Short-time impulse current fast response method of flexible voltage management device

Abstract

The present application relates to a kind of flexible voltage management device short-time impulse current fast response method, comprising the following steps: the current signal of flexible voltage management device is collected, and current signal is converted into digital signal;The preprocessed digital signal is converted, and the training set is constructed by the preprocessed digital signal;Short-time impulse current detection model is constructed based on convolutional neural network and long short-term memory network, short-time impulse current detection model is trained by training set, training set is classified and the digital signal that short-time impulse current is identified in it, finally the short-time impulse current detection model that training is completed is obtained;The input current of flexible voltage management device is detected in real time by the short-time impulse current detection model that training is completed, and according to the size and direction of the short-time impulse current detected, the working state of voltage source converter is adjusted to make it match the voltage of input end or output end.

Description

Technical Field

[0001] This invention relates to a method for rapid response to short-time inrush current in a flexible voltage management device, belonging to the field of flexible DC transmission technology. Background Technology

[0002] Flexible DC transmission is a new type of power transmission that combines DC transmission and flexible AC transmission technologies to improve the efficiency, stability, and reliability of power systems. The research and application of flexible DC technology has become a hot topic and cutting-edge field in the power industry. The emergence of flexible DC technology is to meet the ever-increasing power demand of power systems. Short-time inrush current is a transient overcurrent phenomenon that occurs in power systems. Its duration is generally between a few milliseconds and tens of milliseconds, but its amplitude can reach thousands or even tens of thousands of amperes, causing serious damage to power equipment and the power grid. There are various causes of short-time inrush current, such as lightning strikes, switching operations, and fault clearing. Therefore, a solution is needed to deal with short-term inrush currents during flexible DC transmission in power systems. Summary of the Invention

[0003] To address the problems existing in the prior art, this invention proposes a method for rapid response to short-time inrush current in a flexible voltage control device.

[0004] The technical solution of the present invention is as follows: On one hand, the present invention provides a method for rapid response to short-time inrush current in a flexible voltage control device, comprising the following steps: A current sensor is installed at the input end of the flexible voltage regulation device to collect current signals and convert the current signals into digital signals; The converted digital signal is preprocessed, and a training set is constructed using the preprocessed digital signal. A short-term impulse current detection model is constructed based on convolutional neural networks and long short-term memory networks. The short-term impulse current detection model is trained using a training set. The training set is then classified and the digital signal of the short-term impulse current is identified. Finally, the trained short-term impulse current detection model is obtained. The short-time inrush current detection model, which has been trained, is used to detect the input current of the flexible voltage control device in real time. Based on the magnitude and direction of the detected short-time inrush current, a signal is sent to the controller. The controller then adjusts the operating state of the voltage source converter according to the signal to match the voltage at the input or output terminal.

[0005] In a preferred embodiment of the present invention, the preprocessing of the converted digital signal specifically includes: filtering, normalizing, segmenting, and removing noise and irrelevant information from the converted digital signal.

[0006] In a preferred embodiment of the present invention, a fast Fourier transform is performed on each segment of the preprocessed digital signal to convert the time-domain signal into a frequency-domain signal, and the amplitude, phase, and frequency features of the signal are extracted to construct a feature vector and a training set is constructed based on the feature vector.

[0007] In a preferred embodiment of the present invention, the convolutional neural network includes multiple convolutional layers, pooling layers and fully connected layers, used to extract local features of feature vectors, and to reduce the number of parameters and computational complexity through weight sharing and downsampling.

[0008] In a preferred embodiment of the present invention, the long short-term memory network includes multiple forget gates, input gates, output gates and memory units, used to extract temporal features of feature vectors, and to avoid gradient vanishing and gradient explosion problems through a gating mechanism.

