Substation connection fitting damage identification method and device and computer equipment

Abstract

The transformer substation connection fitting damage identification method provided by the invention comprises the following steps: emitting white noise to a transformer substation connection fitting to obtain a vibration signal of the transformer substation connection fitting; an optimal influence coefficient of the preset harmonic sine structural element is determined by adopting a starfish optimization strategy, an optimal harmonic sine structural element is obtained, and the starfish optimization strategy is that after influence parameters of the preset harmonic sine structural element are initialized, an objective function corresponding to the vibration signal is adopted to perform optimal influence parameter solution search; and carrying out morphological gradient combination product operation on the vibration signal by adopting the optimal harmonic sine structural element, and then carrying out spectral analysis to obtain a damage identification result of the transformer substation connection fitting. Therefore, accurate identification of the damage of the connection fitting is realized.

Description

Technical Field

[0001] The present application relates to the technical field of substations, and in particular to a method, device, and computer equipment for identifying damage to substation connection fittings. Background Art

[0002] With the vigorous development of my country's power system, more and more substations have been built and put into use. Due to the influence of natural factors such as wind, rain, and snow, the internal parts of substations are very prone to failure. Among them, connecting hardware, as a key component in the substation, not only bears complex mechanical stress and electrical loads, but also ensures the reliable connection of various important components in the substation, playing an indispensable role in the stable operation of the substation. Connecting hardware refers to metal devices used to connect wires and wires, and wires and electrical equipment. They mainly include tension clamps, suspension clamps, connecting pipes, connecting pipes, ball head hanging rings, U-shaped rings and other types. They are usually made of aluminum alloy or hot-dip galvanized steel and have good conductivity, corrosion resistance and mechanical strength. In the power system, connecting hardware undertakes the dual tasks of power transmission and mechanical support. Damage or loosening of any small component may cause power system failure or even safety accidents.

[0003] However, connectors are prone to aging, loosening, or cracking during operation. Their vibration signal signatures are often weak and difficult to detect directly. Traditional vibration signal processing methods are ineffective in the presence of strong background noise, making it difficult to accurately identify fault signatures and, consequently, complicating troubleshooting. Therefore, regular inspection and maintenance of connectors in substations is crucial to ensuring the safe and stable operation of power systems. Summary of the Invention

[0004] The purpose of this application is to solve at least one of the above technical deficiencies, especially the technical defect in the prior art that it is difficult to accurately identify the fault characteristics of substation connection fittings.

[0005] In a first aspect, the present application provides a method for identifying damage to substation connection fittings, the method comprising:

[0006] By emitting white noise to the substation connection hardware, the vibration signal of the substation connection hardware is obtained;

[0007] The starfish optimization strategy is used to determine the optimal influence coefficient of the preset harmonic sinusoidal structural element, and the optimal harmonic sinusoidal structural element is obtained. The starfish optimization strategy is to initialize the influence parameters of the preset harmonic sinusoidal structural element and then use the objective function corresponding to the vibration signal to search for the optimal influence parameter solution;

[0008] The optimal harmonic sine structure element is used to perform morphological gradient combination product operation on the vibration signal, and then spectrum analysis is performed to obtain the damage identification results of the substation connection hardware.

[0009] In one embodiment, the preset harmonic sinusoidal structure element is:

[0010]

[0011] in, is a preset harmonic sine structure element, is the amplitude of the fundamental component of the harmonic sinusoidal structural element, is the amplitude of the harmonic component of the harmonic sine structural element, is the length of the harmonic sine structure element, 、 is the angular frequency, 、 are the fundamental frequency and harmonic frequency of the harmonic sine structure element, is the sampling period, is the sampling frequency.

[0012] In one embodiment, the process of determining the objective function corresponding to the vibration signal includes:

[0013] Decompose the vibration signal into multiple independent modal components and calculate the envelope spectrum peak factor of each modal component;

[0014] The weight corresponding to the envelope spectrum peak factor of each modal component is determined, and an objective function is constructed based on the envelope spectrum peak factor of each modal component and its corresponding weight.

[0015] In one embodiment, the step of calculating the envelope spectrum peak factor of each modal component includes:

[0016] The envelope spectrum peak factor of each modal component is calculated according to the following formula:

[0017]

[0018] in, is the envelope spectrum peak factor, which is used to measure the significance of the fault characteristics in the vibration signal. max represents the maximum value. is the envelope spectrum sequence of each mode, is the number of envelope spectrum sequences of each modal component, is the e-th modal component obtained by decomposing the vibration signal through the variational modal decomposition method, and n represents the time series index of the vibration signal, which is used to describe the discrete sampling points of the vibration signal in the time domain.

[0019] In one embodiment, the step of determining the weight corresponding to the envelope spectrum peak factor of each modal component includes:

[0020] The weight corresponding to the envelope spectrum peak factor of each modal component is determined according to the following formula:

[0021]

[0022] in, is the weight of the envelope spectrum peak factor component of the e-th modal component, is the squared envelope spectrum kurtosis, is the e-th modal component obtained by decomposing the vibration signal through the variational modal decomposition method, and t is the time variable, which represents the change of the vibration signal in the time domain.

[0023] In one embodiment, the step of constructing the objective function includes:

[0024] The objective function is constructed as follows:

[0025]

[0026] in, is the objective function, is the weight of the envelope spectrum peak factor component of the e-th modal component, is the envelope spectrum peak factor.

