Wind power digital twinborn co-evolution detection method based on signal distribution characteristics

Abstract

The invention discloses a wind power digital twinning co-evolution detection method based on signal distribution characteristics. The method comprises the following steps: acquiring fan signal data generated by digital twinning and fan signal data acquired by a sensor; the two kinds of draught fan signal data are preprocessed so that the characteristic frequency amplitude error of the preprocessed draught fan signal data can be smaller than a preset threshold value; respectively interpolating the two types of preprocessed fan signal data to the original data volume; performing sequential sequence distribution conversion on the two interpolated results to obtain a sequential sequence signal distribution probability; and calculating a total difference value as a twin co-evolution detection result according to the distribution probabilities of the two time sequence signals, and outputting the result. The invention aims to verify the co-evolution degree of the digital twinborn system by comparing the signal distribution after processing the measured value and the digital twinborn value, so that the digital twinborn system can comprehensively and accurately reflect the operation state of the wind turbine generator.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital twins of wind turbine group service quality, and specifically relates to a wind power digital twin collaborative evolution detection method based on signal distribution characteristics. Background Art

[0002] With the development of the wind power industry, the number and scale of wind turbines are constantly expanding. How to effectively evaluate and improve the service quality of wind turbines has become a problem that needs to be solved. At present, digital twin technology has been applied to aerospace, manufacturing, healthcare, cities, energy and other fields. These applications and explorations have shown the great advantages of digital twin technology. The core idea of ​​digital twin 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. During the long-term operation of wind turbines, various faults may occur, affecting the efficiency of power production and causing the stability of the power grid to decrease. 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. One of the keys to digital twin technology is the "co-evolution" capability, that is, how the virtual model is updated synchronously with the real-time changes of the physical system to accurately reflect its current state. The operating characteristics of wind turbines change continuously during their life cycle, requiring the digital twin system to have strong co-evolution capabilities. Co-evolution ensures that the digital twin system can not only accurately simulate the initial state, but also continuously adjust during long-term operation, so that the virtual system and the physical system evolve synchronously and reflect subtle changes in actual operation.

[0003] In order to ensure this co-evolution, the digital twin system relies on high-quality sensor data input and a high-precision model update mechanism. During the data transmission process, the data collected by the sensors is often large in scale and diverse in variety. How to effectively process and evaluate the quality of these real-time data to ensure that the digital twin model can be adjusted in real time is the focus of current research. Through the precise verification of co-evolution, the overall performance of the digital twin system can be improved, enabling it to more accurately reflect the operating status of wind turbines. Summary of the invention

[0004] Technical problem to be solved by the present invention: In view of the above-mentioned problems of the prior art, a wind power digital twin co-evolution detection method based on signal distribution characteristics is provided. The present invention aims to verify the degree of co-evolution of the digital twin system by comparing the signal distribution after measurement values ​​and digital twin value processing, so that the digital twin system can comprehensively and accurately reflect the operating status of the wind turbine.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A wind power digital twin collaborative evolution detection method based on signal distribution characteristics, comprising: S1, obtaining fan signal data generated by the digital twin and fan signal data collected by the sensor, wherein the fan signal data is one of temperature, radial vibration, axial vibration, voltage, current and power of the fan; S2, preprocessing the two types of fan signal data respectively so that the characteristic frequency amplitude error of the preprocessed fan signal data is less than a preset threshold; S3, interpolating the two pre-processed fan signal data to the original data volume respectively; S4, respectively converting the two interpolation results into time series distribution to obtain the time series signal distribution probability; S5, calculate the overall difference value according to the distribution probability of the two time series signals as the output of the twin co-evolution detection result.

[0006] Optionally, step S4 includes: dividing the fan signal data between the maximum value and the minimum value into M regions, and calculating the distribution probability of the time series signal in any mth region according to the following formula: , In the above formula, is the distribution probability of the time series signal in the mth region, is the total number of data points in the mth region, is the total number of data points of the entire fan signal data.

[0007] Optionally, the function expression for calculating the overall difference value in step S5 is: , In the above formula, is the overall difference value, M is the number of regions where the fan signal data is divided between the maximum value and the minimum value, The probability distribution of the time series signal of the wind turbine signal data generated for the digital twin is The data share of each region, The distribution probability data of the time series signal corresponding to the fan signal data collected by the sensor is in the The data percentage of each district.

