Structural parameter design method of anti-short-circuit direct current converter transformer
By real-time monitoring of the transformer transformation rate and circuit power supply fluctuations, using the gradient boosting tree algorithm to build a prediction model, and dynamically adjusting the transformer design strategy, the lag problem of transformer scheduling and path planning in the existing technology is solved, and intelligent evaluation and efficient scheduling of the transformer operating status are achieved.
Patent Information
- Application Number
- CN202510801430.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-16
- Publication Date
- 2025-09-26
AI Technical Summary
Existing transformer scheduling and path planning methods fail to effectively integrate transformer operating data with the circuit power supply environment, resulting in lagging design strategies and difficulty in coping with circuit fluctuations and unstable power supply, and a lack of dynamic scheduling and path optimization capabilities.
By real-time monitoring of the transformer transformation rate and circuit power supply fluctuations, calculating the corresponding eigenvalues, building a prediction model based on the gradient boosting tree algorithm, and dynamically adjusting the transformer structure design strategy, multi-dimensional evaluation and intelligent scheduling of the transformer operating status can be achieved.
It achieves real-time perception and precise quantification of transformer performance and circuit stability, improves the success rate of transformer tasks, avoids the risk of failure due to equipment abnormalities or circuit fluctuations, and promotes the development of transformer design towards intelligence and high availability.
Smart Images
Figure CN120706238A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of transformer design and manufacturing, and in particular to a structural parameter design method of a short-circuit resistant DC converter transformer. Background Art
[0002] A transformer is a device that uses the principle of electromagnetic induction to change AC voltage. Its main components are a primary coil, a secondary coil, and an iron core (magnetic core). Its main functions include voltage conversion, current conversion, impedance conversion, isolation, and voltage stabilization (magnetic saturation transformer).
[0003] The existing technology has the following deficiencies:
[0004] Current mainstream transformer scheduling and routing methods face several technical bottlenecks: First, most systems rely solely on static indicators such as transformer availability or historical average efficiency for recommendations, ignoring real-time transformer performance changes and service stability. Second, they lack a dynamic assessment mechanism for regional circuit power supply quality, making it difficult to respond promptly to circuit fluctuations and unstable power supplies. Third, they fail to effectively integrate transformer operating data with transformer information to build intelligent prediction models, resulting in delayed and inaccurate design strategies. Therefore, there is an urgent need for a collaborative system and method that can comprehensively perceive the transformer operating status and circuit power supply environment, and accordingly implement dynamic scheduling and routing optimization. Summary of the Invention
[0005] The object of the present invention is to provide a method for designing structural parameters of a short-circuit resistant DC converter transformer to solve the above-mentioned problems.
[0006] The purpose of the present invention can be achieved through the following technical solutions:
[0007] A method for designing structural parameters of a short-circuit resistant DC converter transformer comprises the following steps:
[0008] S1: During the collaborative design of transformer structural parameters, the corresponding transformer is manufactured according to the designed parameters, and the transformer's transformation rate changes and circuit power supply fluctuations are collected and monitored in real time;
[0009] S2: Based on the real-time monitored voltage transformation rate variation, the voltage transformation rate fluctuation characteristic value is calculated to assess the risk of short circuit in the current transformer structure.
[0010] S3: Calculate the circuit power supply stability characteristic value based on the real-time obtained circuit power supply fluctuation level to determine whether the circuit used by the transformer has a power supply instability problem;
[0011] S4: Comprehensively analyze the characteristic values of voltage transformation rate fluctuation and circuit power supply stability, and build a prediction model based on the analysis results to determine whether the transformer can successfully complete the voltage transformation task;
[0012] S5: If the transformer cannot successfully complete the voltage transformation task, the transformer structure design strategy is dynamically adjusted.
[0013] As a further solution of the present invention, the risk of short circuit of the transformer under the current structure is assessed, specifically including:
[0014] During the collaborative design process of transformer structural parameters, the transformer's transformation rate data is collected in real time. Based on the amplitude of the transformation rate change, the transformation rate fluctuation characteristic value is calculated to determine whether the transformation rate fluctuation characteristic value is greater than or equal to a preset threshold. If so, the transformer is at risk of short circuit under the current structure. If not, the transformer is not at risk of short circuit under the current structure.
