A non-contact device vibration monitoring method, device, equipment and medium

Abstract

The application discloses a non-contact device vibration monitoring method and device, equipment and medium, and relates to the field of motion monitoring, comprising: acquiring video data, preprocessing the video data to obtain processed video; determining light intensity matrix information of each video frame based on the processed video, calculating the correlation degree between the light intensity matrix information corresponding to two adjacent video frames, and calculating the correlation coefficient by using the correlation degree; constructing a correlation coefficient matrix based on a search range, generating an initial correlation coefficient function by using the correlation coefficient matrix and the correlation coefficient, calculating a weight coefficient, substituting the weight coefficient into the initial correlation coefficient function to obtain a correlation coefficient function; performing coordinate calculation on the device to be monitored by using the correlation coefficient function to obtain each motion coordinate, monitoring and analyzing each motion coordinate, and realizing non-contact device vibration monitoring of the device to be monitored. The application can realize non-contact device vibration monitoring, improve the precision and efficiency of device vibration monitoring.

Description

Technical Field

[0001] This invention relates to the field of motion monitoring, and in particular to a non-contact method, device, equipment, and medium for monitoring equipment vibration. Background Technology

[0002] The motion status information of mechanical equipment plays a crucial role in various aspects of engineering. Numerous mechanical equipment safety accidents occur globally each year, causing significant casualties and property damage. Researchers have found that real-time motion status monitoring of equipment is practically feasible. Equipment motion information contains both normal operation and fault information. By analyzing and processing this fault information, researchers, combining experience and data, can identify the location and cause of equipment failures. Currently, there are many motion monitoring methods: First, a common method is to install sensors on the mechanical equipment and then transmit the measured equipment status information to a computer for analysis; second, finite element analysis also has some applications in motion monitoring, helping to identify equipment faults through modeling and analysis; simultaneously, data-driven status monitoring has also been extensively researched, most notably the digital twin method for motion status monitoring. However, the above motion monitoring methods all have some drawbacks: sensors are a contact measurement method, which is impractical in many operating conditions; second, finite element analysis can only assist in analysis and cannot achieve real-time motion status detection; finally, digital twin methods are not yet fully developed and require a large amount of data support, making implementation very difficult; and the three common optical flow methods are not suitable for diagnosing complex moving equipment. The correlation coefficient method is a powerful tool for motion tracking. It obtains motion information by calculating the correlation coefficient of the target in adjacent frames. However, the accuracy of motion information is affected by whether a suitable basis can be found to represent the relationship between motion and similarity coefficient. In general, choosing a polynomial function basis can represent simple motion, but it is very likely to cause overfitting, which is fatal for equipment fault diagnosis.

[0003] As can be seen from the above, how to achieve non-contact equipment vibration monitoring, improve the accuracy and efficiency of equipment vibration monitoring, and avoid misjudgment of actual working conditions and inaccurate calculation results are problems to be solved in this field. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a non-contact equipment vibration monitoring method, device, equipment, and medium, which can realize non-contact equipment vibration monitoring, improve the accuracy and efficiency of equipment vibration monitoring, and avoid misjudgment of actual working conditions and inaccurate calculation results. The specific solution is as follows:

[0005] In a first aspect, this application discloses a non-contact method for monitoring equipment vibration, comprising:

[0006] Acquire video data sent by a non-contact monitoring device for the device to be monitored, and preprocess the video data to obtain the processed video;

[0007] Based on the processed video, the light intensity matrix information of each video frame is determined, the correlation between the light intensity matrix information of two adjacent video frames is calculated, and the correlation coefficient is calculated using the correlation.

[0008] The search range for equipment vibration monitoring is determined, a correlation coefficient matrix is ​​constructed based on the search range, an initial correlation coefficient function is generated using the correlation coefficient matrix and the correlation coefficients, weight coefficients are calculated, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function.

[0009] The correlation coefficient function is used to calculate the coordinates of the device to be monitored, and each motion coordinate is obtained. The motion coordinates are then monitored and analyzed to achieve non-contact equipment vibration monitoring of the device to be monitored.

[0010] Optionally, the preprocessing of the video data to obtain the processed video includes:

[0011] Read the video data and trim the video data to obtain the trimmed video data;

[0012] The trimmed video data is converted to grayscale to obtain the processed video.

[0013] Optionally, calculating the correlation between the light intensity matrix information corresponding to two adjacent video frames, and calculating the correlation coefficient using the correlation, includes:

[0014] The correlation coefficient method is used to calculate the degree of correlation between the light intensity matrix information corresponding to two adjacent video frames;

[0015] The correlation coefficient is calculated using the correlation degree and the device light intensity information matrix in the light intensity matrix information.

