Wind power digital twinning robustness detection method based on time-frequency revolving door perception matching

Abstract

The invention discloses a wind power digital twinning robustness detection method based on time-frequency revolving door perception matching, and the method comprises the steps: obtaining a fan detection signal generated by digital twinning and a fan detection signal collected by a sensor, the fan detection signal being the temperature, radial vibration, axial vibration, current, voltage or power of a fan; the two kinds of fan detection signals are preprocessed through a rotating door algorithm SDA so that the characteristic frequency amplitude error of the preprocessed fan detection signals can be smaller than a preset threshold value; and respectively updating receptive fields of the corresponding convolutional neural networks based on the preprocessed fan detection signals so as to determine the number of convolutional layers of the convolutional neural networks, and outputting the difference between the number of convolutional layers of the convolutional neural networks of the two fan detection signals as a robustness detection result of digital twinning. The invention aims to improve the data processing capability, solve the problem of misdiagnosis possibly caused by spectrum deviation and aliasing and signal abrupt change when the signal stably changes, and improve the accuracy of robustness judgment.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins for the service quality of wind turbine groups, and in particular to a method for detecting robustness of wind power digital twins based on time-frequency revolving door perception matching. Background Art

[0002] In the long-term operation of wind turbines, due to the complex and changeable environment in which they are located, they often face various faults and uncertainties. These faults not only affect the production efficiency of electricity, but may also threaten the stability of the power grid. With the rapid development of the global wind power industry, the number and scale of wind turbines continue to expand. How to effectively evaluate and improve the service quality of wind turbines and ensure the long-term stable operation of wind farms has become an important technical problem that needs to be solved urgently. The core idea of ​​digital twins is to make full use of physical data and mechanisms to build ultra-fidelity virtual copies, and monitor, control and optimize the physical world through interaction and iteration between the virtual world and the physical world. The detection and verification technology of the digital twin system of the service quality of wind turbines is crucial to the reliability and performance improvement of wind turbines. It can predict faults, optimize operation, diagnose problems, and provide intelligent management to improve the reliability and performance of wind turbines, reduce downtime and maintenance costs, and ultimately achieve more efficient wind energy utilization. However, in actual applications, the operating environment of wind turbines is extremely complex, and external factors such as wind speed changes, humidity, temperature, etc. will affect the performance of the unit. In addition, internal problems such as sensor accuracy attenuation and signal noise will gradually reduce the detection and diagnosis capabilities of the system. Therefore, robustness has become a key indicator in the application of digital twin technology in wind turbines. Robustness refers to the ability of a system to maintain stable performance in the face of external interference, uncertainty or internal changes. For wind turbine digital twin systems, robustness is not only reflected in its ability to adapt to the external environment, but also in its response to complex situations such as equipment aging and failure. A highly robust system can ensure that it can maintain efficient and stable performance when sensor accuracy decreases, noise interference occurs, or the state of the unit changes. Summary of the invention

[0003] Technical problem to be solved by the present invention: In view of the above-mentioned problems in the prior art, a wind power digital twin robustness detection method based on time-frequency revolving door perception matching is provided. The present invention aims to improve the data processing capability to cope with the problem that the wind power digital twin system usually adopts a high sampling rate when collecting signals to ensure the accuracy of the detection and verification system, resulting in a large amount of data. It solves the misdiagnosis caused by spectrum deviation and aliasing when the signal changes steadily and signal mutation, and improves the accuracy of robustness judgment.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0005] A wind power digital twin robustness detection method based on time-frequency revolving door perception matching, comprising:

[0006] Step S1, obtaining a fan detection signal generated by the digital twin and a fan detection signal collected by a sensor, wherein the fan detection signal is the temperature, radial vibration, axial vibration, current, voltage or power of the fan;

[0007] Step S2, preprocessing the two fan detection signals respectively by using a revolving door algorithm SDA so that the characteristic frequency amplitude error of the preprocessed fan detection signal is less than a preset threshold;

[0008] Step S3: based on the preprocessed fan detection signals, the receptive fields of the corresponding convolutional neural networks are updated respectively to determine the number of convolutional layers of the convolutional neural network, and the difference in the number of convolutional layers of the convolutional neural network between the two fan detection signals is output as the robustness detection result of the digital twin.

[0009] Optionally, the calculation function expression of the characteristic frequency amplitude error in step S2 is:

[0010]

[0011] In the above formula, e max is the characteristic frequency amplitude error, f ε,max is the characteristic frequency amplitude of the fan detection signal after preprocessing, f max is the characteristic frequency amplitude of the original fan detection signal.