[0015] As a further solution of the present invention: the process of obtaining the voltage transformation rate fluctuation characteristic value is as follows:
[0016] Collect the transformer's transformation rate time series data in real time, perform continuous wavelet transform on the transformation rate time series data to obtain wavelet coefficients, and calculate the energy distribution at each scale based on the wavelet coefficients;
[0017] The average value of the energy distribution at all scales is calculated as the reference energy. The sum of the absolute values of the difference between the reference energy and the energy at all scales is calculated. The sum of the absolute values is then ratioed to the total energy at all scales to obtain the voltage transformation rate fluctuation characteristic value.
[0018] As a further solution of the present invention, the step of determining whether the circuit used by the transformer has an unstable power supply problem specifically includes:
[0019] During the collaborative design process of transformer structural parameters, the transformer's circuit power supply fluctuation data is collected in real time. Based on the degree of circuit power supply fluctuation, the circuit power supply stability characteristic value is calculated to determine whether the circuit power supply stability characteristic value is greater than or equal to a preset threshold. If so, the circuit used by the transformer has an unstable power supply problem; if not, the circuit used by the transformer does not have an unstable power supply problem.
[0020] As a further solution of the present invention: the process of obtaining the characteristic value of the circuit power supply stability is:
[0021] The circuit power supply voltage data of the circuit used by the transformer is collected in real time as circuit power supply fluctuation data, and the circuit power supply fluctuation data is subjected to fast Fourier transform to convert it from a time domain signal to a frequency domain signal to obtain a corresponding spectrum function;
[0022] Calculate the power spectral density based on the square of the modulus of the spectrum function;
[0023] Set a reference frequency set, including the circuit fundamental frequency and main harmonic frequency components, as the reference frequency range for evaluating circuit stability;
[0024] The circuit power supply stability characteristic value is obtained according to the energy ratio of the power spectrum density in the entire frequency range and the reference frequency range.
[0025] As a further solution of the present invention: the comprehensive analysis of the voltage transformation rate fluctuation characteristic value and the circuit power supply stability characteristic value, and the construction of a prediction model based on the analysis results, specifically includes:
[0026] During the collaborative design process of transformer structural parameters, the voltage transformation rate fluctuation characteristic value and the circuit power supply stability characteristic value are obtained, and the voltage transformation rate fluctuation characteristic value and the circuit power supply stability characteristic value are constructed into a comprehensive characteristic vector as the input of the prediction model to minimize the error between the predicted voltage transformation planning score and the actual voltage transformation planning score. As the training goal of the model, the voltage transformation planning score is output according to the trained prediction model. The prediction model is a gradient boosting tree algorithm.
[0027] As a further solution of the present invention: the training process of the prediction model is:
[0028] The historical comprehensive feature vectors and transformer planning scores are obtained as training data sets, and the gradient boosting tree algorithm is trained using the training data sets. During the training process, multiple decision trees are used to fit the residual between the current model prediction results and the actual transformer planning scores in sequence, and the overall prediction accuracy is optimized through gradual correction. In each iteration, the model calculates the loss between the current prediction value and the actual label, and generates a new decision tree based on this to make up for the error. Finally, the outputs of all weak learners are superimposed to obtain accurate prediction results. The training goal is to minimize the overall error between the predicted transformer planning score and the actual transformer planning score.
[0029] As a further solution of the present invention: the determination of whether the transformer can successfully complete the voltage transformation task specifically includes:
[0030] During the collaborative design process of transformer structural parameters, it is determined whether the transformation planning score is greater than or equal to a preset threshold. If so, the transformer can successfully complete the transformation task; otherwise, the transformer cannot successfully complete the transformation task.
[0031] As a further solution of the present invention: if the transformer cannot successfully complete the voltage transformation task, the transformer structure design strategy is dynamically adjusted, specifically including:
[0032] If it is determined that the transformer cannot successfully complete the transformation task, a multi-dimensional dynamic scheduling strategy will be automatically initiated: sudden load fluctuations will be identified based on the trend of changes in the transformation rate, and the fault tendency structure of the transformer will be structurally simplified; the regional power supply reliability will be judged based on the degree of circuit power supply fluctuation. If it is detected that circuit instability continues to occur, the structure of the transformers in the area will be structurally simplified.
