Direct-current transformer control method, device and equipment and storage medium

Abstract

The invention discloses a direct-current transformer control method, device and equipment and a storage medium, which are applied to double closed-loop control of a full direct-current power transmission grid, and the method comprises the steps: analyzing the obtained voltage data of the full direct-current power transmission grid and the voltage data output by a direct-current transformer, and obtaining the operation deviation data; based on the second voltage data and the operation deviation data, determining a first PCI controller reference parameter in double closed-loop control corresponding to the interference type; in response to a control signal obtained by analyzing and processing the voltage deviation data and the obtained alternating current voltage variable quantity out-of-limit value, adjusting a reference parameter of a PCI (Peripheral Component Interconnect) controller; the PCI controller is controlled to process the operation deviation data at least according to the adjusted PCI controller parameters, and target voltage data are obtained; and controlling the full-direct-current power transmission grid to execute the generated control strategy. According to the direct current transformer control method provided by the invention, the stability of the output voltage is practically ensured, and the fluctuation amplitude is greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of DC transformer technology, and in particular to a DC transformer control method, device, equipment, and storage medium. Background Technology

[0002] A full DC transmission system is a highly efficient and stable power transmission system. In the system, the DC transformer is responsible for converting the high-voltage DC of the transmission line into medium- or low-voltage DC that is suitable for the load or distributed power source, or vice versa, to complete the voltage boosting. During this process, the amplitude of the AC voltage of the DC transformer needs to be kept stable in order to maintain the efficient operation of the entire transmission system.

[0003] Existing technologies use a constant AC voltage control method to support the stability of AC voltage in transformers. However, this method uses fixed adjustment rules to control the stable output of AC voltage, which leads to significant output voltage fluctuations in complex scenarios such as severe fluctuations in grid load, superposition of multiple types of interference, and random fluctuations in new energy output. It is impossible to flexibly adjust the voltage stability control logic, resulting in unstable output voltage. Consequently, the DC transformer cannot operate stably, which in turn affects the normal operation of the all-DC transmission system and hinders the efficient collection and long-distance transmission of new energy power. Summary of the Invention

[0004] This invention provides a DC transformer control method, apparatus, device, and storage medium to solve the technical problem of unstable output voltage in the prior art, thereby achieving the effect of stable output voltage.

[0005] To address the aforementioned technical problems, this invention provides a DC transformer control method, apparatus, device, and storage medium, applicable to dual closed-loop control of a full DC transmission network. The method includes: The first voltage data of the acquired full DC transmission network and the second voltage data output by the DC transformer are analyzed to obtain operating deviation data, which includes at least voltage deviation data and current deviation data. Based on the second voltage data and the operating deviation data, the interference type corresponding to the DC transformer is obtained, and the reference parameters of the first PCI controller in the dual closed-loop control corresponding to the interference type are determined. The voltage deviation data and the obtained AC voltage change exceeding the limit are analyzed and processed to obtain a control signal; in response to the control signal, the first PCI controller reference parameters are adjusted according to a preset rule to obtain the second PCI controller reference parameters; The PCI controller is controlled to process the voltage deviation data and the current deviation data at least with the reference parameters of the second PCI controller to obtain the target voltage data; Control the all-DC transmission grid to execute a control strategy generated from at least the target voltage data.

[0006] Preferably, the step of obtaining the interference type corresponding to the DC transformer based on the second voltage data and the operating deviation data, and determining the first PCI controller reference parameter in the dual closed-loop control corresponding to the interference type, includes: Time-frequency domain feature extraction is performed on the second voltage data to obtain the second voltage feature data; Based at least on the second voltage characteristic data and the operating deviation data, an artificial intelligence model is used to determine the type of interference corresponding to the DC transformer; The reference parameters of the first PCI controller in the corresponding dual closed-loop control are determined based on the type of interference.

[0007] Preferably, the artificial intelligence model includes a graph neural network model, and the step of determining the interference type corresponding to the DC transformer using the artificial intelligence model based at least on the second voltage feature data and the operating deviation data includes: Based on the preset power grid topology map, the second voltage characteristic data, and the operating deviation data, the graph neural network model is used to perform an identification operation to obtain the interference type. The preset power grid topology map is a structured graph data constructed based on the connection relationship of the entire DC transmission power grid.

[0008] Preferably, the identification operation includes: The second voltage feature data, the operating feature data obtained by extracting the operating deviation data features, and the preset power grid topology map are fused to form the initial features of the graph nodes; The graph neural network model performs feature interaction through a message passing mechanism. In the feature interaction, each graph node aggregates its own initial features with the initial features of its neighboring nodes to obtain aggregated features. Based on a preset power grid topology map, the aggregated features are filtered and denoised to obtain key features; The key features are mapped to obtain the corresponding interference type.

[0009] Preferably, determining the reference parameters of the first PCI controller in the dual closed-loop control based on the interference type includes: The historical operating data of the acquired full DC transmission network are analyzed and processed to obtain an operating database; The interference type is input into a defined model built by a deep learning algorithm trained on a running database to obtain the baseline parameters of the first PCI controller.

[0010] Preferably, the step of analyzing and processing the voltage deviation data and the acquired AC voltage change exceeding the limit value to obtain a control signal includes: The voltage deviation change rate obtained by calculating and processing the voltage deviation data is multiplied by the AC voltage change exceeding the limit value to obtain the comparison benchmark value; A control signal is generated based on the comparison result between the voltage amplitude data obtained by analyzing the voltage deviation data and the comparison reference value.

