A method, device and medium for online monitoring of transformer oil acid value

Abstract

The present application discloses a method, device, and medium for online monitoring of the acid value of transformer oil, relating to the field of power equipment monitoring technology. The method comprises: obtaining a target current signal and target temperature and humidity data in the transformer oil currently being collected; inputting the target current signal and target temperature and humidity data into an optimized acid value calculation model to obtain the acid value data of the transformer oil; the optimized acid value calculation model is an acid value calculation model in which the model dynamic parameters are optimized by a convolutional neural network. The present application calculates the acid value by obtaining the current signal and temperature and humidity data of the transformer oil in real time, thereby enabling online monitoring of the acid value of the transformer oil. The dynamic parameters of the model in the acid value calculation model are optimized before the acid value is calculated, thereby ensuring the accuracy of the acid value calculation result and adapting to acid value monitoring of different oil types and extreme working conditions.

Description

Technical Field

[0001] The present application relates to the technical field of power equipment monitoring, and in particular to a method, device and medium for online monitoring of transformer oil acid value. Background Art

[0002] Transformer oil acidity is a key indicator for assessing oil aging. Traditional testing methods rely on laboratory titration analysis, which suffers from issues such as poor timeliness, high costs, and the inability to monitor in real time. Furthermore, existing oleic acid calculation algorithms rely on fixed parameters and are unsuitable for varying oil types and extreme operating conditions. Summary of the Invention

[0003] The purpose of this application is to provide a method, device and medium for online monitoring of transformer oil acid value, which can monitor the transformer oil acid value in real time, and the model parameters of oleic acid calculation are continuously updated and optimized to adapt to different oil types and extreme working conditions.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a method for online monitoring of transformer oil acid value, comprising:

[0006] Obtain the target current signal and target temperature and humidity data in the transformer oil currently collected;

[0007] The target current signal and target temperature and humidity data are input into the optimized acid value calculation model to obtain the acid value data of the transformer oil; the optimized acid value calculation model is an acid value calculation model whose model dynamic parameters are optimized by a convolutional neural network;

[0008] The expression of the acid value calculation model is:

[0009]

[0010] Alternatively, the acid value calculation model is expressed as:

[0011]

[0012] Where, represents acid value; I is current signal; T is temperature; RH is humidity; k, α, C are model dynamic parameters; v is oil flow rate; β is flow rate compensation coefficient.

[0013] In a second aspect, the present application provides an online monitoring device for transformer oil acid value, comprising:

[0014] A data acquisition module is used to obtain the target current signal and target temperature and humidity data in the transformer oil currently collected;

[0015] The acid value calculation module is used to input the target current signal and target temperature and humidity data into the optimized acid value calculation model to obtain the acid value data of the transformer oil; the optimized acid value calculation model is an acid value calculation model whose model dynamic parameters are optimized by a convolutional neural network;

[0016] The expression of the acid value calculation model is:

[0017]

[0018] Alternatively, the acid value calculation model is expressed as:

[0019]

[0020] Where, represents acid value; I is current signal; T is temperature; RH is humidity; k, α, C are model dynamic parameters; v is oil flow rate; β is flow rate compensation coefficient.

[0021] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for online monitoring of transformer oil acid value.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for online monitoring of transformer oil acid value.

[0023] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0024] The present application provides a method, device, and medium for online monitoring of the acid value of transformer oil, which obtains a target current signal and target temperature and humidity data in the transformer oil; inputs the target current signal and target temperature and humidity data into an optimized acid value calculation model to obtain the acid value data of the transformer oil; the optimized acid value calculation model is an acid value calculation model whose model dynamic parameters have been optimized using a convolutional neural network. The present application calculates the acid value by obtaining the current signal and temperature and humidity data of the transformer oil in real time, which can achieve online monitoring of the acid value of the transformer oil. The dynamic parameters of the model in the acid value calculation model are continuously optimized to ensure the accuracy of the acid value calculation results, and can adapt to acid value monitoring of different oil types and extreme working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 This is an application environment diagram of an online monitoring method for transformer oil acid value in one embodiment of the present application;

[0027] Figure 2 A schematic flow chart of a method for online monitoring of transformer oil acid value provided in one embodiment of the present application;

[0028] Figure 3 A schematic diagram of the technical concept of a method for online monitoring of transformer oil acid value provided in one embodiment of the present application;

[0029] Figure 4 A schematic structural diagram of a three-electrode sensor provided in one embodiment of the present application;

[0030] Figure 5 A schematic diagram of the architecture of the intelligent early warning system provided in one embodiment of the present application;

[0031] Figure 6 A schematic diagram of the functional modules of an online monitoring device for transformer oil acid value provided in one embodiment of the present application;

[0032] Figure 7 A schematic diagram of the structure of a computer device provided in one embodiment of the present application.

