Wind turbine generator transmission chain fault diagnosis method based on time-frequency plane expectation maximization

Abstract

The invention provides a wind turbine generator transmission chain fault diagnosis method based on time-frequency plane expectation maximization, and belongs to the technical field of fault diagnosis. The method comprises the following steps that a cylindrical MEMS acceleration sensor is arranged on a transmission chain of a wind turbine generator, and vibration signals of the transmission chain of the wind turbine generator are collected through the cylindrical MEMS acceleration sensor; an unsupervised classification method based on a spectrogram zero point is adopted, a vibration signal and a rotating speed signal during operation of a wind turbine generator are collected, short-time Fourier transform is used for generating time-frequency representation for the vibration signal, the spectrogram zero point is extracted, unsupervised classification is carried out, and noise reduction processing of the vibration signal is achieved; based on a multi-component signal estimation method under time-frequency plane expectation maximization, the instantaneous frequency and the instantaneous amplitude of a multi-component signal are accurately estimated on a time domain plane of the denoised signal; and order spectrum analysis is carried out, vibration signal characteristics of the wind turbine generator transmission chain are identified, and fault diagnosis of the wind turbine generator transmission chain under the variable rotation speed is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and in particular to a wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization. Background Art

[0002] Wind turbines are important equipment in the utilization of modern renewable energy and are widely used in wind farms around the world. With the increasing global demand for clean energy, the number and scale of wind turbines are also growing rapidly. Wind turbines are usually installed in areas with high altitudes and harsh environments, which makes the reliability and life of key components of the wind turbine transmission chain particularly important. Under complex working conditions such as variable speed, the blades of the wind turbine are subjected to short and frequent impacts, causing the transmission chain to be subjected to alternating loads, which has a great impact on its working life. Therefore, effective monitoring of the operating status of the wind turbine transmission chain can improve operational reliability and prevent major safety accidents. The wind turbine transmission chain is mainly composed of rotating parts such as the main shaft and support bearings (direct drive), speed increase gearbox (double fed). At present, the fault diagnosis of wind turbine transmission chain faces two prominent problems: 1) Due to the continuous changes in rotation speed and other factors, the fault characteristics are typically time-varying and non-stationary; 2) Due to the low main shaft speed, the fault characteristic frequency of key components in the transmission chain is in a lower frequency band, and weak fault signals are easily submerged by strong noise, making it difficult to identify early weak faults and extract variable speed and weak fault characteristics.

[0003] Therefore, it is very necessary to provide a wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization, collect the vibration signals of the wind turbine transmission chain under variable speed conditions, accurately characterize the service status of key components of the wind turbine transmission chain, accurately obtain the instantaneous amplitude and instantaneous frequency of different component signals, and realize early detection and fault diagnosis of wind turbine transmission chain faults. Summary of the invention

[0004] In view of this, the present invention proposes a wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization, which uses a cylindrical MEMS sensor to collect the vibration signal of the wind turbine transmission chain under variable speed conditions, extracts the spectrum zero point and performs unsupervised classification to achieve signal denoising preprocessing, and accurately obtains the instantaneous amplitude and instantaneous frequency of different component signals.

[0005] The present invention provides a wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization, comprising the following steps:

[0006] S1; configuring a cylindrical MEMS acceleration sensor in the transmission chain of the wind turbine, and collecting vibration signals of the wind turbine transmission chain through the cylindrical MEMS acceleration sensor;

[0007] S2: The unsupervised classification method based on the zero point of the spectrum is used to collect the vibration signal and speed signal of the wind turbine during operation. The short-time Fourier transform is used to generate a time-frequency representation of the vibration signal, and the zero point of the spectrum is extracted and unsupervised classification is performed to achieve noise reduction of the vibration signal.

[0008] S3: Based on the multi-component signal estimation method under the expectation maximization of the time-frequency plane, the instantaneous frequency and instantaneous amplitude of the multi-component signal are accurately estimated on the time domain plane of the denoised vibration signal;

[0009] S4: Perform order spectrum analysis to identify the vibration signal characteristics of the wind turbine transmission chain and realize fault diagnosis of the wind turbine transmission chain under variable speed.