[0011] Another aspect of the present invention provides a DC transformer control device, applied in a dual closed-loop control system for a full DC transmission network, comprising: The acquisition module is used to analyze the acquired first voltage data of the full DC transmission network and the second voltage data output by the DC transformer to obtain operating deviation data, which includes at least voltage deviation data and current deviation data. The determination module is used to determine the interference type corresponding to the DC transformer based on the second voltage data and the operating deviation data, and to determine the reference parameters of the first PCI controller in the dual closed-loop control corresponding to the interference type; the analysis module is used to analyze and process the voltage deviation data and the obtained AC voltage change limit value to obtain the control signal. A response module is used to respond to the control signal and adjust the first PCI controller reference parameters according to a preset rule to obtain the second PCI controller reference parameters; The processing module is used to control the PCI controller to process the voltage deviation data and the current deviation data at least with the reference parameters of the second PCI controller to obtain the target voltage data; A control module is used to control the all-DC transmission grid to execute a control strategy generated from at least the target voltage data.

[0012] Preferably, the determining module includes: The extraction unit is used to extract time-frequency domain features from the second voltage data to obtain second voltage feature data; An artificial intelligence unit is used to determine the type of interference corresponding to the DC transformer using an artificial intelligence model, based at least on the second voltage characteristic data and the operating deviation data. The parameter determination unit is used to determine the reference parameters of the first PCI controller in the dual closed-loop control based on the type of interference.

[0013] In another aspect, the present invention provides a DC transformer control device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the DC transformer control method as described in any one of claims 1 to 7.

[0014] In another aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the DC transformer control method as described in any one of claims 1 to 7.

[0015] The beneficial effects of the present invention are at least one of the following: This invention first collects first voltage data from the entire DC transmission network and second voltage data from the DC transformer output, analyzing the resulting operational deviation data including voltage and current deviations. Then, combining the second voltage data and operational deviation data, it identifies the interference type corresponding to the DC transformer and matches the first PCI controller reference parameters required for dual closed-loop control. Subsequently, it analyzes the voltage deviation data and the AC voltage variation exceeding the limit, generating corresponding control signals. Based on the control signals, it adjusts the first PCI controller reference parameters according to preset rules to obtain second PCI controller reference parameters adapted to the current operating conditions. The PCI controller processes the voltage and current deviation data using the second PCI controller reference parameters and outputs the target voltage data. Finally, it guides the entire DC transmission network to execute the control strategy generated based on the target voltage data. This invention, through specific scenario analysis and adaptive parameter adjustment, ensures the stability of the output voltage, effectively preventing the DC transformer from deviating from a stable operating state due to voltage instability, and ultimately achieving a continuous and stable AC voltage output from the DC transformer, laying a stable voltage foundation for the efficient collection and long-distance transmission of new energy power. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a DC transformer control method in one embodiment of the present invention; Figure 2 The diagram shown is a topology diagram of a high-voltage DC transformer in one embodiment of the present invention; Figure 3 The diagram shown is a topology diagram of an ultra-high voltage DC transformer in one embodiment of the present invention; Figure 4 The diagram shown is an AC voltage support control block diagram according to one embodiment of the present invention; Figure 5 The diagram shown is a typical structural diagram of a proportional-complex integral control system in one embodiment of the present invention; Figure 6The diagram shown is a single-phase virtual coordinate system (PCI) control structure diagram in one embodiment of the present invention; Figure 7 The diagram shown is a single-phase virtual coordinate system (PCI) control structure diagram in one embodiment of the present invention; Figure 8 The diagram shown is a linear control model of a grid-connected inverter in one embodiment of the present invention. Figure 9 The amplitude-frequency and phase-frequency characteristic curves of the PCI closed-loop transfer function are shown in one embodiment of the present invention. Figure 10 The amplitude-frequency and phase-frequency characteristic curves are shown as plotted for the closed-loop transfer function corresponding to PI control in one embodiment of the present invention. Figure 11 This is a structural block diagram of a DC transformer control device in one embodiment of the present invention; Figure 12 This is a schematic diagram of the structure of a DC transformer control device in one embodiment of the present invention; Figure 13 The diagram shows the output voltage and output current after adopting the solution of the present invention in one embodiment of the present invention; Figure 14 The diagram shows the active power and reactive power output after adopting the solution of the present invention in one embodiment of the present invention. Figure 15 The diagram shows the output voltage and output current in one embodiment of the present invention without employing the solution of the present invention. Figure 16 The diagram shows the active and reactive power outputs in one embodiment of the present invention without employing the solution of the present invention. Figure label: The module comprises: 11. Acquisition module; 12. Determination module; 13. Analysis module; 14. Response module; 15. Processing module; and 16. Control module. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] In the description of this application, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0019] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. The terms "vertical," "horizontal," "left," "right," "upper," "lower," and similar expressions used herein are for illustrative purposes only and do not indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items. Those skilled in the art will understand the specific meaning of the above terms in this application based on the specific circumstances.

[0020] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0021] The all-DC power transmission system is highly efficient and stable. The DC transformer undertakes the task of converting high and low voltage DC, and the stability of its AC voltage amplitude is the key to the efficient operation of the system.

[0022] Existing constant AC voltage control methods rely on fixed adjustment rules to stabilize transformer voltage. Under complex scenarios such as severe load fluctuations, multiple interferences, and random fluctuations in new energy output, voltage fluctuations are significant, leading to unstable operation of transformers and the all-DC transmission system, hindering the efficient collection and long-distance transmission of new energy power.

[0023] One embodiment of the present invention provides a DC transformer control method; for details, please refer to [link to specific documentation]. Figure 1 , Figure 1 The diagram shown is a flowchart illustrating a DC transformer control method according to one embodiment of the present invention.

[0024] S1. Analyze the first voltage data of the acquired full DC transmission network and the second voltage data output by the DC transformer to obtain the operating deviation data. The operating deviation data includes at least voltage deviation data and current deviation data. S2. Based on the second voltage data and operating deviation data, obtain the interference type corresponding to the DC transformer, and determine the reference parameters of the first PCI controller in the dual closed-loop control corresponding to the interference type. S3. Analyze and process the voltage deviation data and the obtained AC voltage change exceeding the limit to obtain the control signal; S4. In response to the control signal, adjust the reference parameters of the first PCI controller according to the preset rules to obtain the reference parameters of the second PCI controller; S5. Control the PCI controller to process voltage deviation data and current deviation data at least with the reference parameters of the second PCI controller to obtain the target voltage data; S6. Control the entire DC transmission grid to execute a control strategy generated from at least the target voltage data.

