Improved transformer operation state monitoring method and device and transformer

Abstract

The invention provides an improved transformer operation state monitoring method and device and a transformer, and the method comprises the steps: determining an evaluation score of a photoacoustic spectrometry device and a corresponding photoacoustic spectrometry parameter weight; determining an evaluation score of the partial discharge equipment and a corresponding partial discharge weight; determining an evaluation score of the iron core grounding current equipment and a corresponding iron core grounding current weight; based on a transformer state evaluation model, fusing the evaluation score of the photoacoustic spectrum equipment, the photoacoustic spectrum parameter weight, the evaluation score of the partial discharge equipment, the partial discharge weight, the evaluation score of the iron core grounding current equipment and the iron core grounding current weight to obtain a current state value of the transformer; the current state value is input to the LSTM prediction model, the state prediction score of the transformer at any prediction moment is output, the LSTM prediction model is obtained through pre-training based on a dynamic transformer state value sample and a state prediction sample, and the accuracy of transformer operation state monitoring is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and in particular to an improved transformer operating status monitoring method, device and transformer. Background Art

[0002] Usually, the operating status of the transformer is evaluated by online monitoring devices installed on it, such as pressure sensors, voltage and current sensors, and temperature sensors. However, currently, a variety of status monitoring methods are installed for transformer operating status monitoring, so various types of data are involved, including temperature, gas content in oil, internal partial discharge, etc. However, these data come from various sources, with different formats and qualities, and are mostly fixed-size data.

[0003] Therefore, how to improve the accuracy of transformer operating status monitoring has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0004] The present invention provides an improved transformer operating state monitoring method, device and transformer, which are used to solve the defect of poor accuracy of transformer operating state monitoring in the prior art.

[0005] In a first aspect, the present invention provides an improved transformer operating status monitoring method, comprising:

[0006] Determine the evaluation score of the photoacoustic spectroscopy equipment and the corresponding photoacoustic spectroscopy parameter weight;

[0007] Determine the assessment score of the partial discharge equipment and the corresponding partial discharge weight;

[0008] Determine the evaluation score of the core grounding current device and the corresponding core grounding current weight;

[0009] Based on the transformer state assessment model, the assessment score of the photoacoustic spectroscopy device, the photoacoustic spectroscopy parameter weight, the assessment score of the partial discharge device, the partial discharge weight, the assessment score of the core grounding current device and the core grounding current weight are integrated to obtain the current state value of the transformer;

[0010] Wherein, the transformer state assessment model is:

[0011]

[0012] Among them, S represents the current state value of the transformer, ρ i represents the weight of the access parameter, C irepresents the normalized score of the access equipment, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, ρ1=0.45, C2 represents the evaluation score of the partial discharge equipment, ρ2=0.4, C3 represents the evaluation score of the core grounding current equipment, ρ3=0.15;

[0013] The current state value is input into the LSTM prediction model, and the state prediction score of the transformer at any prediction time is output. The LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples.

[0014] According to an improved transformer operating status monitoring method provided by the present invention, the step of determining the evaluation score of the photoacoustic spectroscopy device comprises:

[0015] Determine total hydrocarbon and acetylene values ​​in photoacoustic spectroscopy equipment;

[0016] The total hydrocarbon value and the acetylene value are input into the photoacoustic spectroscopy equipment score evaluation formula to obtain the evaluation score of the photoacoustic spectroscopy equipment.

[0017] According to an improved transformer operating status monitoring method provided by the present invention, the photoacoustic spectroscopy equipment score evaluation formula is:

[0018]

[0019] Among them, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, G1 represents the total hydrocarbon value, and G2 represents the acetylene value.

[0020] According to an improved transformer operation status monitoring method provided by the present invention, the step of determining the evaluation score of the partial discharge device comprises:

[0021] Determine the discharge amplitude and discharge times of partial discharge equipment;

[0022] The discharge amplitude and the number of discharges are input into a partial discharge equipment score evaluation formula to obtain an evaluation score for the partial discharge equipment.

[0023] According to an improved transformer operating status monitoring method provided by the present invention, the partial discharge equipment score evaluation formula is:

[0024]

[0025] Among them, C2 represents the evaluation score of the partial discharge equipment, D1 represents the discharge amplitude, and D2 represents the number of discharges.