[0033] Beneficial effects of the present invention:
[0034] (1) The present invention introduces the characteristic value of transformer rate fluctuation based on continuous wavelet transform and the characteristic value of circuit power supply stability based on fast Fourier transform to construct a multi-dimensional and dynamic transformer operation status evaluation system, which realizes the real-time perception and accurate quantification of transformer facility performance stability and regional power supply quality. Different from the traditional path planning and scheduling system that relies only on static indicators such as transformer idle state or historical average efficiency for decision-making, the present invention starts from the dual perspectives of time domain and frequency domain, deeply explores the hidden abnormal fluctuations caused by factors such as equipment aging, load mutation, circuit interference, etc. during the actual operation of the transformer, and can identify potential service interruption risks in advance. On this basis, the system integrates the above characteristic values into a comprehensive evaluation index, inputs it into the prediction model constructed based on the gradient boosting tree algorithm, generates a quantitative score reflecting the transformation success rate, and dynamically adjusts the design strategy accordingly, thereby effectively avoiding high-risk sites, greatly improving the probability of the transformer successfully completing the transformation task, and promoting the development of transformer design towards intelligence, refinement, and high availability.
[0035] (2) The present invention constructs an efficient and accurate prediction mechanism based on the gradient boosting tree, fully integrating the multi-dimensional operation data of the transformer, including key parameters such as the voltage transformation rate fluctuation characteristic value, the circuit power supply stability characteristic value, and the current load state of the transformer, to form a dynamic comprehensive evaluation characteristic vector as the model input. By combining offline training with online learning, the model can output a quantitative voltage transformation planning score that reflects the service reliability of the transformer, and based on this, judge the success probability of the transformer in completing the voltage transformation task at the target transformer. When the prediction result is lower than the set threshold, the design strategy adjustment mechanism is automatically triggered to avoid the risk of voltage transformation failure due to equipment abnormality or circuit fluctuation. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The present invention will be further described below with reference to the accompanying drawings.
[0037] Figure 1 The present invention is a flowchart of a method for designing structural parameters of a short-circuit resistant DC converter transformer. DETAILED DESCRIPTION
[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 making any creative efforts shall fall within the scope of protection of the present invention.
[0039] See also Figure 1 As shown, the present invention is a structural parameter design method for a short-circuit resistant DC converter transformer, comprising the following steps:
[0040] S1: During the collaborative design of transformer structural parameters, the corresponding transformer is manufactured according to the designed parameters, and the transformer's transformation rate changes and circuit power supply fluctuations are collected and monitored in real time;
[0041] S2: Based on the real-time monitored voltage transformation rate variation, the voltage transformation rate fluctuation characteristic value is calculated to assess the risk of short circuit in the current transformer structure.
[0042] S3: Calculate the circuit power supply stability characteristic value based on the real-time obtained circuit power supply fluctuation level to determine whether the circuit used by the transformer has a power supply instability problem;
[0043] S4: Comprehensively analyze the characteristic values of voltage transformation rate fluctuation and circuit power supply stability, and build a prediction model based on the analysis results to determine whether the transformer can successfully complete the voltage transformation task;
[0044] S5: If the transformer cannot successfully complete the voltage transformation task, the transformer structure design strategy is dynamically adjusted.
[0045] In S1, during the collaborative design of transformer structural parameters, the corresponding transformer is manufactured according to the designed parameters, and the transformer's transformation rate changes and circuit power supply fluctuations are collected and monitored in real time. Specifically, the following are included:
[0046] During the collaborative design of transformer structural parameters, the system uses sensor modules deployed inside the transformer to perform high-frequency acquisition of parameters such as current, voltage, and power during the transformation process, and calculates the change in power output per unit time, thereby obtaining real-time transformation rate data of the transformer; the transformation rate data is uploaded to the cloud scheduling platform at preset time intervals. The platform performs sliding window processing on multi-period data, extracts the transformation rate difference between adjacent time points, and forms a transformation rate change sequence for subsequent analysis of the performance stability of the transformer during actual operation.