[0025] Analyzing the first voltage data and the second voltage data output from the DC transformer in the entire DC transmission network is the core data preprocessing step in the DC transformer voltage control process. The first voltage data is taken from the grid side and is typically the input voltage of the DC transformer connected to the grid, such as the voltage at the connection point between the transformer and the converter station, or the voltage of the main grid lines, directly reflecting the grid's own supply voltage status. The second voltage data is taken from the output side of the DC transformer, i.e., the voltage transmitted to loads, renewable energy plants, or downstream grids after the transformer completes voltage transformation; its value directly determines the voltage quality of subsequent power consumption and transmission. For DC transformer topology, please refer to [link to DC transformer topology documentation]. Figure 2 and Figure 3 , Figure 2 The diagram shown is a topology diagram of a high-voltage DC transformer according to one embodiment of the present invention. Figure 3 The diagram illustrates an ultra-high voltage (UHVDC) transformer topology in one embodiment of the present invention. The DC transformer topology consists of an MMC converter, a power module (SM), and an AC transformer. The low-voltage sections of both the high-voltage and UHVDC transformers are connected in parallel to increase current capacity, while the high-voltage sections are connected in series to increase DC voltage. An AC transformer is used for isolation in between. Overall, it presents a DC voltage input and DC voltage output, consistent with the input-output characteristics of a DC transformer. Currently, in all-DC transmission systems, the low-voltage section of the DC transformer controls the corresponding DC voltage, while the high-voltage section controls the amplitude and frequency of the intermediate transformer.

[0026] In specific analysis, two types of time-series voltage signals are first acquired synchronously using a high-frequency acquisition module (sampling frequency typically not lower than 1kHz). Sensor noise, electromagnetic interference, and other irrelevant signals are filtered out to obtain clean voltage waveform data. Then, quantitative calculations are performed using preset benchmark parameters: The rated voltage on the grid side and the rated output voltage of the transformer are used as benchmarks, and the actual acquired first and second voltage data are compared to obtain voltage deviation data, which includes at least the grid-side voltage deviation and the output-side voltage deviation, directly reflecting whether the voltage deviates from the ideal operating value. The rated current, determined based on the transformer's rated capacity and the grid design load, is used as a benchmark. Combined with the difference between the transformer's equivalent impedance and the first and second voltage data (i.e., the voltage difference across the transformer), the actual current is derived using Ohm's law and compared with the rated current to obtain current deviation data, which reflects current deviations caused by load changes, abnormal line impedance, etc. The final operating deviation data includes at least the aforementioned voltage deviation data and current deviation data. This process provides more accurate quantitative basis for subsequent interference type identification, such as determining whether voltage deviation is caused by load changes or harmonic intrusion, and allows for more precise adjustment of controller parameters. It avoids subjective judgment based solely on raw voltage data and ensures that subsequent control strategies are more targeted.

[0027] Further processing of the voltage deviation data and raw voltage data is performed, and time-frequency domain feature extraction is conducted on the second voltage data using time-frequency analysis techniques. Time-domain feature extraction employs a sliding window method, using the numpy library in MATLAB to calculate 12 time-domain indicators, including peak voltage, mean, variance, and maximum rate of change, within each window to capture the instantaneous fluctuation characteristics of the voltage. Frequency-domain feature extraction uses a short-time Fourier transform to convert the voltage signal from the time domain to the frequency domain, and uses the scipy.fft library in MATLAB to extract 8 frequency-domain indicators, including harmonic frequencies, harmonic amplitude percentages, and spectral entropy, within the 0-500Hz frequency band to characterize the frequency distribution of the voltage signal. Finally, the time-domain and frequency-domain indicators are combined to form second voltage feature data containing 20 dimensions. The second voltage feature data is obtained. Furthermore, based at least on the second voltage characteristic data and the operational deviation data, an artificial intelligence model is used to determine the type of interference corresponding to the DC transformer. First, a power grid topology diagram needs to be constructed, where nodes correspond to various types of equipment such as transformers, lines, and loads, and edges correspond to the connection relationships between these equipment. Then, the second voltage characteristic data is used as the dynamic characteristics of the transformer nodes, and the voltage and current deviations in the operational deviation data are used as the node state characteristics. These two types of characteristics are then fused with the static attributes of the nodes in the topology diagram, such as the rated parameters of the equipment, to form the input data for the graph neural network model.

[0028] Preferably, the second voltage feature data and the operating feature data obtained by extracting features from the operating deviation data are fused with a preset power grid topology map to form initial features of the graph nodes. The graph neural network model performs multiple rounds of feature interaction through a message passing mechanism. In each round, each node in the graph aggregates its own features with the features of its neighboring nodes to obtain aggregated features. The key features obtained by filtering and denoising the aggregated features based on the connection relationship of the preset power grid topology map are mapped to obtain the corresponding interference type. The artificial intelligence model includes a graph neural network model. The determination of the interference type corresponding to the DC transformer using the artificial intelligence model, based at least on the second voltage feature data and the operating deviation data, includes performing an identification operation using the graph neural network model based on the preset power grid topology map, the second voltage feature data, and the operating deviation data to obtain the interference type. The preset power grid topology map is a structured graph data constructed based on the connection relationship of the entire DC transmission network. This model employs a graph convolutional network structure, aggregating node features with those of adjacent nodes through three graph convolutional layers. For example, it aggregates impedance features of line nodes and current features of load nodes. After each graph convolutional operation, an activation function enhances the model's non-linear expressive power, enabling it to more accurately capture complex relationships between features. Finally, a fully connected layer outputs the probability distribution of interference types, covering six types of interference, including load abrupt changes, line short circuits, and harmonic intrusion. The type with the highest probability is selected as the final interference identification result. During model training, the cross-entropy loss function is used to calculate the error between the predicted results and the actual labels. Iterative optimization is performed using historical running data including manually labeled interference types within the PyTorch framework.