[0009] On the other hand, the present invention also provides a rapid response system for short-time inrush current of a flexible voltage management device, including a data acquisition module, a data preprocessing module, a short-time inrush current detection model construction module, and a short-time inrush current detection module; The data acquisition module is used to set a current sensor at the input end of the flexible voltage management device to collect current signals and convert the current signals into digital signals; The data preprocessing module is used to preprocess the converted digital signal, construct a training set using the preprocessed digital signal, and extract features to construct a feature vector. The short-time impulse current detection model construction module is used to construct a short-time impulse current detection model based on convolutional neural network and long short-term memory network. The short-time impulse current detection model is trained through training set, the feature vectors are classified and the feature vectors that are short-time impulse currents are identified, and finally the trained short-time impulse current detection model is obtained. The short-time inrush current detection module is used to detect the input current of the flexible voltage control device in real time through a trained short-time inrush current detection model, and send a signal to the controller according to the magnitude and direction of the detected short-time inrush current. The controller adjusts the operating state of the voltage source converter according to the signal to match the voltage at the input or output end.

[0010] In a preferred embodiment of the present invention, an optimized operation control module is also provided, which is used to optimize and schedule the operating parameters of the flexible voltage management device according to the needs and status of the power system.

[0011] In another aspect, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method as described in any embodiment of the present invention.

[0012] In another aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0013] The present invention has the following beneficial effects: 1. This invention constructs a short-term impulse current detection model based on convolutional neural networks and long short-term memory networks, extracts the features of short-term impulse current from the current signal, and performs accurate classification and identification, thereby improving the efficiency and accuracy of short-term impulse current detection. Attached Figure Description

[0014] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0015] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0017] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0018] The terms “comprising” and “including” indicate the presence of the described feature, whole, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0019] The term “and / or” refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes these combinations.

[0020] Example 1: See Figure 1A method for rapid response to short-time inrush current in a flexible voltage control device includes the following steps: A current sensor is installed at the input end of the flexible voltage regulation device to collect current signals and convert the current signals into digital signals; The converted digital signal is preprocessed, and a training set is constructed using the preprocessed digital signal. A short-term impulse current detection model is constructed based on convolutional neural networks and long short-term memory networks. The short-term impulse current detection model is trained using a training set. The training set is then classified and the digital signal of the short-term impulse current is identified. Finally, the trained short-term impulse current detection model is obtained. The short-time inrush current detection model, which has been trained, is used to detect the input current of the flexible voltage control device in real time. Based on the magnitude and direction of the detected short-time inrush current, a signal is sent to the controller. The controller then adjusts the operating state of the voltage source converter according to the signal to match the voltage at the input or output terminal.

[0021] In a preferred embodiment of this invention, the preprocessing of the converted digital signal specifically includes: filtering, normalizing, and segmenting the converted digital signal to remove noise and irrelevant information. Filtering is a method for removing unwanted components from a signal, such as high-frequency noise and DC components. Normalization is a method for adjusting the amplitude of a signal to a certain range; segmentation is a method for dividing a signal into several small segments according to a certain time interval or length to facilitate subsequent processing and analysis.

[0022] In a preferred embodiment of this invention, a fast Fourier transform is performed on each preprocessed digital signal segment to convert the time-domain signal into a frequency-domain signal, and the amplitude, phase, and frequency features of the signal are extracted to construct a feature vector and a training set is constructed based on the feature vector.

[0023] In a preferred embodiment of this invention, the convolutional neural network includes multiple convolutional layers, pooling layers, and fully connected layers to extract local features of the feature vector, and reduces the number of parameters and computational complexity through weight sharing and downsampling.

[0024] As a preferred embodiment of this example, the Long Short-Term Memory network includes multiple forget gates, input gates, output gates, and memory units, which are used to extract temporal features of feature vectors and to avoid gradient vanishing and gradient explosion problems through a gating mechanism.

[0025] Example 2: A rapid response system for short-time inrush current of a flexible voltage control device includes a data acquisition module, a data preprocessing module, a short-time inrush current detection model construction module, and a short-time inrush current detection module; The data acquisition module is used to set a current sensor at the input end of the flexible voltage management device to collect current signals and convert the current signals into digital signals; The data preprocessing module is used to preprocess the converted digital signal, construct a training set using the preprocessed digital signal, and extract features to construct a feature vector. The short-time impulse current detection model construction module is used to construct a short-time impulse current detection model based on convolutional neural network and long short-term memory network. The short-time impulse current detection model is trained through training set, the feature vectors are classified and the feature vectors that are short-time impulse currents are identified, and finally the trained short-time impulse current detection model is obtained. The short-time inrush current detection module is used to detect the input current of the flexible voltage control device in real time through a trained short-time inrush current detection model, and send a signal to the controller according to the magnitude and direction of the detected short-time inrush current. The controller adjusts the operating state of the voltage source converter according to the signal to match the voltage at the input or output end.

