Pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD

Abstract

The invention discloses a pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD, and relates to the technical field of signal processing, and the method comprises the steps: obtaining a pipeline leakage signal at a pipeline defect position; taking a penalty factor alpha and a modal number K in the VMD algorithm as optimization targets of a whale algorithm, namely a WOA algorithm; setting a VMD algorithm according to the optimal penalty factor alpha and the optimal modal number K obtained by the WOA algorithm, and performing VDM decomposition on the pipeline leakage signal to obtain K IMF components; identifying the K IMF components by using a correlation coefficient method to identify effective IMF components; carrying out SVD decomposition and denoising processing on each effective IMF component by adopting an SVD algorithm, and removing a noise signal in each effective IMF component; and synthesizing each effective IMF component after the de-noising processing to obtain a de-noised pipeline leakage signal. According to the method, the WOA algorithm, the VMD algorithm and the SVD algorithm are combined to form an integrated signal processing framework, and compared with a single method, the performance is remarkably improved.

Description

Technical Field

[0001] The invention relates to the technical field of signal processing, and in particular to a pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD. Background Art

[0002] Acoustic Emission (AE) refers to the phenomenon that a material emits transient elastic waves due to the rapid release of energy locally, sometimes also called stress wave emission. The deformation and crack extension of materials under stress are important mechanisms of structural failure. This source directly related to the deformation and fracture mechanism is called an acoustic emission source. In recent years, another type of elastic wave source that is not directly related to the deformation and fracture mechanism, such as fluid leakage, friction, impact, combustion, etc., is called other or secondary acoustic emission sources.

[0003] Acoustic emission is a common physical phenomenon. The frequency range of acoustic emission signals of various materials is very wide, ranging from infrasound frequencies of several Hz, audio frequencies of 20Hz to 20KHz to ultrasonic frequencies of several MHz; the amplitude of acoustic emission signals also varies greatly, from microscopic dislocation motions of 10-13m to seismic waves of the order of 1m. The output of the sensor can range from several uV to hundreds of mV, but in most cases only weak vibrations can be detected by highly sensitive sensors. Therefore, the detected acoustic signal waveform is the superposition of acoustic waves reaching the sensor through different paths (reverberation effect), and the superposition of different waveforms makes the problem more complicated. In addition, the sensor itself also has the so-called "ringing" effect (the response of the sensor), which makes the output signal more complex. In many cases, how to obtain useful information from such a complex signal becomes the key to the problem.

[0004] In oil and gas pipeline systems, external noise and random interference from the acquisition system often cause the acoustic wave signals captured by the sensor to be full of noise, which seriously affects the effective analysis of the signal. Therefore, it is very important to perform denoising before analysis to improve the accuracy of the analysis. The noise problem in oil and gas pipeline leakage signals is particularly serious, so effective denoising is required. In the current status of pipeline leakage signal processing, traditional denoising methods often face the problems of low processing efficiency and incomplete noise removal. Common signal denoising techniques, such as filters and wavelet transforms, often cannot effectively remove mixed noise and show obvious limitations when processing complex signals.

[0005] Variational mode decomposition (VMD) is an effective denoising technique. It not only has a solid theoretical foundation, but also solves the problem of modal aliasing in empirical mode decomposition (EMD) and the difficulty of wavelet basis function selection in wavelet decomposition. It can decompose complex signals into several band-limited mode functions (IMFs), each of which can basically be regarded as a single frequency waveform. VMD extracts modal components from signals by solving a variational problem. The solution process involves minimizing the bandwidth of the solution, so that different frequency components in the signal can be separated. There is no clear selection standard for determining the number of modes K and the penalty factor α of VMD decomposition. In the actual decomposition process, the parameters K and α often need to be set manually, which is very subjective.

[0006] WOA (Whale Algorithm) is an emerging optimization algorithm that uses simulated whale predation behavior to find the optimal solution and has good global search capabilities.

[0007] Singular value decomposition (SVD) is a linear algebra technique that can decompose any complex data matrix into the product of three simple matrices: an orthogonal matrix U, a diagonal matrix S, and the transpose V of the orthogonal matrix V. T In SVD, the diagonal elements of the diagonal matrix S are singular values, which are arranged in order from large to small. The singular values ​​reflect the energy or information of the matrix in the direction of the corresponding singular vectors. In signal processing, larger singular values ​​usually correspond to the main components of the signal, while smaller singular values ​​are often associated with noise. Summary of the invention

[0008] In order to overcome the defects in the above-mentioned prior art, the present invention provides a pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD. By combining the three algorithms of WOA, VMD and SVD, an integrated signal processing framework is formed, which has significantly improved the performance compared with a single method.