[0012] Optionally, step S2 includes:

[0013] Step S2.1, setting the initial door width of the revolving door algorithm SDA;

[0014] Step S2.2, using the revolving door algorithm SDA to process the two types of fan detection signals respectively;

[0015] Step S2.3, convert the two fan detection signals into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the original fan detection signal, convert the processed in step S2.2 into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the preprocessed fan detection signal, calculate the characteristic frequency amplitude errors of the two preprocessed fan detection signals according to the characteristic frequency amplitude of the preprocessed fan detection signal and the characteristic frequency amplitude of the original fan detection signal, if both characteristic frequency amplitude errors are less than the preset threshold, jump to step S3; otherwise, update the door width of the revolving door algorithm SDA and jump to step S2.2.

[0016] Optionally, after using the revolving door algorithm SDA to process the two fan detection signals respectively in step S2.2, it also includes using an abnormal algorithm to process the two fan detection signals respectively, including for each current data point, based on a given abnormal parameter V E The length of the current data point is 2V above and below E The abnormal range of the next data point is used to determine whether an abnormality occurs in the next data point. If the next data point exceeds the abnormal range, the next data point is deleted, and the data point is reconstructed using linear interpolation based on the first two data points of the deleted data point.

[0017] Optionally, step S2.2 further includes using data segment merging to process the two types of wind turbine detection signals respectively, including detecting the climbing segment with increased data points according to the change of data points, and performing climbing segment merging according to the following formula:

[0018]

[0019] In the above formula, l is the current time; n is the total time; x l+1 is the amplitude of the vibration signal at time l+1; x l is the amplitude of the vibration signal at time l; b(l) is the reverse trend data segment between two identical trends whose amplitudes are both less than the preset threshold.

[0020] Optionally, step S2.2 also includes using small-amplitude jitter data segment detection merging to process the two fan detection signals respectively, including: finding data segments in the fan detection signal that continuously show rising and falling changes within a time period, and the amplitudes of the rising and falling trend segments are both less than a preset threshold value as small-amplitude jitter data segments; Its function expression is:

[0021]

[0022] In the above formula, are small jitter data segments , and there is any d-th monotonic data segment The function expression is:

[0023]

[0024] In the above formula, and are the dth monotonic data segment respectively The starting and ending points of each small jitter data segment The two adjacent monotonic data segments are traversed in turn, and the equivalent revolving door starting point and door width parameters of the small-amplitude jitter data segment are calculated according to the following formulas:

[0025]

[0026] In the above formula, X c t c The signal amplitude at time For a specific point The amplitude of X g t g The signal amplitude at time The revolving door point of the revolving door algorithm SDA The signal amplitude of t c is the current moment; t g It is the time for the gate; For a specific point moment; The revolving door point of the revolving door algorithm SDA moment; The lower support point of the revolving door algorithm SDA The amplitude of The upper support point of the revolving door algorithm SDA moment; The lower support point of the revolving door algorithm SDA moment; The upper support point of the revolving door algorithm SDA The amplitude of; ε' is the small jitter data segment gate width parameter X0 is the starting point signal amplitude; specific point Set to the gate point of the revolving door algorithm SDA

[0027] The signal amplitude V of the current two monotonic data segments and the upper revolving door signal amplitude V are obtained based on the equivalent revolving door starting point and door width parameter detection based on the small-amplitude jitter data segment. h And the lower turnstile signal amplitude V l , determine the detection condition V of the revolving door algorithm h <V<V l If it is true, the two monotonic data segments obtained by traversal are merged.

[0028] Optionally, in step S3, based on the preprocessed fan detection signal, the receptive fields of the corresponding convolutional neural networks are respectively updated to determine the function expression of the number of convolutional layers of the convolutional neural network:

[0029]

[0030] In the above formula, n k-PRAA is the data volume of the fan detection signal after preprocessing, τ is the related constant of different fault characteristics; n kis the amount of original signal data under different faults; ε is the gate width of the revolving door algorithm; r l is the receptive field size of the lth convolutional layer; r l-1 is the receptive field size of the l-1th convolutional layer; f l is the convolution kernel size of the lth convolution layer; s i is the step size of the i-th convolutional layer; the convolutional neural network is composed of multiple convolutional layers and pooling layers.

[0031] In addition, the present invention also provides a wind power digital twin robustness detection system based on time-frequency revolving door perception matching, comprising an interconnected microprocessor and a memory, wherein the microprocessor is programmed or configured to execute the wind power digital twin robustness detection method based on time-frequency revolving door perception matching.

[0032] In addition, the present invention also provides a computer-readable storage medium, which stores a computer program or instruction, and the computer program or instruction is programmed or configured to execute the wind power digital twin robustness detection method based on time-frequency revolving door perception matching through a processor.