[0026] According to an improved transformer operation status monitoring method provided by the present invention, the step of determining the evaluation score of the core grounding current device comprises:

[0027] Determine the ground current data in the core ground current device;

[0028] The grounding current data is input into the core grounding current equipment score evaluation formula to obtain the evaluation score of the core grounding current equipment.

[0029] According to an improved transformer operation status monitoring method provided by the present invention, the core grounding current equipment score evaluation formula is:

[0030] C3=100×cos[(A1-100)π]

[0031] Among them, C3 represents the evaluation score of the core grounding current equipment, and A1 represents the grounding current data.

[0032] An improved transformer operating status monitoring method provided by the present invention also includes:

[0033] The model parameters of the LSTM prediction model are determined as follows:

[0034] The input feature dimension is 3, the number of LSTM hidden units is 200, the number of LSTM layers is 200, the batch size is 3, and the future time length is 5 hours.

[0035] In a second aspect, the present invention further provides an improved transformer operation status monitoring device, comprising:

[0036] A first determination module is used to determine the evaluation score of the photoacoustic spectroscopy device and the corresponding photoacoustic spectroscopy parameter weight;

[0037] A second determination module is used to determine the evaluation score of the partial discharge equipment and the corresponding partial discharge weight;

[0038] A third determination module is used to determine the evaluation score of the core grounding current device and the corresponding core grounding current weight;

[0039] An evaluation module is used to integrate the evaluation score of the photoacoustic spectroscopy device, the photoacoustic spectroscopy parameter weight, the evaluation score of the partial discharge device, the partial discharge weight, the evaluation score of the core grounding current device and the core grounding current weight based on the transformer state evaluation model to obtain the current state value of the transformer;

[0040] Wherein, the transformer state assessment model is:

[0041]

[0042] Among them, S represents the current state value of the transformer, ρ i represents the weight of the access parameter, C irepresents the normalized score of the access equipment, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, ρ1=0.45, C2 represents the evaluation score of the partial discharge equipment, ρ2=0.4, C3 represents the evaluation score of the core grounding current equipment, ρ3=0.15;

[0043] The prediction module is used to input the current state value into the LSTM prediction model and output the state prediction score of the transformer at any prediction time. The LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples.

[0044] In a third aspect, the present invention further provides a transformer, which is used to execute the improved transformer operating status monitoring method as described in any one of the above items.

[0045] In a fourth aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, an improved transformer operating status monitoring method as described above is implemented.

[0046] In a fifth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the improved transformer operating status monitoring method as described in any one of the above is implemented.

[0047] In a sixth aspect, the present invention further provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the improved transformer operating status monitoring method as described above is implemented.

[0048] The present invention provides an improved transformer operation status monitoring method, device and transformer, which determine the evaluation score of a photoacoustic spectroscopy device and the corresponding photoacoustic spectroscopy parameter weight; determine the evaluation score of a local discharge device and the corresponding local discharge weight; determine the evaluation score of a core grounding current device and the corresponding core grounding current weight; based on a transformer state evaluation model, the evaluation score of the photoacoustic spectroscopy device, the photoacoustic spectroscopy parameter weight, the evaluation score of the local discharge device, the local discharge weight, the evaluation score of the core grounding current device and the core grounding current weight are integrated to obtain the current state value of the transformer; the current state value is input into an LSTM prediction model, and the state prediction score of the transformer at any prediction time is output. The LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples. By integrating the data of the photoacoustic spectroscopy device, the local discharge device and the core grounding current device, and then combining the LSTM prediction model to perform dynamic data prediction, the accuracy of transformer operation status monitoring can be effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 is a flow chart of an improved transformer operating status monitoring method provided in this embodiment;

[0051] Figure 2 is a structural schematic diagram of an improved transformer operating status monitoring device provided in this embodiment;

[0052] Figure 3 It is a schematic diagram of the structure of the electronic device provided in this embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Combine the following Figure 1-Figure 3 An improved transformer operating status monitoring method, device and transformer of the present invention are described.

[0055] Figure 1 It is a flow chart of the improved transformer operation status monitoring method provided in this embodiment.

[0056] like Figure 1 As shown, the improved transformer operation status monitoring method provided by the embodiment of the present invention mainly includes the following steps:

[0057] 101. Determine the evaluation score of the photoacoustic spectroscopy equipment and the corresponding photoacoustic spectroscopy parameter weights.