[0008] Optionally, the calculation function expression of the characteristic frequency amplitude error in step S2 is:

[0009] In the above formula, is the characteristic frequency amplitude error, is the characteristic frequency amplitude of the preprocessed fan signal data, is the characteristic frequency amplitude of the original fan signal data.

[0010] Optionally, step S2 includes: S2.1, set the initial door width of the revolving door algorithm SDA; S2.2, using the revolving door algorithm SDA to process the two types of fan signal data respectively; S2.3, convert the two types of fan signal data into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the original fan signal data, convert the data processed in step S2.2 into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the preprocessed fan signal data, calculate the characteristic frequency amplitude errors of the two types of preprocessed fan signal data according to the characteristic frequency amplitude of the preprocessed fan signal data and the characteristic frequency amplitude of the original fan signal data, if both characteristic frequency amplitude errors are less than the preset threshold, jump to step S2.4; otherwise, update the door width of the revolving door algorithm SDA and jump to step S2.2.

[0011] Optionally, after using the revolving door algorithm SDA to process the two types of fan vibration signal data respectively in step S2.2, it also includes using an abnormal algorithm to process the two types of fan vibration signal data respectively, including for each current data point, based on a given abnormal parameter The length of the current data point is formed above and below 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.

[0012] Optionally, after using the revolving door algorithm SDA to process the two types of fan vibration signal data respectively in step S2.2, it also includes using data segment merging to process the two types of fan vibration signal data 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, for the current moment; is the total time; for The amplitude of the vibration signal at the moment; for The amplitude of the vibration signal at the moment; The invention relates to a reverse trend data segment whose amplitude between two identical trends is less than a preset threshold, and uses a small-amplitude jitter data segment detection and merging to process two types of fan vibration signal data respectively, including: finding a data segment in the fan vibration signal data that continuously shows an upward and downward change within a time period, and the amplitude of the upward and downward trend segments is less than a preset threshold as a small-amplitude jitter data segment. , 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 Respectively Monotonic data segment 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, for The signal amplitude at time For a specific point The amplitude of for The signal amplitude at time The revolving door point of the revolving door algorithm SDA The signal amplitude of for the current moment; 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 The gate width parameter for the small jitter data segment is the signal amplitude at the starting point; specific point Set to the gate point of the revolving door algorithm SDA ; The signal amplitude of the current two monotonic data segments is obtained by detecting the equivalent revolving door starting point and door width parameters based on the small-amplitude jitter data segment , upper revolving door signal amplitude And the lower turnstile signal amplitude , determine the detection conditions of the revolving door algorithm Is it true? If so, merge the two monotonic data segments obtained by traversal.

[0013] In addition, the present invention also provides a wind power digital twin collaborative evolution detection system based on signal distribution characteristics, including an interconnected microprocessor and a memory, and the microprocessor is programmed or configured to execute the wind power digital twin collaborative evolution detection method based on signal distribution characteristics.

[0014] 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 collaborative evolution detection method based on signal distribution characteristics through a processor.

[0015] 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 collaborative evolution detection method based on signal distribution characteristics through a processor.

[0016] Compared with the prior art, the present invention mainly has the following advantages: the present invention includes obtaining the wind turbine signal data generated by the digital twin and the wind turbine signal data collected by the sensor; preprocessing the two types of wind turbine signal data respectively so that the characteristic frequency amplitude error of the preprocessed wind turbine signal data is less than a preset threshold; interpolating the two types of preprocessed wind turbine signal data to the original data volume respectively; performing time series distribution conversion on the two interpolated results respectively to obtain the time series signal distribution probability; calculating the overall difference value according to the two time series signal distribution probabilities as the twin co-evolution detection result output. The present invention verifies the degree of co-evolution of the digital twin system by comparing the signal distribution after the measurement value and the digital twin value processing, so that the digital twin system can comprehensively and accurately reflect the operating status of the wind turbine. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1Schematic diagram of the basic flow of the method of the embodiment of the present invention.