[0027] In one embodiment, the step of using the optimal harmonic sine structure element to perform a morphological gradient combination product operation on the vibration signal includes:

[0028] Perform morphological gradient combination product operation according to the following formula:

[0029]

[0030] in, is the result of the morphological gradient combination product operation, is the vibration signal, is the optimal harmonic sinusoidal structural element, for about Corrosion operation; for about The expansion operation of Open operations for mathematical morphology; It is the closing operation in mathematical morphology.

[0031] In a second aspect, the present application provides a device for identifying damage to substation connection fittings, the device comprising:

[0032] A vibration signal acquisition module is used to obtain the vibration signal of the substation connection hardware by transmitting white noise to the substation connection hardware;

[0033] An optimal harmonic sinusoidal structural element determination module is used to determine the optimal influence coefficient of a preset harmonic sinusoidal structural element using a starfish optimization strategy to obtain the optimal harmonic sinusoidal structural element. The starfish optimization strategy is to initialize the influence parameters of the preset harmonic sinusoidal structural element and then use the objective function corresponding to the vibration signal to search for the optimal influence parameter solution.

[0034] The damage identification result determination module is used to use the optimal harmonic sine structure element to perform morphological gradient combination product operation on the vibration signal, and then perform spectrum analysis to obtain the damage identification result of the substation connection hardware.

[0035] In a third aspect, the present application provides a storage medium: the storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the substation connection fitting damage identification method as described in any one of the above embodiments.

[0036] In a fourth aspect, the present application provides a computer device, comprising: one or more processors, and a memory;

[0037] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the steps of the method for identifying damage to substation connection fittings in any one of the above embodiments are performed.

[0038] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0039] The method for identifying damage to substation connection fittings provided in this application addresses the technical defect of traditional vibration signal processing methods that it is difficult to accurately identify fault characteristics under strong background noise interference. By introducing white noise excitation to obtain a more comprehensive vibration response signal of the connection fittings, the observability of the characteristic information is improved. In combination with the starfish optimization strategy, the optimal harmonic sinusoidal structural element is adaptively determined, effectively enhancing the ability to extract weak fault characteristics. Furthermore, the morphological gradient combination product operation is performed on the optimal structural element, and combined with spectrum analysis, accurate identification of damage to the connection fittings is achieved. This method not only improves the robustness and sensitivity of fault detection and significantly improves the accuracy of connection fitting damage identification, but also provides reliable technical support for the intelligent inspection and maintenance of substation connection fittings, thereby effectively ensuring the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 A flowchart of a method for identifying damage to substation connection fittings provided in an embodiment of the present application;

[0042] Figure 2 This is an example diagram of the method for identifying damage to substation connection fittings provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of a device for identifying damage to substation connection fittings provided in an embodiment of the present application;

[0044] Figure 4 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0046] This application provides a method for identifying damage to substation connection fittings. The following embodiments illustrate this method by applying it to a computer device. It is understood that the computer device can be any device with data processing capabilities, including but not limited to a single server, a server cluster, a personal laptop, a desktop computer, etc. Figure 1 As shown, the method may include the following steps:

[0047] S101: A vibration signal of the substation connection fittings is obtained by transmitting white noise to the substation connection fittings.

[0048] White noise refers to a random signal with a constant power spectral density and uniform frequency distribution within a certain frequency band. It has the ability to stimulate the frequency response characteristics of a structure. A vibration signal is the physical response signal obtained by a sensor after a structure is stimulated to vibrate, reflecting the dynamic characteristics of the structure being measured.

[0049] In this step, the computer equipment can be pre-deployed with the sensor system at key locations on the target substation's connectors. To determine the connector's vibration response characteristics, the computer equipment controls the excitation unit to transmit a broadband white noise signal to the connector at specific intervals. This white noise is generated by a signal source module, fed through a power amplifier to an exciter, and then applied to the connector surface or fastening points, generating a vibration response ranging from low to high frequencies.

[0050] During the white noise excitation process, the computer synchronizes and controls sensors to collect vibration response data from the connectors. These sensors can be accelerometers, piezoelectric vibration sensors, or fiber Bragg gratings (FBGs). The raw vibration signals collected by the sensors are converted to digital signals via an analog-to-digital converter and then fed into the computer's data acquisition module for buffering and storage. To ensure data integrity and timing accuracy, a clock synchronization module can also be configured to precisely coordinate excitation and acquisition.

[0051] Furthermore, to accommodate connectors of varying shapes and materials, the computer can utilize white noise emission strategies configured in different frequency bands, automatically adjusting the excitation duration, frequency range, and location to cover the structure's primary modal response region. This approach is particularly useful for aging or complex hardware components, and in actual use, adaptive adjustments can be made based on historical data, enhancing the ability to capture vibration signatures.

[0052] It can be understood that by emitting white noise to the substation connection hardware and obtaining its vibration signal, the dynamic response characteristics of the hardware in multiple frequency bands can be stimulated, making up for the shortcomings of traditional passive monitoring methods in weak feature extraction. White noise excitation has the ability to stimulate the multimodal characteristics of the structure and is particularly suitable for irregular components with significant stress concentration, such as connection hardware. Its frequency response can more completely expose the tiny vibration changes caused by structural defects. Therefore, this method not only enhances the observability of weak damage characteristics in complex backgrounds, but also provides high-quality data input for subsequent feature extraction and identification algorithms based on vibration signals, effectively improving the accuracy and robustness of fault identification.