[0010] On the basis of the above technical scheme, preferably, the cylindrical MEMS acceleration sensor includes a cylindrical base, a mass block and a plurality of pole plates, the surface of the base is provided with a slide groove, and the slide groove is extended along the axial direction of the base; the mass block is embedded in the slide groove and is slidably connected to the inner surface of the slide groove; anchor points are respectively provided at both ends of the mass block, one end of the anchor point is fixedly connected to the mass block, and the other end of the anchor point extends in a direction away from the mass block, the anchor point is attached to the surface of the base and is slidably connected to the base; a plurality of comb teeth are symmetrically provided at non-end positions on both sides of the mass block, and the plurality of comb teeth are spaced along the axial direction of the base. The comb teeth are arranged at intervals, one end of the comb teeth is fixedly connected to the mass block, the other ends of the comb teeth extend in the direction away from the mass block, the comb teeth are slidably connected to the surface of the base, and the adjacent comb teeth and the comb teeth and the anchor points are arranged at intervals; a plurality of pole plates are fixedly arranged on the surface of the base between adjacent comb teeth, and the positions of the pole plates relative to the base remain unchanged; when the fan drive chain generates acceleration, the mass block drives the anchor point and the plurality of comb teeth to slide along the axial direction of the base, changes the spacing between the comb teeth and the adjacent pole plates, thereby generating a current signal, and the size of the current signal is sampled and converted into a vibration signal of the fan drive chain under variable speed conditions.

[0011] Preferably, the noise reduction processing of the vibration signal in step S2 specifically includes:

[0012] The vibration signal of the fan transmission chain is converted into a time-frequency representation, and the vibration signal is processed in segments using a Gaussian window function. The window slides on the vibration signal to obtain the spectrum information corresponding to each time window, and the spectrum information corresponding to each window is combined to obtain the time-frequency spectrogram of the entire vibration signal;

[0013] Find the zero points in the time-frequency spectrum and classify them into SS, SN and NN types according to their properties;

[0014] After completing the zero point classification, SS and SN zero points are selected on the time-frequency plane for Delaunay triangulation to obtain an estimate of the signal domain in the time-frequency plane. The vibration signal in the signal domain estimate is reconstructed using the inverse short-time Fourier transform to obtain an estimate of the noise-free vibration signal.

[0015] Further preferably, the zero point in the time-frequency spectrogram is found and classified according to the properties of the zero point, and a threshold γ is set. Any point whose spectrum value of the time-frequency spectrogram is lower than the threshold is regarded as a zero point. The threshold γ is determined as follows: γ = μ X -k0σ X , where μ X is the mean of the spectrum values, σ X is the standard deviation of the spectrum value, k0 is the adjustment factor; according to the nature of the zero point, the zero point is divided into three categories: 1) SS category: signal-signal zero point; 2) SN category: signal-noise zero point; 3) NN category: noise-noise zero point; Assuming that N noise simulations are performed and N time-frequency spectra are obtained, the position of zero point i in different noise simulations is defined as (t Ki , f Ki ), K = 1, 2, ..., N, for each zero point i, calculate the position change d of the zero point in different noise simulations i : in Together they represent the average position of zero point i in the Nth noise simulation, taking δ SS and δ NN is the position change d i The threshold value, δ SS is the right offset value of the first peak of the signal-signal zero position change, δ NN To cover the left offset value of the second peak of the noise-noise zero point position change, the zero point classification rule is: SS class = {i|d i ≤δ SS}, NN class={i|d i ≥δ NN} and SN class = {i|δ SS ≤d i ≤δ NN}.

[0016] More preferably, the value of the adjustment factor k0 is 2.5.

[0017] More preferably, the estimation of the signal domain in the time-frequency plane is obtained, and the vibration signal in the signal domain estimation is reconstructed using an inverse short-time Fourier transform to obtain an estimated value of the noise-free vibration signal. Specifically, after completing the zero point classification, SS-type and SN-type zero points are selected on the time-frequency plane for Delaunay triangulation. The distribution of the zero points and the collective characteristics of the corresponding triangles are used to identify the signal domain. The side length l of the triangulation ij The calculation formula is: i, j represent two different zero points, (t i , f i ) and (t j , f j ) are the positions of the two zero points respectively; the weight factor ω is introduced ij Make the triangulation take into account both the density and geometric distance of the zero points, Where ρ(t, f) is the local density of zero points in the time-frequency plane, and the weighted length l′ of each edge of the triangulation is obtained by the weight factor ij , l′ ij =ω ij ·l ij , dynamically adjust the effective length of each edge; for each triangulated triangle, if the weighted length of any edge is greater than the preset edge length threshold The triangle is considered to belong to the signal domain; the side length is greater than the side length threshold The triangles are gathered together to obtain an estimate of the signal domain in the time-frequency plane: Based on the obtained signal domain estimation in the time-frequency plane, the signal in the signal domain is reconstructed using the inverse short-time Fourier transform to calculate the estimated value of the noise-free signal

[0018] Further preferably, the content of step S3 is:

[0019] S31, expectation step: calculate the expected value of the vibration signal, and express the estimated value of the noise-free signal with multiple components as: k=1,2,...,m,A k (t) is the instantaneous amplitude of the kth component, φ k (t) is the instantaneous phase, n(t) is the noise; Monte Carlo sampling is then used to estimate the posterior distribution and generate M samples θ from the prior distribution. (i) , where the superscript i represents different moments, assuming that the observed signal is independent at each time point t, for each sample θ (i) , calculates an estimate of the noise-free signal The likelihood function value of t=1,2,3,...,T,then calculate the weight of each sample Then use the weighted average method to estimate the expected value of the posterior distribution:

[0020] S32, maximization step: obtaining the expected value that meets the actual vibration signal characteristics After that, the estimated values ​​of instantaneous frequency and amplitude need to be updated. First, substitute the expected value of the vibration signal feature obtained above, maximize the expected log-likelihood function, and find the optimal instantaneous frequency and amplitude: where θ (t+1) Represents the parameter estimation after the t+1th iteration. The parameters of the instantaneous frequency and amplitude are updated using the result after maximizing the expectation:

[0021]

[0022] in is the instantaneous phase after the t+1th iteration, is the instantaneous amplitude of the k components after the tth iteration, η is the learning rate;

[0023] S33. In order to ensure the stability and accuracy of parameter estimation, it is necessary to repeat the expectation step S31 and the maximization step S32 until the parameter estimation converges. The convergence condition of the parameter estimation is |θ (t+1) -θ (t) |<ε,θ (t) is the parameter estimate after the tth iteration, ε is the convergence threshold; finally, the instantaneous frequency of each signal component is extracted and the instantaneous amplitude As the input condition for the next step of order spectrum analysis.

[0024] Further preferably, the content of step S4 is: after completing the extraction of the instantaneous frequency and instantaneous amplitude of the signal component of the vibration signal, the instantaneous frequency f(t) and f(t) of the signal feature classification and the speed feature classification are obtained. F (t), using the instantaneous frequency f(t) and f F (t) Extracting features of the variable speed signal, and realizing fault diagnosis of the wind turbine transmission chain according to the results of the variable speed signal feature extraction.

[0025] Further preferably, using the instantaneous frequency f(t) and f F (t) To extract the features of the variable speed signal, the order ratio analysis method is used, and the order ratio L is defined as a multiple of the speed. According to the size of the order ratio, different fault types and fault locations of the wind turbine transmission chain are characterized.

[0026] Preferably, the gap between adjacent comb teeth is greater than the sliding distance of the mass block in the slide groove.

[0027] The wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization provided by the present invention has the following beneficial effects compared with the prior art:

[0028] (1) The present invention collects the vibration signals of the wind turbine transmission chain under variable speed conditions to accurately characterize the service status of key components of the wind turbine transmission chain, thereby providing effective data support for subsequent time-frequency analysis; secondly, an unsupervised classification method based on the zero point of the spectrum is proposed. By collecting the vibration and speed signals of the wind turbine during operation, the short-time Fourier transform is used to generate the time-frequency representation, the zero point of the spectrum is extracted and unsupervised classification is performed to achieve signal denoising preprocessing; then, a multi-component signal estimation method under the expectation maximization algorithm of the time-frequency plane is proposed to accurately obtain the instantaneous amplitude and instantaneous frequency of different component signals, thereby achieving high-resolution time-frequency representation of the time-frequency characteristics of multi-component vibration signals under non-stationary working conditions; finally, the time-frequency ridges of the rotation frequency and fault characteristic components are extracted from the highly readable time-frequency plane obtained by the above-mentioned time-frequency analysis method, and the early detection and fault diagnosis of the wind turbine transmission chain fault are achieved by means of order spectrum analysis;

[0029] (2) A cylindrical MEMS sensor structure is provided. Compared with the planar structure of the existing sensor, it can limit the freedom of the mass block so that it can only move along the axial direction of the cylinder and limit the movement of the mass block in other directions, thereby eliminating measurement interference. A plurality of annular plates and annular comb teeth are attached to the surface of the cylinder. The comb teeth follow the mass block to move up and down on the cylindrical surface, ensuring that the capacitance changes only due to the change of the pole distance. At the same time, the influence of the change of the covering area on the measurement is avoided, thereby ensuring the accuracy and stability of the measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 It is a flow chart of the steps of the wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization of the present invention;

[0032] Figure 2 A three-dimensional diagram of a cylindrical MEMS acceleration sensor of a wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization of the present invention;

[0033] Figure 3A three-dimensional diagram of the base of a cylindrical MEMS acceleration sensor of the wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization of the present invention;

[0034] Figure 4 It is a stereogram of the combined state of the mass block, anchor point and comb teeth of the cylindrical MEMS acceleration sensor of the wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization of the present invention;

