Transformer fault prediction method, system and related device

Abstract

The invention provides a transformer fault prediction method and system and a related device, and the method comprises the following steps: obtaining real-time operation parameters corresponding to a transformer, the real-time operation parameters comprising an electrical parameter, a thermal parameter, a case parameter, an environment parameter and data of gas dissolved in oil; the obtained real-time operation parameters are subjected to denoising processing, and denoised data information is obtained; carrying out standardization and fusion processing on the obtained denoised data information to obtain a unified feature vector; the obtained uniform feature vector is used as the input of a pre-constructed prediction model based on a multi-granularity cascade forest, the probability of fault occurrence of the to-be-detected transformer in a future time period is predicted, and the pre-constructed prediction model based on the multi-granularity cascade forest is obtained through optimization of an improved whale algorithm; according to the method, through innovation in multiple aspects of data fusion, comprehensive feature capture, real-time performance and accuracy improvement, generalization ability enhancement and the like, the accuracy and the real-time performance of transformer fault prediction are remarkably improved, and a powerful guarantee is provided for safe and stable operation of a power system.

Description

Technical Field

[0001] The present application belongs to the technical field of transformer fault diagnosis, and in particular relates to a transformer fault prediction method, system and related devices. Background Art

[0002] Transformers, as key nodes connecting all voltage levels in the power grid, play a vital role in the stable and healthy operation of power systems. Their operational status is crucial to the reliability of the power supply system. Transformer failures not only impact the national economy but also endanger public safety. Therefore, real-time monitoring of transformer operating status and the timely detection of potential faults are crucial for ensuring the safe and stable operation of the power grid.

[0003] Currently, data-driven transformer fault prediction technology has become a research hotspot. This method integrates multiple sources of transformer data, including electrical, thermal, mechanical, and environmental data, and uses machine learning algorithms to uncover underlying patterns and achieve early warning of faults. However, existing technologies still have significant drawbacks: severe data fragmentation, heterogeneous data formats from different sources, and difficulty in fusion; feature extraction relies on manual experience, making it difficult to fully capture fault characteristics; multi-physics field coupling simulation is computationally complex and difficult to meet real-time prediction requirements; the lack of a dynamic coordination mechanism makes it impossible to monitor changes in the transformer's operating status in real time; and the model's generalization ability is insufficient, making it poorly adaptable to new environments. These issues limit the accuracy and real-time nature of fault prediction and urgently need to be addressed through technological innovation. Summary of the Invention

[0004] The purpose of the present invention is to provide a transformer fault prediction method, system and related devices to solve the above-mentioned deficiencies in the existing transformer fault prediction.

[0005] In order to achieve the above object, the technical solution adopted in the present invention is: In a first aspect, the present invention provides a transformer fault prediction method comprising the following steps: Obtain the real-time operating parameters corresponding to the transformer, including electrical parameters, thermal parameters, chassis parameters, environmental parameters, and dissolved gas data in the oil; De-noising the obtained real-time operating parameters to obtain de-noised data information; The denoised data information is standardized and fused to obtain a unified feature vector; The obtained unified feature vector is used as the input of the pre-built prediction model based on multi-granularity cascade forest to predict the probability of failure of the transformer under test in the future time period, where: The pre-built prediction model based on multi-granularity cascade forest is optimized by an improved whale algorithm.

[0006] Preferably, the obtained real-time operating parameters are subjected to denoising processing using a wavelet transform method to obtain denoised data information.

[0007] Preferably, based on a dynamic weight allocation strategy, the denoised data information is standardized and fused to obtain a unified feature vector.

[0008] Preferably, the unified eigenvector is calculated by the following formula:

[0009] in, is a unified eigenvector; is the i-th eigenvector; To indicate the i The weight of a feature is calculated by the entropy weight method.

[0010] Preferably, the pre-built prediction model based on multi-granularity cascade forest is optimized by an improved whale algorithm, specifically by: Construct a prediction model based on multi-granularity cascade forests and set the optimization variables of the prediction model based on multi-granularity cascade forests; Randomly generate a population of whales, each individual represents a set of gcForest hyperparameters; Train the gcForest model corresponding to each individual, calculate the cross entropy loss and use it as the fitness value; Update whale positions based on the improved whale algorithm; The above process is repeated until convergence to obtain the pre-built prediction model based on multi-granularity cascade forest.