[0033] In addition, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the wind power digital twin robustness detection method based on time-frequency revolving door perception matching through a processor.

[0034] Compared with the prior art, the present invention mainly has the following advantages:

[0035] 1. During the long-term operation of the wind turbine, the speed changes due to the constantly changing operating conditions, making the signals used for the evaluation of the digital twin system more complex. The change in speed will also lead to problems such as frequency modulation and spectrum blurring of vibration signals, making the evaluation of the digital twin system more difficult. In order to ensure the accuracy of the detection and verification system, the digital twin system generally uses a high sampling rate when collecting signals, resulting in a very large amount of data processing. Due to the large amount of data, the existing robustness detection and verification methods require a large amount of storage memory, which makes the evaluation process very slow. This phenomenon brings data pressure to the entire process. The present invention includes obtaining a fan detection signal generated by a digital twin and a fan detection signal collected by a sensor, wherein the fan detection signal is the temperature, radial vibration, axial vibration, current, voltage or power of the fan; the two fan detection signals are preprocessed by a revolving door algorithm SDA so that the characteristic frequency amplitude error of the preprocessed fan detection signal is less than a preset threshold; based on the preprocessed fan detection signal, the receptive fields of the corresponding convolutional neural networks are updated respectively to determine the number of convolutional layers of the convolutional neural network, and the difference in the number of convolutional layers of the convolutional neural network of the two fan detection signals is output as the robustness detection result of the digital twin. Through the above method, the problem of limited data processing capability of the existing digital twin system evaluation index algorithm can be solved, and the data processing capability can be improved to cope with the problem of large data volume caused by the high sampling rate usually adopted when collecting signals in order to ensure the accuracy of the detection and verification system of the wind power digital twin system.

[0036] 2. The amplitude and frequency of the signal change with the working state of the motor, and the characteristic frequency of the signal in the steady state is very clear. When the working conditions change steadily, the spectrum shows slight deviation and aliasing compared with the steady state. When the working conditions suddenly change, the change in the characteristic frequency of the signal is more obvious. At the same time, signal mutations may lead to misdiagnosis of normal motors. The present invention determines the number of convolutional layers of the convolutional neural network by updating the receptive fields of the corresponding convolutional neural networks based on the preprocessed fan detection signals, and outputs the difference in the number of convolutional layers of the convolutional neural network of the two fan detection signals as the robustness detection result of the digital twin. It can solve the misdiagnosis caused by spectrum deviation and aliasing when the signal changes steadily and signal mutations, thereby improving the accuracy of robustness judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Schematic diagram of the basic flow of the method of the embodiment of the present invention.

[0038] Figure 2 Schematic diagram of the basic principle of the method of the embodiment of the present invention.

[0039] Figure 3 Schematic diagram of the revolving door algorithm SDA in an embodiment of the present invention.

[0040] Figure 4 Schematic diagram of an exception algorithm in an embodiment of the present invention.

[0041] Figure 5 Schematic diagram of data segment merging and wavelet dithering data segment processing in an embodiment of the present invention.

[0042] Figure 6 ] are the time domain and frequency domain digital twin signals in the stable state and transient state in the embodiment of the present invention, where (a) is the stable state and (b) is the transient state.

[0043] Figure 7 Schematic diagram of original vibration signal data collected in an embodiment of the present invention.

[0044] Figure 8 Schematic diagram of data volume comparison in an embodiment of the present invention.

[0045] Fig. 9 : The figure is a comparison of time domain signals after amplitude error preprocessing of different characteristic frequencies in the embodiment of the present invention, wherein (a) is the time domain signal after preprocessing of the original signal, (b) is the time domain signal after preprocessing of the signal with an amplitude error of 0.3%, (c) is the time domain signal after preprocessing of the signal with an amplitude error of 2.2%, and (d) is the time domain signal after preprocessing of the signal with an amplitude error of 4.0%.

[0046] Fig.10 It is the diagnosis rate of the same data under different numbers of convolutional layers in the embodiment of the present invention. DETAILED DESCRIPTION

[0047] like Figure 1 and Figure 2 As shown, the wind power digital twin robustness detection method based on time-frequency revolving door perception matching in this embodiment includes:

[0048] Step S1, obtaining a fan detection signal generated by the digital twin and a fan detection signal collected by a sensor, wherein the fan detection signal is the temperature, radial vibration, axial vibration, current, voltage or power of the fan;

[0049] Step S2, preprocessing the two fan detection signals respectively by using a revolving door algorithm SDA so that the characteristic frequency amplitude error of the preprocessed fan detection signal is less than a preset threshold;

[0050] Step S3: based on the preprocessed fan detection signals, the receptive fields of the corresponding convolutional neural networks are updated respectively to determine the number of convolutional layers of the convolutional neural network, and the difference in the number of convolutional layers of the convolutional neural network between the two fan detection signals is output as the robustness detection result of the digital twin.