[0035] Figure 5 It is a stereoscopic diagram of the pole plate of the cylindrical MEMS acceleration sensor of the wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings of the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0037] The existing wind turbine transmission chain detection methods have the following disadvantages: 1. When using a planar MEMS accelerometer to measure vibration signals, when installed on a rotating device, it is easily disturbed by gravity and centrifugal force, resulting in a decrease in measurement accuracy; when facing complex vibration modes, it is impossible to effectively distinguish signals from different vibration sources, especially when the vibration signal frequencies are close or overlapping, which can easily lead to misjudgment. 2. In signal denoising, the threshold-based wavelet denoising algorithm is one of the widely used methods at present, but the threshold-based wavelet denoising algorithm has the following disadvantages: the wavelet transform itself depends on the pre-selected wavelet basis, and these wavelet bases cannot always perfectly match the characteristics of the signal, resulting in the loss of signal details or the generation of artifacts. 3. Synchronous compression transform concentrates the signal energy at the instantaneous frequency position by rearranging the time-frequency diagram obtained by traditional continuous wavelet transform or short-time Fourier transform, but it is essentially a post-processing method of time-frequency analysis, which is sensitive to noise, especially when the frequency components of the signal are dense or overlapping, the noise will have a greater interference with the rearrangement process, resulting in an increase in the estimation error, especially when processing large-scale data or real-time signals, which is not suitable for industrial applications. In view of this, if Figure 1 As shown, the present invention provides a wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization, which specifically includes the following steps:

[0038] S1: A cylindrical MEMS acceleration sensor is configured in the transmission chain of the wind turbine, and a vibration signal of the wind turbine transmission chain is collected through the cylindrical MEMS acceleration sensor.

[0039] like Figure 2-5 As shown, the cylindrical MEMS acceleration sensor includes a cylindrical base 1, a mass block 2 and a plurality of pole plates 3. A slide groove is provided on the surface of the base 1, and the slide groove is extended along the axial direction of the base 1; the mass block 2 is embedded in the slide groove and is slidably connected to the inner surface of the slide groove; anchor points 2.1 are respectively provided at both ends of the mass block 2, one end of the anchor point 2.1 is fixedly connected to the mass block 2, and the other end of the anchor point 2.1 extends in a direction away from the mass block 2, and the anchor point 2.1 is attached to the surface of the base 1 and is slidably connected to the base 1; a plurality of comb teeth 2.2 are symmetrically provided at non-end positions on both sides of the mass block 2, and the plurality of comb teeth 2.2 are spaced apart along the axial direction of the base 1, and the plurality of comb teeth 2.2 are spaced apart from each other. One end is fixedly connected to the mass block 2, and the other ends of the comb teeth 2.2 extend in a direction away from the mass block 2. The comb teeth 2.2 are slidably connected to the surface of the base 1, and the adjacent comb teeth 2.2 and the comb teeth 2.2 are spaced apart from the anchor point 2.1; a plurality of pole plates 3 are fixedly arranged on the surface of the base 1 between the adjacent comb teeth 2.2, and the position of the pole plates 3 relative to the base 1 remains unchanged; when the fan drive chain generates acceleration, the mass block 2 drives the anchor point 2.1 and the comb teeth 2.2 to slide along the axial direction of the base 1, changing the spacing between the comb teeth 2.2 and the adjacent pole plates 3, thereby generating a current signal, sampling the magnitude of the current signal and converting it into a vibration signal of the fan drive chain under variable speed conditions. The main function of the pole plate 3 is to cooperate with the comb teeth on the mass block to facilitate the perception of the displacement of the mass block. Since the spacing between the comb teeth and the adjacent pole plates 3 can change, the capacitance between the output and the pole plates also changes, thereby generating a detection signal corresponding to the acceleration generated by the vibration. In order to avoid the comb teeth 2.2 and the pole plate 3 from overlapping each other, the gap between adjacent comb teeth 2.2 can be set to be larger than the sliding distance of the mass block 2 in the slide groove.

[0040] In the wind turbine transmission chain of this embodiment, the bearing is the key part that bears load and vibration, and the gearbox is the core component that transmits power. Therefore, the sensor is installed above the outer shell of the gearbox bearing seat to ensure that the axial direction of the sensor is aligned with the expected vibration direction so as to accurately measure the vibration in the up and down directions. This can effectively monitor the vibration state of the wind turbine transmission chain and identify potential faults. Figure 2-5 It can be seen that the comb teeth 2.2 and the electrode plate 3 are both arc-shaped structures that fit the base 1. The slide groove has a wedge-shaped cross-section, which limits the movement of the mass block in other directions, thereby reducing the measurement error caused by lateral movement. The comb tooth structure can greatly expand the sensing area, improve measurement accuracy, and reduce the difficulty of signal processing.