[0009] To achieve the above object, the present invention adopts the following technical solutions, including:

[0010] A pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD includes the following steps:

[0011] S1, obtaining the original acoustic emission signal at the pipeline defect location, i.e., the pipeline leakage signal;

[0012] S2, taking the penalty factor α and the number of modes K in the variational mode decomposition algorithm, namely the VMD algorithm, as the optimization target of the whale algorithm, namely the WOA algorithm, and finding the optimal penalty factor α and the optimal number of modes K in the VMD algorithm;

[0013] S3, setting a VMD algorithm according to the optimal penalty factor α and the optimal mode number K obtained in step S2, and using the VMD algorithm to perform VDM decomposition on the pipeline leakage signal in step S1 to obtain K intrinsic mode components, namely, IMF components;

[0014] S4, using the correlation coefficient method to identify the K IMF components obtained in step S3, and identify the effective IMF components;

[0015] S5, using a singular value decomposition algorithm, namely, an SVD algorithm, to perform SVD decomposition and denoising processing on each effective IMF component, thereby removing the noise signal in each effective IMF component; synthesizing each effective IMF component after denoising processing to obtain a denoised pipeline leakage signal.

[0016] Preferably, in step S2, the optimization target is selected according to the fitness value, and the fitness function is:

[0017]

[0018] Where a(j) is the envelope signal of the intrinsic mode component obtained by VMD decomposition of the pipeline leakage signal after Hilbert demodulation; j represents the jth sampling point in the envelope signal a(j), N is the number of sampling points; P j is the probability distribution sequence obtained after normalization of a(j); calculate the probability distribution sequence P j The entropy value of the envelope entropy E p ; Calculate the envelope entropy E of each eigenmode component after VMD decomposition p , select the smallest envelope entropy E p As fitness value;

[0019] Find the penalty factor α and the number of modes K corresponding to the minimum fitness value as the optimal penalty factor α and the optimal number of modes K.

[0020] Preferably, in step S4, the correlation coefficient method is used to calculate the correlation coefficient between each IMF component and the pipeline leakage signal, and the IMF component with a correlation coefficient greater than the first threshold is a valid IMF component; specifically as follows:

[0021]

[0022]

[0023] Wherein, x(t) represents the signal value at the tth moment in the pipeline leakage signal; imf(t) represents the signal value at the tth moment in the IMF component; t represents the time, t=1,2,...,N, N represents the signal length; Indicates the average signal value of pipeline leakage signal; represents the average signal value of the IMF component; Conf(x,IMF) represents the correlation coefficient between the IMF component and the pipeline leakage signal;

[0024] The first threshold η r =ρ·R max , where R max is the calculated maximum correlation coefficient, and ρ is the set ratio.

[0025] Preferably, the specific process of step S5 is as follows:

[0026] S51, IMF component is represented by {imf(t)|t=1,2,...,N}; imf(t) is the signal value at the tth moment in the IMF component, t represents the moment, t=1,2,...,N, and N is the signal length;

[0027] Convert the one-dimensional effective IMF components into a two-dimensional matrix Y:

[0028]

[0029] Wherein, L is the number of rows of the two-dimensional matrix Y, H is the number of columns of the two-dimensional matrix Y, H=N-L+1;

[0030] S52, perform singular value decomposition (SVD) on the two-dimensional matrix Y to decompose it into an orthogonal matrix U, a diagonal matrix S, and the transpose V of the orthogonal matrix V. T ;

[0031] Y=USV T

[0032] S=[diag(σ1,σ2,…,σ p ),0]

[0033] The diagonal matrix S is a L×H diagonal matrix, and the diagonal elements σ1, σ2, …, σ p is a non-negative value, the off-diagonal elements are 0, and the diagonal elements of the diagonal matrix S are σ1,σ2,…,σ p That is, the singular value of the effective IMF component; p = min{L,H};

[0034] S53, by calculating the energy differential spectrum D of each singular value i , grouping the singular values ​​into signal-related components and noise components, and setting a second threshold;

[0035]

[0036] Among them, σ i is the i-th singular value, p is the number of singular values; D i is the i-th singular value σ iThe energy differential spectrum; η σ is the second threshold;

[0037] Let D i be greater than the second threshold η σ The singular values are denoted as signal-related components, and let D i be less than or equal to the second threshold η σ The singular values are denoted as noise components;

[0038] S54. Using the anti-diagonal averaging method, the signal-related components are reconstructed from the two-dimensional matrix into a time series to obtain the denoised effective IMF component imf'(t);

[0039]

[0040] wherein, L * = min(L, H), H * = max(L, H); when L < H, Otherwise, y i,j and y j,i are elements in the two-dimensional matrix Y;

[0041] S55. Synthesize the denoised effective IMF components to obtain the denoised pipeline leakage signal.