[0053] S102: Using the starfish optimization strategy to determine the optimal influence coefficient of the preset harmonic sinusoidal structural element, and obtain the optimal harmonic sinusoidal structural element, wherein the starfish optimization strategy is to initialize the influence parameters of the preset harmonic sinusoidal structural element, and then use the objective function corresponding to the vibration signal to search for the optimal influence parameter solution.

[0054] Among them, the starfish optimization strategy is a global search strategy based on a bionic intelligent optimization algorithm. It simulates the behavior of starfish in finding the optimal path in a complex environment through chemical perception, self-regeneration and group behavior mechanisms, and is used to search for the optimal solution in a multi-dimensional solution space. The preset harmonic sinusoidal structural element refers to a sinusoidal function template set in advance for signal analysis and processing. It can be used as a kernel function to participate in structural transformation operations in signal morphology processing. The influencing parameters refer to the variable parameters that define the waveform characteristics of the sinusoidal structural element, such as amplitude and length. Their values ​​directly affect the structural element's ability to fit the signal. The objective function is a functional indicator used to evaluate the degree of matching between the current structural element and the original vibration signal. It can be designed based on criteria such as signal reconstruction error and feature retention to guide the optimization algorithm's optimization process.

[0055] In this step, the computer receives the vibration signal data from the connection hardware, collected and preprocessed by the sensor, and calls upon the internal optimization module to load a preset harmonic sinusoidal structural element template. To ensure that this structural element more accurately matches the subtle fault characteristics of the current vibration signal, the Starfish optimization strategy automatically searches for the optimal combination of influencing parameters within the template, thereby obtaining the optimal harmonic sinusoidal structural element.

[0056] Specifically, a preset harmonic sinusoidal structural element is loaded as the core template for morphological analysis. This structural element is expressed as a parameterized sinusoidal function model, which contains multiple adjustable influencing parameters such as amplitude, frequency, and phase. These parameters together determine the structural element's ability to fit signal characteristics in the time or frequency domain. To improve the structural element's sensitivity to potential damage characteristics in the current vibration signal, these influencing parameters are adaptively searched and adjusted through intelligent optimization.

[0057] At this point, the computer calls the Starfish optimization strategy module to initialize the aforementioned influencing parameters. In the initial stage, several sets of candidate parameter vectors are randomly or semi-randomly generated and represented as the positions of individual Starfish in parameter space. Each individual Starfish represents a set of parameter settings for a structural element, and the computer evaluates the fitness of each individual under the current signal conditions. This fitness function, known as the objective function, is typically constructed based on metrics such as signal feature matching, minimizing reconstruction error, and maximizing spectral clarity.

[0058] During the optimization process, the starfish optimization strategy iteratively searches for parameter vectors by simulating the starfish's local environmental perception and collaborative updating of the entire population. In each iteration, the local density information of each starfish is calculated, and its parameters are guided towards the optimal update direction based on the overall optimal position. Specifically, the reconstruction result of the structural elements corresponding to the current parameter combination acting on the vibration signal is obtained; its reconstruction error, spectral clarity, and other indicators are calculated; these indicators are combined to construct the objective function value; based on this value, the quality of the parameter combination in the search space is judged; and the guidance mechanism is then used to update the parameter group to approach the optimal solution in the next round.

[0059] As iterations progress, the computer continuously updates the optimal parameter record until convergence conditions are met, such as the objective function change falling below a threshold or reaching the maximum number of iterations. Ultimately, a set of influencing parameters that optimize the objective function is determined, and based on this, an optimal harmonic sinusoidal structural element is constructed. This structural element is then used to extract sensitive features, perform morphological transformations, and perform spectral analysis on the vibration signals of the connection hardware, ultimately generating the final damage identification results.

[0060] Furthermore, if the connectors are subject to long-term online monitoring, multi-day or multi-operating condition vibration signal data can be incorporated into the optimization process to construct diverse objective function models, thereby enhancing the broad-spectrum adaptability and cross-operating stability of the structural elements. This online self-learning capability enables the computer equipment to continuously optimize recognition accuracy in complex substation operating environments, providing more robust data support for connector fault warnings.

[0061] It can be understood that by using the starfish optimization strategy to search for the influencing parameters of the preset harmonic sinusoidal structural element, it is possible to accurately find the structural template that best matches the target vibration signal in the multidimensional parameter space, thereby constructing the optimal harmonic sinusoidal structural element with stronger feature adaptability. The starfish optimization strategy not only improves the response sensitivity of the harmonic sinusoidal structural element to weak damage characteristics, but also maintains good feature extraction results in strong noise interference environments. This solution has adaptive capabilities and global optimality guarantees, effectively solving the problem of fault feature identification distortion in traditional signal processing, and improving the robustness and overall accuracy of signal analysis.