[0016] Optionally, the step of constructing a correlation coefficient matrix based on the search range and generating an initial correlation coefficient function using the correlation coefficient matrix and the correlation coefficients includes:

[0017] The correlation coefficient matrix is ​​constructed based on all search points in the search range and their corresponding correlation coefficients.

[0018] The initial correlation coefficient function between the search point and the correlation coefficient is generated using the correlation coefficient matrix.

[0019] Optionally, the calculation of the weighting coefficients includes:

[0020] The weighting coefficients are calculated using radial basis function interpolation.

[0021] Optionally, the calculation of the weighting coefficients using radial basis function interpolation includes:

[0022] The Gaussian kernel function is used as a basis, and an interpolation function is constructed using the basis.

[0023] Calculate the inverse matrix of the basis, and use the inverse matrix to solve the interpolation function to obtain the weight coefficients.

[0024] Optionally, the step of using the correlation coefficient function to calculate the coordinates of the device under monitoring to obtain each motion coordinate includes:

[0025] Calculate the partial derivative of the correlation coefficient function to obtain the extreme value;

[0026] Calculate the coordinates of the device to be monitored corresponding to the extreme values ​​to obtain each motion coordinate.

[0027] Secondly, this application discloses a non-contact equipment vibration monitoring device, comprising:

[0028] The preprocessing module is used to acquire video data sent by the non-contact monitoring device for the device to be monitored, and to preprocess the video data to obtain the processed video.

[0029] The correlation calculation module is used to determine the light intensity matrix information of each video frame based on the processed video, calculate the correlation between the light intensity matrix information of two adjacent video frames, and use the correlation to calculate the correlation coefficient.

[0030] The function determination module is used to determine the search range for equipment vibration monitoring, construct a correlation coefficient matrix based on the search range, generate an initial correlation coefficient function using the correlation coefficient matrix and the correlation coefficients, calculate weight coefficients, and substitute the weight coefficients into the initial correlation coefficient function to obtain the correlation coefficient function.

[0031] The monitoring and analysis module is used to calculate the coordinates of the device to be monitored using the correlation coefficient function, obtain each motion coordinate, and monitor and analyze each motion coordinate to achieve non-contact equipment vibration monitoring of the device to be monitored.

[0032] Thirdly, this application discloses an electronic device, including:

[0033] Memory, used to store computer programs;

[0034] A processor is used to execute the computer program to implement the aforementioned non-contact equipment vibration monitoring method.

[0035] Fourthly, this application discloses a computer storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed non-contact equipment vibration monitoring method.

[0036] As can be seen, this application provides a non-contact equipment vibration monitoring method, including acquiring video data of the device to be monitored sent by a non-contact monitoring device, preprocessing the video data to obtain processed video; determining the light intensity matrix information of each video frame based on the processed video, calculating the correlation between the light intensity matrix information corresponding to two adjacent video frames, and calculating the correlation coefficient using the correlation; determining the search range for equipment vibration monitoring, constructing a correlation coefficient matrix based on the search range, generating an initial correlation coefficient function using the correlation coefficient matrix and the correlation coefficient, calculating weight coefficients, and substituting the weight coefficients into the initial correlation coefficient function to obtain the correlation coefficient function; calculating the coordinates of the device to be monitored using the correlation coefficient function to obtain each motion coordinate, and monitoring and analyzing each motion coordinate to achieve non-contact equipment vibration monitoring of the device to be monitored. This application achieves non-contact equipment vibration monitoring by acquiring video data of the device under test sent by a non-contact monitoring device. Based on the video data, the light intensity matrix information of each video frame is determined, and then the correlation between the light intensity matrix information of two adjacent video frames is calculated to obtain the correlation coefficient. A correlation coefficient matrix is ​​constructed based on the search range, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function. The correlation coefficient function is then used to calculate the coordinates of the device under test to obtain the motion coordinates, thereby improving the accuracy and efficiency of equipment vibration monitoring and avoiding misjudgment of actual working conditions and inaccurate calculation results. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0038] Figure 1 This is a flowchart of a non-contact equipment vibration monitoring method disclosed in this application;

[0039] Figure 2 This is an example diagram of two consecutive video frames disclosed in this application;

[0040] Figure 3 This is a flowchart of a non-contact equipment vibration monitoring method disclosed in this application;

[0041] Figure 4 This is a flowchart illustrating a non-contact equipment vibration monitoring method disclosed in this application.