[0011] In a second aspect, the present invention provides a transformer fault prediction system, comprising: A parameter acquisition unit is used to obtain the real-time operating parameters corresponding to the transformer, including electrical parameters, thermal parameters, chassis parameters, environmental parameters and dissolved gas data in the oil; A parameter denoising unit is used to denoise the obtained real-time operating parameters to obtain denoised data information; A data fusion unit is used to standardize and fuse the denoised data information to obtain a unified feature vector; The fault prediction unit is used to use the obtained unified feature vector as the input of a pre-built prediction model based on a multi-granularity cascade forest to predict the probability of failure of the transformer under test in a future time period, where: The pre-built prediction model based on multi-granularity cascade forest is optimized by an improved whale algorithm.

[0012] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the electronic device executes the described method.

[0013] In a fourth aspect, the present invention provides a computing device cluster, comprising at least one computing device, each computing device comprising a processor and a memory; The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster performs the method.

[0014] In a fifth aspect, the present invention provides a computer program product, which includes computer-executable instructions, and the computer-executable instructions implement the method when executed.

[0015] In a sixth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions implement the described method when executed by a processor.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a transformer fault prediction method. This technical solution addresses the problems of data fragmentation, difficulty in feature extraction, poor real-time performance, and insufficient generalization capability in current transformer fault prediction technologies. It proposes denoising multi-source real-time operating parameters through wavelet transform, effectively removing noise interference and improving data quality. The denoised data is standardized and fused based on a dynamic weight allocation strategy, overcoming the problems of heterogeneous data formats and difficulty in fusion, generating a more representative unified feature vector, and providing a high-quality data foundation for subsequent fault prediction. The improved whale algorithm is used to optimize the multi-granularity cascade forest prediction model. By replacing manual experience with automated parameter adjustment, fault characteristics can be captured more comprehensively, avoiding the subjectivity and limitations of manual feature extraction, and improving the model's ability to capture fault characteristics.

[0017] In summary, this technical solution significantly improves the accuracy and real-time performance of transformer fault prediction through innovations in data fusion, comprehensive feature capture, improved real-time performance and accuracy, and enhanced generalization capabilities, providing a strong guarantee for the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0020] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0021] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0022] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0023] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0024] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0025] Example 1 This embodiment provides a transformer fault prediction method, comprising the following steps: Step 1: Obtain the real-time operating parameters corresponding to the transformer, which include electrical parameters, thermal parameters, chassis parameters, environmental parameters, and dissolved gas data in oil; The electrical parameters include voltage, current, power factor and other data collected in real time by smart meters and PMUs installed on the high-voltage and low-voltage sides of the transformer (sampling frequency ≥ 1kHz).

[0026] The thermal parameters include temperature information (spatial resolution ≤ 1 cm) obtained by global monitoring using optical fiber temperature sensors deployed on the transformer windings, core, and oil channel surfaces in combination with infrared thermal imagers.

[0027] The mechanical parameters include vibration signals captured by accelerometers (range ±50g, frequency range 0.5-10kHz) installed on the top and bottom of the transformer tank; and noise signals (frequency range 20Hz-20kHz) collected by a microphone array deployed in the surrounding environment.

[0028] The environmental parameters include temperature and humidity sensors (accuracy ±0.5°C, ±2%RH) installed around the transformer and weather station data (such as wind speed and sunshine intensity) obtained synchronously.

[0029] The concentration of dissolved gases in the oil is regularly collected by laser photoacoustic spectroscopy (detection limit ≤ 1 ppm) to obtain the concentrations of H2, CH4, C2H2 and other gases.

[0030] Step 2: De-noising the obtained real-time operating parameters using wavelet transform to obtain de-noised data information; Step 3: Based on the dynamic weight allocation strategy, the denoised data information is standardized and fused to obtain a unified feature vector; In step 4, the obtained unified feature vector is used as the input of the pre-built improved whale algorithm optimized multi-granularity cascade forest prediction model to predict the probability of failure of the transformer to be tested in the future time period.

[0031] Example 2 Based on Example 1, this embodiment provides a transformer fault prediction method. In step 3, a unified eigenvector is calculated by the following formula:

[0032] in, is a unified eigenvector; is the i-th eigenvector; To indicate the i The weight of a feature is calculated by the entropy weight method.