[0062] In one example, when the Starfish optimization strategy is activated, the solution space of the amplitude and length of the harmonic sine structure element is randomly generated between the upper and lower limits of the influencing parameters, thereby completing the initialization process of the harmonic sine structure element influencing parameter solution. Specifically, the establishment of the initialization of the harmonic sine structure element influencing parameter solution can be expressed by the following formula:

[0063]

[0064] in, represents the population size of the starfish optimization strategy, represents the dimension of the search space, It is a set of randomly generated solutions of harmonic sinusoidal structural elements affecting parameters. Its generation process can be expressed by the following formula:

[0065]

[0066] in, , represents each individual in the population, , representing each dimension of each individual, and They are The upper and lower limits of the dimension parameters, rand is a random number in the range [0,1], used to generate random values ​​in a given interval.

[0067] In the main loop of the Starfish optimization strategy, a vector is constructed. The construction process of the vector is as follows:

[0068]

[0069] in, Represents a vector with dimension N×1, that is, N rows and 1 column; Indicates the Nth solution The value obtained after performing a certain function operation, here Might be a solution vector, It is an objective function or fitness function defined in the solution space, which is used to measure the quality of the solution; It represents the Nth solution, which is a vector containing the values ​​of various variables in the problem and is used to describe a possible solution to the problem; N represents the number of solutions or the size of the population. In the optimization algorithm, a population containing multiple solutions is usually initialized, and N is the number of solutions in this population. In simple terms, this vector F is to put each solution The vector of values ​​obtained after substituting function f, each element Reflects the corresponding solution The degree of quality.

[0070] In this process, to determine the location of the local optimal solution for the influencing parameters, the five arms of the starfish are simulated for exploration. When the dimension of the search space does not exceed 5, the starfish will use a one-dimensional search mode to explore the local optimal solution. The exploration process can be expressed as follows:

[0071]

[0072] in, and are the positions of two randomly selected starfish in dimension p, and is a random number in the interval [-1,1], used to control the step size and direction of exploration. It represents the energy of the starfish, reflecting its activity level during the search process, and T is the current number of iterations, which is used to record the progress of the optimization process.

[0073] In addition, the starfish's predation and regeneration behaviors are taken into account when searching for the global optimal solution for the influencing parameters. During the development phase, the starfish uses the following formula to find the optimal solution for the influencing parameters of the harmonic sine structural element:

[0074]

[0075] in, 、 is a random number between [0,1], is the distance between the optimal influencing parameter solution and other solutions, 、 For Two randomly selected distances in The maximum number of iterations for the starfish optimization strategy.

[0076] S103: Using the optimal harmonic sine structural element, a morphological gradient combination product operation is performed on the vibration signal, and then a spectrum analysis is performed to obtain damage identification results of the substation connection hardware.

[0077] The morphological gradient combination product operation refers to a mathematical operation that enhances features by combining and multiplying the results of morphological dilation and erosion operations on the original vibration signal using the optimal structural element during signal processing. Spectral analysis involves performing frequency domain analysis operations such as Fourier transforms on the morphologically processed signal to identify the energy distribution characteristics of the signal at each frequency component. Damage identification results for substation connection fittings are based on abnormal energy changes, sudden frequency changes, or specific patterns in the spectral characteristics, ultimately determining whether the fittings have structural damage such as looseness, cracks, or fatigue.

[0078] In this step, the computer device first receives and loads the original vibration signal collected by the substation's on-site sensors. This signal often contains vibration response data generated by the connection hardware during operation due to factors such as environmental disturbances, current excitation, or structural looseness. The computer device then uses the optimal harmonic sinusoidal structural element obtained through the optimization process as a structural template to perform morphological processing on the original signal. During execution, the computer device sequentially uses this structural element as the convolution kernel to perform dilation and erosion operations on the original signal. The difference or product of the two is then calculated according to the morphological gradient combination rules to generate a feature-enhanced signal sequence.

[0079] Next, based on the results of the morphological gradient combination multiplication, the computer device calls its built-in spectrum analysis module to perform Fourier transform processing on the signal and extract its frequency domain features. Specifically, the device converts the morphologically enhanced time domain signal into a frequency domain spectrogram and identifies possible signs of damage based on key indicators such as energy density, harmonic distribution, or frequency mutation points on the frequency components. For example, when an abnormal increase in energy in a specific frequency band is detected and matches the typical damage characteristic frequency range, this result is marked as a potential damage point.

[0080] Finally, the device uses the spectrum analysis results and a preset threshold model to output a final damage identification conclusion for the substation connection hardware. This identification result can include damage type (such as looseness, cracks, and metal fatigue), as well as risk level and recommended maintenance measures.

[0081] It can be understood that by obtaining the optimal harmonic sinusoidal structural elements and combining morphological and frequency domain analysis techniques, the most representative characteristic indicators can be extracted from the raw vibration data, achieving accurate judgment of the structural state of the connection hardware. In other words, while ensuring that the key signal characteristics are not weakened, the interference of environmental noise on the damage identification results is effectively reduced, making the final judgment more sensitive and accurate. This method can automatically adapt to the vibration characteristics of different equipment and operating conditions, and has greater versatility and engineering practicality. Therefore, it not only improves the targetedness of vibration signal processing, but also significantly enhances the safety assurance capabilities and automation level of substation operation.