[0029] It's important to note that graph neural networks were originally designed to solve data processing problems with topological relationships. Their core idea is to capture spatial relationships in data by enabling nodes to interact with their neighbors through message passing mechanisms. Traditionally, they have been used to handle tasks with clearly defined node and edge connections, such as social networks, molecular structures, and transportation networks. This solution chooses graph neural networks primarily because of the inherent topological characteristics of a full DC transmission power grid. The grid consists of transformers, lines, and loads as nodes, connected by physical lines as edges. Interference propagation follows a chain-like path of nodes, edges, and neighboring nodes. Traditional machine learning models cannot capture this topological relationship and can only analyze data from individual devices in isolation, leading to significant errors in interference identification. Graph neural networks, on the other hand, are naturally adapted to the power grid topology, which is the core necessity for their selection. Meanwhile, this solution applies a graph neural network design that fuses features from static topology and dynamic data. This allows the model to utilize both the fixed static parameters of the power grid's nodes and edges, and to incorporate dynamic information such as second voltage feature data and operational deviation data in real time. Through multiple rounds of graph convolution operations, it achieves deep interaction between the dynamic features of transformer nodes and adjacent nodes, accurately simulating the propagation trajectory of interference in the power grid. This solves the pain point of traditional graph neural networks, which only focus on static topology and are difficult to adapt to dynamic power grid interference, and can meet the real-time response requirements of DC transformer voltage control. For example, when faced with combined interference from load mutations and line impedance changes, traditional models may misjudge it as a single load interference, while the graph neural network in this solution can clearly capture the interference correlation logic and accurately identify the type of combined interference, significantly outperforming traditional models and fully demonstrating the necessity and innovation of choosing a graph neural network.

[0030] Furthermore, the identification operation includes N rounds of identification processing, where N is a positive integer. The identification processing includes feature aggregation and feature refinement. In the i-th round of the N rounds of identification processing, the feature aggregation is constructed based on the node connection relationship of the preset power grid topology, aggregating the node features output by the (i-1)-th round of identification processing with the neighboring node features to obtain the i-th round aggregated features. The feature refinement is constructed based on the second voltage feature data and the operating deviation data, performing nonlinear transformation and noise filtering on the i-th round aggregated features to obtain the node features output by the i-th round of identification processing, where 1≤i≤N. The interference type is determined by the target node features output by the N-th round of identification processing through classification mapping. When i=1, the node features output by the (i-1)-th round of identification processing are the initial node features, which include the rated parameters and real-time basic monitoring data of each node in the preset power grid topology.

[0031] Optionally, the historical operating data of the acquired full DC transmission network is analyzed and processed to obtain an operating database. The interference type is input into a deterministic model built using a deep learning algorithm trained on the operating database to obtain the first PCI controller baseline parameters. A dataset of interference types and their corresponding PCI controller baseline parameters is constructed. This dataset includes basic input data interference types and also labels the structured output of the operating results with matching baseline parameter labels to establish a mapping relationship between input and output. Subsequently, a machine learning algorithm is used to train the initial AI model based on this dataset. During training, methods such as transfer learning, hyperparameter optimization, or incremental training are combined to fine-tune the model and enhance its generalization ability to unknown data. Finally, the optimized model matrix after training is output. In the deployment phase, the user only needs to input the interference type to be analyzed into the model, and the model can automatically calculate and output the corresponding baseline parameters based on its learned inherent patterns.

[0032] The PCI controller and traditional dual-loop control represent a collaborative relationship between the control framework and the core execution components. For traditional dual-loop control, please refer to [link to relevant documentation]. Figure 4 , Figure 4 The diagram shown is an AC voltage support control block diagram according to one embodiment of the present invention. Wherein, Q... ref V is the reactive power reference value, Q is the reactive power sample value, and V is the reactive power sample value. dcref This is the DC voltage reference value, V dc This is a DC voltage sample value, V g V is the grid voltage. c VSC is the output voltage, s is the differential operator, C is the DC bus capacitor, and X is the output voltage. base Here, θ is the system impedance base value, θ is the phase angle of the VSC output voltage, and V is the output voltage amplitude. dref V is the reference value for the d-axis voltage. d For the d-axis voltage sampling value, i N i is the rated output current of VSC. d i represents the d-axis current sampling value. q i represents the q-axis current sampling value. dref k is the reference value for the d-axis current. P The proportional gain of the PCI controller. Vac is the AC voltage reference value, and Vac is the AC voltage sample value. Δ is the change in direct current. V i represents the change in AC voltage. qref This is the reference value for the q-axis current. The sampled value is the DC voltage, k0 is the reactive power droop coefficient, and PWM is the IGBT drive signal modulation process.

[0033] Traditional dual-loop control, a classic hierarchical control framework in power electronic devices such as converters and DC transformers, uses a voltage outer loop for target setting and a current inner loop for strong tracking as its core logic. The outer loop processes voltage deviations through a controller and outputs a current reference command; the inner loop tracks current deviations through a controller and directly drives power devices. However, it relies on traditional PI controllers with fixed parameters, resulting in poor adaptability and lag in response to complex operating conditions. Embedding a PCI controller in either the outer or inner loop to replace the traditional fixed-parameter PI controller retains the advantages of dual-loop hierarchical control and precise tracking. Furthermore, by dynamically adjusting control parameters and predicting deviation changes, it improves the adaptability and response accuracy of dual-loop control in complex scenarios such as grid interference and load surges. Ultimately, it achieves improved control performance while maintaining the same framework, making dual-loop control more suitable for the dynamic operating conditions required in actual operation.