[0041] S2: The unsupervised classification method based on the zero point of the spectrum is used to collect the vibration signal and speed signal of the wind turbine during operation. The short-time Fourier transform is used to generate a time-frequency representation of the vibration signal, and the zero point of the spectrum is extracted and unsupervised classification is performed to achieve noise reduction of the vibration signal.

[0042] The specific contents of step S2 include:

[0043] The vibration signal of the fan drive chain is converted into a time-frequency representation, and the vibration signal is processed in segments using a Gaussian window function. The window slides on the vibration signal to obtain the spectrum information corresponding to each time window, and the spectrum information corresponding to each window is combined to obtain the time-frequency spectrogram of the entire vibration signal; this step is to use the short-time Fourier transform (STFT) to generate the time-frequency (TF) representation of the vibration signal x(t) measured by the cylindrical MEMS acceleration sensor, that is, X(t, f) = STFT(x(t)). In this way, the one-dimensional time signal can be converted into a two-dimensional time-frequency spectrogram, so as to observe the change law of the frequency of the measured vibration signal over time. Next, the signal is processed in segments using a Gaussian window function. In the short-time Fourier transform, the window function slides on the signal, and only the signal in a short time window is processed each time, and then these short time segments are Fourier transformed. In this way, the spectrum information corresponding to each time window can be obtained, and it is combined to form the time-frequency spectrogram of the entire signal.

[0044] Find the zero point in the time-frequency spectrogram, and classify the zero point into SS, SN and NN according to the nature of the zero point; specifically, set a threshold γ, and any point whose spectrum value of the time-frequency spectrogram is lower than the threshold is regarded as a zero point. The threshold γ is determined as follows: γ = μ X -k0σ X , where μ X is the mean of the spectrum values, σ X is the standard deviation of the spectrum value, k0 is the adjustment factor; according to the nature of the zero point, the zero point is divided into three categories: 1) SS type: signal-signal zero point; caused by the interference between signal components, usually the most stable. 2) SN type: signal-noise zero point; caused by the interference between signal and noise, its stability is between SS type and NN type. 3) NN type: noise-noise zero point; caused only by noise, the least stable.

[0045] Assuming that N noise simulations are performed, N time-frequency spectra are obtained, and the position of zero point i in different noise simulations is defined as (t Ki , f Ki ), K = 1, 2, ..., N, for each zero point i, calculate the position change d of the zero point in different noise simulations i : in Together they represent the average position of zero point i in the Nth noise simulation, taking δ SS and δ NN is the position change d i The threshold value, δ SS is the right offset value of the first peak that covers most of the signal-signal zero position changes, δ NN In order to cover the left offset value of the second peak of most noise-noise zero point position changes, the rule for zero point classification is: SS class = {i|d i ≤δ SS}, NN class={i|d i ≥δ NN} and SN class = {i|δ SS ≤d i ≤δ NN}.

[0046] Through cross-validation, this embodiment provides that the value of the adjustment factor k0 is 2.5.

[0047] After completing the zero point classification, on the time-frequency plane, select SS and SN zero points for Delaunay triangulation to obtain an estimate of the signal domain in the time-frequency plane, and use the inverse short-time Fourier transform to reconstruct the vibration signal in the signal domain estimate to obtain an estimate of the noise-free vibration signal. Specifically, after completing the zero point classification, on the time-frequency plane, select SS and SN zero points for Delaunay triangulation, and ignore NN zero points to reduce the impact of noise. The distribution of zero points and the collective characteristics of the corresponding triangles are used to identify the signal domain, and the side length l of the triangulation is ij The calculation formula is: i, j represent two different zero points, (t i , f i ) and (t j , f j ) are the positions of the two zero points respectively; the weight factor ω is introduced ij Make the triangulation take into account both the density and geometric distance of the zero points, Where ρ(t, f) is the local density of zero points in the time-frequency plane, and the weighted length l′ of each edge of the triangulation is obtained by the weight factor ij , l′ ij =ω ij ·l ij , dynamically adjust the effective length of each edge; for each triangulated triangle, if the weighted length of any edge is greater than the preset edge length threshold The triangle is considered to belong to the signal domain; the side length is greater than the side length threshold The triangles are gathered together to obtain an estimate of the signal domain in the time-frequency plane: Based on the obtained signal domain estimation in the time-frequency plane, the signal in the signal domain is estimated using the inverse short-time Fourier transform (ISTFT). Perform reconstruction and calculate an estimate of the noise-free signal

[0048] Traditional methods may not be sufficient to effectively distinguish signals from noise in some cases, especially when the signal components are dense or the noise is strong. The present invention can more accurately reflect the actual importance and distribution characteristics of zero points by introducing weight factors, thereby improving the denoising effect. The introduction of weight factors makes triangulation not only rely on geometric distance, but also take into account the density of zero points, because areas with high density may contain more noise zero points, while areas with low density are more likely to be signal domains. In traditional methods, areas with large noise are easily misjudged as signal domains. By considering the local density of zero points and introducing weight factors, such misjudgments can be effectively reduced and the overall denoising effect can be improved. This improvement makes the algorithm more robust and reduces misjudgments when dealing with dense noise areas. This method effectively utilizes the stability characteristics of zero points, accurately distinguishes signals from noise, and achieves the purpose of signal denoising.