[0058] In a specific implementation process, the total hydrocarbon value G1 and the acetylene value G2 in the photoacoustic spectroscopy device are first determined, and then the total hydrocarbon value and the acetylene value are input into the photoacoustic spectroscopy device score evaluation formula to obtain the photoacoustic spectroscopy device evaluation score, which is recorded as C1. The photoacoustic spectroscopy device evaluation score refers to the size of the role played by the photoacoustic spectroscopy device in the working process of the transformer.

[0059] The evaluation formula for the photoacoustic spectroscopy equipment score is as follows:

[0060]

[0061] Among them, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, G1 represents the total hydrocarbon value, and G2 represents the acetylene value.

[0062] Therefore, the score of the photoacoustic spectroscopy device can be calculated by formula (1), and the calculation method is also implemented in different situations, with voltages of 220KV and 5500KV as the dividing points to implement segmented calculation. The evaluation score of the photoacoustic spectroscopy device determined by different segmented calculation methods is more accurate.

[0063] It can be determined that the photoacoustic spectroscopy parameter weight ρ1=0.45.

[0064] 102. Determine the evaluation score of the partial discharge equipment and the corresponding partial discharge weight.

[0065] The evaluation score of the partial discharge equipment refers to the numerical assessment of the contribution of the partial discharge equipment. First, the discharge amplitude D1 and the number of discharges D2 of the partial discharge equipment are determined; then the discharge amplitude and the number of discharges are input into the partial discharge equipment score evaluation formula to obtain the evaluation score of the partial discharge equipment.

[0066] The partial discharge equipment score evaluation formula is (2):

[0067]

[0068] Among them, C2 represents the evaluation score of the partial discharge equipment, D1 represents the discharge amplitude, and D2 represents the number of discharges.

[0069] Different calculation methods are used to determine the evaluation scores of partial discharge equipment for different discharge amplitudes D1 and discharge times D2. Compared with a single calculation method, the calculation results are more accurate and reliable. The corresponding partial discharge weight ρ2 = 0.4 can be determined.

[0070] 103. Determine the evaluation score of the core grounding current device and the corresponding core grounding current weight.

[0071] The evaluation score of the core grounding current device refers to the numerical evaluation of the contribution of the core grounding current device, specifically determining the grounding current data A1 in the core grounding current device; inputting the grounding current data into the core grounding current device score evaluation formula to obtain the evaluation score of the core grounding current device.

[0072] The core grounding current equipment score evaluation formula is formula (3):

[0073] C3=100×cos[(A1-100)π] (3)

[0074] Among them, C3 represents the evaluation score of the core grounding current equipment, and A1 represents the grounding current data.

[0075] The core grounding current device score evaluation formula can effectively calculate the core grounding current device evaluation score corresponding to any grounding current data A1, and the corresponding core grounding current weight ρ3 = 0.15 can be determined.

[0076] 104. Based on the transformer state assessment model, the assessment score of the photoacoustic spectroscopy equipment, the photoacoustic spectroscopy parameter weight, the assessment score of the local discharge equipment, the local discharge weight, the assessment score of the core grounding current equipment and the core grounding current weight are integrated to obtain the current state value of the transformer.

[0077] The transformer status assessment model is used to determine the current operating status of the transformer. Through the data fusion of photoacoustic spectroscopy equipment, partial discharge equipment and core grounding current equipment, it can more accurately reflect the current status value of the transformer. The photoacoustic spectroscopy parameter weight, partial discharge weight and core grounding current weight refer to the influence of different equipment parameters on the transformer status. The sum of different weights is 1.

[0078] Among them, the transformer status assessment model is formula (4):

[0079]

[0080] Among them, S represents the current state value of the transformer, ρ i represents the weight of the access parameter, C i represents the normalized score of the access equipment, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, ρ1=0.45, C2 represents the evaluation score of the partial discharge equipment, ρ2=0.4, and C3 represents the evaluation score of the core grounding current equipment, ρ3=0.15.

[0081] By inputting C1, C2, C3 and ρ1, ρ2, ρ3 into formula (4), the current state value of the transformer can be quickly determined.