[0042] Preferably, an improved WOA algorithm is used to find the optimal solution, namely the optimal penalty factor α and the optimal number of modes K, as follows:

[0043] In the algorithm initialization, add a pheromone matrix P, which represents the pheromone concentration of each individual in the solution space;

[0044] For each individual X i , if its fitness value is better than the current global optimal solution, then increase the pheromone:

[0045] P ij = P ij + ΔP·(f(X best ) - f(X i ))

[0046]

[0047] wherein, f(X i ) is the fitness value of the individual X i , and each individual represents a set of solutions of the number of modes K and the penalty factor α; f(X best ) is the fitness value of the current optimal solution; X best is the current optimal solution; P ijis an element in the pheromone matrix; ΔP is the pheromone increment; C is a constant used to control the pheromone increment;

[0048] When the position is updated, the search direction is guided according to the pheromone concentration to obtain the new individual X new :

[0049] d i =|X best -X i |

[0050] X new =X i +α1·P ij -β1·d i

[0051] Among them, α1 and β1 are the weights of pheromone and distance respectively, d i For each individual X i and the current optimal solution X best distance;

[0052] Evaluate new individual X new The fitness f(X new ), and update the current optimal solution X best :

[0053]

[0054] A computer program product includes a computer program / instruction, which implements the above-mentioned pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD when executed by a processor.

[0055] A readable storage medium stores a computer program, which, when executed, implements the above-mentioned pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD.

[0056] An electronic device comprises a processor, a memory and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD is implemented.

[0057] The advantages of the present invention are:

[0058] (1) The present invention combines the three algorithms of WOA, VMD and SVD to form an integrated signal processing framework, which has significantly improved the performance compared with a single method.

[0059] (2) The present invention uses the VMD algorithm to remove the high oscillation part, and then uses the SVD algorithm to filter out the residual low-frequency random wave number. It can handle various types of noise (such as white noise, pulse noise, etc.) and improve the adaptability to different signal environments.

[0060] (3) The present invention optimizes the parameters of the VMD algorithm through the WOA algorithm, making the signal decomposition more accurate, effectively suppressing the noise, and improving the signal-to-noise ratio (SNR) of the signal.

[0061] (4) The present invention adopts an improved WOA algorithm, which shows better performance in search efficiency and convergence speed compared with the traditional WOA algorithm. This means that in practical applications, the algorithm can find suitable parameters more quickly, thereby speeding up the entire denoising process.

[0062] (5) The method of the present invention can achieve good results in denoising the pipeline leakage signal, while filtering out the noise and retaining the effective features in the pipeline leakage signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 The present invention is a flow chart of a pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD.

[0064] Figure 2 It is an iteration diagram of the fitness value before and after the improvement of the WOA algorithm in the embodiment of the present invention.

[0065] Figure 3 1 is a time domain diagram and a spectrum diagram of each IMF component obtained by VMD decomposition in an embodiment of the present invention.

[0066] Figure 4 The diagram is a time domain diagram and a spectrum diagram of the pipeline leakage signal after denoising finally obtained in the embodiment of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Depend on Figure 1 As shown, a denoising method for pipeline leakage signals based on WOA (whale algorithm)-VMD (variational mode decomposition) combined with SVD (singular value decomposition) is provided. The specific implementation steps are as follows:

[0069] S1, using an acoustic emission acquisition device to obtain the original acoustic emission signal of the pipeline defect position, that is, the pipeline leakage signal.

[0070] S2, set the parameters of the optimized WOA algorithm, take the penalty factor α and the number of modes K in the VMD algorithm as the optimization target of the WOA algorithm, and take the envelope entropy of the signal as the fitness function of the WOA algorithm. The envelope entropy represents the sparse characteristics of the pipeline leakage signal. When the intrinsic mode component, i.e., the IMF component, has more noise and less feature information, the envelope entropy value is larger; otherwise, the envelope entropy value is smaller. Input the pipeline leakage signal in step 1 into the WOA algorithm, and select the optimization target according to the fitness function.

