Diesel generator pilot protection method based on waveform similarity

Abstract

The invention relates to the technical field of generator protection methods, in particular to a waveform similarity-based pilot protection method for a diesel generator, which comprises the following steps of: arranging a current transformer and a voltage transformer at each key node of the diesel generator, and acquiring waveform data of each key node in real time; waveform data acquired by each key node is synchronously transmitted through a wireless network communication channel, so that each protection device of the generator exchanges and shares the waveform data in real time; generating a waveform feature vector by adopting a convolutional neural network, wherein the waveform feature vector comprises a waveform shape and amplitude information; calculating the waveform similarity between the waveform feature vectors of different key nodes, and judging whether waveform abnormity exists or not; fault type analysis is carried out on nodes with abnormal waveforms; and executing pilot protection action. According to the method, the adaptive capacity to a complex power grid fault scene is improved, and particularly, the method has remarkable advantages in processing multi-node concurrent faults.

Description

Technical Field

[0001] The invention relates to the technical field of generator protection methods, and in particular to a diesel generator longitudinal protection method based on waveform similarity. Background Art

[0002] Diesel generator systems are widely used in industry, electricity, transportation and other fields. As important power security equipment, it is crucial to ensure their stable operation and rapid fault response. Longitudinal protection is a common protection method in power systems. It is usually used to determine whether the system operation is abnormal by real-time monitoring of electrical quantities between multiple nodes, and take protective measures in time. However, with the increasing complexity of power systems, traditional longitudinal protection methods face many challenges when dealing with complex fault scenarios.

[0003] First of all, most of the existing longitudinal protection methods rely on fixed fault current and voltage thresholds. When faults such as short circuit, open circuit or overload occur in the system, the protection action is triggered by current or voltage exceeding the limit. However, this method based on simple threshold judgment is difficult to cope with more complex fault modes and waveform changes, especially in the case of concurrent faults at multiple nodes or small changes in waveform characteristics. The detection accuracy of traditional methods is low, and it is easy to make misjudgments or missed judgments, and the stable operation of the system cannot be guaranteed.

[0004] Secondly, traditional fault location methods usually rely on single-node waveform data and lack comprehensive analysis of multi-node waveforms. This method is very limited in its positioning accuracy in complex power grid faults, such as line faults or when multiple nodes are affected at the same time. This can easily lead to inaccurate fault location identification, which in turn affects the execution efficiency of protection actions.

[0005] Finally, the traditional longitudinal protection system lacks an effective coordination mechanism when executing protection actions, resulting in inconsistent responses of the protection devices at each node, and unable to ensure that protection measures can be taken synchronously when a fault occurs. Existing systems are usually based on fixed protection strategies and cannot flexibly adjust the order and priority of protection actions according to the type and location of the fault, resulting in poor response speed and effect of the system when a fault occurs, and may even cause secondary faults. Summary of the invention

[0006] The invention provides a diesel generator longitudinal protection method based on waveform similarity.

[0007] The diesel generator longitudinal protection method based on waveform similarity includes the following steps:

[0008] S1. Multi-node collection of waveform data: Current transformers and voltage transformers are installed at key nodes of the diesel generator, including output ports, both ends of the tie line and load nodes, and waveform data of each key node is collected in real time. The waveform data includes current waveform and voltage waveform, and the waveform data obtained from each node is subjected to wavelet transform denoising;

[0009] S2. Synchronous transmission and communication of waveform data: The waveform data collected by each key node is synchronously transmitted through the wireless network communication channel, so that each protection device of the generator can exchange and share waveform data in real time, ensuring the timing synchronization between each protection point in the system;

[0010] S3. Waveform feature vector generation: Based on the preprocessed waveform data, a convolutional neural network is used to generate a waveform feature vector. The waveform feature vector includes waveform shape and amplitude information. The feature vector generation process considers waveform changes under multiple time scales.

[0011] S4. Waveform similarity calculation: The improved dynamic time warping (IDTW) algorithm is used, combined with the spatiotemporal dynamic association, to calculate the waveform similarity between the waveform feature vectors of different key nodes to determine whether there is a waveform anomaly. If the waveform similarity between a node and other nodes is lower than the preset threshold, the node is judged to be faulty.

[0012] S5. Fault type and location judgment: Based on the calculation results of waveform similarity and the preset fault feature library, the fault type analysis is performed on the nodes with abnormal waveforms, and the short circuit, open circuit, and overload fault types are automatically identified. At the same time, the specific location of the fault is analyzed and determined;

[0013] S6. Execution of longitudinal protection action: When the fault location and type are determined, a signal is sent to the protection devices of other nodes through the longitudinal protection communication network to coordinate the protection devices to simultaneously execute corresponding protection actions, including generator tripping, interconnection line disconnection or load shedding, and adjust the priority and sequence of protection actions according to the actual operating environment.

[0014] Optionally, the S3 specifically includes:

[0015] S31, construct a multi-layer convolutional neural network. The network structure includes several convolutional layers, pooling layers and fully connected layers. The convolutional layer extracts the local features of the waveform, including the shape and amplitude change of the waveform. The pooling layer is used to reduce the dimension, reduce feature redundancy and retain key features.

[0016] S32, through the convolution kernel (convolution window of different sizes) at multiple time scales, the waveform data is scanned and feature extracted to ensure that the convolution neural network captures the changing characteristics of the waveform on short and long time scales. The size of the convolution kernel is dynamically adjusted according to the sampling rate and frequency characteristics of the waveform signal to ensure that rich waveform information is obtained on different time scales.

[0017] S33, waveform shape and amplitude feature vector generation: After multiple layers of convolution and pooling, the local features of the waveform are extracted and combined layer by layer. Finally, the feature map extracted by the convolution layer will be processed by the fully connected layer to generate multiple feature vectors V containing waveform shape and amplitude information. The feature vector V not only captures the overall shape characteristics of the waveform, but also includes the information of the fluctuation amplitude.