[0051] The calculation function expression of the characteristic frequency amplitude error in step S2 of this embodiment is:

[0052]

[0053] In the above formula, e max is the characteristic frequency amplitude error, f ε,max is the characteristic frequency amplitude of the fan detection signal after preprocessing, f max is the characteristic frequency amplitude of the original fan detection signal.

[0054] The revolving door algorithm SDA is an existing well-known algorithm. The revolving door algorithm SDA was originally proposed for trend fitting of signals. The principle of the revolving door algorithm SDA is as follows Figure 3 As shown in the figure, the measurement data composed of each measurement data point, the revolving door algorithm SDA selects a gate width at the starting point of each iteration process during the measurement data point retrieval process, and the subsequent data points are connected to the gate width as the upper and lower boundaries. When one of the boundaries reaches the maximum value, the boundary is fixed, and the other boundary continues to update with the change of the data point. When the two boundary lines are parallel, the current measurement data point is selected as the end point of the iteration, and a new iteration begins. For the current measurement data point, the detection method of the revolving door algorithm is as follows:

[0055] V h <V<V l ,

[0056] In the above formula, V is the signal amplitude of the current detection point; V h is the upper revolving door signal amplitude; V l is the amplitude of the lower revolving door signal. In this embodiment, step S2 includes:

[0057] Step S2.1, setting the initial door width of the revolving door algorithm SDA;

[0058] Step S2.2, using the revolving door algorithm SDA to process the two types of fan detection signals respectively;

[0059] Step S2.3, convert the two fan detection signals into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the original fan detection signal, convert the processed in step S2.2 into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the preprocessed fan detection signal, calculate the characteristic frequency amplitude errors of the two preprocessed fan detection signals according to the characteristic frequency amplitude of the preprocessed fan detection signal and the characteristic frequency amplitude of the original fan detection signal, if both characteristic frequency amplitude errors are less than the preset threshold, jump to step S3; otherwise, update the door width of the revolving door algorithm SDA and jump to step S2.2.

[0060] In step S2.2 of this embodiment, after using the revolving door algorithm SDA to process the two fan detection signals respectively, it also includes using an abnormal algorithm to process the two fan detection signals respectively, including for each current data point, based on a given abnormal parameter V E The length of the current data point is 2V above and below E The abnormal range of the next data point is used to determine whether an abnormality occurs in the next data point. If the next data point exceeds the abnormal range, the next data point is deleted, and the data point is reconstructed using linear interpolation based on the first two data points of the deleted data point. The abnormal algorithm can be used to identify the erroneous data points after the signal is preprocessed by this type of method. Figure 4 As shown, the abnormal parameter V E Determines the tolerance of each data point for abnormal conditions, based on the upper and lower lengths of the current data point being 2V E The abnormal range of the next data point is used to determine whether an abnormality occurs. As shown in the figure, at the 3-second horizontal axis, the fourth data point is outside the abnormal range of the previous point, and it is determined to be a data abnormal point and deleted. Then, based on the linear relationship of the first two data points, the data point is reconstructed using linear interpolation, and the reconstructed data point is the reconstruction point.

[0061] After obtaining the preprocessed data segments through the revolving door algorithm SDA and the anomaly algorithm, there are still some data segments with the same trend or continuous floating. For such data segments, the parameter and resolution adaptive algorithm mainly performs data segment merging and small jitter data segment processing. Step S2.2 of this embodiment also includes using data segment merging to process the two types of fan detection signals respectively, including detecting the climbing segment with increased data points according to the change of data points, and performing climbing segment merging according to the following formula:

[0062]

[0063] In the above formula, l is the current time; n is the total time; x l+1 is the amplitude of the vibration signal at time l+1; x l is the amplitude of the vibration signal at time l; b(l) is the reverse trend data segment whose amplitude between two identical trends is less than the preset threshold, which is called a bump event. The data segment merging stage mainly processes the redundant points that still exist after the revolving door algorithm is processed, and merges these points. Figure 5 As shown in the figure, the data points with abscissas between 0s and 3.5s are continuous ascending slopes. During the continuous backward detection process, it is found that the downhill slope is between 3.5s and 7s. The data point at 3.5s is set as the end point of the previous ascending slope and may also be the starting point of the next downhill slope. Similarly, the data point at 7s is also the end point of the previous slope and may be the starting point of the next slope.