[0047] At the same time, the system obtains the circuit voltage fluctuation data of the circuit used by the transformer in real time by accessing the circuit distribution unit or smart meter, with a sampling frequency of not less than once per second, to ensure that abnormal phenomena such as short-term voltage drops, sudden increases or harmonic disturbances can be captured; the collected voltage data is filtered and further converted into a standard voltage deviation index, and compared with the historical voltage baseline for analysis to identify whether there is an abnormal fluctuation trend in the circuit power supply; the above two types of data are jointly used as important dynamic inputs for path planning and scheduling decisions, realizing refined perception and response to the transformer operating environment.
[0048] In S2, based on the real-time monitored voltage transformation rate change amplitude, the voltage transformation rate fluctuation characteristic value is calculated to assess the risk of short circuit of the transformer under the current structure;
[0049] During the collaborative design process of transformer structural parameters, the transformer's transformation rate data is collected in real time. Based on the amplitude of the transformation rate change, the transformation rate fluctuation characteristic value is calculated to determine whether the transformation rate fluctuation characteristic value is greater than or equal to a preset threshold. If so, the transformer is at risk of short circuit under the current structure. If not, the transformer is not at risk of short circuit under the current structure.
[0050] The process of obtaining the voltage transformation rate fluctuation characteristic value is as follows:
[0051] The transformer transformation rate time series data is collected in real time, and continuous wavelet transform is performed on the transformation rate time series data to obtain wavelet coefficients. The energy distribution at each scale is calculated based on the wavelet coefficients. The calculation expression is:
[0052] E(a)=∫|W x (a,b)| 2 db;
[0053] Where a represents the number of scales, E(a) represents the energy distribution of the a-th scale, b represents the translation parameter, and W x (a,b) represents the wavelet coefficient of the a-th scale position b;
[0054] Calculate the average value of the energy distribution of all scales as the reference energy, and calculate the voltage transformation rate fluctuation characteristic value based on the reference energy. The calculation expression is:
[0055]
[0056] Where FI represents the characteristic value of voltage transformation rate fluctuation, E ref Represents the reference energy.
[0057] It should be noted that: by collecting the real-time transformation rate data of the transformer and using the continuous wavelet transform technology to perform multi-scale analysis on the transformation rate time series, the energy distribution characteristics at each scale are extracted, and then the average value of the energy distribution of all scales is used as the reference energy to construct the transformation rate fluctuation characteristic value. The transformation rate fluctuation characteristic value can effectively reflect the abnormal fluctuation caused by external load changes, equipment aging or circuit interference in the actual operation of the transformer, so as to accurately assess its service interruption risk. The present invention uses wavelet transform to capture the local mutation characteristics of the signal in the time and frequency domain, has higher sensitivity and robustness, can identify early potential fault trends, and provide a reliable basis for dynamic scheduling and path planning. It significantly improves the system's perception of the transformer's operating status and the level of intelligent decision-making, and has outstanding technological advancement and practicality.
[0058] In S3, based on the real-time obtained circuit power supply fluctuation level, the circuit power supply stability characteristic value is calculated to determine whether the circuit used by the transformer has a power supply instability problem, specifically including:
[0059] During the collaborative design process of transformer structural parameters, the transformer's circuit power supply fluctuation data is collected in real time. Based on the degree of circuit power supply fluctuation, the circuit power supply stability characteristic value is calculated to determine whether the circuit power supply stability characteristic value is greater than or equal to a preset threshold. If so, the circuit used by the transformer has an unstable power supply problem; if not, the circuit used by the transformer does not have an unstable power supply problem.