[0033] Example 3 Based on Example 1, this embodiment provides a transformer fault prediction method, which uses a pre-built improved whale algorithm to optimize the multi-granularity cascade forest prediction model. The specific method is: First, construct the objective function and use the cross entropy loss L as the objective function to measure the difference between the model prediction result and the true label:

[0034] Where N is the number of samples, C is the number of fault categories, is the true label, is the predicted probability.

[0035] Secondly, use IWOA to optimize gcForest hyperparameters: (1) Optimization variables: The hyperparameters of gcForest include the number of cascade layers L, the number of forests per layer F, the maximum depth of each tree D, etc. (2) Optimization process: 1. Initialize the population: Randomly generate a population of whales, each individual represents a set of gcForest hyperparameters (such as: ).

[0036] 2. Calculate fitness: Train the gcForest model corresponding to each individual and calculate the cross entropy loss L as the fitness value.

[0037] 3. Position update: Update the whale position (i.e., gcForest hyperparameters) according to the improved WOA strategy, including adaptive weight adjustment, nonlinear convergence factor update, and chaotic perturbation.

[0038] 4. Iterative optimization: Repeat the above process until convergence (e.g., the maximum number of iterations T = 100 or the fitness value change is less than the threshold).

[0039] Finally, model training and validation: (1) Data partitioning: The dataset is divided into a training set (70%), a validation set (15%), and a test set (15%).

[0040] (2) Cross-validation: Use 5-fold cross-validation to evaluate model performance and avoid overfitting.

[0041] (3) Hyperparameter selection: Record the hyperparameter combination that minimizes the cross entropy loss as the optimal gcForest model.

[0042] Example 4 This embodiment provides a transformer fault prediction system, including: A parameter acquisition unit is used to obtain the real-time operating parameters corresponding to the transformer, including electrical parameters, thermal parameters, chassis parameters, environmental parameters and dissolved gas data in the oil; A parameter denoising unit is used to denoise the obtained real-time operating parameters to obtain denoised data information; A data fusion unit is used to standardize and fuse the denoised data information to obtain a unified feature vector; The fault prediction unit is used to use the obtained unified feature vector as the input of a pre-built prediction model based on a multi-granularity cascade forest to predict the probability of failure of the transformer under test in a future time period, where: The pre-built prediction model based on multi-granularity cascade forest is optimized by an improved whale algorithm.

[0043] Example 5 This embodiment also provides a computing device. The computing device includes a bus, a processor, a memory, and a communication interface. The processor, the memory, and the communication interface communicate with each other via the bus. The computing device can be a server or a terminal device. It should be understood that this application does not limit the number of processors and memories in the computing device.

[0044] A bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, control buses, and so on. For ease of presentation, a bus can include the pathways that transmit information between various components of a computing device (e.g., memory, processor, and communication interfaces).

[0045] The processor may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a microprocessor (MP), or a digital signal processor (DSP).

[0046] The memory may include volatile memory, such as random access memory (RAM). The processor may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0047] The memory stores executable program code, and the processor executes the executable program code to implement the functions of the aforementioned units, thereby implementing, for example, the method described in Example 1. That is, the memory may store instructions for the methods and functions of the computing device described in any of the above embodiments.

[0048] The communication interface uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device and other devices or a communication network.

[0049] Example 6 This embodiment also provides a computing device cluster. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0050] The computing device cluster includes at least one computing device. The memory of one or more computing devices in the computing device cluster may store the same instructions for executing the method and functions related to the computing device in any of the above embodiments.

[0051] In some possible implementations, the memory of one or more computing devices in the computing device cluster may also store partial instructions for executing the methods and functions related to the computing devices in any of the above embodiments. In other words, the combination of one or more computing devices can jointly execute instructions for executing the methods and functions of the computing devices.

[0052] It should be noted that the memories in different computing devices in the computing device cluster may store different instructions, each for executing part of the functions of the apparatus.

[0053] In some possible implementations, one or more computing devices in a computing device cluster may be connected via a network. The network may be a wide area network (WAN) or a local area network (LAN). Two computing devices are connected via the network. Specifically, the connection to the network is achieved via a communication interface in each computing device.

[0054] An embodiment of the present disclosure further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method and functions involving a computing device in any of the above embodiments.

[0055] Example 7 This embodiment further provides a computer-readable storage medium having computer instructions stored thereon. When a processor executes the instructions, the processor executes the methods and functions related to the computing device in any of the above embodiments.