[0064] In the above merging process, some unimportant slope events are still retained, that is, the rising and falling changes continue to occur within a time period, and the amplitudes of the rising and falling trend segments are not large. Such data segments are defined as small-amplitude jitter data segments. Therefore, step S2.2 of this embodiment also includes using small-amplitude jitter data segment detection merging to process the two fan detection signals respectively, including: according to finding the data segments in the fan detection signals that continue to rise and fall within a time period, and the amplitudes of the rising and falling trend segments are both less than the preset threshold, as small-amplitude jitter data segments Its function expression is:

[0065]

[0066] In the above formula, are small jitter data segments , and there is any d-th monotonic data segment The function expression is:

[0067]

[0068] In the above formula, and are the dth monotonic data segment respectively The starting and ending points of each small jitter data segment The two adjacent monotonic data segments are traversed in turn, and the equivalent revolving door starting point and door width parameters of the small-amplitude jitter data segment are calculated according to the following formulas:

[0069]

[0070]

[0071] In the above formula, X c t c The signal amplitude at time For a specific point The amplitude of X g t g The signal amplitude at time The revolving door point of the revolving door algorithm SDA The signal amplitude of t c is the current moment; t g It is the time for the gate; For a specific point moment; The revolving door point of the revolving door algorithm SDA moment; The lower support point of the revolving door algorithm SDA The amplitude of The upper support point of the revolving door algorithm SDA moment; The lower support point of the revolving door algorithm SDA moment; The upper support point of the revolving door algorithm SDA The amplitude of; ε' is the small jitter data segment gate width parameter X0 is the starting point signal amplitude; specific point Set to the gate point of the revolving door algorithm SDA

[0072] The signal amplitude V of the current two monotonic data segments and the upper revolving door signal amplitude V are obtained based on the equivalent revolving door starting point and door width parameter detection based on the small-amplitude jitter data segment. h And the lower turnstile signal amplitude V l , determine the detection condition V of the revolving door algorithm h <V<V l If it is true, the two monotonic data segments obtained by traversal are merged.

[0073] Updating the door width of the revolving door algorithm SDA in step S2.3 refers to adding the door width of the revolving door algorithm SDA to the preset door width accuracy. For example, in this embodiment, the door width accuracy is 0.0001, then the expression for updating the door width of the revolving door algorithm SDA is: ε′=ε+0.0001, in the above formula, ε′ is the door width of the revolving door algorithm SDA after update, and ε is the door width of the revolving door algorithm SDA before update. Then the door width ε′ of the updated revolving door algorithm SDA can be used as the new door width ε of the revolving door algorithm SDA to jump to step S2.2 to continue iterating the execution of the revolving door algorithm SDA.

[0074] The amplitude and frequency of the signal change with the working state of the wind turbine. Figure 6 are the digital twin signals in the time domain and frequency domain in the stable state (a) and transient state (b) in this embodiment. Figure 6As shown, the characteristic frequency of the signal in the stable state (a) is very clear. When the working conditions change smoothly, the spectrum in the transient state (b) shows slight deviation and aliasing compared with the stable state (a). When the working conditions suddenly change, the change in the characteristic frequency of the signal is more obvious. At the same time, the sudden change of the signal may lead to misdiagnosis of normal wind turbines, reducing the accuracy of the judgment of the robustness of the digital twin system. In order to solve the above technical problems, the method of this embodiment includes using step S2 to pre-process the two wind turbine detection signals respectively through the revolving door algorithm SDA so that the characteristic frequency amplitude error of the pre-processed wind turbine detection signal is less than the preset threshold; and using step S3, based on the pre-processed wind turbine detection signal, respectively update the receptive field of each corresponding convolutional neural network to determine the number of convolutional layers of the convolutional neural network, and output the difference in the number of convolutional layers of the convolutional neural network of the two wind turbine detection signals as the robustness detection result of the digital twin, so as to improve the accuracy of the judgment of the robustness of the digital twin system.