[0049] S3: Based on the multi-component signal estimation method under the expectation maximization of the time-frequency plane, the instantaneous frequency and instantaneous amplitude of the multi-component signal are accurately estimated on the time domain plane of the denoised vibration signal.

[0050] After the above denoising preprocessing, the noise in the vibration signal of the wind turbine is effectively suppressed. However, in order to further accurately extract the instantaneous frequency and instantaneous amplitude of different signal components (such as rotation frequency and fault characteristic frequency) in the vibration signal of the wind turbine transmission chain under variable speed, further processing is required, that is, extracting the time-frequency ridges corresponding to the rotation frequency and fault characteristic frequency in the two-dimensional time-frequency plane. This method uses a method based on the expectation maximization algorithm to perform a deeper level of processing on the denoised signal to accurately estimate the instantaneous frequency and instantaneous amplitude of the multi-component signal, thereby laying the foundation for the next step of order spectrum analysis under variable speed.

[0051] The specific content of step S3 is:

[0052] S31, expectation step: calculate the expected value of the vibration signal, and express the estimated value of the noise-free signal with multiple components as: k=1,2,...,m,A k (t) is the instantaneous amplitude of the kth component, φ k (t) is the instantaneous phase, n(t) is the noise; Monte Carlo sampling is then used to estimate the posterior distribution and generate M samples θ from the prior distribution. (i) , where the superscript i represents different moments, assuming that the observed signal is independent at each time point t, for each sample θ(i) , calculates an estimate of the noise-free signal The likelihood function value of t=1,2,3,...,T,then calculate the weight of each sample Then use the weighted average method to estimate the expected value of the posterior distribution:

[0053] S32, maximization step: obtaining the expected value that meets the actual vibration signal characteristics After that, the estimated values ​​of instantaneous frequency and amplitude need to be updated. First, substitute the expected value of the vibration signal feature obtained above, maximize the expected log-likelihood function, and find the optimal instantaneous frequency and amplitude: where θ (t+1) Represents the parameter estimation after the t+1th iteration. The parameters of the instantaneous frequency and amplitude are updated using the result after maximizing the expectation:

[0054]

[0055] in is the instantaneous phase after the t+1th iteration, is the instantaneous amplitude of the k components after the tth iteration, η is the learning rate;

[0056] S33. In order to ensure the stability and accuracy of parameter estimation, it is necessary to repeat the expectation step S31 and the maximization step S32 until the parameter estimation converges. The convergence condition of the parameter estimation is |θ (t+1) -θ (t) |<ε,θ (t) is the parameter estimate after the tth iteration, ε is the convergence threshold; finally, the instantaneous frequency of each signal component is extracted and the instantaneous amplitude As the input condition for the next step of order spectrum analysis.

[0057] S4: Perform order spectrum analysis to identify the vibration signal characteristics of the wind turbine transmission chain and realize fault diagnosis of the wind turbine transmission chain under variable speed.

[0058] Step S4 includes: after extracting the instantaneous frequency and instantaneous amplitude of the signal component of the vibration signal, obtaining the instantaneous frequency f(t) and f(t) of the signal feature classification and the speed feature classification. F (t), using the instantaneous frequency f(t) and f F(t) Extract the features of the variable speed signal, and realize the fault diagnosis of the wind turbine transmission chain based on the results of the feature extraction of the variable speed signal. If the speed of the equipment is not uniform or fluctuates greatly, the various characteristic signals will not appear at equal intervals, and the traditional spectrum analysis method based on Fourier transform is no longer applicable. For this situation, the order ratio analysis method shows greater advantages. The order ratio L is defined as a multiple of the speed, that is, According to the size of the order ratio, different fault types and fault locations of the wind turbine transmission chain are characterized. The order ratio L = 1 means that the signal frequency is consistent with the rotation frequency; the order ratio L = 2 means that the signal frequency is twice the rotation frequency. It can be seen that the order ratio is actually a frequency representation method, which is equivalent to a multiple of the rotation frequency. For rotating machinery such as wind turbines, their vibration signals are closely related to the rotation speed. The order ratio can better represent this correspondence, and the order ratio can eliminate the influence of speed changes. If a specific order ratio appears through calculation, such as an integer multiple of 0.6×Z corresponding to an inner ring fault, and an integer multiple of 0.4×Z corresponding to an outer ring fault, where Z represents the number of rolling elements of the rolling bearing, it can be used to characterize different fault types and fault locations, thereby realizing wind turbine fault diagnosis under variable speed.