[0018] Optionally, S3 also includes the introduction of a cross-layer feature fusion mechanism. The waveform features extracted by multi-scale convolution need to be fused to ensure that the waveform information at different time scales can comprehensively reflect the overall changes of the waveform. This is accomplished by cross-layer feature fusion, which combines the short-time scale features extracted by different convolutional layers with the long-time scale features to improve the ability to analyze complex waveform changes and ensure the accuracy of waveform changes at different time scales. The fused comprehensive feature vector F fusion The expression is:

[0019] F fusion =α1Y1+α2Y2+…+α n Y n , where α1, α2, …, α n are weight coefficients of features at different time scales. The weights are automatically adjusted through historical data training. Y1, Y2, …, Y n They are the convolution outputs at different time scales respectively.

[0020] Optionally, the waveform similarity calculation in S4 specifically includes:

[0021] S41, input comprehensive feature vector: the waveform comprehensive feature vector F generated by each key node fusion As input;

[0022] S42, performing an improved dynamic time warping algorithm on each comprehensive feature vector:

[0023] D(i,j)=min{D(i-1,j),D(i,j-1),D(i-1,j-1)}+dist(F fusion1 (i),F fussion2 (j)), where D(i,j) is the minimum cumulative distance between the waveform feature vectors of two nodes, dist(F fusion1 (i),F fussion2(j)) is the local distance calculation between the feature vectors of two nodes at time i and j;

[0024] S43, introduce spatiotemporal dynamic association: Based on spatiotemporal dynamic association, combined with the spatial position of each node and the time series characteristics of the waveform data, dynamically adjust the time weight w of the similarity calculation t and the spatial weight w s , w t and w s Influence factors that represent temporal and spatial correlations:

[0025] D adjusted (i,j)=w t time diff(i,j)+w s D(i,j), where D adjusted (i,j) is the knot

[0026] The cumulative distance after time-space weight adjustment, w t is the time weight dynamically adjusted according to the waveform time difference, w s It is the spatial weight adjusted according to the spatial distance between nodes, and time diff represents the time step difference between two nodes at time i and time j;

[0027] S44, after calculating the waveform similarity between different nodes, the calculation result is compared with the preset similarity threshold θ. If the similarity of a node is lower than the threshold, that is: sim(F fusion1 ,F fusion2 )<θ, it is judged that the node has waveform anomaly or fault.

[0028] Optionally, the time weight w t Adjusted by the differences between waveforms at different time points, it is defined as: Among them, α is the adjustment parameter of the time difference, which is a constant used to control the influence of the time difference and determine the weight of the time difference on the final similarity calculation. Δt is the time difference between the two nodes, which is expressed as the offset of the two feature vectors on the time axis. Δt = |t i -t j |, where t i and t j is the corresponding time point of two nodes on the time axis, w t The larger the value, the smaller the impact of time difference on similarity; the smaller the value, the greater the impact of time difference on similarity.

[0029] Optionally, the spatial weight w s Adjusted according to the physical space distance between nodes, it is defined as:

[0030] Among them, β is the adjustment parameter of spatial difference, which is a constant used to control the influence of physical distance between nodes on similarity calculation. space Represents the physical distance between two nodes.

[0031] Optionally, the S5 specifically includes:

[0032] Preset fault feature library, which includes the fault types for diesel generator system, including waveform feature templates of short circuit, open circuit and overload. Each fault type in the fault feature library corresponds to specific waveform features, including the fluctuation mode, duration and amplitude change information of current and voltage. The fault feature library is formed through the analysis and induction of historical fault data, and is continuously updated to cover new fault modes;

[0033] Abnormal judgment based on waveform similarity: According to the waveform similarity calculation results, when the waveform similarity Sim(F fusion1 ,F fusion2 ) is lower than the preset threshold θ, the waveform of the node is judged to be abnormal, and the abnormal waveform will be compared with the feature template in the fault feature library to analyze the specific fault type.

[0034] Optionally, the fault type is identified by a support vector machine classifier, and the waveform feature vector F of the abnormal node is fusion The waveform feature template extracted from the fault feature library is used for training, and the support vector machine classifier automatically classifies the waveform features to identify the fault type.

[0035] Optionally, S5 further includes comparing and analyzing the waveform similarities of multiple nodes, combining the spatial positions of each node and the waveform feature differences, to determine the specific location where the fault occurs, specifically including:

[0036] S51, multi-node waveform similarity comparison: calculate the waveform similarity between every two nodes in the diesel generator system, and judge the similarity between them by comparing the waveform characteristics of each node. The more similar, the more consistent the waveform changes, and the greater the difference, the greater the probability of abnormal waveform.

[0037] S52, waveform difference analysis combined with spatial position: combining the physical positions between nodes to analyze the changes in waveform similarity;

[0038] S53, inference of fault location: infer the fault location based on waveform similarity and node location. If the waveform of a node is greatly different from that of other nodes, it indicates that a fault has occurred at the node. If the waveforms of multiple adjacent nodes are different, it indicates a line or regional fault. If multiple remote nodes are abnormal at the same time, it indicates a concurrent fault at multiple nodes.

[0039] S54, waveform feature difference analysis: Analyze the difference between the waveform feature vectors of the abnormal nodes, and verify the fault location by comparing the changes in the waveform features. The greater the difference in the waveform features, the more obvious the node waveform abnormality.

[0040] S55, final decision on fault location: Determine the specific location of the fault by integrating waveform similarity, spatial position and waveform feature differences.

[0041] Optionally, the S6 specifically includes:

[0042] S61, fault signal generation and transmission: when the fault type and location of a node are detected, a fault alarm signal is generated, which includes the location information of the fault node, the fault type (such as short circuit, open circuit, overload) and priority information. The fault signal is transmitted in real time through the longitudinal protection communication network;

[0043] S62, coordinated transmission of the pilot protection communication network: Fault information is propagated to all protection devices through the pilot protection communication network, and is synchronized with the central control unit through a high-speed communication protocol (IEC 61850);

[0044] S63, triggering and synchronous execution of protection actions: After the fault information is transmitted to each node protection device, the corresponding protection action is automatically triggered according to the severity and type of the fault. The protection action includes:

[0045] Generator tripping: When the fault type involves generator overload or short circuit, the generator protection device performs a tripping operation to stop the generator output and prevent the fault from expanding;

[0046] Tie line disconnection: If a fault occurs on a tie line or affects lines between multiple nodes, the tie line protection device is triggered to cut off the fault line and prevent the current from being transmitted to other areas;

[0047] Load shedding: In severe fault scenarios, a load shedding signal will be sent to the load protection device based on load priority, with non-critical loads being shelved first.