[0042] Figure 5 This is a schematic diagram of the structure of a non-contact equipment vibration monitoring device disclosed in this application;

[0043] Figure 6 This application provides a structural diagram of an electronic device. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] The motion status information of mechanical equipment plays a crucial role in various aspects of engineering. Numerous mechanical equipment safety accidents occur globally each year, causing significant casualties and property damage. Researchers have found that real-time motion status monitoring of equipment is practically feasible. Equipment motion information contains both normal operation and fault information. By analyzing and processing this fault information, researchers, combining experience and data, can identify the location and cause of equipment failures. Currently, there are many motion monitoring methods: First, a common method is to install sensors on the mechanical equipment and then transmit the measured equipment status information to a computer for analysis; second, finite element analysis also has some applications in motion monitoring, helping to identify equipment faults through modeling and analysis; simultaneously, data-driven status monitoring has also been extensively researched, most notably the digital twin method for motion status monitoring. However, the above motion monitoring methods all have some drawbacks: sensors are a contact measurement method, which is impractical in many operating conditions; second, finite element analysis can only assist in analysis and cannot achieve real-time motion status detection; finally, digital twin methods are not yet fully developed and require a large amount of data support, making implementation very difficult; and the three common optical flow methods are not suitable for diagnosing complex moving equipment. The correlation coefficient method is a powerful tool for motion tracking. It obtains motion information by calculating the correlation coefficient of a target in adjacent frames. However, the accuracy of this method depends on finding a suitable basis to represent the relationship between motion and similarity coefficients. While polynomial function bases can typically represent simple motions, they are highly susceptible to overfitting, which is detrimental to equipment fault diagnosis. Therefore, achieving non-contact equipment vibration monitoring, improving its accuracy and efficiency, and avoiding misjudgments of actual operating conditions and inaccurate calculation results are problems that need to be solved in this field.

[0046] See Figure 1 As shown in the figure, an embodiment of the present invention discloses a non-contact equipment vibration monitoring method, which may specifically include:

[0047] Step S11: Obtain video data sent by the non-contact monitoring device for the device to be monitored, and preprocess the video data to obtain the processed video.

[0048] Step S12: Determine the light intensity matrix information of each video frame based on the processed video, calculate the correlation between the light intensity matrix information corresponding to two adjacent video frames, and calculate the correlation coefficient using the correlation.

[0049] In this embodiment, the light intensity matrix information of each video frame is determined based on the processed video, the correlation coefficient method is used to calculate the correlation degree between the light intensity matrix information corresponding to two adjacent video frames, and the correlation coefficient is calculated using the correlation degree and the device light intensity information matrix in the light intensity matrix information.

[0050] Understandably, the correlation coefficient is a commonly used metric to measure the degree of correlation between two sets of data. Each video frame is composed of numerous pixels, and a video is obtained by continuously playing these video frames at a certain frame rate. In a computer, each video frame can be represented as a specific light intensity matrix, and the device information in the video is also part of the light intensity matrix. Suppose there are two video frames, Frame I and Frame II, as follows... Figure 2 As shown, matrices A and B represent the light intensity matrix information of two video frames. Therefore, the correlation coefficient method can be used to represent the correlation between matrices A and B, that is, the correlation between Frame I and Frame II, as shown in the formula:

[0051]

[0052] Where A(i,j) represents the light intensity in the i-th row and j-th column of matrix A. Let B(i,j) represent the mean light intensity of matrix A and B(i,j). Similarly, the similarity coefficient ranges from [0, 1].

[0053] The purpose of motion tracking is to obtain the device's motion information, including vibration information; however, device information is only a portion of the information contained in video frames. Typically, the shape and size of the device do not change abruptly. Therefore, to improve tracking performance and save computational resources, the correlation coefficient can be calculated within a reasonable range, which must encompass the device information, as shown in the formula:

[0054] F = Corr(A(l*h), B(l*h));

[0055] Where A(l*h) represents the device light intensity information matrix with length 1 and width h in Frame I, and B(l*h) is similarly represented. F is the correlation coefficient between A(l*h) and B(l*h).

[0056] Step S13: Determine the search range for equipment vibration monitoring, construct a correlation coefficient matrix based on the search range, generate an initial correlation coefficient function using the correlation coefficient matrix and the correlation coefficients, calculate the weight coefficients, and substitute the weight coefficients into the initial correlation coefficient function to obtain the correlation coefficient function.

[0057] In this embodiment, the search range for equipment vibration monitoring is determined, the correlation coefficient matrix is ​​constructed based on all search points in the search range and the corresponding correlation coefficients, the initial correlation coefficient function between the search points and the correlation coefficients is generated using the correlation coefficient matrix, the weight coefficients are calculated, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function.