[0034] Please refer to the basic principles of proportional-complex-integral control. Figure 5 , Figure 5 The diagram shows a typical proportional-complex-integral (PII) control system structure in one embodiment of the present invention. First, the PII control is analyzed from a control theory perspective. Wherein, R... (s) For reference, C (s) For output, D (s) P is the disturbance quantity. (s) As the controlled object, G (s) For the controller. To ensure precise control of the output, the output C needs to be... (s) Follow the reference value R (s) And unaffected by disturbance quantity D (s) Impact, i.e., C (s) =R (s) .

[0035] according to Figure 4 As shown in the block diagram, the output transfer function is: The PCI controller transfer function is: Substituting equation (2) into equation (1), we get: From equation (3), it can be seen that when R (s) and D (s) When the frequency ω is the same as the frequency ω0 in equation (2), that is, ω=ω0, then equation (4) can be expressed as: From equation (3), it can be seen that as long as the complex domain controller frequency ω0 and the reference quantity and the disturbance quantity frequency are the same in equation (4), that is, A=1, B=0, then the output quantity R (s) It can follow the reference value R(s) And unaffected by disturbance quantity D (s) Impact, i.e., C (s) =D (s) It can achieve accurate control of the controlled quantity.

[0036] For ease of design, the PCI controller can be rewritten based on equation (4) as follows: It can be seen that the PCI controller is a first-order system, which is convenient for engineering design. When the controlled object is a DC quantity, ω0 = 0 is chosen. Therefore, PI control can be considered a special case of PCI control, and it is known that the PCI controller G... (s) Since the AC variable has infinite gain at both the given frequency and the frequency of the disturbance, it can be known that PCI control can achieve error-free control of the AC variable. Therefore, PCI control can be selected to control the zero-sequence component in the circulating current.

[0037] The formulas (1)-(5) used in the aforementioned embodiments are the principle formulas of the PCI controller. All formulas are publicly available in the prior art. In addition to the implementation using the formula embodiments, formula embodiments (1)-(5) can be implemented by existing model algorithms. Another embodiment of the present invention also provides an alternative implementation path based on a machine learning model. Through a deep neural network architecture, data from a large-scale dataset is absorbed during the training phase to grasp multi-dimensional feature associations and hidden rules. In actual deployment, the input data only needs to be imported into the trained model, and its built-in intelligent processing mechanism can automatically generate high-precision output results that meet the requirements.

[0038] For single-phase general proportional-complex integral control, please refer to [link / reference]. Figure 6 and Figure 7 , Figure 6 The diagram shown is a single-phase virtual coordinate system (PCI) control structure diagram according to one embodiment of the present invention. Figure 7 The diagram shown illustrates a single-phase virtual coordinate system PCI control structure in one embodiment of the present invention. The current error signal x is used to construct a virtual three-phase coordinate system variable through a delay, simulating the PCI control of a three-phase system. The difference is that the output signal only takes y. a As the output quantity y.

[0039] Figure 6 In the middle, x a Let x be the voltage of phase A. b For phase B voltage, x c For phase C voltage, m α Let m be the integral output of α. β Let y be the integral output of β. α α is the proportional output, y βFor β, the proportional output, x α Let α be the voltage, and x be the voltage. β For the β voltage, the error signal is delayed by ±240° to construct a virtual three-phase coordinate system variable to achieve PCI control. The maximum delay of this method is 240°. Figure 7 As shown, in order to reduce signal delay, the single-phase error signal is delayed by 90° to construct a three-phase virtual coordinate system to realize PCI control. The maximum delay of this method is 90°.

[0040] This invention provides another embodiment for determining the reference parameters of the first PCI controller in the corresponding dual-loop control. Based on the disturbance type, the reference parameters of the first PCI controller in the dual-loop control are determined by first constructing a dynamic mapping library between disturbance types and parameters, and then using a deep Q-network for offline training on historical data to learn the correspondence between disturbance types and PCI parameters. Simultaneously, expert rules are added, such as requiring the proportional gain parameter to be no less than 0.8 to improve response speed in response to sudden load changes, thus constraining the mapping results. Once a specific disturbance type is identified, the model retrieves the corresponding parameter combination from the mapping library, then verifies and corrects it using expert rules, finally outputting the first PCI controller reference parameters that meet the current disturbance control requirements. The entire process utilizes MATLAB to dynamically update the mapping library and call parameters.

[0041] After obtaining the baseline parameters, the voltage deviation data and the acquired AC voltage change exceeding the limit are analyzed and compared to obtain the control signal. This is achieved through real-time data comparison technology: the AC voltage change exceeding the limit is a multi-level threshold preset according to the power grid safety operation standard, including normal threshold, warning threshold, and emergency threshold, which correspond to different allowable ranges of voltage deviation; the voltage deviation data is a pre-processed, real-time quantitative result reflecting the voltage deviation from the rated value. During the analysis and comparison, the difference between the voltage deviation data and the exceeding limit values ​​at each level is first calculated using the difference calculation method. Then, a logic judgment module based on C language embedded programming is used to determine the threshold range of the voltage deviation. If the deviation is within the normal threshold, a zero control signal is generated to maintain the current parameters; if the warning threshold is reached, a weak control signal with a small adjustment is generated, and the signal value can be set to 0.3; if the emergency threshold is exceeded, a strong control signal with a large adjustment is generated, and the signal value can be set to 0.8. This allows the control signal to accurately quantify and map the severity of the voltage deviation.