[0060] The process of obtaining the characteristic value of the circuit power supply stability is as follows:
[0061] The circuit power supply voltage data of the circuit used by the transformer is collected in real time as circuit power supply fluctuation data, and the circuit power supply fluctuation data is subjected to fast Fourier transform to convert it from a time domain signal to a frequency domain signal to obtain a corresponding spectrum function;
[0062] The power spectrum density is calculated based on the spectrum function. The calculation expression is:
[0063] S(f)=|X(f)| 2 ;
[0064] Where f represents the frequency variable, S(f) represents the power spectrum density of the f-th frequency variable, and X(f) represents the spectrum function of the f-th frequency variable;
[0065] Set a reference frequency set, including the circuit fundamental frequency and main harmonic frequency components, as the reference frequency range for evaluating circuit stability;
[0066] According to the energy ratio of the power spectrum density in the entire frequency range and the reference frequency range, the circuit power supply stability characteristic value is obtained, and the calculation expression is:
[0067]
[0068] Where, F ref It represents the reference frequency range, and SI represents the characteristic value of the circuit power supply stability.
[0069] It should be noted that: by collecting the circuit power supply voltage data of the circuit used by the transformer in real time, the time domain fluctuation signal is converted into a frequency domain signal using fast Fourier transform, and then the power spectrum density is calculated to extract the energy distribution characteristics of the circuit at different frequencies. On this basis, a reference frequency set containing the circuit fundamental frequency and its main harmonic components is set as the ideal frequency band for evaluating the stable operation of the circuit, and by calculating the energy ratio between the non-reference frequency component and the reference frequency component, the circuit power supply stability characteristic value is constructed. The circuit power supply stability characteristic value can effectively reflect the power supply quality and stability level of the regional circuit, identify hidden abnormal phenomena such as voltage harmonic distortion and frequency offset, and thus accurately determine whether the transformer is in an unstable power supply area. Starting from the frequency domain perspective, the present invention introduces a frequency component analysis mechanism with higher sensitivity and anti-interference ability, which can achieve refined perception of the circuit status, provide a scientific and reliable dynamic input basis for path planning and scheduling decisions, and has significant technical innovation and engineering application value.
[0070] In S4, a comprehensive analysis is performed on the characteristic values of the voltage transformation rate fluctuation and the circuit power supply stability. Based on the analysis results, a prediction model is constructed to determine whether the transformer can successfully complete the voltage transformation task. Specifically, the following are performed:
[0071] During the collaborative design process of transformer structural parameters, the voltage transformation rate fluctuation characteristic value and the circuit power supply stability characteristic value are obtained, and the voltage transformation rate fluctuation characteristic value and the circuit power supply stability characteristic value are constructed into a comprehensive characteristic vector as the input of the prediction model to minimize the error between the predicted voltage transformation planning score and the actual voltage transformation planning score. As the training goal of the model, the voltage transformation planning score is output according to the trained prediction model. The prediction model is a gradient boosting tree algorithm.
[0072] The training process of the prediction model is:
[0073] The historical comprehensive feature vectors and transformer planning scores are obtained as training data sets, and the gradient boosting tree algorithm is trained using the training data sets. During the training process, multiple decision trees are used to fit the residual between the current model prediction results and the actual transformer planning scores in sequence, and the overall prediction accuracy is optimized through gradual correction. In each iteration, the model calculates the loss between the current prediction value and the actual label, and generates a new decision tree based on this to make up for the error. Finally, the outputs of all weak learners are superimposed to obtain accurate prediction results. The training goal is to minimize the overall error between the predicted transformer planning score and the actual transformer planning score.
[0074] After model training is complete, the system can input the real-time transformer feature vectors into the trained gradient boosting tree model and output the corresponding transformer planning score, which is used to evaluate the reliability and service quality of the transformer under its current operating state. This score can be used to dynamically adjust transformer routing recommendations and transformer reservation priorities, thereby improving the overall system's responsiveness and service level.
[0075] The step of judging whether the transformer can successfully complete the voltage transformation task specifically includes:
[0076] During the collaborative design process of transformer structural parameters, it is determined whether the transformation planning score is greater than or equal to a preset threshold. If so, the transformer can successfully complete the transformation task; otherwise, the transformer cannot successfully complete the transformation task.