[0026] As a preferred embodiment of this invention, an optimized operation control module is also provided, which is used to optimize and schedule the operating parameters of the flexible voltage management device according to the needs and status of the power system.

[0027] The principle of optimized operation control is to optimize and schedule the operating parameters of the flexible DC power grid through a hierarchical optimization framework, combined with advanced information communication, measurement technology, big data, artificial intelligence and other technologies, so as to achieve the optimal allocation of voltage, power, energy and so on, thereby improving the operating efficiency and stability of the flexible DC power grid.

[0028] This embodiment is used to implement the functions in Embodiment 1, and will not be described again here.

[0029] Example 3: This embodiment proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the method described in any embodiment of the present invention.

[0030] Example 4: This embodiment proposes a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0031] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0032] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0033] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0034] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0035] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for rapid response to short-time inrush current in a flexible voltage control device, characterized in that, Includes the following steps: A current sensor is installed at the input end of the flexible voltage regulation device to collect current signals and convert the current signals into digital signals; The converted digital signal is preprocessed, and a training set is constructed based on the preprocessed digital signal: a fast Fourier transform is performed on each segment of the preprocessed digital signal to convert the time domain signal into a frequency domain signal, the amplitude, phase and frequency features of the signal are extracted, a feature vector is constructed, and a training set is constructed based on the feature vector. A short-term impulse current detection model is constructed based on convolutional neural networks and long short-term memory networks. The short-term impulse current detection model is trained using a training set. The training set is then classified and the digital signal of the short-term impulse current is identified. Finally, the trained short-term impulse current detection model is obtained. The short-time inrush current detection model, which has been trained, is used to detect the input current of the flexible voltage control device in real time. Based on the magnitude and direction of the detected short-time inrush current, a signal is sent to the controller. The controller then adjusts the operating state of the voltage source converter according to the signal to match the voltage at the input or output terminal.

2. The method for rapid response to short-time impulse current in a flexible voltage control device according to claim 1, characterized in that, The preprocessing of the converted digital signal specifically includes filtering, normalizing, segmenting, and removing noise and irrelevant information from the converted digital signal.

3. The method for rapid response to short-time impulse current in a flexible voltage control device according to claim 1, characterized in that, The convolutional neural network includes multiple convolutional layers, pooling layers, and fully connected layers, which are used to extract local features of the feature vector and reduce the number of parameters and computational complexity through weight sharing and downsampling.

4. The method for rapid response to short-time impulse current in a flexible voltage control device according to claim 1, characterized in that, The Long Short-Term Memory (LSTM) network includes multiple forget gates, input gates, output gates, and memory units, used to extract temporal features of feature vectors, and uses a gating mechanism to avoid gradient vanishing and gradient exploding problems.

5. A short-time impulse current rapid response system for a flexible voltage control device, characterized in that, The method for implementing the method as described in any one of claims 1 to 4 includes a data acquisition module, a data preprocessing module, a short-time impulse current detection model construction module, and a short-time impulse current detection module. The data acquisition module is used to set a current sensor at the input end of the flexible voltage management device to collect current signals and convert the current signals into digital signals; The data preprocessing module is used to preprocess the converted digital signal, construct a training set using the preprocessed digital signal, and extract features to construct a feature vector. The short-time impulse current detection model construction module is used to construct a short-time impulse current detection model based on convolutional neural network and long short-term memory network. The short-time impulse current detection model is trained through training set, the feature vectors are classified and the feature vectors that are short-time impulse currents are identified, and finally the trained short-time impulse current detection model is obtained. The short-time inrush current detection module is used to detect the input current of the flexible voltage control device in real time through a trained short-time inrush current detection model, and send a signal to the controller according to the magnitude and direction of the detected short-time inrush current. The controller adjusts the operating state of the voltage source converter according to the signal to match the voltage at the input or output end.

6. The short-time impulse current rapid response system of the flexible voltage control device according to claim 5, characterized in that, It also includes an optimized operation control module, which is used to optimize and schedule the operating parameters of the flexible voltage management device according to the needs and status of the power system.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 4.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 4.

Images