[0042] In response to control signals, the first PCI controller reference parameters are adjusted according to preset rules to obtain the second PCI controller reference parameters. This is accomplished using a parameter adaptive adjustment algorithm. The preset rules are based on a mapping relationship between control signals and parameter adjustment amounts, trained using historical control data. For example, a strong control signal corresponds to a 20% increase in the proportional coefficient Kp and a 15% decrease in the integral time, while a weak control signal corresponds to a 5% increase in the proportional coefficient and a 5% decrease in the integral time. These rules are stored in a rule base managed by a MySQL database. Upon receiving a control signal, the corresponding rules are called using a lookup method implemented in the control system. Numerical calculations are then performed using the initial values ​​of the first PCI controller reference parameters. For instance, the new parameters are calculated using the formula that the second PCI controller proportional coefficient parameter equals the first PCI controller proportional coefficient parameter multiplied by the voltage deviation value. Simultaneously, a limiting mechanism is introduced to ensure that the adjusted parameters are within the safe operating range of the equipment, such as a proportional coefficient not exceeding 1.5 and an integral time not less than 0.05s. Finally, the second PCI controller reference parameters adapted to the current operating conditions are output. The entire process achieves millisecond-level real-time response through industrial control software, ensuring the timeliness and accuracy of parameter adjustment.

[0043] Another embodiment of the present invention provides a method for adaptively adjusting the proportional coefficient parameter, specifically expressed as equation (6): In the above formula, k p0 k is the initial value of the adjustment coefficient. j Used to regulate the rate of change of AC voltage, where ΔVac is the amount of change in AC voltage. V is the rate of change of AC voltage. set The AC voltage amplitude and rate of change exceed the limit, where M is the frequency conversion rate, which is generally determined according to national standards, industry standards, or specific circumstances. Equation (6) shows that when both the AC voltage amplitude and rate of change exceed the limit, the parameter k... p When the change is greatest, the adjustment effect is most obvious, aiming to adjust the AC voltage that deviates from the normal range to a controllable range as soon as possible; and when only one variable, voltage amplitude or rate of change, exceeds the limit, specific parameters can be adaptively adjusted only for the variable that exceeds the limit.

[0044] A comparison of the PCI control and PI control characteristics with parameter adaptation proposed in this invention is provided. For the linear control model of the grid-connected inverter, please refer to [link / reference needed]. Figure 8 , Figure 8 The diagram shown is a linear control model of a grid-connected inverter in one embodiment of the present invention, wherein G (s) For a current controller, R is the equivalent series resistance of inductor L, and K is the PWM equivalent gain, typically taken as... I0 is the output current, I ref U is the reference value for the current.g For grid voltage, U in Input voltage, Δ e This represents the current error.

[0045] according to Figure 8 The expression for the output current of the grid-connected inverter can be obtained as follows: The closed-loop transfer function T(s), amplitude frequency response |T(s)|, and phase frequency response ∠T(s) of the system are as follows: The closed-loop amplitude-frequency characteristic |T(s)| and phase-frequency characteristic ∠T(s) of the system using PI control (ω=0) are as follows: In the formula k i Operating parameters for the complex integral coefficient test system: system switching frequency 10kHz, DC bus voltage 200V, mains voltage 50V / 50Hz, filter inductance 6mH.

[0046] First, design the system's proportional coefficient k. p To ensure system response speed, the system bandwidth is generally chosen to be greater than 10 times the fundamental frequency and less than 1 / 5 of the switching frequency. Therefore, the bandwidth f of a parallel system is... b The selection range is: 500≤f b ≤2000.

[0047] When only k is considered p At that time, the closed-loop amplitude-frequency characteristic of the system is: Parallel system bandwidth selection f b =700Hz, i.e., ω b =4400, substituting into equation (4.27) above, we get k p =0.1, counting the complex integral coefficient k i Substituting into equation (9) yields k i =15, f b This refers to the bandwidth of the control system.

[0048] Frequency domain analysis is performed on both PCI control and PI control to illustrate the performance differences between the two control methods. Please refer to [link / reference]. Figure 9 and Figure 10 , Figure 9 The figures shown are the amplitude-frequency and phase-frequency characteristic curves plotted for the PCI closed-loop transfer function in one embodiment of the present invention. Figure 9 The top figure shows the amplitude-frequency response, and the bottom figure shows the phase-frequency response. Figure 10The diagram shows the amplitude-frequency and phase-frequency characteristic curves plotted for the closed-loop transfer function corresponding to PI control in one embodiment of the present invention. Figure 10 The top figure shows the amplitude-frequency response, and the bottom figure shows the phase-frequency response.

[0049] Figure 9 The amplitude-frequency response and phase-frequency response curves plotted based on the PCI closed-loop transfer function show that when f = 150Hz, the amplitude-frequency response is infinitely close to 1 and the phase-frequency response is infinitely close to 0. This indicates that PCI control can achieve almost zero steady-state error-free control in the frequency range below 150Hz, and the phase has almost no lag or lead. f is the frequency at the point of maximum gain.

[0050] Figure 10 The amplitude-frequency characteristic and phase-frequency characteristic curves are plotted based on the closed-loop transfer function corresponding to PI control. It can be seen that the amplitude-frequency characteristic is not 1 and the phase-frequency characteristic is not 0. PI control cannot achieve zero steady-state error-free control of AC quantities, and phase lag will occur when f > 40Hz.

[0051] The PCI controller processes voltage and current deviation data using at least the reference parameters of the second PCI controller to obtain the target voltage data. This is achieved through dual closed-loop control technology: the PCI controller incorporates two layers of control logic, a voltage loop and a current loop. The voltage loop uses parameters such as the proportional coefficient and integral time of the second PCI controller as the core adjustment basis. After receiving the voltage deviation data, it performs proportional-integral-derivative operations to output a preliminary current reference value. The current loop then compares this reference value with the actual current deviation data to further correct the output signal. Finally, pulse width modulation technology is used to convert the calculation result into a control signal that can drive power electronic devices. After signal conditioning, the target voltage data is generated. This data is an ideal voltage value that can bring the DC transformer output voltage back to a stable state. The entire process is performed in milliseconds by a digital signal processor to ensure timely control response.