[0059] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization, characterized in that: The steps include: S1; a cylindrical MEMS acceleration sensor is configured in the transmission chain of the wind turbine, and a vibration signal of the wind turbine transmission chain is collected through the cylindrical MEMS acceleration sensor; S2: The unsupervised classification method based on the zero point of the spectrum is used to collect the vibration signal and speed signal of the wind turbine during operation. The short-time Fourier transform is used to generate a time-frequency representation of the vibration signal, and the zero point of the spectrum is extracted and unsupervised classification is performed to achieve noise reduction of the vibration signal. S3: Based on the multi-component signal estimation method under the expectation maximization of the time-frequency plane, the instantaneous frequency and instantaneous amplitude of the multi-component signal are accurately estimated on the time domain plane of the denoised signal; S4: Perform order spectrum analysis to identify the vibration signal characteristics of the wind turbine transmission chain and realize fault diagnosis of the wind turbine transmission chain under variable speed.

2. The wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization according to claim 1 is characterized in that: The cylindrical MEMS acceleration sensor comprises a cylindrical base (1), a mass block (2) and a plurality of pole plates (3); a slide groove is provided on the surface of the base (1), and the slide groove is extended along the axial direction of the base (1); the mass block (2) is embedded in the slide groove and is slidably connected to the inner surface of the slide groove; anchor points (2.1) are respectively provided at both ends of the mass block (2); one end of the anchor point (2.1) is fixedly connected to the mass block (2), and the other end of the anchor point (2.1) extends in a direction away from the mass block (2); the anchor point (2.1) is attached to the surface of the base (1) and is slidably connected to the base (1); a plurality of comb teeth (2.2) are symmetrically provided at non-end positions on both sides of the mass block (2); the plurality of comb teeth (2.2) are spaced apart along the axial direction of the base (1), and the plurality of comb teeth (2.2) are spaced apart from each other. One end is fixedly connected to the mass block (2), the other ends of the plurality of comb teeth (2.2) extend in a direction away from the mass block (2), the comb teeth (2.2) are slidably connected to the surface of the base (1), and adjacent comb teeth (2.2) and comb teeth (2.2) and anchor points (2.1) are arranged at intervals; a plurality of pole plates (3) are fixedly arranged on the surface of the base (1) between adjacent comb teeth (2.2), and the position of the pole plates (3) relative to the base (1) remains unchanged; when the fan drive chain generates acceleration, the mass block (2) drives the anchor points (2.1) and the plurality of comb teeth (2.2) to slide along the axial direction of the base (1), changing the spacing between the comb teeth (2.2) and adjacent pole plates (3), thereby generating a current signal, sampling the magnitude of the current signal and converting it into a vibration signal of the fan drive chain under variable speed conditions.

3. The wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization according to claim 2 is characterized in that: The noise reduction process of the vibration signal in step S2 specifically includes: The vibration signal of the fan transmission chain is converted into a time-frequency representation, and the vibration signal is processed in segments using a Gaussian window function. The window slides on the vibration signal to obtain the spectrum information corresponding to each time window, and the spectrum information corresponding to each window is combined to obtain the time-frequency spectrogram of the entire vibration signal; Find the zero points in the time-frequency spectrum and classify them into SS, SN and NN types according to their properties; After completing the zero point classification, SS and SN zero points are selected on the time-frequency plane for Delaunay triangulation to obtain an estimate of the signal domain in the time-frequency plane. The vibration signal in the signal domain estimate is reconstructed using the inverse short-time Fourier transform to obtain an estimate of the noise-free vibration signal.

4. The wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization according to claim 3 is characterized in that: Find the zero point in the time-frequency spectrum and classify it according to its properties. The threshold γ is set. Any point whose spectrum value of the time-frequency spectrum is lower than the threshold is regarded as a zero point. The threshold γ is determined as follows: γ = μ X -k0σ X , where μ X is the mean of the spectrum values, σ X is the standard deviation of the spectrum value, K0 is the adjustment factor; according to the nature of the zero point, the zero point is divided into three categories: 1) SS category: signal-signal zero point; 2) SN category: signal-noise zero point; 3) NN category: noise-noise zero point; Assuming that N noise simulations are performed and N time-frequency spectra are obtained, the position of zero point i in different noise simulations is defined as (t Ki , f Ki ), K = 1, 2, ..., N, for each zero point i, calculate the position change d of the zero point in different noise simulations i : in Together they represent the average position of zero point i in the Nth noise simulation, taking δ SS and δ NN is the position change d i The threshold value, δ SS is the right offset value of the first peak of the signal-signal zero position change, δ NN To cover the left offset value of the second peak of the noise-noise zero point position change, the zero point classification rule is: SS class = {i|d i ≤δ SS }, NN class={i|d i ≥δ NN } and SN class = {i|δ SS ≤d i ≤δ NN }.