[0082] The current state value is obtained by integrating three types of data: photoacoustic spectroscopy, core grounding current, and partial discharge. Compared with the conventional single sensor method, the accuracy of current state value detection is greatly improved. And with the changes in the total hydrocarbon value G1, acetylene value G2, discharge amplitude D1, discharge number D2, and grounding current data A1, the monitoring data is continuously updated.

[0083] 105. Input the current state value to the LSTM prediction model, and output the state prediction score of the transformer at any prediction time. The LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples.

[0084] After obtaining the accurate current state value of the transformer, it is input into the pre-trained LSTM prediction model, namely the Long Short-Term Memory Network (LSTM). After the internal parameters are calculated, the transformer operating state parameters at a certain moment in the future can be predicted. The LSTM treats the transformer state as a time series data, combines the real-time data with the historical data and results to obtain the predicted transformer state value. Compared with previous methods, the input and output of LSTM are dynamic through the constantly changing real-time data, and can dynamically change the data of any dimension at any time, which is reflected in the final operating state prediction result, effectively improving the accuracy of transformer operating state monitoring.

[0085] Among them, when the LSTM prediction model is trained, the model parameters of the LSTM prediction model obtained are as follows:

[0086] The input feature dimension is 3, that is, input_size=3;

[0087] The number of LSTM hidden units is 200, i.e. hidden_size = 200;

[0088] The number of LSTM layers is 200, i.e. num_layers = 200;

[0089] The batch size is 3, that is, batch_size = 3;

[0090] The future time length is 5 hours, that is, seq_length = 5, the unit is hours, indicating the transformer status after 5 hours;

[0091] It should be noted that the length of time in the future can be flexibly adjusted according to user needs, and can also be used as the input for each prediction. That is, if you want to get the transformer status at any time, just input the corresponding time.

[0092] Based on the same general inventive concept, the present invention also protects an improved transformer operating status monitoring device. The improved transformer operating status monitoring device provided by the present invention is described below. The improved transformer operating status monitoring device described below and the improved transformer operating status monitoring method described above can be referenced to each other.

[0093] Figure 2 Schematic diagram of the structure of the improved transformer operating status monitoring device provided in this embodiment.

[0094] like Figure 2 As shown, this embodiment provides an improved transformer operation status monitoring device, comprising:

[0095] A first determination module 201 is used to determine an evaluation score of a photoacoustic spectroscopy device and a corresponding photoacoustic spectroscopy parameter weight;

[0096] A second determination module 202, used to determine the evaluation score of the partial discharge device and the corresponding partial discharge weight;

[0097] A third determination module 203 is used to determine the evaluation score of the core grounding current device and the corresponding core grounding current weight;

[0098] An evaluation module 204 is used to integrate the evaluation score of the photoacoustic spectroscopy device, the photoacoustic spectroscopy parameter weight, the evaluation score of the partial discharge device, the partial discharge weight, the evaluation score of the core grounding current device and the core grounding current weight based on the transformer state evaluation model to obtain the current state value of the transformer;

[0099] Among them, the transformer condition assessment model is:

[0100]

[0101] Among them, S represents the current state value of the transformer, ρ i represents the weight of the access parameter, C i represents the normalized score of the access equipment, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, ρ1=0.45, C2 represents the evaluation score of the partial discharge equipment, ρ2=0.4, C3 represents the evaluation score of the core grounding current equipment, ρ3=0.15;

[0102] The prediction module 205 is used to input the current state value into the LSTM prediction model and output the state prediction score of the transformer at any prediction time. The LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples.

[0103] Furthermore, the first determining module 201 in this embodiment is specifically configured to:

[0104] Determine total hydrocarbon and acetylene values ​​in photoacoustic spectroscopy equipment;

[0105] The total hydrocarbon value and the acetylene value are input into the photoacoustic spectroscopy equipment score evaluation formula to obtain the evaluation score of the photoacoustic spectroscopy equipment.

[0106] Furthermore, the photoacoustic spectroscopy equipment score evaluation formula in this embodiment is:

[0107]

[0108] Among them, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, G1 represents the total hydrocarbon value, and G2 represents the acetylene value.

[0109] Furthermore, the second determining module 202 in this embodiment is specifically configured to:

[0110] Determine the discharge amplitude and number of discharges of partial discharge equipment;

[0111] The discharge amplitude and the number of discharges are input into a partial discharge equipment score evaluation formula to obtain an evaluation score for the partial discharge equipment.