[0071] The fitness function is as follows:

[0072]

[0073] Where a(j) is the envelope signal of the intrinsic mode component obtained by VMD decomposition of the pipeline leakage signal after Hilbert demodulation; j represents the jth sampling point in the envelope signal a(j), N is the number of sampling points; P j is the probability distribution sequence obtained after normalization of a(j); calculate the probability distribution sequence P j The entropy value of the envelope entropy E p .

[0074] Calculate the envelope entropy of all intrinsic modal components obtained by VMD decomposition under this position condition (penalty factor α and modal number K), and take the smallest envelope entropy value as the fitness value.

[0075] Find the penalty factor α and the number of modes K corresponding to the minimum fitness value as the optimal penalty factor α and the optimal number of modes K.

[0076] S3, according to the optimization target (penalty factor α and mode number K) output in step 2, the parameters of the VMD algorithm are set, and the pipeline leakage signal in step 1 is imported into the VMD algorithm for VMD decomposition to obtain K intrinsic mode components, namely IMF components.

[0077] S4, the K IMF components obtained in step 3 are distinguished into effective IMF components and noise IMF components using the correlation coefficient method. The details are as follows:

[0078] The correlation coefficient method is used to evaluate the correlation between each IMF component and the pipeline leakage signal. This is achieved by calculating the correlation coefficient between each IMF component and the pipeline leakage signal. The IMF component with a higher correlation coefficient is considered to contain more information of the original signal and is therefore classified as a valid IMF component; conversely, the component with a lower correlation coefficient is considered to be a noise IMF component. The first threshold is defined as η r=ρ·R max , where R max is the maximum correlation coefficient calculated, ρ is the set ratio, in this embodiment, based on the characteristics of the pipeline acoustic emission crack signal, ρ is taken to be equal to 0.025. The correlation coefficient is less than or equal to the first threshold η r The IMF component of will be regarded as the noise IMF component and removed, and the correlation coefficient is greater than the first threshold η r The IMF components of will be considered as valid IMF components.

[0079] The specific calculation formula of the correlation coefficient is:

[0080]

[0081] Wherein, x(t) represents the signal value at the tth moment in the pipeline leakage signal; imf(t) represents the signal value at the tth moment in the IMF component; t represents the time, t=1,2,...,N, N represents the signal length; Indicates the average signal value of pipeline leakage signal; represents the average signal value of the IMF component; Conf(x,IMF) represents the correlation coefficient between the IMF component and the pipeline leakage signal.

[0082] S5, using the singular value decomposition algorithm, namely the SVD algorithm, to perform SVD decomposition and denoising on each effective IMF component, to remove the noise signal in each effective IMF component; and synthesize each effective IMF component after denoising to obtain the denoised pipeline leakage signal. The details are as follows:

[0083] S51, IMF component is expressed as {imf(t)|t=1,2,...,N}; imf(t) is the signal value at the tth moment in the IMF component, t represents the moment, t=1,2,...,N, and N is the signal length. Convert the one-dimensional effective IMF component into a two-dimensional matrix Y, namely the Hankel matrix:

[0084]

[0085] Wherein, L is the number of rows of the two-dimensional matrix Y, H is the number of columns of the two-dimensional matrix Y, H=N-L+1; L is the number of samples close to or greater than one cycle of the lowest frequency component, to ensure that at least one complete cycle of the lowest frequency component can be captured in each time window to avoid distortion or aliasing of the frequency component.

[0086] S52, Singular Value Decomposition: Perform SVD decomposition on the two-dimensional matrix Y and decompose it into an orthogonal matrix U, a diagonal matrix S, and the transpose V of the orthogonal matrix V. T ;

[0087] Y=USVT

[0088] S = [diag(σ1, σ2, …, σ p ), 0]

[0089] where the diagonal matrix S is an L×H diagonal matrix, the diagonal elements σ1, σ2, …, σ p are non - negative values, the non - diagonal elements are 0, and the diagonal elements σ1, σ2, …, σ p of the diagonal matrix S are the singular values of the effective IMF components; p = min{L, H}.