[0048] Beneficial effects of the present invention:

[0049] The present invention adopts a fault detection method based on waveform similarity, and realizes high-precision fault detection through real-time collection and feature extraction of multi-node waveform data and an improved dynamic time warping algorithm combined with a spatiotemporal dynamic correlation model. Compared with the traditional waveform comparison method, the introduced multi-scale convolution kernel dynamic adjustment technology greatly improves the accuracy of waveform feature extraction, ensuring that it can cope with waveform changes at different time scales. By flexibly aligning the waveform feature vectors in time sequence, it can more sensitively capture waveform abnormalities, improve the adaptability to complex power grid fault scenarios, and has significant advantages in dealing with multi-node concurrent faults.

[0050] The present invention combines waveform similarity analysis with comprehensive consideration of spatial position differences to achieve accurate fault location judgment. By analyzing the waveform differences between multiple nodes and combining the information of physical space distance, the location of the fault can be quickly located, and the precise positioning of concentrated faults, line faults and multi-node concurrent faults is supported. The waveform feature difference analysis ensures that when the waveforms of multiple nodes are abnormal, the fault severity of each node can be comprehensively evaluated and the fault location can be further verified, thereby achieving more effective fault isolation and rapid response, and greatly reducing the scope of fault impact.

[0051] The present invention, when the fault type and location are determined, synchronously sends a fault signal to each node protection device through the longitudinal protection communication network, realizes the automatic coordination of system protection actions, and ensures the synchronous execution of protection actions such as generator tripping, interconnection line disconnection and load shedding through a high-speed communication protocol, avoids inconsistent responses between systems, and introduces a protection action priority management mechanism to ensure that the order and execution time of protection actions are optimized under different fault scenarios, thereby minimizing system damage and downtime. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A schematic diagram of a method flow of an embodiment of the present invention;

[0054] Figure 2 Schematic diagram of waveform similarity calculation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0056] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0057] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0058] like Figure 1-Figure 2 As shown, the diesel generator longitudinal protection method based on waveform similarity includes the following steps:

[0059] S1. Multi-node collection of waveform data: Current transformers and voltage transformers are arranged at key nodes of the diesel generator, including output ports, both ends of the tie line and load nodes, and waveform data of each key node is collected in real time. The waveform data includes current waveform and voltage waveform. Wavelet transform denoising is performed on the waveform data obtained from each node. The pre-processed waveform data is further used for feature extraction to generate waveform feature vectors of each key node;

[0060] A current transformer is installed at the output port of the diesel generator to monitor the output current waveform of the generator in real time, and a voltage transformer is installed in the parallel circuit of the generator output port to obtain the output voltage waveform;

[0061] Current transformers are installed at both ends of the tie line to ensure that the current waveforms at both ends of the tie line can be monitored simultaneously, and voltage transformers are used to collect voltage waveform data at both ends of the tie line to facilitate fault location and tie line abnormality judgment in subsequent similarity calculations;

[0062] Current transformers are installed at the load nodes to monitor changes in load current, and voltage transformers are installed at the load connection ends to obtain changes in the voltage waveform at the load end in real time to ensure that the operating status and abnormal conditions of the load end can be accurately reflected;

[0063] S2. Synchronous transmission and communication of waveform data: The essence of longitudinal protection lies in the collaborative work between key nodes. Each node does not make protection decisions independently, but needs to cooperate with other nodes to ensure that when a node fails, other nodes can respond in time and cooperate to perform protection actions. Synchronous transmission of waveform data allows each node to exchange information in real time, facilitates comprehensive analysis based on global waveform changes, and coordinates the protection devices of each node to ensure rapid linkage response of the entire system. Therefore, the waveform data collected by each key node is synchronously transmitted through the wireless network communication channel, so that each protection device of the generator can exchange and share waveform data in real time, ensuring the timing synchronization between each protection point in the system;

[0064] S3. Waveform feature vector generation: Based on the preprocessed waveform data, a convolutional neural network is used to generate waveform feature vectors. The waveform feature vectors include waveform shape and amplitude information. The feature vector generation process considers waveform changes under multiple time scales to improve the response capability to long and short-term fluctuations.

[0065] S4. Waveform similarity calculation: The improved dynamic time warping (IDTW) algorithm is used, combined with the spatiotemporal dynamic association, to calculate the waveform similarity between the waveform feature vectors of different key nodes to determine whether there is a waveform anomaly. If the waveform similarity between a node and other nodes is lower than the preset threshold, the node is judged to have a fault. Compared with the traditional similarity algorithm, the spatiotemporal dynamic association parameter is introduced, which can dynamically adjust the similarity threshold according to the waveform changes in different time and space, so as to more accurately determine whether the waveform is abnormal;

[0066] S5. Fault type and location judgment: Based on the calculation results of waveform similarity and the preset fault feature library, the fault type analysis is performed on the nodes with abnormal waveforms, and the short circuit, open circuit, and overload fault types are automatically identified. At the same time, the specific location of the fault is analyzed and determined;

[0067] S6. Execution of longitudinal protection action: When the fault location and type are determined, a signal is sent to the protection devices of other nodes through the longitudinal protection communication network to coordinate the protection devices to simultaneously execute corresponding protection actions, including generator tripping, tie line disconnection or load shedding. The action of the longitudinal protection needs to be completed within milliseconds to ensure rapid response of fault isolation. Different from the traditional fixed protection action scheme, the priority and sequence of protection actions are adjusted according to the actual operating environment to ensure that the operating risks and losses of the system are minimized.

[0068] The wavelet transform denoising process specifically includes:

[0069] Decomposition of waveform data: The current waveform and voltage waveform data obtained from each node are input into the wavelet transform processing module, and the original waveform is decomposed into multi-scale using discrete wavelet transform. The waveform data is decomposed into different frequency band levels through wavelet basis functions to obtain detail signals and approximate signals. The higher frequency components contain noise information, while the lower frequency components retain the main features of the waveform.