[0058] Specifically, the weight coefficients are calculated using radial basis function interpolation. A Gaussian kernel function is used as the basis, and an interpolation function is constructed using the basis. The inverse matrix of the basis is calculated, and the interpolation function is solved using the inverse matrix to obtain the weight coefficients.

[0059] In this embodiment, the previous step calculated the correlation coefficients at the same positions in matrices A and B, but the device positions change over time. When the correlation coefficient calculation range is fixed, the search range determines the accuracy of the subsequent similarity function. Typically, the location of A(l*h) is defined as the origin, and the search range is the surrounding rectangular area. Because each point in the search range corresponds to a correlation coefficient, the correlation coefficients corresponding to all points in the search range constitute a correlation coefficient matrix, satisfying the following formula:

[0060]

[0061] Here, 2x*2y is the search range, F(-x, y) is the correlation coefficient of A(l*h) and B(l*h) with coordinates (-x, y), and the same applies to other points. Corrmatrix represents the correlation coefficient matrix.

[0062] After obtaining the correlation coefficient matrix, the relationship between each correlation coefficient and the search point can be expressed as a correlation coefficient function. Obviously, this function is a bivariate function, and the formula is as follows:

[0063] F = Function(x, y);

[0064] Here, F represents the correlation coefficient corresponding to coordinates (x, y), and Function(x, y) denotes the correlation coefficient function. The quality of the correlation coefficient function determines the effectiveness of motion tracking; therefore, choosing a suitable basis to represent the function is crucial. This application selects a superior interpolation method—RBF (Radial Basis Function Interpolation): using a Gaussian kernel function. Using the intermediate value σ = 0.5 as the basis, this basis has excellent expressive power and adaptability, making it more suitable for practical engineering. For ease of understanding, the following explanation will use univariate radial basis function interpolation:

[0065] Suppose there is an interpolation point, list the interpolation function, which satisfies the following formula:

[0066]

[0067] Where, ω i For the weighting coefficients, ||xx i ||For x and x i The absolute value of the difference.

[0068] Substitute the known N interpolation points into the interpolation function F(x), and let y = F(x). The following formula can be obtained:

[0069]

[0070] in, express express express ω is the weighting coefficient, and y is the function value.

[0071] Based on the above formula, the coefficients ω of the interpolation function F(x) can be solved using the inverse matrix, as shown in the following formula: in, express The inverse of a matrix.

[0072] As can be seen from the above formula, the RBF function does not suffer from the error problem caused by solving the function coefficients using the least squares method. This step ensures the accuracy of the RBF correlation coefficient method. Furthermore, because the radial basis function itself has a local property—that is, the function value is mainly determined by the neighborhood points, and other points further away have a smaller impact on the function value—this property guarantees the robustness of the RBF correlation coefficient method.

[0073] After obtaining the weight coefficient ω, substitute it into the formula. Thus, the interpolation function can be obtained:

[0074]

[0075] The correlation coefficient function for bivariate radial basis functions is similar to that for univariate functions. Here, we first list the correlation coefficient function, as shown in the formula below:

[0076]

[0077] Where F(x, y) is the corresponding correlation coefficient, ||(x, y)-(x i y i )|| represents the points (x, y) and (x... i y iThe Euclidean distance is calculated as follows:

[0078]

[0079] Finally, following the process of a univariate radial basis function, the N coordinates (x... i y i , z i Substituting i∈[1,N] into the correlation coefficient function, we obtain the interpolation matrix and calculate the weight coefficient ω. Substituting ω into the matrix, we can obtain the correlation coefficient function F(x,y), as shown in the following formula:

[0080]

[0081] Step S14: Calculate the coordinates of the device to be monitored using the correlation coefficient function to obtain each motion coordinate, and monitor and analyze each motion coordinate to achieve non-contact equipment vibration monitoring of the device to be monitored.