[0052] Controlling the entire DC transmission grid to execute control strategies generated from at least the target voltage data is accomplished with the help of a grid dispatch automation system. First, the target voltage data is transmitted to the monitoring host at the grid dispatch center via data interaction technology. The host then calls a preset control strategy generation algorithm, and, combined with the real-time operating status of the grid, breaks down the target voltage data into specific execution commands, including voltage regulation commands for DC transformers, firing angle adjustment commands for converter stations, and switching commands for reactive power compensation devices. Subsequently, these commands are sent to the local controllers of the corresponding devices via industrial Ethernet. The local controllers drive the devices to act through relay output modules or analog output modules, such as adjusting the tap position of transformers or changing the conduction timing of converter valves, so that the voltage operating status of the entire DC transmission grid aligns with the target voltage data, ultimately achieving stable voltage control. Throughout the process, the dispatch automation system provides real-time feedback on the device execution status through remote signaling and telemetry functions, forming a closed-loop control of command issuance, execution, and status feedback, ensuring the accurate implementation of the control strategy.

[0053] In another embodiment of the invention, the voltage amplitude and phase angle are then combined, and the voltage phase angle is used as the rotation angle for the dq coordinate transformation to obtain the d-axis voltage reference value. This is used as a reactive voltage reference value for control. Reactive power control is achieved through voltage and current loops, and then the rated current i is utilized. N The q-axis current reference value i is obtained by calculating the d-axis current reference value. qref and satisfy The active current reference value needs to be dynamically adjusted based on the reactive current to ensure that the VSC converter does not operate under overload. Finally, VSC voltage support control is achieved through PWM modulation.

[0054] See Figure 11 This is a structural block diagram of a DC transformer control device provided in an embodiment of the present invention. The DC transformer control device 20 provided in this embodiment includes a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, it implements the steps as described in the above-described DC transformer control embodiment, for example... Figure 1 The steps S1 to S6 described above; or, when the processor 21 executes the computer program, it implements the functions of each module in the above-described device embodiments, such as the acquisition module 11.

[0055] For example, the computer program can be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the DC transformer control device 20. For example, the computer program can be divided into an acquisition module 11, a determination module 12, an analysis module 13, a response module 14, a processing module 15, and a control module 16, as detailed in the following description. Figure 12 , Figure 12 This is a schematic diagram of the structure of a DC transformer control device in one embodiment of the present invention. The specific functions of each module are as follows: Acquisition module 11 is used to analyze the first voltage data of the acquired full DC transmission network and the second voltage data output by the DC transformer to obtain operating deviation data, which includes at least voltage deviation data and current deviation data; Determination module 12 is used to obtain the interference type corresponding to the DC transformer based on the second voltage data and the operating deviation data, and determine the first PCI controller reference parameter in the dual closed-loop control corresponding to the interference type. Analysis module 13 is used to analyze and process the voltage deviation data and the obtained AC voltage change exceeding the limit value to obtain the control signal; Response module 14 is used to respond to the control signal and adjust the reference parameters of the first PCI controller according to the preset rules to obtain the reference parameters of the second PCI controller. Processing module 15 is used to control the PCI controller to process the voltage deviation data and the current deviation data at least with the second PCI controller reference parameters to obtain the target voltage data; Control module 16 is used to control the all-DC transmission grid to execute a control strategy generated from at least the target voltage data.

[0056] The DC transformer control device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of a DC transformer control processing device and does not constitute a limitation on the DC transformer control device 20. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the DC transformer control device 20 may also include input / output devices, network access devices, buses, etc.

[0057] The processor 21 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 21 is the control center of the DC transformer control device 20, connecting all parts of the DC transformer control device 20 via various interfaces and lines.

[0058] The memory 22 can be used to store the computer programs and / or modules. The processor 21 implements various functions of the DC transformer control device 20 by running or executing the computer programs and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0059] If the integrated module of the DC transformer control device 20 is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0060] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0061] Accordingly, embodiments of the present invention provide a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform steps in the DC transformer control method of the above embodiments, for example... Figure 1 Steps S1 to S6 are described above. Another embodiment of the present invention provides a voltage control effect diagram using the present invention; specific parameter settings are shown in Table 1. Figure 13 The diagram shown illustrates the output voltage and output current after employing the solution of this invention in one embodiment of the invention. Figure 13 In the top diagram, red represents phase A voltage, blue represents phase B voltage, and green represents phase C voltage. In the bottom diagram, red represents phase A current, blue represents phase B current, and green represents phase C current. From Figure 13 It can be seen that by adopting the control strategy proposed in this invention, the AC voltage can be supported to the normal operating range of 30kV within 0.1s when the voltage drops, thereby improving the robustness of the VSC voltage. At the same time, it can also be seen that the output current has a significant increasing trend. Figure 14 The diagram shows the active power and reactive power output after adopting the solution of the present invention in one embodiment of the present invention. Figure 14 The top image shows the active power waveform, and the bottom image shows the reactive power waveform. From... Figure 14 It can be seen that during voltage dips, the method proposed in this invention can increase the reactive power output of the VSC, which can help support the AC voltage to return to normal. In addition, the oscillation of active and reactive power during the fault phase is due to the existence of power coupling, which is a normal phenomenon. Figure 15 The diagram shown illustrates the output voltage and output current in one embodiment of the present invention without employing the solution described herein. Figure 15 In the upper diagram, red represents phase A voltage, blue represents phase B voltage, and green represents phase C voltage; in the lower diagram, red represents phase A current, blue represents phase B current, and green represents phase C current. Figure 15 It can be seen that without any control, when a voltage drop occurs, the AC voltage cannot be restored to the normal range, which will cause the VSC system to operate abnormally. Figure 16 The diagram shows the active and reactive power outputs in one embodiment of the present invention without employing the solution of the present invention. Figure 16 The top image shows the active power waveform, and the bottom image shows the reactive power waveform. From... Figure 16 It can be seen that after a voltage dip, the reactive power only fluctuates briefly due to power coupling, and the amplitude is low, which cannot support the AC voltage. In summary, the current voltage support control proposed in this invention can effectively support the VSC AC voltage during grid voltage dips.