[0070] Threshold processing: Perform threshold processing on the decomposed high-frequency detail components to remove noise. Set a hard threshold and select the threshold size based on the characteristics of the waveform data and the noise level. High-frequency components smaller than the threshold will be regarded as noise and removed, while components larger than the threshold will be retained to reduce waveform distortion caused by noise.

[0071] Reconstruction of wavelet coefficients: After threshold processing, the retained high-frequency and low-frequency components are used to reconstruct the wavelet coefficients. The decomposed signal is reconstructed back to the time domain through inverse wavelet transform to obtain the denoised waveform signal, and the waveform data after denoising is restored, while retaining its main features and removing noise interference.

[0072] Waveform smoothing and refinement: The waveform data after wavelet transform denoising will be further smoothed, and multiple reconstruction and signal fusion techniques will be used to eliminate the edge effects caused by wavelet transform to ensure that the denoised waveform signal has high smoothness and integrity.

[0073] The processed waveform data will be input into the feature vector generation as clear current and voltage waveforms to generate waveform feature vectors for subsequent similarity calculation and fault judgment.

[0074] The synchronous transmission and communication of waveform data are as follows:

[0075] Wireless communication module deployment: Wireless communication modules are deployed at each key node of the diesel generator. The communication module of each node maintains real-time connection with the preset central control unit. The waveform data collected from each node is digitized by the local data processing unit and data packet processing is performed. Each data packet contains the identification, timestamp, waveform data, and waveform characteristic value information of the collection node. In order to ensure the consistency of timing, the timestamp of the waveform data will be uniformly processed based on the global synchronized clock system (GPS synchronized clock); in order to improve transmission efficiency and ensure data security, the waveform data will be compressed after packaging to reduce the size of the data packet. At the same time, the data packet will be processed by AE S encryption processing ensures that data will not be attacked or tampered with externally during wireless network transmission; the data packets collected by each node are transmitted to the central control unit in real time through the wireless communication channel. The central control unit receives the waveform data from each node in real time and uses the clock synchronization mechanism to align the data of each node in time to ensure that the data of different nodes can be compared and analyzed in a unified time frame. If there is a delay or data loss in the network, the automatic retransmission mechanism (ARQ) is started to ensure the integrity and accuracy of the waveform data; after the central control unit receives the waveform data of all nodes, it will share and exchange these data in real time between the various protection devices of the generator. Through the internal wireless Mesh network, each protection device can receive global waveform data at the same time.

[0076] S3 specifically includes:

[0077] S31, construct a multi-layer convolutional neural network. The network structure includes several convolutional layers, pooling layers and fully connected layers. The convolutional layer extracts the local features of the waveform, including the shape and amplitude change of the waveform. The pooling layer is used to reduce the dimension, reduce feature redundancy and retain key features.

[0078] In convolutional neural networks, the convolution operation is the core calculation step for feature extraction of input waveform data. For the input waveform data X and the convolution kernel W, the convolution operation is expressed as: Among them, X(i) represents the i-th data point of the waveform data, W(k) represents the k-th parameter of the convolution kernel, Y(i) is the output after the convolution operation, reflecting the local waveform characteristics, K is the size of the convolution kernel, that is, the length of the waveform data covered by one operation. In the present invention, the convolution operation is applied to the preprocessed current and voltage waveform data, the purpose is to extract the local shape and amplitude characteristics of the waveform. Through convolution kernels of different sizes, the changes of the waveform on different time scales can be captured. In order to ensure that the features after convolution retain valid information, the ReLU activation function is introduced. The activation function sets negative numbers to zero after the convolution operation and retains non-negative eigenvalues ​​to ensure that the extracted waveform features are valid.

[0079] S32, the waveform data is scanned and features are extracted through convolution kernels (convolution windows of different sizes) at multiple time scales to ensure that the convolutional neural network captures the changing characteristics of the waveform on short and long time scales. The size of the convolution kernel is dynamically adjusted according to the sampling rate and frequency characteristics of the waveform signal to ensure that rich waveform information is obtained on different time scales;

[0080] In the present invention, the size of the convolution kernel should be dynamically adjusted according to the sampling rate and frequency characteristics of the waveform signal. The frequency characteristics and sampling rate of the waveform signal determine the distribution of different frequency components in the signal. For high-frequency components, a smaller convolution kernel is required to capture fast-changing features; and for low-frequency components, a larger convolution kernel is required to capture slower changes.

[0081] Sampling rate: The sampling rate of waveform data determines the temporal resolution of the signal, that is, the number of data points collected per second. The higher the sampling rate, the more subtle the signal can reflect. Therefore, for data with a high sampling rate, a smaller convolution kernel can be used to capture rapid waveform changes.

[0082] Frequency characteristics: The frequency characteristics of a waveform signal determine the frequency range in which the main energy in the waveform is concentrated. If the high-frequency component dominates the signal, the convolution kernel size should be smaller to accurately capture these rapidly changing features; for low-frequency signals, a larger convolution kernel is required to capture slow changes over a long period of time.

[0083] Dynamically adjust the convolution kernel size as follows:

[0084] Perform spectral analysis on the collected waveform data, calculate the dominant frequency distribution of the signal, obtain the spectrum of the signal through fast Fourier transform (FFT), identify the frequency ranges where the energy in the signal is mainly concentrated, determine the characteristics of different frequency components based on the results of the spectral analysis, and then assign a suitable convolution kernel size to each frequency range.

[0085] Assume the sampling rate of the waveform signal is f s , the frequency characteristics of the signal are determined by the frequency range f min to f max Definition: The size K of the convolution kernel is dynamically adjusted, expressed as: Among them, f s is the sampling rate of the waveform signal, f target It is the target frequency component that needs to be captured in the signal;

[0086] In order to capture the characteristics of different frequency ranges, the frequency characteristics of the signal are analyzed and multiple target frequencies f are selected. target1 ,f target2 ,…,f targetn, and use different convolution kernel sizes for each target frequency.