[0112] Furthermore, the partial discharge equipment score evaluation formula in this embodiment is:

[0113]

[0114] Among them, C2 represents the evaluation score of the partial discharge equipment, D1 represents the discharge amplitude, and D2 represents the number of discharges.

[0115] Furthermore, the third determining module 203 in this embodiment is specifically configured to:

[0116] Determine the ground current data in the core ground current device;

[0117] The grounding current data is input into the core grounding current equipment score evaluation formula to obtain the evaluation score of the core grounding current equipment.

[0118] Furthermore, the core grounding current equipment score evaluation formula in this embodiment is:

[0119] C3=100×cos[(A1-100)π]

[0120] Among them, C3 represents the evaluation score of the core grounding current equipment, and A1 represents the grounding current data.

[0121] Furthermore, the prediction module 205 in this embodiment is also specifically used for:

[0122] The model parameters of the LSTM prediction model are determined as follows:

[0123] The input feature dimension is 3, the number of LSTM hidden units is 200, the number of LSTM layers is 200, the batch size is 3, and the future time length is 5 hours.

[0124] Based on the same general inventive concept, the present invention also protects a transformer, which is used to execute the improved transformer operating status monitoring method as described in any of the above embodiments.

[0125] Figure 3 It is a schematic diagram of the structure of the electronic device provided in this embodiment.

[0126] like Figure 3As shown, the electronic device may include: a processor (processor) 310, a communication interface (Communications Interface) 320, a memory (memory) 330 and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call the logic instructions in the memory 330 to execute an improved transformer operating status monitoring method, which includes: determining an evaluation score of a photoacoustic spectroscopy device and a corresponding photoacoustic spectroscopy parameter weight; determining an evaluation score of a local discharge device and a corresponding local discharge weight; determining an evaluation score of a core grounding current device and a corresponding core grounding current weight; based on a transformer status evaluation model, integrating the evaluation score of the photoacoustic spectroscopy device, the photoacoustic spectroscopy parameter weight, the evaluation score of the local discharge device, the local discharge weight, the evaluation score of the core grounding current device and the core grounding current weight to obtain a current state value of the transformer; inputting the current state value into an LSTM prediction model, and outputting a state prediction score of the transformer at any prediction time, wherein the LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples.

[0127] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0128] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the improved transformer operation status monitoring method provided by the above methods, which method includes: determining an evaluation score of a photoacoustic spectroscopy device and a corresponding photoacoustic spectroscopy parameter weight; determining an evaluation score of a local discharge device and a corresponding local discharge weight; determining an evaluation score of a core grounding current device and a corresponding core grounding current weight; based on a transformer state evaluation model, the evaluation score of the photoacoustic spectroscopy device, the photoacoustic spectroscopy parameter weight, the evaluation score of the local discharge device, the local discharge weight, the evaluation score of the core grounding current device and the core grounding current weight are integrated to obtain a current state value of the transformer; the current state value is input into an LSTM prediction model to output a state prediction score of the transformer at any prediction time, wherein the LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples.

[0129] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the improved transformer operation status monitoring method provided by the above-mentioned methods, the method comprising: determining an evaluation score of a photoacoustic spectroscopy device and a corresponding photoacoustic spectroscopy parameter weight; determining an evaluation score of a local discharge device and a corresponding local discharge weight; determining an evaluation score of a core grounding current device and a corresponding core grounding current weight; based on a transformer state evaluation model, integrating the evaluation score of the photoacoustic spectroscopy device, the photoacoustic spectroscopy parameter weight, the evaluation score of the local discharge device, the local discharge weight, the evaluation score of the core grounding current device and the core grounding current weight to obtain a current state value of the transformer; inputting the current state value into an LSTM prediction model to output a state prediction score of the transformer at any prediction time, wherein the LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples.