[0090] S53, Signal recombination: By calculating the energy differential spectrum D i of each singular value, the singular values are grouped into signal - related components and noise components, and a second threshold is set;

[0091]

[0092] where, σ i is the i - th singular value, p is the number of singular values; D i is the energy differential spectrum of the i - th singular value σ i ; η σ is the second threshold;

[0093] The singular values with D i greater than the second threshold η σ are denoted as signal - related components, and the singular values with D i less than or equal to the second threshold η σ are denoted as noise components.

[0094] In the present invention, the second threshold is set as the average value of the singular values. For signals and noises satisfying certain statistical distribution characteristics, the average value can be used as a criterion for judging the noise boundary.

[0095] S54: Signal reconstruction: Using the anti - diagonal averaging method, the signal - related components are reconstructed from a two - dimensional matrix into a time series to obtain the denoised effective IMF component imf'(t).

[0096] The total length of the signal is N, and the signal is divided into three segments for reconstruction using the anti - diagonal averaging method:

[0097]

[0098] In the formula, L * = min(L, H), H * = max(L, H); when L < H, Otherwise, y i,j 、y j,iare the elements in the two-dimensional matrix Y. After processing, the low-frequency random wavenumber signal is effectively filtered out.

[0099] S55, synthesizing the effective IMF components after the denoising process to obtain a denoised pipeline leakage signal.

[0100] The method of the present invention can achieve better results by performing denoising on the pipeline leakage signal, and can filter out the noise while retaining the effective features in the pipeline leakage signal.

[0101] In the present invention, when using the WOA algorithm for optimization, the traditional WOA algorithm is also improved. Pheromones are an important concept in the ant colony algorithm. Ants communicate and find paths by releasing and sensing pheromones. Through the concentration of pheromones, ants can find a better path and avoid suboptimal solutions. The present invention draws on the pheromone mechanism in the ant colony algorithm and introduces pheromones into the WOA algorithm to guide the search process, enhance the utilization of excellent solutions, and effectively select the appropriate number of modes K and penalty factor α. The specific improvements are as follows:

[0102] In the algorithm initialization, the pheromone matrix P is added to represent the pheromone concentration of each individual in the solution space. The pheromone increment ΔP is usually related to the fitness function value. The learning factors α1 and β1 are used to balance the pheromone guidance and distance guidance. In the iterative process, the pheromone is updated according to the fitness function. For each individual X i , if its fitness is better than the current global optimal solution, then increase the pheromone:

[0103] P ij =P ij +ΔP·(f(X best )-f(X i ))

[0104] Among them, f(X i ) is individual X i The fitness value of each individual represents a solution of a set of modal number K and penalty factor α; f(X best ) is the fitness value of the current optimal solution; X best is the current optimal solution; P ij is an element in the pheromone matrix; ΔP is the pheromone increment, which can be set as:

[0105]

[0106] Among them, C is a constant used to control the increment of pheromone. After each iteration, the concentration of pheromone will decay. This can ensure that the poor solutions are gradually eliminated and avoid pheromone concentration.

[0107] When the position is updated, the search direction is guided according to the pheromone concentration to obtain the new individual X new :

[0108] d i =|X best -X i |

[0109] X new =X i +α1·P ij -β1·d i

[0110] Among them, α1 and β1 are the weights of pheromone and distance respectively, d i For each individual X i and the current optimal solution X best By adjusting these two parameters, we can control the influence of pheromone and distance in the update. new The fitness f(X new ), and update the current optimal solution X best :

[0111]

[0112] Example 1

[0113] S101, using acoustic emission acquisition device to obtain the original acoustic emission signal of the pipeline defect position, that is, the pipeline leakage signal. Among them, the signal excitation part has a calibration device and a steel pipe (L = 1000mm, d = 30mm), and the signal receiving part has a sensor, a preamplifier, an acoustic emission host and a host computer software. Among them, the standard configuration of the acoustic emission instrument host has a sampling rate of 10M / S per channel, 16bit sampling accuracy, low system noise and high dynamic range acquisition card. Each acquisition card comes with a 1Gb waveform buffer, which perfectly realizes full waveform acquisition without data loss, and the signal length is 1000. The pipeline crack acoustic emission signal is exported to the host computer for denoising.

[0114] Specifically, the signal excitation part mainly consists of a calibration device that simulates crack signals on the surface of the steel pipe. The sensor of the signal receiving part collects the mechanical vibration of the material and converts it into an electrical signal, which is amplified by the preamplifier and then processed and recorded by the host computer. It is transmitted to the host computer for processing to obtain the original acoustic emission signal, that is, the pipeline leakage signal.