[0087] For high frequency components, choose a smaller K, such as In order to capture the details of fast fluctuations; for low-frequency components, choose a larger K, such as To capture long-term waveform trends.

[0088] S33, waveform shape and amplitude feature vector generation: After multi-layer convolution and pooling processing, the local features of the waveform are extracted and combined layer by layer. Finally, the feature map extracted by the convolution layer will be processed by the fully connected layer to generate multiple feature vectors V containing waveform shape and amplitude information. The feature vector V not only captures the overall shape characteristics of the waveform, but also includes information on the amplitude of the fluctuation, ensuring that it can fully reflect the changes in the waveform at each time point; the generation expression of the feature vector V is as follows: V = W fc ·Y pool +b, where W fc is the weight matrix of the fully connected layer, b is the bias term, and Y pool It is a waveform feature map after convolution and pooling.

[0089] S3 also includes the introduction of a cross-layer feature fusion mechanism. The waveform features extracted by multi-scale convolution need to be fused to ensure that the waveform information at different time scales can comprehensively reflect the overall changes of the waveform. This is accomplished through cross-layer feature fusion. The short-scale features extracted by different convolutional layers are fused with the long-scale features to improve the ability to analyze complex waveform changes and ensure the accuracy of waveform changes at different time scales. The fused comprehensive feature vector F fusion The expression is:

[0090] F fusion =α1Y1+α2Y2+…+α n Y n , where α1, α2, …, α n are weight coefficients of features at different time scales. The weights are automatically adjusted through historical data training. Y1, Y2, …, Y n They are the convolution outputs of different time scales respectively. Through feature fusion, the important features of the waveform at multiple time scales are effectively extracted, and a comprehensive feature vector is generated for subsequent waveform similarity calculation and fault identification.

[0091] The waveform similarity calculation in S4 specifically includes:

[0092] S41, input comprehensive feature vector: the waveform comprehensive feature vector F generated by each key node fusion As input;

[0093] S42, performing an improved dynamic time warping algorithm on each comprehensive feature vector:

[0094] D(i,j)=min{D(i-1,j),D(i,j-1),D(i-1,j-1)}+dist(F fusion1 (i),F fussion2 (j)), where D(i,j) is the minimum cumulative distance between the waveform feature vectors of two nodes, dist(F fusion1 (i),F fussion2 (j)) is the local distance calculation of the feature vectors of two nodes at time i and j, using the Euclidean distance measurement method. The algorithm allows the waveform feature vectors to be flexibly aligned in time sequence by dynamically adjusting the time axis to capture the differences in the spatiotemporal characteristics of the waveforms of each node;

[0095] S43, introduce spatiotemporal dynamic association: Based on spatiotemporal dynamic association, combined with the spatial position of each node and the time series characteristics of the waveform data, dynamically adjust the time weight w of the similarity calculation t and the spatial weight w s , w t and w s Influence factors that represent temporal and spatial correlations:

[0096] D adjusted (i,j)=w t time diff(i,j)+w s D(i,j), where D adjusted (i, j) is the cumulative distance adjusted with spatiotemporal weights, w t is the time weight dynamically adjusted according to the waveform time difference, w s It is the spatial weight adjusted according to the spatial distance between each node. Time diff represents the time step difference between two nodes at time i and time j, and is used to measure whether two feature vectors are aligned on the time axis. Generally, the larger the time step difference, the lower the waveform similarity. By combining spatiotemporal features, waveform changes across time and nodes can be captured more accurately.

[0097] S44, after calculating the waveform similarity between different nodes, the calculation result is compared with the preset similarity threshold θ. If the similarity of a node is lower than the threshold, that is: sim(F fusion1 ,F fusion2 )<θ, it is judged that the node has abnormal waveform or fault, sim(F fusion1 ,F fusion2 ) is the comprehensive feature vector F of the two nodes fusion1 ,F fusion2 The similarity between

[0098] Preset similarity threshold It is an important criterion for judging whether the waveforms of two nodes are similar. It calculates the waveform similarity between different nodes under normal and fault conditions, and sets a reasonable threshold based on the experimental results.

[0099] Under normal operating conditions: collect waveform data under normal conditions and calculate the similarity. Usually, the similarity value of these data will be high (close to 1). Based on these normal data, select a high similarity threshold that can identify normal waveforms.

[0100] Under fault conditions: Similarly, the waveform data when the fault occurs is collected and the similarity is calculated. These data usually have a low similarity value (close to 0). By analyzing these data, a suitable threshold is set to ensure that when the waveform is abnormal, the similarity is lower than the threshold, triggering the fault judgment.

[0101] Time weight w t Adjusted by the differences between waveforms at different time points, it is defined as: Among them, α is the adjustment parameter of the time difference, which is a constant used to control the influence of the time difference and determine the weight of the time difference on the final similarity calculation. Δt is the time difference between the two nodes, which is expressed as the offset of the two feature vectors on the time axis. Δt = |t i -t j |, where t i and t j is the corresponding time point of two nodes on the time axis, w t The larger the value, the smaller the impact of time difference on similarity; the smaller the value, the greater the impact of time difference on similarity.

[0102] Spatial weight w s Adjusted according to the physical space distance between nodes, it is defined as:

[0103] Among them, β is the adjustment parameter of spatial difference, which is a constant used to control the influence of physical distance between nodes on similarity calculation. space represents the physical distance between two nodes, measured by the actual geographical location, which is similar to the control parameter of the time weight, and it determines the degree of influence of spatial difference on the final similarity. s The larger the value, the smaller the effect of spatial distance on similarity; the smaller the value, the greater the effect of spatial distance on similarity.

[0104] Through a large number of experiments and data set verification, the values ​​of α and β are adjusted to obtain the best results in actual scenarios. The following are the specific steps:

[0105] 1. Dataset preparation: By collecting waveform data under different operating conditions, a set of training and validation data sets are formed. The data set should contain data from normal operation and data under fault scenarios. The corresponding fault type and spatial location should also be marked in the data set to ensure that the accuracy of fault detection by adjusting parameters can be evaluated.