[0018] Figure 2 Schematic diagram of the revolving door algorithm SDA in an embodiment of the present invention.

[0019] Figure 3 Schematic diagram of an exception algorithm in an embodiment of the present invention.

[0020] Figure 4 Schematic diagram of data segment merging and wavelet dithering data segment processing in an embodiment of the present invention.

[0021] Figure 5 Schematic diagram of original vibration signal data collected in an embodiment of the present invention.

[0022] Figure 6 Schematic diagram of data volume comparison in an embodiment of the present invention.

[0023] Figure 7 : The figures are a comparison of time domain signals after amplitude error preprocessing of different characteristic frequencies in the embodiments 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%.

[0024] Figure 8 It is a schematic diagram of the process of interpolating fan signal data to the original data volume in an embodiment of the present invention.

[0025] Fig. 9 It is the fan signal data before conversion in the embodiment of the present invention.

[0026] Fig.10 is the distribution probability of the time series signal obtained by conversion in the embodiment of the present invention.

[0027] Fig.11 The figure is a comparison of the distribution probabilities of the time series signals obtained by converting the two types of wind turbine signal data in the embodiment of the present invention.

[0028] Fig.12 1 is a comparison of the distribution probability of the first group of time series signals of the axial vibration of the tower in an embodiment of the present invention.

[0029] Fig.13 1 is a comparison of the distribution probability of the second group of time series signals of the axial vibration of the tower in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] like Figure 1 As shown, the wind power digital twin collaborative evolution detection method based on signal distribution characteristics in this embodiment includes: S1, obtaining fan signal data (digital twin data) generated by the digital twin and fan signal data (collected data) collected by the sensor, where the fan signal data is one of the temperature, radial vibration, axial vibration, voltage, current and power of the fan; S2, preprocessing the two types of fan signal data respectively so that the characteristic frequency amplitude error of the preprocessed fan signal data is less than a preset threshold; S3, interpolating the two pre-processed fan signal data to the original data volume respectively; S4, respectively converting the two interpolation results into time series distribution to obtain the time series signal distribution probability; S5, calculate the overall difference value according to the distribution probability of the two time series signals as the output of the twin co-evolution detection result.

[0031] In this embodiment, the calculation function expression of the characteristic frequency amplitude error in step S2 is:

[0032] In the above formula, is the characteristic frequency amplitude error, is the characteristic frequency amplitude of the preprocessed fan signal data, is the characteristic frequency amplitude of the original fan signal data.

[0033] 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 2 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:

[0034] In the above formula, is the signal amplitude of the current detection point; is the upper revolving door signal amplitude; is the amplitude of the lower revolving door signal. Step S2 in this embodiment includes: S2.1, set the initial door width of the revolving door algorithm SDA; S2.2, using the revolving door algorithm SDA to process the two types of fan signal data respectively; S2.3, convert the two types of fan signal data into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the original fan signal data, convert the data processed in step S2.2 into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the preprocessed fan signal data, calculate the characteristic frequency amplitude errors of the two types of preprocessed fan signal data according to the characteristic frequency amplitude of the preprocessed fan signal data and the characteristic frequency amplitude of the original fan signal data, if both characteristic frequency amplitude errors are less than the preset threshold, jump to step S2.4; otherwise, update the door width of the revolving door algorithm SDA and jump to step S2.2.

[0035] As an optional implementation, in step S2.2 of this embodiment, after using the revolving door algorithm SDA to process the two types of fan vibration signal data respectively, it also includes using an abnormal algorithm to process the two types of fan vibration signal data respectively, including for each current data point, based on a given abnormal parameter The length of the current data point is formed above and below 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 3 As shown, the abnormal parameters Determines the tolerance of each data point to abnormal situations. The length of the upper and lower formations based on the current data point is 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.

[0036] 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. In step S2.2 of this embodiment, after using the revolving door algorithm SDA to process the two types of fan vibration signal data respectively, it also includes using data segment merging to process the two types of fan vibration signal data 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, for the current moment; is the total time; for The amplitude of the vibration signal at the moment; for The amplitude of the vibration signal at the moment; The reverse trend data segment whose amplitude between two identical trends is less than the preset threshold 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 4 This is a schematic diagram of data segment merging and wavelet dithering data segment processing in this embodiment. Figure 4 The data points with abscissas between 0s and 3.5s are continuous ascending slopes. During the continuous backward detection process, a downhill slope with abscissas between 3.5s and 7s is found. 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.