[0033] Reference numerals:

[0034] 1-housing; 2-porous filter; 3-circuit board; 4-humidity sensor; 5-STM32F407 microcontroller; 6-temperature sensor; 7-reference electrode; 8-working electrode; 9-graphite electrode. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0036] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0037] The transformer oil acid value online monitoring method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal communicates with the server via a network. The data storage system can store data that the server needs to process. The data storage system can be set up separately, integrated on the server, or placed on a cloud or other server. The terminal can send the currently collected target current signal and target temperature and humidity data of the transformer oil to the server. After receiving the target current signal and target temperature and humidity data of the transformer oil, the server obtains the target current signal and target temperature and humidity data; inputs the target current signal and target temperature and humidity data into an optimized acid value calculation model to obtain the acid value data of the transformer oil; the optimized acid value calculation model is an acid value calculation model whose model dynamic parameters are optimized using a convolutional neural network. The server can feed back the obtained transformer oil acid value data to the terminal. In addition, in some embodiments, the transformer oil acid value online monitoring method can also be implemented independently by the server or the terminal. For example, the terminal can directly perform online transformer oil acid value monitoring based on the currently collected target current signal and target temperature and humidity data of the transformer oil, or the server can obtain the currently collected target current signal and target temperature and humidity data of the transformer oil from the data storage system and perform online transformer oil acid value monitoring.

[0038] The terminals may be, but are not limited to, various desktop computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The server may be implemented as an independent server or a server cluster consisting of multiple servers, or as a cloud server.

[0039] In an exemplary embodiment, Figure 2 and Figure 3 As shown, a method for online monitoring of transformer oil acid value is provided. The method is executed by a computer device, which can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 The server in is used as an example for description, including the following steps 101 to 102.

[0040] Step 101: Acquire the target current signal and target temperature and humidity data in the transformer oil currently collected.

[0041] The collected current signal and temperature and humidity data can be pre-processed first, such as signal filtering and normalization.

[0042] Step 102: Input the target current signal and the target temperature and humidity data into the optimized acid value calculation model to obtain the acid value data of the transformer oil; the optimized acid value calculation model is an acid value calculation model after the model dynamic parameters are optimized by a convolutional neural network.

[0043] By implementing steps 101 to 102 above, on the one hand, the acid value is calculated using the current signal and temperature and humidity data in the transformer oil. Compared with the traditional detection method that relies on laboratory titration analysis, this method improves timeliness and enables real-time online monitoring. On the other hand, the acid value measurement conditions of transformer oil are relatively complex. The working conditions of the transformer oil change dynamically, and the dynamic parameters of the acid value calculation model need to change continuously to achieve a relatively high accuracy of the acid value measurement. Therefore, the model parameters of the acid value calculation model are continuously optimized through a convolutional neural network to ensure the accuracy of the parameter values, thereby improving the accuracy of the acid value calculation.

[0044] In another exemplary embodiment of the present application, in step 101, considering that the existing monitoring sensor is easily disturbed by environmental factors such as temperature, humidity, and oil flow rate, and the error exceeds ±10%, the present application adopts a three-electrode sensor to collect the electrochemical signal (current signal) and temperature and humidity data in the transformer oil in real time, such as Figure 4 As shown, the three-electrode sensor includes a working electrode 8, a reference electrode 7, and an auxiliary electrode. The working electrode 8 is a platinum nanocoated electrode with a plasma-permeable surface, resulting in an active surface area ≥50 cm² / g. The reference electrode 7 is an Ag / AgCl electrode (using 3M KCl as the electrolyte) with a potential stability error of less than ±2 mV. The auxiliary electrode is a graphite electrode 9, which stabilizes the electrochemical reaction current. The three-electrode sensor's housing 1 is made of polytetrafluoroethylene (PTFE) and has a temperature resistance range of -50°C to 250°C. It integrates a temperature sensor 6 (with an accuracy of ±0.1°C) and a humidity sensor 4 (with an error of less than 3%RH). The three-electrode sensor also includes an STM32F407 microcontroller 5 and a circuit board 3. The temperature sensor 6, humidity sensor 4, and STM32F407 microcontroller 5 are mounted on circuit board 3. The electrodes of the three-electrode sensor transmit collected signals to the STM32F407 microcontroller 5 via circuit board 3, which then outputs the temperature, humidity, and current signals. In order to ensure the accuracy of the current signal detected by the three-electrode sensor, a porous filter 2 is provided outside each electrode.