[0106] 2. Parameter adjustment process: Experiment with different α and β values. You can start with smaller values, such as α = 0.1 and β = 0.1, and then gradually increase them to observe the system's similarity calculation results and the effect of fault detection. In each experiment, evaluate the false alarm rate and missed alarm rate. Ideally, adjust these parameters to find a balance point so that both the false alarm rate and missed alarm rate are low.

[0107] 3. Grid search: Using the grid search method, we can find the optimal combination by systematically searching for α and β within a predetermined range. For example:

[0108] Set the value range of α to [0.1, 0.5, 1.0, 1.5];

[0109] Set the value range of β to [0.1, 0.5, 1.0, 1.5];

[0110] Perform similarity calculation and fault detection under each combination, observe the performance changes, and select the combination with the best false alarm rate and false negative rate as the final parameter value.

[0111] S5 specifically includes:

[0112] Preset fault feature library, which includes the fault types for diesel generator system, including waveform feature templates of short circuit, open circuit and overload. Each fault type in the fault feature library corresponds to specific waveform features, including the fluctuation mode, duration and amplitude change information of current and voltage. The fault feature library is formed through the analysis and induction of historical fault data, and is continuously updated to cover new fault modes;

[0113] Abnormal judgment based on waveform similarity: According to the waveform similarity calculation results, when the waveform similarity Sim(F fusion1 ,F fusion2 ) is lower than the preset threshold θ, the waveform of the node is judged to be abnormal, and the abnormal waveform will be compared with the feature template in the fault feature library to analyze the specific fault type.

[0114] The fault type is identified by the support vector machine classifier, and the waveform feature vector F of the abnormal node is fusion The waveform feature template extracted from the fault feature library is used for training, and the support vector machine classifier automatically classifies the waveform features and identifies the fault type. The discriminant formula of the support vector machine classifier is as follows:

[0115]

[0116] in, represents the identified fault type label, α i is the Lagrange multiplier of the support vector machine, used for the support vector weight, y i is the true label of the fault type, is the waveform feature F fusion Templates in the fault signature library The kernel function, Gaussian kernel or linear kernel, is used to measure the similarity between the current waveform and the fault template, and b is the bias term of the support vector machine.

[0117] S5 also includes comparing and analyzing the waveform similarity of multiple nodes, combining the spatial position of each node and the difference in waveform characteristics, determining the specific location of the fault, and analyzing the abnormality of the waveforms of multiple nodes to determine whether the fault occurs in a certain node or extends in a certain line or area. Specifically, it includes:

[0118] S51, multi-node waveform similarity comparison: calculate the waveform similarity between every two nodes in the diesel generator system, and judge the similarity between them by comparing the waveform characteristics of each node. The more similar, the more consistent the waveform changes, and the greater the difference, the greater the probability of abnormal waveform.

[0119] S52, waveform difference analysis combined with spatial position: combining the physical positions between nodes to analyze the changes in waveform similarity;

[0120] S53, inference of fault location: infer the fault location based on waveform similarity and node location. If the waveform of a node is greatly different from that of other nodes, it indicates that a fault has occurred at the node. If the waveforms of multiple adjacent nodes are different, it indicates a line or regional fault. If multiple remote nodes are abnormal at the same time, it indicates a concurrent fault at multiple nodes.

[0121] S54, waveform feature difference analysis: Analyze the difference between the waveform feature vectors of the abnormal nodes, and verify the fault location by comparing the changes in the waveform features. The greater the difference in the waveform features, the more obvious the node waveform abnormality.

[0122] S55, final decision on fault location: Determine the specific location of the fault by integrating waveform similarity, spatial position and waveform feature differences.

[0123] The detailed plan is as follows:

[0124] 1. Multi-node waveform similarity comparison, there are N nodes, their comprehensive waveform feature vectors are:

[0125] Ffusion1 ,F fusion2 ,…,F fusionN For each pair of nodes, the waveform similarity is calculated to evaluate whether their waveform changes are consistent. The similarity calculation formula in S44 is: in;

[0126] Sim(F fusioni ,F fusionj ) represents the waveform similarity between node i and node j;

[0127] D adjusted (i, j) is the cumulative minimum distance after combining the spatiotemporal weights, which is used to measure the waveform difference between node i and node j (see the formula given above);

[0128] By calculating the similarity matrix S between every two nodes, we can get:

[0129]

[0130] Each matrix element Sim(F fusioni ,F fusionj ) represent the similarity of the waveforms of two nodes. The closer the value is to 1, the more similar the waveforms of the two nodes are, and the closer the value is to 0, the greater the difference in the waveforms is.

[0131] 2. In order to further combine the physical spatial location information of the node, the spatial distance matrix D of the node is introduced space , where D space (i, j) represents the physical distance between node i and node j. A comprehensive analysis matrix C is constructed by the following formula to determine the location of the fault by combining waveform similarity and spatial distance: Among them, C(i,j) is a comprehensive value combining waveform similarity and spatial distance, which is used to describe the correlation between the waveforms of two nodes. If the waveforms of the two nodes are very different and the spatial distance is far, C(i,j) will be small; if the waveforms are similar and the distance is close, C(i,j) will be large;

[0132] 3. Inference of fault location: By analyzing the values ​​in the comprehensive matrix C, the location of the fault can be inferred. The following are the inference rules:

[0133] 3.1 Single-node concentrated failure: If a node has low similarity with multiple other nodes, that is: And the spatial distance between this node and other nodes is not large (i.e. D space (i,j) is smaller), then it is inferred that the fault is concentrated on this node;

[0134] 3.2 Extended fault in a certain line or area:

[0135] If the waveform similarity of multiple adjacent nodes is low at the same time, that is:

[0136] sim(F fusioni ,F fusioni+1 )<θ and sim(F fusioni+1 ,F fusioni+2 )<θ, indicating that the fault occurs between these adjacent nodes and is a line fault or a regional fault;

[0137] 3.3 Concurrent failures of multiple nodes:

[0138] If multiple nodes in different regions have low similarity at the same time, that is:

[0139] sim(F fusioni ,F fusionj )<θ and sim(F fusionk ,F fusionl )<θ, and the physical distance between these nodes is far (i.e., D space (i,j) is larger), it is judged that multiple nodes fail at the same time, F fusionk is the waveform comprehensive feature vector of node k, F fusionl is the waveform comprehensive feature vector of node l.