[0077] In S5, if the transformer cannot successfully complete the transformation task, the transformer structure design strategy is dynamically adjusted, including:
[0078] If it is determined that the transformer cannot successfully complete the transformation task, a multi-dimensional dynamic scheduling strategy will be automatically initiated: sudden load fluctuations will be identified based on the trend of changes in the transformation rate, and the fault tendency structure of the transformer will be structurally simplified; the regional power supply reliability will be judged based on the degree of circuit power supply fluctuation. If it is detected that circuit instability continues to occur, the structure of the transformers in the area will be structurally simplified.
[0079] In the above process, the design circuit of the transformer can be divided into at least one local structure and local area. Then, data can be acquired for the local structure and local area in the same way as for the entire transformer, so that it can be determined whether there are design anomalies in the local structure and local area. For the local structure and local area with abnormalities, simplification processing can be used, that is, the structure of the part is simplified into a single wire structure. In this way, the problems existing here can be overcome. Through continuous iterative design and analysis of the design circuit of the transformer, the required circuit structure can be finally obtained.
[0080] The present invention operates by collecting real-time transformer transformation rate data and circuit supply voltage data, then employing continuous wavelet transform and fast Fourier transform techniques to extract transformation rate fluctuation eigenvalues and circuit supply stability eigenvalues, respectively, thereby enabling accurate assessment of transformer performance and regional circuit stability. The transformation rate fluctuation eigenvalue analyzes energy distribution at multiple scales, effectively identifying potential service interruption risks caused by factors such as sudden load changes and equipment aging. The circuit supply stability eigenvalue, based on frequency domain analysis, determines whether abnormal disturbances exist in the regional circuit by comparing the energy ratio of reference frequency components to non-reference frequency components, improving the ability to detect hidden power faults. Furthermore, the system constructs these two eigenvalues into a comprehensive feature vector, which serves as input to a gradient boosting tree model. The model is trained using historical data to output a transformation planning score reflecting the overall service quality of the transformer, which is then used to determine whether the transformer can successfully complete its transformation task. If the prediction result does not meet a set threshold, the system automatically triggers a dynamic design strategy. This technical solution realizes closed-loop control from operating status perception to dispatch response, significantly improving the service quality and dispatch intelligence level of the transformer network, and has good practical value and promotion prospects.
[0081] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.
[0082] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.
[0083] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.
[0084] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0085] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.
Claims
1. A method for designing structural parameters of a short-circuit resistant DC converter transformer, characterized in that: The following steps are involved: S1: During the collaborative design of transformer structural parameters, the corresponding transformer is manufactured according to the designed parameters, and the transformer's transformation rate changes and circuit power supply fluctuations are collected and monitored in real time; S2: Based on the real-time monitored voltage transformation rate variation, the voltage transformation rate fluctuation characteristic value is calculated to assess the risk of short circuit in the current transformer structure. S3: Calculate the circuit power supply stability characteristic value based on the real-time obtained circuit power supply fluctuation level to determine whether the circuit used by the transformer has a power supply instability problem; S4: Comprehensively analyze the characteristic values of voltage transformation rate fluctuation and circuit power supply stability, and build a prediction model based on the analysis results to determine whether the transformer can successfully complete the voltage transformation task; S5: If the transformer cannot successfully complete the voltage transformation task, the transformer structure design strategy is dynamically adjusted.
2. The structural parameter design method of a short-circuit-resistant DC converter transformer according to claim 1, characterized in that: The assessment of the risk of short circuit of the transformer under the current structure specifically includes: During the collaborative design process of transformer structural parameters, the transformer's transformation rate data is collected in real time. Based on the amplitude of the transformation rate change, the transformation rate fluctuation characteristic value is calculated to determine whether the transformation rate fluctuation characteristic value is greater than or equal to a preset threshold. If so, the transformer is at risk of short circuit under the current structure. If not, the transformer is not at risk of short circuit under the current structure.
3. The structural parameter design method of a short-circuit-resistant DC converter transformer according to claim 2, characterized in that: The process of obtaining the voltage transformation rate fluctuation characteristic value is as follows: Collect the transformer's transformation rate time series data in real time, perform continuous wavelet transform on the transformation rate time series data to obtain wavelet coefficients, and calculate the energy distribution at each scale based on the wavelet coefficients; The average value of the energy distribution at all scales is calculated as the reference energy. The sum of the absolute values of the difference between the reference energy and the energy at all scales is calculated. The sum of the absolute values is then ratioed to the total energy at all scales to obtain the voltage transformation rate fluctuation characteristic value.