[0075] Figure 7 Schematic diagram of the original vibration signal data collected in this embodiment. Figure 7 As shown, in this embodiment, a vibration signal of 10,000 data points is selected to explore the compression of the data volume before and after processing with different signal frequency domain characteristic frequency amplitude errors. Figure 8 Schematic diagram of data volume comparison in this embodiment. Figure 8 As shown in the figure, when the characteristic frequency amplitude error begins to increase, the data volume begins to drop sharply, and when the error reaches 0.3%, the data volume does not change significantly. However, since the signal frequency domain is composed of multiple characteristic frequencies, and their amplitudes are different, when the gate width is greater than the corresponding value, the characteristic frequency of the corresponding amplitude will be processed. Figure 8 It can be seen that as the error increases, the data volume shows a "platform phenomenon". Fig. 9 The comparison of time domain signals after amplitude error preprocessing of different characteristic frequencies in the embodiment of the present invention, where (a) is the time domain signal after the original signal is preprocessed, (b) is the time domain signal after the signal with an amplitude error of 0.3%, (c) is the time domain signal after the signal with an amplitude error of 2.2%, and (d) is the time domain signal after the signal with an amplitude error of 4.0%. Fig. 9 It can be seen that with the increase of the characteristic frequency amplitude error, the vibration signal gradually becomes sparse. While reducing the noise, the fault information will continue to be lost. Therefore, considering the reduction of data volume and the retention of fault characteristics, this paper selects the frequency domain characteristic frequency amplitude error of 0.3% as the threshold for adaptive selection of the gate width. Step S2 pre-processes the two fan detection signals respectively through the revolving door algorithm SDA. The goal is to make the characteristic frequency amplitude error of the pre-processed fan detection signal e max Less than 0.3%;

[0076] In step S3, the number of convolutional layers is calculated for both the digital twin signal and the original model that meet the conditions. In step S3 of this embodiment, the receptive field of each corresponding convolutional neural network is updated based on the preprocessed fan detection signal to determine the function expression of the number of convolutional layers of the convolutional neural network:

[0077]

[0078] In the above formula, n k-PRAA is the data volume of the fan detection signal after preprocessing, τ is the related constant of different fault characteristics; n k is the amount of original signal data under different faults; ε is the gate width of the revolving door algorithm; r l is the receptive field size of the lth convolutional layer; r l-1 is the receptive field size of the l-1th convolutional layer; f l is the convolution kernel size of the lth convolution layer; s i is the step size of the i-th convolutional layer; the convolutional neural network (CNN) is composed of a plurality of convolutional layers and pooling layers.

[0079] In order to recognize through convolutional neural network, it is necessary to convert the preprocessed fan detection signal into an image. For example, after the preprocessed fan detection signal is converted into a two-dimensional image through GASF (a kind of Gram angular field GAF) or SDP (symmetric point diagram) method, the image size is n×n, where n=n k-PRAA / 2. Then, the two-dimensional image is input into the convolutional neural network, and the receptive fields of the corresponding convolutional neural networks can be updated based on the preprocessed fan detection signal to determine the number of convolutional layers of the convolutional neural network. The matching relationship between the preprocessed fan detection signal and the diagnostic perception of the convolutional neural network is obtained by combining the above convolution kernel receptive field calculation formula:

[0080]

[0081] In the above formula, the left end is the size of the two-dimensional image obtained based on the preprocessed fan detection signal; the right end is the number of layers and the size of the convolution kernel corresponding to the receptive field range of the convolutional neural network.

[0082] In order to verify the effectiveness of the robustness detection method of wind power digital twins based on time-frequency revolving door perception matching, Case Western Reserve bearing data is used in this embodiment to verify the above method. The frequency domain data of Case Western Reserve bearing data is preprocessed by the revolving door algorithm SDA, exception handling and other methods and then converted into a GASF two-dimensional image to facilitate the neural network model to identify faults. In the convolutional neural network in this embodiment, only 3×3 convolution kernels are used, and the padding and step size are set to 1. This embodiment is mainly used to verify that the missing number of convolutional layers is related to recognition ability. The structure of the neural network model is shown in Table 1.

[0083] Table 1: Neural network model results

[0084] Number of layers content 1 3x3-8 convolution kernel 2 3x3-8 convolution kernel Pooling Layer 2x2 stride 2 pooling layer 3 3x3-16 convolution kernel 4 3x3-16 convolution kernel Pooling Layer 2x2 stride 2 pooling layer 5 3x3-32 convolution kernel 6 3x3-32 convolution kernel 7 3x3-32 convolution kernel 8 3x3-32 convolution kernel Pooling Layer 2x2 stride 2 pooling layer 9 3x3-32 convolution kernel 10 3x3-32 convolution kernel 11 3x3-32 convolution kernel 12 3x3-32 convolution kernel Pooling Layer 2x2 stride 2 pooling layer 13 3x3-64 convolution kernel 14 3x3-64 convolution kernel 15 3x3-64 convolution kernel 16 3x3-64 convolution kernel Pooling Layer 2x2 stride 2 pooling layer 17 3x3-64 convolution kernel 18 3x3-64 convolution kernel 19 3x3-64 convolution kernel 20 3x3-64 convolution kernel Pooling Layer 2x2 stride 2 pooling layer Fully connected layer 32-node fully connected layer Fully connected layer 8-node fully connected layer

[0085] After the Case Western Reserve bearing data passes through the revolving door algorithm, anomaly algorithm, merged data segment algorithm, and small jitter detection algorithm, the loop termination condition is set. max <0.3%, the diagnostic rate can be obtained as shown in Table 2 and Fig.10 shown.