[0140] 4. Determine the fault location by combining the waveform feature difference: When determining the fault location, the location can be further verified by the difference in waveform feature vectors. For each node’s comprehensive feature vector F fusioni, , analyze the difference between its feature vector and other nodes:

[0141] ΔF ij =F fusioni -F fusionj , where ΔF ij represents the difference in waveform characteristics between node i and node j. If ΔF ij The value is large, and the similarity Sim(F fusioni ,F fusionj ) is low, it means that the waveform anomaly at node i is more serious, and it is inferred that the failure probability of this node is higher.

[0142] In general, the comprehensive waveform similarity matrix S and spatial distance matrix D space And the characteristic difference analysis ΔF, determine the specific location of the fault through the following decision process:

[0143] First, by analyzing the nodes in the similarity matrix that are below the threshold θ, we determine which nodes may be abnormal;

[0144] Next, based on the spatial distance, determine whether these abnormal nodes are concentrated in a certain physical area;

[0145] Finally, the specific node or line location of the fault is determined by analyzing the differences in the waveform feature vectors.

[0146] S6 specifically includes:

[0147] S61, fault signal generation and transmission: when the fault type and location of a node are detected, a fault alarm signal is generated, which includes the location information of the fault node, the fault type (such as short circuit, open circuit, overload) and priority information. The fault signal is transmitted in real time through the longitudinal protection communication network;

[0148] S62, coordinated transmission of the pilot protection communication network: Fault information is propagated to all protection devices through the pilot protection communication network, and is synchronized with the central control unit through a high-speed communication protocol (IEC 61850). The fault signal received by each protection device contains a synchronized clock to ensure that each node in the system responds to the fault signal at the same time to avoid delays or misoperation;

[0149] S63, triggering and synchronous execution of protection actions: After the fault information is transmitted to each node protection device, the corresponding protection action is automatically triggered according to the severity and type of the fault. The protection action includes:

[0150] Generator tripping: When the fault type involves generator overload or short circuit, the generator protection device performs a tripping operation to stop the generator output and prevent the fault from expanding;

[0151] Tie line disconnection: If a fault occurs on a tie line or affects lines between multiple nodes, the tie line protection device is triggered to cut off the fault line and prevent the current from being transmitted to other areas;

[0152] Load shedding: In the event of a serious fault, a load shedding signal will be sent to the load protection device based on the load priority, with non-critical loads being shelved first;

[0153] Coordinate the order and priority of executing protection actions:

[0154] Each protection device determines the corresponding action sequence and priority through the received fault signal. For example, when a generator fault occurs, the tripping operation is triggered first, and then it is determined whether it is necessary to further disconnect the interconnection line or cut off the load according to the situation. All protection actions are executed under the unified coordination of the system to ensure fault isolation and safe operation of the system.

[0155] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0156] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A diesel generator longitudinal protection method based on waveform similarity, characterized in that: The following steps are involved: S1. Multi-node collection of waveform data: Current transformers and voltage transformers are installed at key nodes of the diesel generator, including output ports, both ends of the tie line and load nodes, and waveform data of each key node is collected in real time. The waveform data includes current waveform and voltage waveform, and the waveform data obtained from each node is subjected to wavelet transform denoising; S2. Synchronous transmission and communication of waveform data: The waveform data collected by each key node is synchronously transmitted through the wireless network communication channel, so that each protection device of the generator can exchange and share waveform data in real time; S3. Waveform feature vector generation: Based on the preprocessed waveform data, a convolutional neural network is used to generate a waveform feature vector. The waveform feature vector includes waveform shape and amplitude information. The feature vector generation process considers waveform changes under multiple time scales. S4. Waveform similarity calculation: The improved dynamic time warping algorithm is used in combination with the spatiotemporal dynamic association to calculate the waveform similarity between the waveform feature vectors of different key nodes to determine whether there is a waveform anomaly. If the waveform similarity between a node and other nodes is lower than the preset threshold, the node is judged to be faulty. S5. Fault type and location judgment: Based on the calculation results of waveform similarity and the preset fault feature library, the fault type analysis is performed on the nodes with abnormal waveforms, and the short circuit, open circuit, and overload fault types are automatically identified. At the same time, the specific location of the fault is analyzed and determined; S6. Execution of longitudinal protection action: When the fault location and type are determined, a signal is sent to the protection devices of other nodes through the longitudinal protection communication network to coordinate the protection devices to simultaneously execute corresponding protection actions, including generator tripping, interconnection line disconnection or load shedding, and adjust the priority and sequence of protection actions according to the actual operating environment.

2. The diesel generator longitudinal protection method based on waveform similarity according to claim 1 is characterized in that: The S3 specifically includes: S31, construct a multi-layer convolutional neural network. The network structure includes several convolutional layers, pooling layers and fully connected layers. The convolutional layer extracts the local features of the waveform, including the shape and amplitude change of the waveform. The pooling layer is used to reduce the dimension and reduce feature redundancy. S32, scanning and feature extraction of waveform data through convolution kernels at multiple time scales, ensuring that the convolutional neural network captures the changing characteristics of the waveform at short and long time scales, and the size of the convolution kernel is dynamically adjusted according to the sampling rate and frequency characteristics of the waveform signal; S33, waveform shape and amplitude feature vector generation: The feature map extracted by the convolution layer will be processed by the fully connected layer to generate multiple feature vectors V containing waveform shape and amplitude information. The feature vector V not only captures the overall shape characteristics of the waveform, but also includes the information of the fluctuation amplitude.

3. The diesel generator longitudinal protection method based on waveform similarity according to claim 2 is characterized in that: S3 also includes the introduction of a cross-layer feature fusion mechanism to fuse the short-scale features extracted by different convolutional layers with the long-scale features. The fused comprehensive feature vector F fusion The expression is: F fusion =α1Y1+α2Y2+…+α n Y n , where α1, α2, …, α n are weight coefficients of features at different time scales. The weights are automatically adjusted through historical data training. Y1, Y2, …, Y n They are the convolution outputs at different time scales respectively.