[0115] S102, setting parameters for the optimized WOA algorithm, taking the penalty factor α and the number of modes K in the VMD algorithm as optimization targets, and taking the minimum envelope entropy of the signal as the fitness function of the WOA algorithm, inputting the pipeline leakage signal in step S101 into the WOA algorithm, and selecting the optimization target parameter value according to the fitness function.

[0116] In this embodiment, after the WOA algorithm optimization, when the number of iterations is 3, the fitness function value reaches the minimum of 2.919. Figure 2 As shown, using the improved WOA algorithm of the present invention ( Figure 2 The iteration speed and fitness value of P-WOA in the improved WOA algorithm are both better than those of the traditional WOA algorithm ( Figure 2 The optimal parameter penalty factor α=994 and the optimal number of modes K=3 are output.

[0117] S103, according to the optimal target penalty factor α and the optimal mode number K output in step S102, the parameters of the VMD algorithm are set, and the pipeline leakage signal in step 1 is imported into the VMD algorithm for decomposition to obtain three intrinsic mode components, namely IMF components, and the time domain diagram and spectrum diagram of the components are drawn, as shown in FIG. Figure 3 shown.

[0118] S104: The three IMF components obtained in step S3 are distinguished into effective IMF components and noise IMF components using the correlation coefficient method. The first threshold η r It is set to 0.25, where the correlation coefficient value of the decomposed IMF1 component is 0.9796, the correlation coefficient value of the IMF2 component is 0.2369, and the correlation coefficient value of the IMF3 component is 0.1939. Specifically, IMF1 is the effective IMF component, and IMF2 and IMF3 are noise IMF components.

[0119] S105, using the SVD algorithm to perform SVD decomposition and denoising on the effective IMF component, that is, the IMF1 component in step S104, to remove the noise signal in the effective IMF component, and to reconstruct the effective IMF component after denoising to obtain the final denoised pipeline leakage signal, the time domain diagram and the spectrum diagram of the denoised pipeline leakage signal, as shown in FIG. Figure 4 As shown, Figure 4 Here |P1(f)| represents the amplitude or intensity of the frequency.

[0120] The signal-to-noise ratio of the denoised pipeline leakage signal obtained by using only the VMD algorithm is 13.4495dB, and the root mean square error is 0.0219. The signal-to-noise ratio of the denoised pipeline leakage signal obtained by using only the SVD algorithm is 11.0395dB, and the root mean square error is 0.0366. The signal-to-noise ratio of the denoised pipeline leakage signal obtained by using the WOA-VMD combined SVD method of the present invention is 14.1311dB, and the root mean square error is 0.0183. Figure 4 It can be shown that the method proposed in the present invention has a higher signal-to-noise ratio and a lower root mean square error, and has a better denoising effect.

[0121] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD, characterized in that: The following steps are involved: S1, obtaining the original acoustic emission signal at the pipeline defect location, i.e., the pipeline leakage signal; S2, taking the penalty factor α and the number of modes K in the variational mode decomposition algorithm, namely the VMD algorithm, as the optimization target of the whale algorithm, namely the WOA algorithm, and finding the optimal penalty factor α and the optimal number of modes K in the VMD algorithm; S3, setting a VMD algorithm according to the optimal penalty factor α and the optimal mode number K obtained in step S2, and using the VMD algorithm to perform VDM decomposition on the pipeline leakage signal in step S1 to obtain K intrinsic mode components, namely, IMF components; S4, using the correlation coefficient method to identify the K IMF components obtained in step S3, and identify the effective IMF components; S5, using a singular value decomposition algorithm, namely, an SVD algorithm, to perform SVD decomposition and denoising processing on each effective IMF component, thereby removing the noise signal in each effective IMF component; synthesizing each effective IMF component after denoising processing to obtain a denoised pipeline leakage signal.

2. According to claim 1, a pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD is characterized in that: In step S2, the optimization target is selected according to the fitness value, and the fitness function is: Where a(j) is the envelope signal of the intrinsic mode component obtained by VMD decomposition of the pipeline leakage signal after Hilbert demodulation; j represents the jth sampling point in the envelope signal a(j), N is the number of sampling points; P j is the probability distribution sequence obtained after normalization of a(j); calculate the probability distribution sequence P j The entropy value of the envelope entropy E p ; Calculate the envelope entropy E of each eigenmode component after VMD decomposition p , select the smallest envelope entropy E p As fitness value; Find the penalty factor α and the number of modes K corresponding to the minimum fitness value as the optimal penalty factor α and the optimal number of modes K.