[0130] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An improved transformer operating status monitoring method, characterized in that: include: Determine the evaluation score of the photoacoustic spectroscopy equipment and the corresponding photoacoustic spectroscopy parameter weight; Determine the assessment score of the partial discharge equipment and the corresponding partial discharge weight; Determine the evaluation score of the core grounding current device and the corresponding core grounding current weight; Based on the transformer state assessment model, the assessment score of the photoacoustic spectroscopy device, the photoacoustic spectroscopy parameter weight, the assessment score of the partial discharge device, the partial discharge weight, the assessment score of the core grounding current device and the core grounding current weight are integrated to obtain the current state value of the transformer; Wherein, the transformer state assessment model is: Among them, S represents the current state value of the transformer, ρ i represents the weight of the access parameter, C i represents the normalized score of the access equipment, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, ρ1=0.45, C2 represents the evaluation score of the partial discharge equipment, ρ2=0.4, C3 represents the evaluation score of the core grounding current equipment, ρ3=0.15; The current state value is input into the LSTM prediction model, and the state prediction score of the transformer at any prediction time is output. The LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples.

2. The improved transformer operating status monitoring method according to claim 1 is characterized in that: Determining the evaluation score of the photoacoustic spectroscopy device comprises: Determine total hydrocarbon and acetylene values ​​in photoacoustic spectroscopy equipment; The total hydrocarbon value and the acetylene value are input into the photoacoustic spectroscopy equipment score evaluation formula to obtain the evaluation score of the photoacoustic spectroscopy equipment.

3. The improved transformer operating status monitoring method according to claim 2 is characterized in that: The photoacoustic spectroscopy equipment score evaluation formula is: Among them, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, G1 represents the total hydrocarbon value, and G2 represents the acetylene value.

4. The improved transformer operating status monitoring method according to claim 1 is characterized in that: The step of determining the evaluation score of the partial discharge device comprises: Determine the discharge amplitude and number of discharges of partial discharge equipment; The discharge amplitude and the number of discharges are input into a partial discharge equipment score evaluation formula to obtain an evaluation score for the partial discharge equipment.

5. The improved transformer operating status monitoring method according to claim 4 is characterized in that: The partial discharge equipment score evaluation formula is: Among them, C2 represents the evaluation score of the partial discharge equipment, D1 represents the discharge amplitude, and D2 represents the number of discharges.

6. The improved transformer operating status monitoring method according to claim 1 is characterized in that: Determining the evaluation score of the core grounding current device includes: Determine the ground current data in the core ground current device; The grounding current data is input into the core grounding current equipment score evaluation formula to obtain the evaluation score of the core grounding current equipment.

7. The improved transformer operating status monitoring method according to claim 6 is characterized in that: The core grounding current equipment score evaluation formula is: C3=100×cos[(A1-100)π] Among them, C3 represents the evaluation score of the core grounding current equipment, and A1 represents the grounding current data.

8. The improved transformer operating status monitoring method according to any one of claims 1 to 7, characterized in that: Also includes: The model parameters of the LSTM prediction model are determined as follows: The input feature dimension is 3, the number of LSTM hidden units is 200, the number of LSTM layers is 200, the batch size is 3, and the future time length is 5 hours.

9. An improved transformer operating status monitoring device, characterized in that: include: A first determination module is used to determine the evaluation score of the photoacoustic spectroscopy device and the corresponding photoacoustic spectroscopy parameter weight; A second determination module is used to determine the evaluation score of the partial discharge equipment and the corresponding partial discharge weight; A third determination module is used to determine the evaluation score of the core grounding current device and the corresponding core grounding current weight; An evaluation module is used to integrate the evaluation score of the photoacoustic spectroscopy device, the photoacoustic spectroscopy parameter weight, the evaluation score of the partial discharge device, the partial discharge weight, the evaluation score of the core grounding current device and the core grounding current weight based on the transformer state evaluation model to obtain the current state value of the transformer; Wherein, the transformer state assessment model is: Among them, S represents the current state value of the transformer, ρ i represents the weight of the access parameter, C i represents the normalized score of the access equipment, C1 represents the evaluation score of the photoacoustic spectroscopy equipment, ρ1=0.45, C2 represents the evaluation score of the partial discharge equipment, ρ2=0.4, C3 represents the evaluation score of the core grounding current equipment, ρ3=0.15; The prediction module is used to input the current state value into the LSTM prediction model and output the state prediction score of the transformer at any prediction time. The LSTM prediction model is pre-trained based on dynamic transformer state value samples and state prediction samples.

10. A transformer, characterized in that: The transformer is used to execute the improved transformer operation status monitoring method as described in any one of claims 1-8.

Images