[0082] In the above embodiment, in order to address the technical defect of traditional vibration signal processing methods that fault characteristics are difficult to accurately identify under strong background noise interference, white noise excitation is introduced to obtain a more comprehensive vibration response signal of the connecting hardware, thereby improving the observability of the characteristic information; combined with the starfish optimization strategy, the optimal harmonic sinusoidal structural element is adaptively determined, effectively enhancing the ability to extract weak fault characteristics; further, morphological gradient combination product operations are performed on the optimal structural element, and combined with spectrum analysis, accurate identification of connecting hardware damage is achieved. This method not only improves the robustness and sensitivity of fault detection and significantly improves the accuracy of connecting hardware damage identification, but also provides reliable technical support for the intelligent inspection and maintenance of substation connecting hardware, thereby effectively ensuring the safe and stable operation of the power system.

[0083] In one embodiment, the preset harmonic sine structure element is:

[0084]

[0085] in, is a preset harmonic sine structure element, is the amplitude of the fundamental component of the harmonic sinusoidal structural element, is the amplitude of the harmonic component of the harmonic sine structural element, is the length of the harmonic sine structure element, 、 is the angular frequency, 、 are the fundamental frequency and harmonic frequency of the harmonic sine structure element, is the sampling period, is the sampling frequency.

[0086] This formula is used to generate a preset harmonic sinusoidal structural element signal. , specifically, in terms of signal composition, is the superposition of two sinusoidal signals, where and are the amplitudes of the two sinusoidal signals, and are their angular frequencies, is a time variable. For angular frequency calculation, and The relationship between angular frequency and fundamental frequency and harmonic frequency is explained, where is the fundamental frequency, is the harmonic frequency, which is obtained by multiplying the frequency by Get the corresponding angular frequency. In the definition of time variable, Defined time variable The value range and interval of is the length of the harmonic sine structure element, that is, the number of sampling points of the signal, The sampling period determines the interval of the time variable, starting from time 0 and every Take a time point and take points, forming a discrete time series. Finally, regarding the relationship between the sampling period and the sampling frequency, It can be seen that the sampling period is the sampling frequency The sampling frequency is the reciprocal of the sampling rate. It determines the number of samples collected per unit time. A higher sampling frequency can capture signal changes more finely.

[0087] In this embodiment, the formula is mainly used to generate a preset harmonic sinusoidal structural element signal by superimposing two sinusoidal signals with different amplitudes and frequencies to synthesize the signal. At the same time, the amplitude and frequency of the fundamental wave and harmonics can be changed to control the characteristics and frequency combination of the signal, thereby improving the accuracy and reliability of signal recognition.

[0088] In one embodiment, the process of determining the objective function corresponding to the vibration signal includes:

[0089] Decompose the vibration signal into multiple independent modal components and calculate the envelope spectrum peak factor of each modal component;

[0090] The weight corresponding to the envelope spectrum peak factor of each modal component is determined, and an objective function is constructed based on the envelope spectrum peak factor of each modal component and its corresponding weight.

[0091] A modal component is a set of eigenmode functions with distinct frequency characteristics, derived from analyzing the original vibration signal using a signal decomposition algorithm such as EMD, VMD, or EEMD. Each component represents an independent vibration characteristic of the structure. The envelope spectrum peak factor is a metric derived by performing envelope analysis on each modal component and extracting the ratio of the peak energy to the average energy in its spectrum. This metric is used to measure the significance of sudden shocks or non-stationary events in the signal. The weight is a numerical ratio assigned to each modal component based on its importance, reflecting its contribution to subsequent diagnosis.

[0092] In specific implementations, the computer device first receives raw vibration signal data collected by vibration sensors installed on substation connection fittings. It then invokes its built-in modal decomposition module, employing methods such as empirical mode decomposition (EMD) or variational mode decomposition (VMD), to decompose the raw signal into multiple eigenmodal components. Each modal component represents the energy characteristics of a specific frequency band, helping to isolate local vibration signatures associated with faults. The computer device then performs envelope analysis on each modal component. The envelope analysis process generally involves a Hilbert transform to obtain the signal's instantaneous amplitude envelope, followed by a Fourier transform of the envelope to produce a spectrum. Based on this, the peak-to-mean ratio of the spectrum is extracted and the envelope spectrum peak factor of the modal component is calculated. A higher factor indicates a more significant impact component or periodic anomaly in the modal component, and its contribution to damage identification is greater. To ensure the appropriate influence of each modal component when constructing the comprehensive diagnostic model, the computer device assigns weights based on the relative magnitude of the envelope spectrum peak factor of each modal component or the fault sensitivity of its corresponding frequency band. Weights can be determined by normalizing the peak factor or by using sensitivity curves from historical samples. The computer then multiplies the peak factor of each modal component by its corresponding weight and constructs an objective function. This objective function serves as an important criterion for evaluating the current parameter combination or identifying damage modes in subsequent optimization algorithms.

[0093] In this embodiment, decomposing the original signal into multiple modal components effectively eliminates interference between frequency band components and enhances the identifiability of target fault characteristics. By calculating the envelope spectrum peak factor, the intensity of shock or periodic changes can be quantified, enabling the identification of fault information in non-stationary signals. Furthermore, introducing a weighting mechanism to construct the objective function strengthens the diagnostic effect of highly sensitive modal components and suppresses the influence of low-contribution components on the final judgment. This not only improves the accuracy of structural damage identification but also enhances the adaptability and intelligent diagnostic capabilities of the equipment under complex operating conditions.