[0062] Table 1 Parameters of High Voltage DC Transformer This invention first collects the first voltage data of the entire DC transmission network and the second voltage data output by the DC transformer. Analysis yields operational deviation data including voltage and current deviations. Then, combining the second voltage data and the operational deviation data, the type of interference faced by the DC transformer is identified, and the first PCI controller reference parameters required for dual closed-loop control are matched. Subsequently, a control signal is generated by analyzing the voltage deviation data and the AC voltage change exceeding the limit. Based on this signal, the first PCI controller reference parameters are adjusted according to preset rules to obtain second PCI controller reference parameters adapted to the current operating conditions. The PCI controller processes the voltage and current deviation data using the second PCI controller reference parameters, outputs the target voltage data, and ultimately guides the entire DC transmission network to execute a control strategy generated based on the target voltage data. The entire process achieves adaptive adjustment of controller parameters through targeted analysis of actual operating scenarios, effectively avoiding sudden fluctuations in output voltage and preventing the DC transformer from deviating from a stable operating state due to voltage instability. Ultimately, it ensures a continuous and stable AC voltage output from the DC transformer, laying a stable voltage foundation for the efficient collection and long-distance transmission of new energy power.

[0063] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A direct current transformer control method applied to a double closed-loop control of a full direct current power transmission grid, characterized in that, Comprise: analyze the obtained first voltage data of the whole direct current power transmission grid and the second voltage data output by the direct current transformer to obtain operation deviation data, the operation deviation data at least including voltage deviation data and current deviation data; based on the second voltage data and the operation deviation data, the interference type corresponding to the direct current transformer is obtained, and the first PCI controller reference parameter in the double closed loop control corresponding to the interference type is determined; analyze the voltage deviation data and the obtained AC voltage change limit value, and obtain a control signal; in response to the control signal, the first PCI controller reference parameter is adjusted according to the preset rule to obtain the second PCI controller reference parameter; the PCI controller at least processes the voltage deviation data and the current deviation data with the second PCI controller reference parameter to obtain target voltage data; control the whole direct current power transmission grid to execute the control strategy generated at least by the target voltage data.

2. The DC transformer control method of claim 1, wherein, The second voltage data is extracted in time and frequency domain to obtain second voltage feature data; at least based on the second voltage feature data and the operation deviation data, the interference type corresponding to the direct current transformer is determined by using an artificial intelligence model; based on the interference type, the first PCI controller reference parameter in the double closed loop control corresponding to the interference type is determined. The artificial intelligence model includes a graph neural network model, and the interference type corresponding to the direct current transformer is determined by using an artificial intelligence model at least based on the second voltage feature data and the operation deviation data, which includes:

3. The DC transformer control method of claim 2, wherein based on the preset power grid topology graph, the second voltage feature data and the operation deviation data, the graph neural network model is used to execute identification operation to obtain the interference type, wherein the preset power grid topology graph is constructed based on the connection relationship of the whole direct current power transmission grid. The identification operation includes:

4. The DC transformer control method of claim 3, wherein the second voltage feature data, the operation feature data obtained by feature extraction on the operation deviation data and the preset power grid topology graph are fused to form the initial feature of the graph node; the graph neural network model performs feature interaction through message passing mechanism, wherein in the feature interaction, each graph node aggregates and processes its initial feature and the initial feature of adjacent nodes to obtain aggregated feature; the aggregated feature is filtered and denoised based on the preset power grid topology graph to obtain key feature the key feature is mapped to obtain the corresponding interference type. The first PCI controller reference parameter in the double closed loop control corresponding to the interference type is determined based on the interference type, which includes:

5. The DC transformer control method of claim 1, wherein, analyze the obtained historical operation data of the whole direct current power transmission grid to obtain an operation database; ​ The interference type input is input into a determination model built by a deep learning algorithm trained by a database, to obtain the first PCI controller reference parameter.

6. The dc-dc converter control method of claim 1, wherein, The analysis and processing of the voltage deviation data and the obtained AC voltage change limit value obtains a control signal, including: The voltage deviation change rate obtained by calculating and processing the voltage deviation data is multiplied by the AC voltage change limit value to obtain a comparison reference value; Based on the comparison result of the voltage amplitude data obtained by analyzing the voltage deviation data and the comparison reference value, a control signal is generated.

7. A DC transformer control device applied to double closed-loop control of a full DC power transmission grid, characterized in that, Including: The acquisition module is configured to analyze the first voltage data of the full DC power transmission grid and the second voltage data output by the DC transformer to obtain operation deviation data, wherein the operation deviation data at least includes voltage deviation data and current deviation data; The determination module is configured to obtain an interference type corresponding to the DC transformer based on the second voltage data and the operation deviation data, and determine a first PCI controller reference parameter in the double closed-loop control corresponding to the interference type; The analysis module is configured to analyze and process the voltage deviation data and the obtained AC voltage change limit value to obtain a control signal; The response module is configured to adjust the first PCI controller reference parameter according to a preset rule to obtain a second PCI controller reference parameter in response to the control signal; The processing module is configured to control the PCI controller to process the voltage deviation data and the current deviation data at least with the second PCI controller reference parameter to obtain target voltage data; The control module is configured to control the full DC power transmission grid to execute a control strategy generated at least by the target voltage data.

8. The DC transformer control device of claim 7, wherein The determination module includes: The extraction unit is configured to perform time-frequency domain feature extraction on the second voltage data to obtain second voltage feature data; The artificial intelligence unit is configured to determine the interference type corresponding to the DC transformer based on at least the second voltage feature data and the operation deviation data by using an artificial intelligence model; The determination parameter unit is configured to determine the first PCI controller reference parameter in the double closed-loop control corresponding to the interference type.

9. A DC transformer control device, characterized by comprising: The computer readable storage medium stores a computer program, wherein when the device where the computer readable storage medium is located executes the computer program, the DC transformer control method according to any one of claims 1-7 is implemented.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, wherein when the device where the computer readable storage medium is located executes the computer program, the DC transformer control method according to any one of claims 1-7 is implemented.

Images