4. The structural parameter design method of a short-circuit-resistant DC converter transformer according to claim 1, characterized in that: The determining whether the circuit used by the transformer has an unstable power supply problem specifically includes: During the collaborative design process of transformer structural parameters, the transformer's circuit power supply fluctuation data is collected in real time. Based on the degree of circuit power supply fluctuation, the circuit power supply stability characteristic value is calculated to determine whether the circuit power supply stability characteristic value is greater than or equal to a preset threshold. If so, the circuit used by the transformer has an unstable power supply problem; if not, the circuit used by the transformer does not have an unstable power supply problem.
5. The structural parameter design method of a short-circuit-resistant DC converter transformer according to claim 2, characterized in that: The process of obtaining the characteristic value of the circuit power supply stability is as follows: The circuit power supply voltage data of the circuit used by the transformer is collected in real time as circuit power supply fluctuation data, and the circuit power supply fluctuation data is subjected to fast Fourier transform to convert it from a time domain signal to a frequency domain signal to obtain a corresponding spectrum function; Calculate the power spectral density based on the square of the modulus of the spectrum function; Set a reference frequency set, including the circuit fundamental frequency and main harmonic frequency components, as the reference frequency range for evaluating circuit stability; The circuit power supply stability characteristic value is obtained according to the energy ratio of the power spectrum density in the entire frequency range and the reference frequency range.
6. The structural parameter design method of a short-circuit-resistant DC converter transformer according to claim 1, characterized in that: The comprehensive analysis of the voltage transformation rate fluctuation characteristic value and the circuit power supply stability characteristic value, and the construction of a prediction model based on the analysis results, specifically includes: During the collaborative design process of transformer structural parameters, the voltage transformation rate fluctuation characteristic value and the circuit power supply stability characteristic value are obtained, and the voltage transformation rate fluctuation characteristic value and the circuit power supply stability characteristic value are constructed into a comprehensive characteristic vector as the input of the prediction model to minimize the error between the predicted voltage transformation planning score and the actual voltage transformation planning score. As the training goal of the model, the voltage transformation planning score is output according to the trained prediction model. The prediction model is a gradient boosting tree algorithm.
7. The structural parameter design method of a short-circuit-resistant DC converter transformer according to claim 1, characterized in that: The training process of the prediction model is: The historical comprehensive feature vectors and transformer planning scores are obtained as training data sets, and the gradient boosting tree algorithm is trained using the training data sets. During the training process, multiple decision trees are used to fit the residual between the current model prediction results and the actual transformer planning scores in sequence, and the overall prediction accuracy is optimized through gradual correction. In each iteration, the model calculates the loss between the current prediction value and the actual label, and generates a new decision tree based on this to make up for the error. Finally, the outputs of all weak learners are superimposed to obtain accurate prediction results. The training goal is to minimize the overall error between the predicted transformer planning score and the actual transformer planning score.
8. The method for designing structural parameters of a short-circuit-resistant DC converter transformer according to claim 1, characterized in that: The step of judging whether the transformer can successfully complete the voltage transformation task specifically includes: During the collaborative design process of transformer structural parameters, it is determined whether the transformation planning score is greater than or equal to a preset threshold. If so, the transformer can successfully complete the transformation task; otherwise, the transformer cannot successfully complete the transformation task.
9. The structural parameter design method of a short-circuit resistant DC converter transformer according to claim 1, characterized in that: If the transformer cannot successfully complete the transformation task, the transformer structure design strategy is dynamically adjusted, specifically including: If it is determined that the transformer cannot successfully complete the transformation task, a multi-dimensional dynamic scheduling strategy will be automatically initiated: sudden load fluctuations will be identified based on the trend of changes in the transformation rate, and the fault tendency structure of the transformer will be structurally simplified; the regional power supply reliability will be judged based on the degree of circuit power supply fluctuation. If it is detected that circuit instability continues to occur, the structure of the transformers in the area will be structurally simplified.