3. According to claim 1, a pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD is characterized in that: In step S4, the correlation coefficient method is used to calculate the correlation coefficient between each IMF component and the pipeline leakage signal, and the IMF component with a correlation coefficient greater than the first threshold is a valid IMF component; specifically, as shown below: Wherein, x(t) represents the signal value at the tth moment in the pipeline leakage signal; imf(t) represents the signal value at the tth moment in the IMF component; t represents the time, t=1,2,...,N, N represents the signal length; Indicates the average signal value of the pipeline leakage signal; represents the average signal value of the IMF component; Conf(x,IMF) represents the correlation coefficient between the IMF component and the pipeline leakage signal; The first threshold η r =ρ·R max , where R max is the calculated maximum correlation coefficient, and ρ is the set ratio.

4. According to claim 1, a pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD is characterized in that: The specific process of step S5 is as follows: S51, IMF component is represented by {imf(t)|t=1,2,...,N}; imf(t) is the signal value at the tth moment in the IMF component, t represents the moment, t=1,2,...,N, and N is the signal length; Convert the one-dimensional effective IMF components into a two-dimensional matrix Y: Wherein, L is the number of rows of the two-dimensional matrix Y, H is the number of columns of the two-dimensional matrix Y, H=N-L+1; S52, perform singular value decomposition (SVD) on the two-dimensional matrix Y to decompose it into an orthogonal matrix U, a diagonal matrix S, and the transpose V of the orthogonal matrix V. T ; Y=USV T S=[diag(σ1,σ2,…,σ p ),0] The diagonal matrix S is a L×H diagonal matrix, and the diagonal elements σ1, σ2, …, σ p is a non-negative value, the off-diagonal elements are 0, and the diagonal elements of the diagonal matrix S are σ1,σ2,…,σ p That is, the singular value of the effective IMF component; p = min{L,H}; S53, by calculating the energy differential spectrum D of each singular value i , grouping the singular values ​​into signal-related components and noise components, and setting a second threshold; Among them, σ i is the i-th singular value, p is the number of singular values; D i is the i-th singular value σ i The energy differential spectrum of σ is the second threshold; D i Greater than the second threshold η σ The singular values ​​of D are recorded as signal-related components. i Less than or equal to the second threshold value η σ The singular values ​​of are recorded as noise components; S54, using the anti-diagonal averaging method to reconstruct the signal correlation components from the two-dimensional matrix into a time series, and obtain the effective IMF component imf'(t) after denoising; where L * = min(L, H), H * = max(L, H); when L < H, otherwise, y i,j and y j,i are elements in the two-dimensional matrix Y; S55, synthesizing the effective IMF components after the denoising process to obtain a denoised pipeline leakage signal.

5. According to claim 1, the pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD is characterized in that: The improved WOA algorithm is used to find the optimal solution, that is, the optimal penalty factor α and the optimal number of modes K, as shown below: In the algorithm initialization, the pheromone matrix P is added to represent the pheromone concentration of each individual in the solution space; For each individual X i , if its fitness value is better than the current global optimal solution, then add pheromone: P ij =P ij +ΔP·(f(X best )-f(X i )) Among them, f(X i ) is individual X i The fitness value of each individual represents a solution of a set of modal number K and penalty factor α; f(X best ) is the fitness value of the current optimal solution; X best is the current optimal solution; P ij is an element in the pheromone matrix; ΔP is the pheromone increment; C is a constant used to control the pheromone increment; When the position is updated, the search direction is guided according to the pheromone concentration to obtain the new individual X new : d i =|X best -X i | X new =X i +α1·P ij -β1·d i Among them, α1 and β1 are the weights of pheromone and distance respectively, d i For each individual X i and the current optimal solution X best distance; Evaluate new individual X new The fitness f(X new ), and update the current optimal solution X best :

6. A computer program product, characterized in that It includes a computer program / instruction, which, when executed by a processor, implements a pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD as described in any one of claims 1 to 5.

7. A readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed, the pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD as claimed in any one of claims 1 to 5 is implemented.

8. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the pipeline leakage signal denoising method based on improved WOA-VMD combined with SVD as described in any one of claims 1 to 5.

Images