[0094] In one embodiment, the step of calculating the envelope spectrum peak factor of each modal component includes:

[0095] The envelope spectrum peak factor of each modal component is calculated according to the following formula:

[0096]

[0097] in, is the envelope spectrum peak factor, which is used to measure the significance of the fault characteristics in the vibration signal. max represents the maximum value. is the envelope spectrum sequence of each mode, is the number of envelope spectrum sequences of each modal component, is the e-th modal component obtained by decomposing the vibration signal through the variational modal decomposition method, and n represents the time series index of the vibration signal, which is used to describe the discrete sampling points of the vibration signal in the time domain.

[0098] Specifically, the formula is used to calculate the envelope spectrum peak factor , Represents the envelope spectrum sequence The maximum value is used to reflect the amplitude of the fault characteristic frequency in the envelope spectrum; The RMS value of the envelope spectrum sequence is calculated to measure the overall energy of the envelope spectrum. This formula can effectively assess the significance of fault features in vibration signals.

[0099] In this embodiment, the envelope spectrum peak factor is used to measure the significance of the fault characteristics in the vibration signal. By comparing the maximum value of the envelope spectrum with the overall energy, the relative magnitude of the amplitude at the fault characteristic frequency can be highlighted. If there is an obvious fault characteristic in the vibration signal, the envelope spectrum will have a larger amplitude at the fault characteristic frequency. The value will be larger, which can effectively identify and evaluate the significance of fault features in vibration signals.

[0100] In one embodiment, the step of determining the weight corresponding to the envelope spectrum peak factor of each modal component includes:

[0101] The weight corresponding to the envelope spectrum peak factor of each modal component is determined according to the following formula:

[0102]

[0103] in, is the weight of the envelope spectrum peak factor component of the e-th modal component, is the squared envelope spectrum kurtosis, is the e-th modal component obtained by decomposing the vibration signal through the variational modal decomposition method, and t is the time variable, which represents the change of the vibration signal in the time domain.

[0104] Specifically, this formula is used to calculate the weight corresponding to the envelope spectrum peak factor of each modal component , represents the square envelope spectrum kurtosis of the e-th modal component, which is used to measure the characteristic information strength of the modal component; The squared envelope spectral kurtosis of all modal components is summed to normalize the weights and ensure that the sum of all weights is 1. In this way, the formula can effectively determine the importance of each modal component in fault diagnosis.

[0105] The calculation formula of the square envelope spectrum kurtosis is as follows:

[0106]

[0107]

[0108] in, is the fast Fourier transform; is an imaginary unit; is the Hilbert transform; For the modulo operation, For individual elements The square envelope spectrum of is the average value of the squared envelope spectrum.

[0109] In this embodiment, the squared envelope spectral kurtosis is used to measure signal singularity. By calculating and normalizing the squared envelope spectral kurtosis of each modal component, the weight of each modal component in fault diagnosis can be determined. Modal components with higher weights contain more fault characteristic information, which facilitates subsequent fault detection and diagnosis.

[0110] In one embodiment, the step of constructing the objective function includes:

[0111] The objective function is constructed as follows:

[0112]

[0113] in, is the objective function, is the weight of the envelope spectrum peak factor component of the e-th modal component, is the envelope spectrum peak factor.

[0114] Specifically, this formula is used to construct the objective function, which is obtained by multiplying the envelope spectrum peak factor of each modal component with its corresponding weight and summing them. represents the weight of the e-th modal component, reflecting the importance of this modal component in the overall signal; is the envelope spectrum peak factor, which is used to measure the significance of fault features in vibration signals.

[0115] In this embodiment, the objective function By integrating information from all modal components and weighting the envelope spectrum peak factor of each modal component, this objective function can more comprehensively reflect the overall significance of fault characteristics in the vibration signal. In fault diagnosis, this objective function can be used to comprehensively evaluate the fault characteristics of different modal components, thereby more accurately determining the operating status and fault conditions of the equipment.

[0116] In one embodiment, the step of performing a morphological gradient combination product operation on the vibration signal using an optimal harmonic sinusoidal structure element includes:

[0117] Perform morphological gradient combination product operation according to the following formula:

[0118]

[0119] in, is the result of the morphological gradient combination product operation, is the vibration signal, is the optimal harmonic sinusoidal structural element, for about Corrosion operation; for about The expansion operation of Open operations for mathematical morphology; It is the closing operation in mathematical morphology.

[0120] In this embodiment, vibration signal features are extracted through a combination of morphological operations—namely, erosion, dilation, opening, and closing. Erosion and dilation identify local extreme points in the signal, while opening and closing smooth the signal and remove noise. By combining these operations, the formula enhances the characteristic information in the signal while suppressing noise interference. This processing method can help identify and extract fault characteristics in vibration signal analysis, providing a more reliable basis for equipment fault diagnosis.

[0121] To facilitate understanding of the solutions of this application, specific examples are provided below for illustration.

[0122] like Figure 2 The figure below schematically illustrates the experimental process and associated calculations for vibration signal analysis. First, the experimental equipment is used to collect vibration signals, inputting white noise as the excitation signal and connecting hardware as the experimental object. The collected vibration signal can be classified into three states: normal, faulty, and noise-interferenced.

