, an embodiment of the present invention further provides a monitoring and adjustment device for a transformer.

[0075] Figure 4 The structure diagram of the monitoring and adjustment device for the transformer according to the embodiment of the present invention is shown. Figure 4 As shown, the transformer monitoring and adjustment device according to the embodiment of the present invention includes a feature acquisition module, a probability prediction module and a period adjustment module.

[0076] A feature acquisition module is used to acquire vibration monitoring data and oil chromatography monitoring data within a preset time range before the current moment;

[0077] A probability prediction module, configured to input the vibration monitoring data and the oil chromatogram monitoring data into a transformer fault probability prediction time series model to obtain a corresponding transformer fault probability value;

[0078] A cycle adjustment module, configured to adjust the cycle of oil chromatogram monitoring based on the transformer fault probability value to obtain a corresponding adjusted cycle;

[0079] The adjusted period is in inverse proportion to the transformer failure probability value.

[0080] The transformer monitoring and adjustment device of an embodiment of the present invention utilizes a transformer fault probability prediction time series model to predict the transformer fault probability value based on vibration and oil chromatogram data. It then adjusts the oil chromatogram monitoring period accordingly based on the transformer fault probability value, achieving intelligent adjustment of the oil chromatogram monitoring period while balancing monitoring costs and the timeliness of fault detection. Furthermore, a fault risk assessment model is provided that first predicts the transformer condition (normal or abnormal) at each specific time in the future based on a preset AI model, and then probabilistically quantifies the prediction results through a probability conversion module. This allows for more granular assessments to effectively improve the accuracy of transformer fault probabilities.

[0081] In order to solve the above technical problems existing in the prior art, an embodiment of the present invention further provides a storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, all steps of the transformer monitoring and adjustment method of the embodiment are implemented.

[0082] The specific steps of the transformer monitoring and adjustment method and the beneficial effects obtained by applying the readable storage medium provided by the embodiment of the present invention are the same as those in the above embodiment and will not be described in detail here.

[0083] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above-mentioned embodiment can be performed by instructing a processor through a program, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state drive, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above-mentioned storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0084] In order to solve the above technical problems existing in the prior art, an embodiment of the present invention further provides a terminal. Figure 5 The schematic diagram of the structure of the terminal according to the embodiment of the present invention is shown. Figure 5 As shown, the terminal of the embodiment of the present invention includes a processor and a memory, and the memory and the processor are communicatively connected; the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory, so that the terminal performs all steps of the transformer monitoring and adjustment method of the above embodiment.

[0085] The specific steps of the transformer monitoring and adjustment method and the beneficial effects obtained by applying the terminal provided by the embodiment of the present invention are the same as those in the above embodiment and will not be described in detail here.

[0086] It should be noted that the memory may include random access memory (RAM) and may also include non-volatile memory (non-volatile memory), such as at least one disk storage. Similarly, the processor may also be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0087] Although the embodiments disclosed herein are as described above, the contents described herein are merely embodiments for facilitating understanding of the present invention and are not intended to limit the present invention. Any person skilled in the art may make any modifications and variations in the form and details of the embodiments without departing from the spirit and scope of the present invention. However, the scope of protection of the present invention shall remain subject to the scope defined by the appended claims.

Claims

1. A transformer monitoring and adjustment method, comprising: Obtain vibration monitoring data and oil chromatography monitoring data within a preset time range before the current moment; Inputting the vibration monitoring data and the oil chromatogram monitoring data into a transformer fault probability prediction time series model to obtain a corresponding transformer fault probability value; Adjusting the period of oil chromatogram monitoring based on the transformer fault probability value to obtain a corresponding adjusted period; The adjusted period is in inverse proportion to the transformer failure probability value.

2. The method according to claim 1, characterized in that The transformer fault probability prediction time series model includes a time series prediction module and a probability conversion module; The time series prediction module is used to make predictions based on a preset AI model, wherein the preset AI model uses vibration monitoring data and oil chromatography monitoring data within a preset time range as prediction factors, and uses the transformer condition within a preset future time range as the prediction result; The probability conversion module is used to convert the transformer status within the preset future time range into the transformer failure probability value; The transformer status includes normal and abnormal.

3. The method according to claim 2, characterized in that Converting the transformer condition within the preset future time range into the transformer failure probability value includes: Obtaining the difference between the time when the transformer condition is abnormal for the first time in the preset future time range and the current time as the abnormality time; The difference obtained by subtracting the abnormal time consumption from one and dividing it by the preset future time range is used as the transformer failure probability value.

4. The method according to claim 1, wherein The vibration monitoring data includes vibration acceleration and vibration frequency, and the oil chromatography monitoring data includes gas concentration mean, gas concentration maximum and gas concentration minimum.

5. The method according to claim 1, wherein Adjusting the oil chromatogram monitoring period based on the transformer fault probability value to obtain a corresponding adjusted period includes: Obtaining a preset maximum cycle and a preset minimum cycle of oil chromatogram monitoring, and obtaining a difference between the preset maximum cycle and the preset minimum cycle as an adjustment space value; Obtaining the product of the adjustment space value and the transformer failure probability value as the adjustment amplitude; The preset minimum period is added to the adjustment amplitude to obtain an adjusted period.

6. The method according to claim 2, characterized in that The preset time range is 7 days, and the preset future time range is 7 hours.

7. A transformer monitoring and adjustment device, characterized in that: include: A feature acquisition module is used to acquire vibration monitoring data and oil chromatography monitoring data within a preset time range before the current moment; A probability prediction module, configured to input the vibration monitoring data and the oil chromatogram monitoring data into a transformer fault probability prediction time series model to obtain a corresponding transformer fault probability value; A cycle adjustment module, configured to adjust the cycle of oil chromatogram monitoring based on the transformer fault probability value to obtain a corresponding adjusted cycle; The adjusted period is in inverse proportion to the transformer failure probability value.

8. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the transformer monitoring and adjustment method according to any one of claims 1 to 6 is implemented.

9. A terminal, characterized in that: It includes a processor and a memory, and the memory is communicatively connected to the processor; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the transformer monitoring and adjustment method according to any one of claims 1 to 6.

Images