[0056] In general, various embodiments of the present disclosure may be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software, which may be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are shown and described as block diagrams, flow charts, or using some other pictorial representation, it should be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented as, by way of non-limiting example, hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or a controller or other computing device, or some combination thereof.

[0057] Example 8 The present embodiment provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which are executed in a device on a real or virtual processor of a target to perform the process / method described above with reference to the accompanying drawings. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functionality of program modules can be combined or divided between program modules as needed. The machine-executable instructions for the program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0058] The computer program code for implementing the disclosed method can be written in one or more programming languages. These computer program codes can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device so that the program code, when executed by the computer or other programmable data processing device, causes the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on a computer, partially on a computer, as an independent software package, partially on a computer and partially on a remote computer or entirely on a remote computer or server.

[0059] In the context of the present disclosure, computer program code or related data may be carried by any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, and the like. Examples of signals may include electrical, optical, radio, acoustic, or other forms of propagated signals, such as carrier waves, infrared signals, and the like.

[0060] A computer-readable medium may be any tangible medium containing or storing a program for or relating to an instruction execution system, apparatus, or device, or a data storage device such as a data center containing one or more available media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination thereof. More detailed examples of computer-readable storage media include an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0061] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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. 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 various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A transformer fault prediction method, characterized in that: The following steps are involved: Obtain the real-time operating parameters corresponding to the transformer, including electrical parameters, thermal parameters, chassis parameters, environmental parameters, and dissolved gas data in the oil; De-noising the obtained real-time operating parameters to obtain de-noised data information; The denoised data information is standardized and fused to obtain a unified feature vector; The obtained unified feature vector is used as the input of the pre-built prediction model based on multi-granularity cascade forest to predict the probability of failure of the transformer under test in the future time period, where: The pre-built prediction model based on multi-granularity cascade forest is optimized by an improved whale algorithm.

2. A transformer fault prediction method according to claim 1, characterized in that: The obtained real-time operating parameters are denoised using wavelet transform to obtain denoised data information.

3. A transformer fault prediction method according to claim 1, characterized in that: Based on the dynamic weight allocation strategy, the denoised data information is standardized and fused to obtain a unified feature vector.

4. A transformer fault prediction method according to claim 3, characterized in that: The unified eigenvector is calculated by the following formula: in, is a unified eigenvector; is the i-th eigenvector; To indicate the i The weight of a feature is calculated by the entropy weight method.

5. A transformer fault prediction method according to claim 1, characterized in that: The pre-built prediction model based on multi-granularity cascade forest is optimized by the improved whale algorithm, specifically: Construct a prediction model based on multi-granularity cascade forests and set the optimization variables of the prediction model based on multi-granularity cascade forests; Randomly generate a population of whales, each individual represents a set of gcForest hyperparameters; Train the gcForest model corresponding to each individual, calculate the cross entropy loss and use it as the fitness value; Update whale positions based on the improved whale algorithm; The above process is repeated until convergence, and the pre-built prediction model based on multi-granularity cascade forest is obtained.

6. A transformer fault prediction system, characterized in that: include: A parameter acquisition unit is used to obtain the real-time operating parameters corresponding to the transformer, including electrical parameters, thermal parameters, chassis parameters, environmental parameters and dissolved gas data in the oil; A parameter denoising unit is used to denoise the obtained real-time operating parameters to obtain denoised data information; A data fusion unit is used to standardize and fuse the denoised data information to obtain a unified feature vector; The fault prediction unit is used to use the obtained unified feature vector as the input of a pre-built prediction model based on a multi-granularity cascade forest to predict the probability of failure of the transformer under test in a future time period, where: The pre-built prediction model based on multi-granularity cascade forest is optimized by an improved whale algorithm.

7. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein computer instructions are stored in the memory. When the computer instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 5.

8. A computing device cluster, characterized in that: comprising at least one computing device, each computing device including a processor and a memory; The processor of the at least one computing device is configured to execute instructions stored in a memory of the at least one computing device, so that the computing device cluster performs the method according to any one of claims 1 to 5.

9. A computer program product, characterized in that The computer program product contains computer-executable instructions, which implement the method according to any one of claims 1 to 5 when executed.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which implement the method according to any one of claims 1 to 5 when executed by a processor.

Images