[0123] In the signal processing phase, the initial parameters are first determined by initializing the influencing parameter solution. Next, the optimal parameters for the harmonic sinusoidal structural element are determined by calculating the structural elastic strength. The squared envelope spectrum kurtosis of each modal component is then calculated to measure the strength of the characteristic information. Normalization is performed to determine the weight of each modal component. Next, the envelope spectrum peak factor is calculated to measure the significance of the fault signature in the vibration signal. The weights are combined with the envelope spectrum peak factor to construct the objective function. By optimizing the objective function, the local and global optimal influencing parameter solutions are determined.

[0124] Morphological processing uses the Morphological Gradient Combination Product (MGCP) to process vibration signals. Morphological operations such as corrosion, dilation, and opening and closing enhance the signal's characteristic information. The processed signal is displayed as a time-domain waveform and spectrum analysis, facilitating further analysis and diagnosis.

[0125] The entire process starts with experimental data acquisition, goes through signal processing and feature extraction, and finally achieves feature analysis and fault diagnosis of vibration signals through morphological operations and objective function optimization.

[0126] The following describes the substation connection fitting damage identification device provided by the embodiment of the present application. The substation connection fitting damage identification device described below and the substation connection fitting damage identification method described above can be referred to each other. Figure 3 As shown, the present application provides a device for identifying damage to substation connection fittings, the device comprising:

[0127] The vibration signal acquisition module 201 is used to obtain the vibration signal of the substation connection hardware by transmitting white noise to the substation connection hardware;

[0128] The optimal harmonic sinusoidal structural element determination module 202 is configured to determine the optimal influence coefficient of the preset harmonic sinusoidal structural element using a starfish optimization strategy to obtain the optimal harmonic sinusoidal structural element. The starfish optimization strategy is to initialize the influence parameters of the preset harmonic sinusoidal structural element and then use the objective function corresponding to the vibration signal to search for the optimal influence parameter solution.

[0129] The damage identification result determination module 203 is used to use the optimal harmonic sine structure element to perform a morphological gradient combination product operation on the vibration signal, and then perform spectrum analysis to obtain the damage identification result of the substation connection hardware.

[0130] In one embodiment, the preset harmonic sine structure element is:

[0131]

[0132] in, is a preset harmonic sine structure element, is the amplitude of the fundamental component of the harmonic sinusoidal structural element, is the amplitude of the harmonic component of the harmonic sine structural element, is the length of the harmonic sine structure element, 、 is the angular frequency, 、 are the fundamental frequency and harmonic frequency of the harmonic sine structure element, is the sampling period, is the sampling frequency.

[0133] In one embodiment, the optimal harmonic sinusoidal structure element determination module 202 includes:

[0134] An envelope spectrum peak factor calculation unit is used to decompose the vibration signal into multiple independent modal components and calculate the envelope spectrum peak factor of each modal component;

[0135] The objective function construction unit is used to determine the weight corresponding to the envelope spectrum peak factor of each modal component, and construct the objective function according to the envelope spectrum peak factor of each modal component and its corresponding weight.

[0136] In one embodiment, the envelope spectrum peak factor calculation unit includes:

[0137] The envelope spectrum peak factor calculation unit is used to calculate the envelope spectrum peak factor of each modal component according to the following formula:

[0138]

[0139] in, is the envelope spectrum peak factor, which is used to measure the significance of the fault characteristics in the vibration signal. max represents the maximum value. is the envelope spectrum sequence of each mode, is the number of envelope spectrum sequences of each modal component, is the e-th modal component obtained by decomposing the vibration signal through the variational modal decomposition method, and n represents the time series index of the vibration signal, which is used to describe the discrete sampling points of the vibration signal in the time domain.

[0140] In one embodiment, the objective function construction unit includes:

[0141] The weight determination subunit is used to determine the weight corresponding to the envelope spectrum peak factor of each modal component according to the following formula:

[0142]

[0143] in, is the weight of the envelope spectrum peak factor component of the e-th modal component, is the squared envelope spectrum kurtosis, is the e-th modal component obtained by decomposing the vibration signal through the variational modal decomposition method, and t is the time variable, which represents the change of the vibration signal in the time domain.

[0144] In one embodiment, the objective function construction unit includes:

[0145] The objective function construction subunit is used to construct the objective function according to the following formula:

[0146]

[0147] in, is the objective function, is the weight of the envelope spectrum peak factor component of the e-th modal component, is the envelope spectrum peak factor.

[0148] In one embodiment, the damage identification result determination module 203 includes:

[0149] The morphological gradient combination product operation unit is used to perform the morphological gradient combination product operation according to the following formula:

[0150]

[0151] in, is the result of the morphological gradient combination product operation, is the vibration signal, is the optimal harmonic sinusoidal structural element, for about Corrosion operation; for about The expansion operation of Open operations for mathematical morphology; It is the closing operation in mathematical morphology.

[0152] In one embodiment, the present application also provides a storage medium, which stores computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the substation connection fitting damage identification method as described in any of the above embodiments.

[0153] In one embodiment, the present application also provides a computer device having computer-readable instructions stored therein. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the method for identifying damage to substation connection fittings as described in any one of the above embodiments.

[0154] Schematically, as Figure 4 As shown, Figure 4 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 300 can be provided as a server. Figure 4Computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by memory 301 for storing instructions executable by processing component 302, such as application programs. The application programs stored in memory 301 may include one or more modules, each corresponding to a set of instructions. Furthermore, processing component 302 is configured to execute the instructions to implement the substation connection fitting damage identification method according to any of the aforementioned embodiments.