[0045] In a real-world monitoring environment, the three-electrode sensor was vertically inserted into the oil circulation area at the bottom of a transformer oil tank, ensuring that the electrodes were completely immersed in the oil (immersion depth ≥ 10 cm). The housing 1 was sealed, and the sensor was secured with a PTFE seal to prevent impurities in the transformer oil from entering the sensor's internal circuitry. During signal acquisition, a step voltage (-0.2 V to +0.5 V) was applied to the working electrode 8 in constant potential mode. The redox current signal was collected (sampling frequency 1 Hz), and the oil temperature (accuracy ±0.1°C) and humidity (error <3%RH) were simultaneously recorded.

[0046] In another exemplary embodiment of the present application, in step 102, the expression of the acid value calculation model is:

[0047]

[0048] Where, represents the acid value; I is the electrochemical signal, that is, the current signal; T is the temperature; RH is the humidity; k, α, and C are the dynamic parameters of the model (parameters that need to be optimized).

[0049] As an example, before model parameter optimization, the current signal I = 12.5 μA, temperature T = 45 ° C, and humidity RH = 65% are input into the oleic acid calculation model:

[0050]

[0051] After the convolutional neural network dynamically optimized the model parameters, the output optimized model parameters were: k=0.85, α=0.025, C=0.008, and the final acid value calculation result was 0.068 mg KOH / g. The acid value calculation result has been calibrated and the result is more accurate.

[0052] In another exemplary embodiment of the present application, in step 102, the expression of the acid value calculation model is:

[0053]

[0054] Where, represents acid value; I is the electrochemical signal, i.e., the current signal; T is temperature; RH is humidity; v is the oil flow rate; β is the flow rate compensation coefficient; k, α, and C are model dynamic parameters.

[0055] Through the above two acid value calculation formulas, the acid value in transformer oil can be accurately calculated based on the current signal and temperature and humidity data, realizing online monitoring of acid value.

[0056] In another exemplary embodiment of the present application, the online monitoring method for transformer oil acid value further includes: optimizing the model parameters of the acid value calculation model using a convolutional neural network to obtain an optimized acid value calculation model, specifically:

[0057] (1) The current signal peak, temperature gradient, humidity change rate, and historical acid value in the preset time period before the target data acquisition time are input into the convolutional neural network to obtain the optimal model parameter values ​​of the acid value calculation model. The target data refers to the currently acquired target current signal and target temperature and humidity data.

[0058] Figure 3 The convolutional neural network shown in the figure takes current signals, temperature, humidity, and acid value as inputs. In practice, the current signal peak, temperature gradient, and humidity change rate are calculated based on the current signals, temperature, and humidity over a preset time period to determine the optimal model parameters for the acid value calculation model. The convolutional neural network comprises an input layer, multiple convolutional layers, a fully connected layer, and an output layer, all connected in series. The convolutional layers can use a 3×3 convolution kernel.

[0059] The dynamic parameters (such as k, α, C) of the convolutional neural network dynamic optimization model are adopted. The input of the convolutional neural network includes the current signal peak, temperature gradient, humidity change rate and historical acid value data of a preset time period (such as a time window of 7 days). The output layer is the optimized parameter value (such as k, α, C).

[0060] The convolutional neural network used in this step is a trained network. Its training dataset uses 100,000 sets of experimental data from 10 types of transformer oil (including mineral oil and synthetic ester) at temperatures between -30°C and 80°C. The experimental data includes the transformer oil's current signal, temperature and humidity data, the corresponding acid value, and the corresponding model parameter values. To ensure the accuracy of the convolutional neural network training, data with calculated acid values ​​that are closer to the measured acid values ​​are selected to ensure more accurate assignment of model parameters. The validation error of the trained convolutional neural network is less than 1%.

[0061] (2) Substitute the optimal values ​​of the model parameters of the acid value calculation model into the acid value calculation model to obtain the optimized acid value calculation model.

[0062] In another exemplary embodiment of the present application, after executing step 102, the transformer oil acid value online monitoring method further includes:

[0063] The acid value data of the transformer oil is uploaded to the cloud platform using the NB-IoT module. Figure 5 shown.