[0037] 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 the fan vibration signal data, find the data segments 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 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 Respectively Monotonic data segment 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, for The signal amplitude at time For a specific point The amplitude of for The signal amplitude at time The revolving door point of the revolving door algorithm SDA The signal amplitude of for the current moment; 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 The gate width parameter for the small jitter data segment is the signal amplitude at the starting point; specific point Set to the gate point of the revolving door algorithm SDA ; The signal amplitude of the current two monotonic data segments is obtained by detecting the equivalent revolving door starting point and door width parameters based on the small-amplitude jitter data segment , upper revolving door signal amplitude And the lower turnstile signal amplitude , determine the detection conditions of the revolving door algorithm Is it true? If so, merge the two monotonic data segments obtained by traversal.

[0038] In step S2.3 of this embodiment, updating the door width of the revolving door algorithm SDA means adding the door width of the revolving door algorithm SDA to the preset door width precision. For example, in this embodiment, the door width precision is 0.0001, and the expression for updating the door width of the revolving door algorithm SDA is: , in the above formula, is the gate width of the updated revolving door algorithm SDA, is the gate width of the revolving door algorithm SDA before the update, and then the gate width of the revolving door algorithm SDA after the update can be As the gate width of the new revolving door algorithm SDA Jump to step S2.2 and continue to iterate the revolving door algorithm SDA.

[0039] Figure 5 Schematic diagram of the original vibration signal data collected in this embodiment. Figure 5 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 6 Schematic diagram of data volume comparison in this embodiment. Figure 6 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 6 It can be seen that as the error increases, the data volume shows a "plateau phenomenon".

[0040] Figure 7 The figure is a 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 is preprocessed with an amplitude error of 0.3%, (c) is the time domain signal after the signal is preprocessed with an amplitude error of 2.2%, and (d) is the time domain signal after the signal is preprocessed with an amplitude error of 4.0%. Figure 7 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 door 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 Less than 0.3%.

[0041] like Figure 8 As shown, in step S3 of this embodiment, interpolating the pre-processed fan signal data to the original data volume includes: S3.1, inputting the preprocessed signal, i.e. the preprocessed fan signal data; S3.2, find the location of the missing point; S3.3, creating a complete sequence number range corresponding to the original data volume; S3.4, fill the known data into the interpolation array; S3.5, combine the interpolated data with the complete sequence number.

[0042] When the known data is filled into the interpolation array in step S3.4 of this embodiment, the interpolation array adopts cubic spline interpolation, and the following conditions need to be met: Condition 1: At each node, the spline function is equal to the value of the data point: and ; In the above formula, For the Segment spline function at the node The value at For data points at nodes The value at For the Segment spline function at the node The value at For data points at nodes The node is the data point. Before interpolation, it is the value preprocessed by the revolving door algorithm and is discontinuous. Now we use spline interpolation to complete the missing data. The spline function is composed of some polynomials, each of which is determined by two adjacent data points. Any two adjacent polynomials and their derivatives are continuous at the connection point.

[0043] Condition 2: At each internal node, the first and second order derivatives of the spline are continuous: and ; In the above formula, and They are The first and second derivatives of and for The first and second derivatives of For the Segment spline function at the node The value at Condition 3: The second-order derivative is zero at the boundary: and ; In the above formula, For a function at a node The second-order derivative of The n-1th segment of the spline function at the node The second-order derivative of is the starting node of the spline, is the ending node of the spline.

[0044] The polynomial for cubic spline interpolation can be written as: , In the above formula, For the Segment spline function at the node The value of For the The constant term coefficient of the segment spline function, For the The coefficient of the first-order term of the segment spline function, For the The coefficients of the quadratic terms of the segment spline function, For the The cubic coefficients of the segment spline function, For the The starting point of the spline segment.