5. The wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization according to claim 4 is characterized in that: The value of the adjustment factor k0 is 2.

5.

6. The wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization according to claim 4 is characterized in that: The method obtains an estimate of the signal domain in the time-frequency plane, reconstructs the vibration signal in the signal domain estimate using an inverse short-time Fourier transform, and obtains an estimate of the noise-free vibration signal. Specifically, after completing the zero point classification, SS-type and SN-type zero points are selected on the time-frequency plane for Delaunay triangulation. The distribution of the zero points and the collective characteristics of the corresponding triangles are used to identify the signal domain. The side length l of the triangulation ij The calculation formula is: i, j represent two different zero points, (t i , f i ) and (t j , f j ) are the positions of the two zero points respectively; the weight factor ω is introduced ij Make the triangulation take into account both the density and geometric distance of the zero points, Where ρ(t, f) is the local density of zero points in the time-frequency plane, and the weighted length l′ of each edge of the triangulation is obtained by the weight factor ij , l′ ij =ω ij ·l ij , dynamically adjust the effective length of each edge; for each triangulated triangle, if the weighted length of any edge is greater than the preset edge length threshold l max , the triangle is considered to belong to the signal domain; the side length is greater than the side length threshold l max The triangles are gathered together to obtain an estimate of the signal domain in the time-frequency plane: Based on the obtained signal domain estimation in the time-frequency plane, the signal in the signal domain is reconstructed using the inverse short-time Fourier transform to calculate the estimated value of the noise-free signal 7. A wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization according to claim 6, characterized in that: The content of step S3 is: S31, expectation step: calculate the expected value of the vibration signal, and express the estimated value of the noise-free signal with multiple components as: A k (t) is the instantaneous amplitude of the kth component, φ k (t) is the instantaneous phase, n(t) is the noise; Monte Carlo sampling is then used to estimate the posterior distribution and generate M samples θ from the prior distribution. (i) , where the superscript i represents different moments, assuming that the observed signal is independent at each time point t, for each sample θ (i) , calculate an estimate of the noise-free signal The likelihood function value of Then calculate the weight of each sample Then use the weighted average method to estimate the expected value of the posterior distribution: S32, maximization step: obtaining the expected value that meets the actual vibration signal characteristics After that, the estimated values ​​of instantaneous frequency and amplitude need to be updated. First, substitute the expected value of the vibration signal feature obtained above, maximize the expected log-likelihood function, and find the optimal instantaneous frequency and amplitude: where θ (t+1) Represents the parameter estimation after the t+1th iteration. The parameters of the instantaneous frequency and amplitude are updated using the result after maximizing the expectation: in is the instantaneous phase after the t+1th iteration, is the instantaneous amplitude of the k components after the tth iteration, η is the learning rate; S33. In order to ensure the stability and accuracy of parameter estimation, it is necessary to repeat the expectation step S31 and the maximization step S32 until the parameter estimation converges. The convergence condition of the parameter estimation is |θ (t+1) -θ (t) |<ε,θ (t) is the parameter estimate after the tth iteration, ε is the convergence threshold; finally, the instantaneous frequency of each signal component is extracted and the instantaneous amplitude As the input condition for the next step of order spectrum analysis.

8. The wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization according to claim 7 is characterized in that: Step S4 includes: after extracting the instantaneous frequency and instantaneous amplitude of the signal component of the vibration signal, obtaining the instantaneous frequency f(t) and f(t) of the signal feature classification and the speed feature classification. F (t), using the instantaneous frequency f(t) and f F (t) Extracting features of the variable speed signal, and realizing fault diagnosis of the wind turbine transmission chain according to the results of the variable speed signal feature extraction.

9. The wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization according to claim 8, characterized in that: Using the instantaneous frequency f(t) and f F (t) To extract the features of the variable speed signal, the order ratio analysis method is used, and the order ratio L is defined as the multiple of the speed. According to the size of the order ratio, different fault types and fault locations of the wind turbine drive chain are characterized.

10. The wind turbine transmission chain fault diagnosis method based on time-frequency plane expectation maximization according to claim 2, characterized in that: The gap between adjacent comb teeth (2.2) is greater than the sliding distance of the mass block (2) in the slide groove.

Images