[0155] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate based on an operating system stored in the memory 301, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or the like.

[0156] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0157] Finally, it should be noted that, in this article, relational terms such as first and second are merely used to distinguish one entity or operation from another, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. Without further restriction, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element. Herein, "one," "said," "the," and "its" may also include plural forms unless the context clearly indicates otherwise. A plurality refers to at least two, such as 2, 3, 5, or 8. "And / or" includes any and all combinations of the relevant listed items.

[0158] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referenced to each other.

[0159] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying damage to substation connection fittings, characterized in that: The method comprises: By transmitting white noise to the substation connection hardware, a vibration signal of the substation connection hardware is obtained; The optimal influence coefficient of the preset harmonic sinusoidal structural element is determined by adopting a starfish optimization strategy to obtain the optimal harmonic sinusoidal structural element, wherein the starfish optimization strategy is to initialize the influence parameters of the preset harmonic sinusoidal structural element and then use the objective function corresponding to the vibration signal to search for the optimal influence parameter solution; The optimal harmonic sinusoidal structural element is used to perform a morphological gradient combination product operation on the vibration signal, and then a spectrum analysis is performed to obtain a damage identification result of the substation connection fittings.

2. The method for identifying damage to substation connection fittings according to claim 1, characterized in that: The preset harmonic sine structure element is: in, is the preset harmonic sinusoidal structural element, is the amplitude of the fundamental component of the harmonic sinusoidal structural element, is the amplitude of the harmonic component of the harmonic sine structural element, is the length of the harmonic sine structure element, 、 is the angular frequency, 、 are the fundamental frequency and harmonic frequency of the harmonic sine structure element, is the sampling period, is the sampling frequency.

3. The method for identifying damage to substation connection fittings according to claim 1, characterized in that: The process of determining the objective function corresponding to the vibration signal includes: Decomposing the vibration signal into multiple independent modal components, and calculating the envelope spectrum peak factor of each modal component; The weight corresponding to the envelope spectrum peak factor of each of the modal components is determined, and the objective function is constructed according to the envelope spectrum peak factor of each of the modal components and its corresponding weight.

4. The method for identifying damage to substation connection fittings according to claim 3, characterized in that: The step of calculating the envelope spectrum peak factor of each modal component comprises: The envelope spectrum peak factor of each modal component is calculated according to the following formula: in, is the envelope spectrum peak factor, which is used to measure the significance of the fault characteristics in the vibration signal. max represents the maximum value. is the envelope spectrum sequence of each mode, is the number of envelope spectrum sequences of each modal component, is the e-th modal component obtained by decomposing the vibration signal through the variational modal decomposition method, and n represents the time series index of the vibration signal, which is used to describe the discrete sampling points of the vibration signal in the time domain.

5. The method for identifying damage to substation connection fittings according to claim 4, characterized in that: The step of determining the weight corresponding to the envelope spectrum peak factor of each modal component includes: The weight corresponding to the envelope spectrum peak factor of each modal component is determined according to the following formula: in, is the weight of the envelope spectrum peak factor component of the e-th modal component, is the squared envelope spectrum kurtosis, is the e-th modal component obtained by decomposing the vibration signal using the variational modal decomposition method, and t is a time variable, indicating the change of the vibration signal in the time domain.

6. The method for identifying damage to substation connection fittings according to claim 4, characterized in that: The step of constructing the objective function comprises: The objective function is constructed as follows: in, is the objective function, is the weight of the envelope spectrum peak factor component of the e-th modal component, is the envelope spectrum peak factor.

7. The method for identifying damage to substation connection fittings according to claim 1, characterized in that: The step of using the optimal harmonic sinusoidal structure element to perform a morphological gradient combination product operation on the vibration signal includes: Perform morphological gradient combination product operation according to the following formula: in, is the result of the morphological gradient combination product operation, is the vibration signal, is the optimal harmonic sinusoidal structural element, for about Corrosion operation; for about The expansion operation of Open operations for mathematical morphology; It is the closing operation in mathematical morphology.

8. A device for identifying damage to substation connection fittings, characterized in that: The device comprises: A vibration signal acquisition module, configured to obtain a vibration signal of a substation connection fitting by transmitting white noise to the substation connection fitting; an optimal harmonic sinusoidal structural element determination module, configured to determine the optimal influence coefficient of a preset harmonic sinusoidal structural element using a starfish optimization strategy to obtain the optimal harmonic sinusoidal structural element, wherein the starfish optimization strategy is to initialize the influence parameters of the preset harmonic sinusoidal structural element and then use the objective function corresponding to the vibration signal to search for the optimal influence parameter solution; The damage identification result determination module is used to use the optimal harmonic sine structure element to perform a morphological gradient combination product operation on the vibration signal, and then perform spectrum analysis to obtain the damage identification result of the substation connection fittings.

9. A storage medium, characterized in that: The storage medium stores computer-readable instructions, which, when executed by one or more processors, enable the one or more processors to perform the steps of the method for identifying damage to substation connection fittings as described in any one of claims 1 to 7.

10. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the method for identifying damage to substation connection fittings according to any one of claims 1 to 7 are executed.

Images