4. The diesel generator longitudinal protection method based on waveform similarity according to claim 3 is characterized in that: The waveform similarity calculation in S4 specifically includes: S41, input comprehensive feature vector: the waveform comprehensive feature vector F generated by each key node fusion As input; S42, performing an improved dynamic time warping algorithm on each comprehensive feature vector: D(i,j)= min{D(i-1,j),D(i,j-1),D(i-1,j-1)}+dist(F fusion1 (i),F fussion2 (j)), where D(i,j) is the minimum cumulative distance between the waveform feature vectors of two nodes, dist(F fusion1 (i),F fussion2 (j)) is the local distance calculation between the feature vectors of two nodes at time i and j; S43, introduce spatiotemporal dynamic association: Based on spatiotemporal dynamic association, combined with the spatial position of each node and the time series characteristics of the waveform data, dynamically adjust the time weight w of the similarity calculation t and the spatial weight w s , w t and w s Influence factors that represent temporal and spatial correlations: D adjusted (i,j)=w t time diff(i,j)+w s D(i,j), where D adjusted (i,j) is the knot The cumulative distance after time-space weight adjustment, w t is the time weight dynamically adjusted according to the waveform time difference, w s It is the spatial weight adjusted according to the spatial distance between nodes, and time diff represents the time step difference between two nodes at time i and time j; S44, after calculating the waveform similarity between different nodes, the calculation result is compared with the preset similarity threshold θ. If the similarity of a node is lower than the threshold, that is: sim(F fusion1 ,F fusion2 )<θ, it is judged that the node has waveform anomaly or fault.

5. The diesel generator longitudinal protection method based on waveform similarity according to claim 4 is characterized in that: The time weight w t Adjusted by the differences between waveforms at different time points, it is defined as: Among them, α is the adjustment parameter of the time difference, which is a constant, Δt is the time difference between the two nodes, expressed as the offset of the two feature vectors on the time axis, Δt = |t i -t j |, where t i and t j It is the corresponding time point of two nodes on the timeline.

6. The diesel generator longitudinal protection method based on waveform similarity according to claim 4 is characterized in that: The spatial weight w s Adjusted according to the physical space distance between nodes, it is defined as: Among them, β is the adjustment parameter of spatial difference, which is a constant used to control the influence of physical distance between nodes on similarity calculation. space Represents the physical distance between two nodes.

7. The diesel generator longitudinal protection method based on waveform similarity according to claim 6 is characterized in that: The S5 specifically includes: Preset fault feature library, which includes the fault types for diesel generator system, including waveform feature templates of short circuit, open circuit and overload. Each fault type in the fault feature library corresponds to specific waveform features, including the fluctuation mode, duration and amplitude change information of current and voltage. The fault feature library is formed by analyzing and summarizing historical fault data; Abnormal judgment based on waveform similarity: According to the waveform similarity calculation results, when the waveform similarity Sim(F fusion1 ,F fusion2 ) is lower than the preset threshold θ, the waveform of the node is judged to be abnormal, and the abnormal waveform will be compared with the feature template in the fault feature library to analyze the specific fault type.

8. The diesel generator longitudinal protection method based on waveform similarity according to claim 7 is characterized in that: The fault type is identified by a support vector machine classifier, and the waveform feature vector F of the abnormal node is fusion The waveform feature template extracted from the fault feature library is used for training, and the support vector machine classifier automatically classifies the waveform features to identify the fault type.

9. The diesel generator longitudinal protection method based on waveform similarity according to claim 1, characterized in that: S5 also includes comparing and analyzing the waveform similarities of multiple nodes, combining the spatial positions of each node and the waveform feature differences, to determine the specific location where the fault occurs, specifically including: S51, multi-node waveform similarity comparison: calculate the waveform similarity between every two nodes in the diesel generator system, and judge the similarity between them by comparing the waveform characteristics of each node. The more similar, the more consistent the waveform changes, and the greater the difference, the greater the probability of abnormal waveform. S52, waveform difference analysis combined with spatial position: combining the physical positions between nodes to analyze the changes in waveform similarity; S53, inference of fault location: infer the fault location based on waveform similarity and node location. If the waveform of a node is greatly different from that of other nodes, it indicates that a fault has occurred at the node. If the waveforms of multiple adjacent nodes are different, it indicates a line or regional fault. If multiple remote nodes are abnormal at the same time, it indicates a concurrent fault at multiple nodes. S54, waveform feature difference analysis: Analyze the difference between the waveform feature vectors of the abnormal nodes, and verify the fault location by comparing the changes in the waveform features. The greater the difference in the waveform features, the more obvious the node waveform abnormality. S55, final decision on fault location: Determine the specific location of the fault by integrating waveform similarity, spatial position and waveform feature differences.

10. The diesel generator longitudinal protection method based on waveform similarity according to claim 1, characterized in that: The S6 specifically includes: S61, fault signal generation and transmission: when the fault type and location of a node are detected, a fault alarm signal is generated, the fault alarm signal includes the location information, fault type and priority information of the fault node, and the fault signal is transmitted in real time through the longitudinal protection communication network; S62, coordinated transmission of the pilot protection communication network: Fault information is propagated to all protection devices through the pilot protection communication network, and is synchronized with the central control unit through a high-speed communication protocol; S63, triggering and synchronous execution of protection actions: After the fault information is transmitted to each node protection device, the corresponding protection action is automatically triggered according to the severity and type of the fault. The protection action includes: Generator tripping: When the fault type involves generator overload or short circuit, the generator protection device performs a tripping operation to stop the generator output and prevent the fault from expanding; Tie line disconnection: If a fault occurs on a tie line or affects lines between multiple nodes, the tie line protection device is triggered to cut off the fault line and prevent the current from being transmitted to other areas; Load shedding: In severe fault scenarios, a load shedding signal will be sent to the load protection device based on load priority, with non-critical loads being shelved first.

Images