[0064] The NB-IoT module supports multi-node networking, connecting up to 50 sensor nodes, and data transmission intervals can be configured from 1 minute to 1 hour. The NB-IoT module uses the AES-256 encryption protocol to transmit data, ensuring data security and supporting resumable uploads to ensure data integrity. Data can be uploaded to the cloud using the NB-IoT module every 5 minutes, using the AES-256 encryption protocol and a transmission success rate of ≥99%. The NB-IoT module transmits data to the cloud platform via a LoRa gateway or base station using the LoRaWAN Class C communication protocol. This cloud platform allows for ARIMA trend analysis, alarm list display, acid value curve display, multi-level alarm triggering, and InfluxDB database configuration.

[0065] In another exemplary embodiment of the present application, after executing step 102, the transformer oil acid value online monitoring method further includes:

[0066] Determine whether the acid value data of the transformer oil exceeds a preset threshold; if so, trigger a multi-level alarm mechanism according to the extent to which the acid value data of the transformer oil exceeds the preset threshold.

[0067] When the acid value exceeds a preset threshold, a multi-level alarm system is triggered. The multi-level alarm system includes three levels: early warning, serious, and emergency. The preset threshold for the multi-level alarm signal is dynamically adjusted with the ambient temperature. For example, the preset threshold in winter is 10% lower than that in summer.

[0068] Early warning (0.08 mg KOH / g): Triggers local audible and visual alarms.

[0069] Severe (0.12 mg KOH / g): A text message is sent to the maintenance personnel's mobile phone.

[0070] Emergency (0.15 mg KOH / g): Automatically generates an oil change work order and synchronizes it to the operation and maintenance platform (for example, the maintenance terminal).

[0071] When the acid value exceeds 0.12 mg KOH / g (exceeding the critical threshold), a text message is sent to maintenance personnel and an oil change work order is generated. It is recommended to change the oil within 48 hours.

[0072] In another exemplary embodiment of the present application, after executing step 102, the transformer oil acid value online monitoring method further includes:

[0073] (1) When the acid value of the transformer oil exceeds a preset threshold value for a preset number of days (e.g., 3 days), the LSTM model is used to automatically analyze the oil temperature trend of the transformer oil and determine the optimal oil change time.

[0074] (2) Generate a maintenance work order based on the optimal oil change time and oil change priority of each transformer and push it to the mobile terminal device.

[0075] Maintenance work orders are pushed to mobile devices via the MQTT protocol, supporting real-time tracking of work order status.

[0076] After the transformer oil is changed, the three-electrode sensor needs to be recalibrated and the initial values ​​of the model parameters in the acid value calculation model need to be recalculated. The laboratory calibration value of the new oil (initial acid value 0.05 mg KOH / g) is entered, and the initial calibration program is automatically run. Ten sets of electrochemical signal and temperature and humidity data are collected (at 1-minute intervals). Based on the collected electrochemical signals and temperature and humidity data and the corresponding initial acid values, the initial model parameters k = 0.82, α = 0.03, and C = 0.01 are calculated. The calibration error is less than 0.5%, and the verification error is less than 0.3%.

[0077] This application uses a three-electrode sensor to collect electrochemical signals, combines an acid value calculation model with the dynamic optimization parameters of a convolutional neural network, and achieves high-precision real-time acid value calculation. It also integrates NB-IoT multi-node transmission, multi-level intelligent alarms, and automatic maintenance work order generation to support dynamic threshold adjustment and full-process operation and maintenance management. This application addresses the issues of strong lag and poor adaptability of traditional detection methods, making it particularly suitable for extreme environments and complex working conditions. It significantly improves the efficiency and safety of transformer operation and maintenance, and is suitable for real-time monitoring of oil quality, intelligent early warning, and operation and maintenance management of transformers in power systems. It has important practical value and broad application prospects.

[0078] The present application also provides an application scenario, which applies the above-mentioned method for online monitoring of the acid value of transformer oil. Specifically: the method for online monitoring of the acid value of transformer oil provided in this embodiment can be applied to the transformer oil product evaluation scenario in the power system. The scenario includes a data acquisition link, a transformer oil acid value calculation link and a transformer oil product evaluation link; the data acquisition link is used to collect the current signal and temperature and humidity data of the transformer oil; the transformer oil acid value calculation link is used to calculate the acid value based on the collected current signal and temperature and humidity data; the transformer oil product evaluation link is used to evaluate the degree of aging of the transformer oil according to the acid value calculation results. The method for online monitoring of the acid value of transformer oil provided in this embodiment belongs to the transformer oil acid value calculation link.