[0086] Table 2: e max Case Western Reserve bearing data diagnostic rate <0.3%

[0087] Number of convolutional layers 3 6 7 9 13 16 Diagnosis rate 92.0％ 96.7％ 97.0％ 98.5％ 98.0％ 96.7％

[0088] See Table 2 and Fig.10 It can be seen that the diagnosis rate of the same data of the wind power digital twin robustness detection method based on time-frequency revolving door perception matching in this embodiment is different under different numbers of convolutional layers, and the diagnosis rate is the highest when there are 9 layers.

[0089] In summary, the method of this embodiment realizes the robustness judgment of the wind turbine digital twin system through time-frequency preprocessing of the wind turbine signal, spectrum feature extraction and adaptive updating of the convolutional neural network. Specifically, it includes obtaining the wind turbine detection signal generated by the digital twin and the wind turbine detection signal collected by the sensor, and preprocessing the two wind turbine detection signals respectively through the revolving door algorithm SDA so that the characteristic frequency amplitude error of the preprocessed wind turbine detection signal is less than the preset threshold; based on the preprocessed wind turbine detection signal, the receptive field of each corresponding convolutional neural network is updated to determine the number of convolutional layers of the convolutional neural network, and the difference in the number of convolutional layers of the convolutional neural network of the two wind turbine detection signals is used as the robustness detection result of the digital twin. The above method can solve the problem of limited data processing capability of existing digital twin system evaluation index algorithms, and improve data processing capability to cope with the problem of large data volume caused by high sampling rate when collecting signals in order to ensure the accuracy of the detection and verification system of wind power digital twin systems. The method in this embodiment updates the receptive fields of the corresponding convolutional neural networks based on the preprocessed wind turbine detection signals to determine the number of convolutional layers of the convolutional neural network, and outputs the difference in the number of convolutional layers of the convolutional neural network of the two wind turbine detection signals as the robustness detection result of the digital twin. It can solve the misdiagnosis caused by spectrum deviation and aliasing when the signal changes steadily and signal mutation, and improve the accuracy of robustness judgment.

[0090] In addition, this embodiment also provides a wind power digital twin robustness detection system based on time-frequency revolving door perception matching, including an interconnected microprocessor and a memory, and the microprocessor is programmed or configured to execute the wind power digital twin robustness detection method based on time-frequency revolving door perception matching.

[0091] In addition, this embodiment also provides a computer-readable storage medium, which stores a computer program or instruction, and the computer program or instruction is programmed or configured to execute the wind power digital twin robustness detection method based on time-frequency revolving door perception matching through a processor.

[0092] In addition, this embodiment also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the wind power digital twin robustness detection method based on time-frequency revolving door perception matching through a processor.

[0093] Those skilled in the art will appreciate that the technical solutions provided by the embodiments of the present application may be in the form of methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0094] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A wind power digital twin robustness detection method based on time-frequency revolving door perception matching, characterized in that include: Step S1, obtaining a fan detection signal generated by the digital twin and a fan detection signal collected by a sensor, wherein the fan detection signal is the temperature, radial vibration, axial vibration, current, voltage or power of the fan; Step S2, preprocessing the two fan detection signals respectively by using a revolving door algorithm SDA so that the characteristic frequency amplitude error of the preprocessed fan detection signal is less than a preset threshold; Step S3: based on the preprocessed fan detection signals, the receptive fields of the corresponding convolutional neural networks are updated respectively to determine the number of convolutional layers of the convolutional neural network, and the difference in the number of convolutional layers of the convolutional neural network between the two fan detection signals is output as the robustness detection result of the digital twin.

2. According to claim 1, the wind power digital twin robustness detection method based on time-frequency revolving door perception matching is characterized in that: The calculation function expression of the characteristic frequency amplitude error in step S2 is: In the above formula, e max is the characteristic frequency amplitude error, f ε,max is the characteristic frequency amplitude of the fan detection signal after preprocessing, f max is the characteristic frequency amplitude of the original fan detection signal.

3. According to claim 1, the wind power digital twin robustness detection method based on time-frequency revolving door perception matching is characterized in that: Step S2 includes: Step S2.1, setting the initial door width of the revolving door algorithm SDA; Step S2.2, using the revolving door algorithm SDA to process the two types of fan detection signals respectively; Step S2.3, convert the two fan detection signals into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the original fan detection signal, convert the processed in step S2.2 into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the preprocessed fan detection signal, calculate the characteristic frequency amplitude errors of the two preprocessed fan detection signals according to the characteristic frequency amplitude of the preprocessed fan detection signal and the characteristic frequency amplitude of the original fan detection signal, if both characteristic frequency amplitude errors are less than the preset threshold, jump to step S3; otherwise, update the door width of the revolving door algorithm SDA and jump to step S2.