[0045] In this embodiment, step S4 includes: dividing the fan signal data between the maximum value and the minimum value into M regions, and calculating the distribution probability of the time series signal in any mth region according to the following formula: , In the above formula, is the distribution probability of the time series signal in the mth region, is the total number of data points in the mth region, is the total number of data points of the entire fan signal data. In this embodiment, the fan signal data before conversion in step S4 is as follows Fig. 9 As shown, the distribution probability of the converted time series signal is as follows Fig.10 shown. Fig.11 The following is a comparison of the distribution probability of the time series signals obtained by converting the two types of wind turbine signal data in the embodiment of the present invention. Figures 9 to 11 It can be seen that the method of this embodiment can greatly reduce the amount of data processing, and is particularly suitable for fan signal data of a digital twin system with a high sampling rate.

[0046] In this embodiment, the function expression for calculating the overall difference value in step S5 is: , In the above formula, is the overall difference value, M is the number of regions where the fan signal data is divided between the maximum value and the minimum value, The probability distribution of the time series signal of the wind turbine signal data generated for the digital twin is The data share of each region, The distribution probability data of the time series signal corresponding to the fan signal data collected by the sensor is in the The data proportion of each area. The overall difference value TD can effectively quantify the performance data of the wind power digital twin co-evolution. For example, in this embodiment, the axial vibration of the tower is used as the wind turbine detection data, and the time series signal distribution probability comparison is obtained for the wind turbine signal data (digital twin data) generated by the two groups of digital twins and the wind turbine signal data (collected data) collected by the sensor. Fig.12 and Fig.13 As shown, for Fig.12The first set of data, the calculated overall difference value TD is 0.0000. Fig.13 For the second set of data, the calculated overall difference value TD is 0.0750.

[0047] In summary, the wind power digital twin collaborative evolution detection method based on signal distribution characteristics of this embodiment includes obtaining the wind turbine signal data generated by the digital twin and the wind turbine signal data collected by the sensor; preprocessing the two wind turbine signal data respectively so that the characteristic frequency amplitude error of the preprocessed wind turbine signal data is less than the preset threshold; interpolating the two preprocessed wind turbine signal data to the original data volume respectively; performing time series distribution conversion on the two interpolated results respectively to obtain the time series signal distribution probability; calculating the overall difference value according to the two time series signal distribution probabilities as the twin collaborative evolution detection result output, and the method of this embodiment compares the time series signal distribution probabilities obtained by converting the two wind turbine signal data. It can greatly reduce the amount of data processing, especially suitable for wind turbine signal data of digital twin systems with high sampling rates, and verifies the degree of collaborative evolution of the digital twin system by comparing the signal distribution after the measurement value and the digital twin value processing, so that the digital twin system can comprehensively and accurately reflect the operating status of the wind turbine.

[0048] In addition, this embodiment also provides a wind power digital twin collaborative evolution detection system based on signal distribution characteristics, including an interconnected microprocessor and a memory, and the microprocessor is programmed or configured to execute the wind power digital twin collaborative evolution detection method based on signal distribution characteristics.

[0049] In addition, this embodiment also provides a computer-readable storage medium, which stores a computer program or instructions, and the computer program or instructions are programmed or configured to execute the wind power digital twin collaborative evolution detection method based on signal distribution characteristics through a processor.

[0050] 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 collaborative evolution detection method based on signal distribution characteristics through a processor.

[0051] Those skilled in the art should understand 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 take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take 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 1 These 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.

[0052] 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 collaborative evolution detection method based on signal distribution characteristics, characterized in that: include: S1, obtaining fan signal data generated by the digital twin and fan signal data collected by the sensor, wherein the fan signal data is one of temperature, radial vibration, axial vibration, voltage, current and power of the fan; S2, preprocessing the two types of fan signal data respectively so that the characteristic frequency amplitude error of the preprocessed fan signal data is less than a preset threshold; S3, interpolating the two pre-processed fan signal data to the original data volume respectively; S4, respectively converting the two interpolation results into time series distribution to obtain the time series signal distribution probability; S5, calculate the overall difference value according to the distribution probability of the two time series signals as the output of the twin co-evolution detection result.

2. The wind power digital twin collaborative evolution detection method based on signal distribution characteristics according to claim 1 is characterized in that: Step S4 includes: dividing the fan signal data between the maximum value and the minimum value into M regions, and calculating the distribution probability of the time series signal in any mth region according to the following formula: ， In the above formula, is the distribution probability of the time series signal in the mth region, is the total number of data points in the mth region, is the total number of data points of the entire fan signal data.