[0079] Based on the same inventive concept, embodiments of the present application also provide an online transformer oil acid value monitoring device for implementing the aforementioned online transformer oil acid value monitoring method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the online transformer oil acid value monitoring device provided below can be found in the above-described limitations of the online transformer oil acid value monitoring method and will not be further elaborated here.

[0080] In an exemplary embodiment, Figure 6 As shown, a transformer oil acid value online monitoring device is provided, comprising:

[0081] The data acquisition module M1 is used to obtain the target current signal and target temperature and humidity data in the transformer oil currently collected.

[0082] The acid value calculation module M2 is used to input the target current signal and the target temperature and humidity data into the optimized acid value calculation model to obtain the acid value data of the transformer oil; the optimized acid value calculation model is an acid value calculation model whose model parameters are optimized by a convolutional neural network;

[0083] The expression of the acid value calculation model is:

[0084]

[0085] Alternatively, the acid value calculation model is expressed as:

[0086]

[0087] Where, represents acid value; I is current signal; T is temperature; RH is humidity; k, α, C are model dynamic parameters; v is oil flow rate; β is flow rate compensation coefficient.

[0088] In an exemplary embodiment, a computer device is provided. The computer device (also referred to as a computer device) may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store online monitoring data of transformer oil acid value. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for online monitoring of transformer oil acid value is implemented.

[0089] Those skilled in the art will understand that Figure 7The structure shown in the figure is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method embodiments are implemented.

[0090] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0091] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0092] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0093] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0094] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for online monitoring of transformer oil acid value, characterized in that: include: Obtain the target current signal and target temperature and humidity data in the transformer oil currently collected; The collected target current signal and target temperature and humidity data are input into the optimized acid value calculation model to obtain the acid value data of the transformer oil; the optimized acid value calculation model is an acid value calculation model whose model dynamic parameters are optimized by a convolutional neural network; The expression of the acid value calculation model is: ； Alternatively, the acid value calculation model is expressed as: ； Where, represents acid value; I is current signal; T is temperature; RH is humidity; k, α, C are model dynamic parameters; v is oil flow rate; β is flow rate compensation coefficient.

2. The method for online monitoring of transformer oil acid value according to claim 1, wherein: The online monitoring method for transformer oil acid value further includes: optimizing the model parameters of the acid value calculation model using a convolutional neural network to obtain an optimized acid value calculation model, specifically: The current signal peak, temperature gradient, humidity change rate, and historical acid value in a preset time period before the target data acquisition time are input into a convolutional neural network to obtain the optimal model parameter values ​​of the acid value calculation model; the target data refers to the currently acquired target current signal and target temperature and humidity data; The optimal values ​​of the model parameters of the acid value calculation model are substituted into the acid value calculation model to obtain an optimized acid value calculation model.

3. The method for online monitoring of transformer oil acid value according to claim 1, wherein: The transformer oil acid value online monitoring method further comprises: The acid value data of the transformer oil is uploaded to the cloud platform using the NB-IoT module.

4. The method for online monitoring of transformer oil acid value according to claim 1, wherein: The transformer oil acid value online monitoring method further comprises: Determining whether the acid value data of the transformer oil exceeds a preset threshold; If so, a multi-level alarm mechanism is triggered according to the extent that the acid value data of the transformer oil exceeds the preset threshold.

5. The method for online monitoring of transformer oil acid value according to claim 1, wherein: The transformer oil acid value online monitoring method further comprises: When the acid value data of the transformer oil exceeds a preset threshold for a preset number of days, the LSTM model is used to automatically analyze the oil temperature trend of the transformer oil and determine the optimal oil change time; A maintenance work order is generated based on the optimal oil change time and oil change priority level of each transformer and pushed to the mobile terminal device.

6. A transformer oil acid value online monitoring device, characterized in that: include: A data acquisition module is used to obtain the target current signal and target temperature and humidity data in the transformer oil currently collected; The acid value calculation module is used to input the target current signal and target temperature and humidity data into the optimized acid value calculation model to obtain the acid value data of the transformer oil; the optimized acid value calculation model is an acid value calculation model whose model dynamic parameters are optimized by a convolutional neural network; The expression of the acid value calculation model is: ； Alternatively, the acid value calculation model is expressed as: ； Where, represents acid value; I is current signal; T is temperature; RH is humidity; k, α, C are model dynamic parameters; v is oil flow rate; β is flow rate compensation coefficient.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for online monitoring of transformer oil acid value according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for online monitoring of the acid value of transformer oil according to any one of claims 1 to 5 is implemented.

Images