2.

4. The robustness detection method for wind power digital twin based on time-frequency revolving door perception matching according to claim 3 is characterized in that: After the revolving door algorithm SDA is used to process the two fan detection signals respectively in step S2.2, the two fan detection signals are processed respectively using an abnormal algorithm, including for each current data point, based on a given abnormal parameter V E The length of the current data point is 2V above and below E The abnormal range of the next data point is used to determine whether an abnormality occurs in the next data point. If the next data point exceeds the abnormal range, the next data point is deleted, and the data point is reconstructed using linear interpolation based on the first two data points of the deleted data point.

5. According to claim 3, the wind power digital twin robustness detection method based on time-frequency revolving door perception matching is characterized in that: Step S2.2 also includes using data segment merging to process the two types of wind turbine detection signals respectively, including detecting the climbing segment with increased data points according to the change of data points, and performing climbing segment merging according to the following formula: In the above formula, l is the current time; n is the total time; x l+1 is the amplitude of the vibration signal at time l+1; x l is the amplitude of the vibration signal at time l; b(l) is the reverse trend data segment between two identical trends whose amplitudes are both less than the preset threshold.

6. The wind power digital twin robustness detection method based on time-frequency revolving door perception matching according to claim 3 is characterized in that: Step S2.2 also includes using small-amplitude jitter data segment detection merging to process the two fan detection signals respectively, including: finding data segments in the fan detection signal that continuously show rising and falling changes within a time period, and the amplitudes of the rising and falling trend segments are both less than a preset threshold value as small-amplitude jitter data segments; Its function expression is: In the above formula, are small jitter data segments , and there is any d-th monotonic data segment The function expression is: In the above formula, and are the dth monotonic data segment respectively The starting and ending points of each small jitter data segment The two adjacent monotonic data segments are traversed in turn, and the equivalent revolving door starting point and door width parameters of the small-amplitude jitter data segment are calculated according to the following formulas: In the above formula, X c t c The signal amplitude at time For a specific point The amplitude of X g t g The signal amplitude at time The revolving door point of the revolving door algorithm SDA The signal amplitude of t c is the current moment; t g It is the time for the gate; For a specific point moment; The revolving door point of the revolving door algorithm SDA moment; The lower support point of the revolving door algorithm SDA The amplitude of The upper support point of the revolving door algorithm SDA moment; The lower support point of the revolving door algorithm SDA moment; The upper support point of the revolving door algorithm SDA The amplitude of; ε' is the small jitter data segment gate width parameter X0 is the starting point signal amplitude; specific point Set as the gate point of the revolving door algorithm SDA The signal amplitude V of the current two monotonic data segments and the upper revolving door signal amplitude V are obtained based on the equivalent revolving door starting point and door width parameter detection based on the small-amplitude jitter data segment. h And the lower turnstile signal amplitude V l , determine the detection condition V of the revolving door algorithm h <V<V l If it is true, the two monotonic data segments obtained by traversal are merged.

7. The wind power digital twin robustness detection method based on time-frequency revolving door perception matching according to claim 1 is characterized in that: In step S3, based on the preprocessed fan detection signal, the receptive fields of the corresponding convolutional neural networks are updated respectively to determine the function expression of the number of convolutional layers of the convolutional neural network: In the above formula, n k-PRAA is the data volume of the fan detection signal after preprocessing, τ is the related constant of different fault characteristics; n k is the amount of original signal data under different faults; ε is the gate width of the revolving door algorithm; r l is the receptive field size of the lth convolutional layer; r l-1 is the receptive field size of the l-1th convolutional layer; f l is the convolution kernel size of the lth convolution layer; s i is the step size of the i-th convolutional layer; the convolutional neural network is composed of multiple convolutional layers and pooling layers.

8. A wind power digital twin robustness detection system based on time-frequency revolving door perception matching, comprising an interconnected microprocessor and a memory, characterized in that: The microprocessor is programmed or configured to execute the wind power digital twin robustness detection method based on time-frequency revolving door perception matching as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program or instruction stored therein, characterized in that: The computer program or instruction is programmed or configured to execute the wind power digital twin robustness detection method based on time-frequency revolving door perception matching as described in any one of claims 1 to 7 through a processor.

10. A computer program product comprising a computer program or instructions, characterized in that The computer program or instruction is programmed or configured to execute the wind power digital twin robustness detection method based on time-frequency revolving door perception matching as described in any one of claims 1 to 7 through a processor.

Images