3. The wind power digital twin collaborative evolution detection method based on signal distribution characteristics according to claim 2 is characterized in that: The function expression for calculating the overall difference value in step S5 is: ， In the above formula, is the overall difference value, M is the number of regions where the fan signal data is divided between the maximum value and the minimum value, The probability distribution of the time series signal of the wind turbine signal data generated for the digital twin is The data share of each region, The distribution probability data of the time series signal corresponding to the fan signal data collected by the sensor is in the The data percentage of each district.

4. The wind power digital twin collaborative evolution detection method based on signal distribution characteristics according to claim 1 is characterized in that: The calculation function expression of the characteristic frequency amplitude error in step S2 is: In the above formula, is the characteristic frequency amplitude error, is the characteristic frequency amplitude of the preprocessed fan signal data, is the characteristic frequency amplitude of the original fan signal data.

5. The wind power digital twin collaborative evolution detection method based on signal distribution characteristics according to claim 4 is characterized in that: Step S2 includes: S2.1, set the initial door width of the revolving door algorithm SDA; S2.2, using the revolving door algorithm SDA to process the two types of fan signal data respectively; S2.3, convert the two types of fan signal data into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the original fan signal data, convert the data processed in step S2.2 into frequency domain signals through fast Fourier transform and extract the characteristic frequency amplitude of the preprocessed fan signal data, calculate the characteristic frequency amplitude errors of the two types of preprocessed fan signal data according to the characteristic frequency amplitude of the preprocessed fan signal data and the characteristic frequency amplitude of the original fan signal data, if both characteristic frequency amplitude errors are less than the preset threshold, jump to step S2.4; otherwise, update the door width of the revolving door algorithm SDA and jump to step S2.

2.

6. The wind power digital twin collaborative evolution detection method based on signal distribution characteristics according to claim 5 is characterized in that: After the revolving door algorithm SDA is used to process the two types of fan vibration signal data respectively in step S2.2, the two types of fan vibration signal data are processed respectively using an abnormal algorithm, including for each current data point, based on a given abnormal parameter The length of the current data point is formed above and below 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.

7. The wind power digital twin collaborative evolution detection method based on signal distribution characteristics according to claim 5 is characterized in that: After the revolving door algorithm SDA is used to process the two types of fan vibration signal data respectively in step S2.2, the two types of fan vibration signal data are processed respectively using data segment merging, 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, for the current moment; is the total time; for The amplitude of the vibration signal at the moment; for The amplitude of the vibration signal at the moment; The invention relates to a reverse trend data segment whose amplitude between two identical trends is less than a preset threshold, and uses a small-amplitude jitter data segment detection and merging to process two types of fan vibration signal data respectively, including: finding a data segment in the fan vibration signal data that continuously shows an upward and downward change within a time period, and the amplitude of the upward and downward trend segments is less than a preset threshold as a small-amplitude jitter data segment. , 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 Respectively Monotonic data segment 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, for The signal amplitude at time For a specific point The amplitude of for The signal amplitude at time The revolving door point of the revolving door algorithm SDA The signal amplitude of for the current moment; 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 The gate width parameter for the small jitter data segment is the signal amplitude at the starting point; specific point Set as the gate point of the revolving door algorithm SDA ; The signal amplitude of the current two monotonic data segments is obtained by detecting the equivalent revolving door starting point and door width parameters based on the small-amplitude jitter data segment , upper revolving door signal amplitude And the lower turnstile signal amplitude , determine the detection conditions of the revolving door algorithm Is it true? If so, merge the two monotonic data segments obtained by traversal.

8. A wind power digital twin collaborative evolution detection system based on signal distribution characteristics, comprising an interconnected microprocessor and a memory, characterized in that: The microprocessor is programmed or configured to execute the wind power digital twin collaborative evolution detection method based on signal distribution characteristics 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 collaborative evolution detection method based on signal distribution characteristics 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 collaborative evolution detection method based on signal distribution characteristics as described in any one of claims 1 to 7 through a processor.

Images