[0082] In this embodiment, video data of the device to be monitored sent by a non-contact monitoring device is acquired, and the video data is preprocessed to obtain a processed video. Based on the processed video, the light intensity matrix information of each video frame is determined, and the correlation between the light intensity matrix information corresponding to two adjacent video frames is calculated. The correlation coefficient is calculated using the correlation coefficient. The search range for device vibration monitoring is determined, and a correlation coefficient matrix is ​​constructed based on the search range. An initial correlation coefficient function is generated using the correlation coefficient matrix and the correlation coefficients. Weight coefficients are calculated, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function. The coordinates of the device to be monitored are calculated using the correlation coefficient function to obtain each motion coordinate. Each motion coordinate is monitored and analyzed to achieve non-contact device vibration monitoring of the device to be monitored. This application achieves non-contact equipment vibration monitoring by acquiring video data of the device under test sent by a non-contact monitoring device. Based on the video data, the light intensity matrix information of each video frame is determined, and then the correlation between the light intensity matrix information of two adjacent video frames is calculated to obtain the correlation coefficient. A correlation coefficient matrix is ​​constructed based on the search range, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function. The correlation coefficient function is then used to calculate the coordinates of the device under test to obtain the motion coordinates, thereby improving the accuracy and efficiency of equipment vibration monitoring and avoiding misjudgment of actual working conditions and inaccurate calculation results.

[0083] See Figure 3 As shown in the figure, an embodiment of the present invention discloses a non-contact equipment vibration monitoring method, which may specifically include:

[0084] Step S21: Obtain video data sent by the non-contact monitoring device for the device to be monitored, read the video data, trim the video data to obtain trimmed video data, and perform grayscale operation on the trimmed video data to obtain the processed video.

[0085] Step S22: Determine the light intensity matrix information of each video frame based on the processed video, calculate the correlation between the light intensity matrix information corresponding to two adjacent video frames, and calculate the correlation coefficient using the correlation.

[0086] Step S23: Determine the search range for equipment vibration monitoring, construct a correlation coefficient matrix based on the search range, generate an initial correlation coefficient function using the correlation coefficient matrix and the correlation coefficients, calculate the weight coefficients, and substitute the weight coefficients into the initial correlation coefficient function to obtain the correlation coefficient function.

[0087] Step S24: Calculate the partial derivative of the correlation coefficient function to obtain the extreme value, calculate the coordinates of the device to be monitored corresponding to the extreme value to obtain each motion coordinate, and perform monitoring and analysis on each motion coordinate to realize non-contact equipment vibration monitoring of the device to be monitored.

[0088] In this embodiment, the correlation coefficient function is used to track the motion of the device under monitoring. Vibration information is essentially about determining the device's position change over time, and the correlation coefficient function represents the relationship between position and correlation coefficient. Therefore, the position corresponding to the maximum similarity is the device's current position. The maximum similarity is the extreme value of the correlation coefficient function, thus the coordinates corresponding to the extreme value of the function are obtained, and the motion tracking of the device is achieved. The solution formula is as follows:

[0089]

[0090] The specific process for this application is as follows: Figure 4As shown, (1) video data sent by the non-contact monitoring device for the device to be monitored is obtained; (2) the video data is preprocessed, namely, read, trim and grayscale, to obtain the processed video; (3) the light intensity matrix information of each video frame is determined based on the processed video, the correlation degree between the light intensity matrix information of two adjacent video frames is calculated, the correlation coefficient is calculated using the correlation degree, the search range of device vibration monitoring is determined, and the correlation coefficient matrix is ​​constructed based on the search range; (4) the initial correlation coefficient function is generated using the correlation coefficient matrix and the correlation coefficient, the weight coefficient is calculated, and the weight coefficient is substituted into the initial correlation coefficient function to obtain the correlation coefficient function; (5) the coordinates of the device to be monitored are calculated using the correlation coefficient function to obtain each motion coordinate, and each motion coordinate is monitored and analyzed to realize non-contact device vibration monitoring of the device to be monitored. This application proposes an RBF-correlation coefficient method with superior tracking performance by combining the RBF and correlation coefficient methods. Using this algorithm, motion tracking can obtain vibration information of equipment accurately and efficiently. In the correlation coefficient method, the radial basis function is used as the basis to calculate the correlation coefficient function. The obtained vibration information is accurate and the calculation is simple, thereby realizing non-contact equipment vibration monitoring and improving the accuracy and efficiency of equipment vibration monitoring, avoiding misjudgment of actual working conditions and inaccurate calculation results.

[0091] In this embodiment, video data of the device to be monitored sent by a non-contact monitoring device is acquired, and the video data is preprocessed to obtain a processed video. Based on the processed video, the light intensity matrix information of each video frame is determined, and the correlation between the light intensity matrix information corresponding to two adjacent video frames is calculated. The correlation coefficient is calculated using the correlation coefficient. The search range for device vibration monitoring is determined, and a correlation coefficient matrix is ​​constructed based on the search range. An initial correlation coefficient function is generated using the correlation coefficient matrix and the correlation coefficients. Weight coefficients are calculated, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function. The coordinates of the device to be monitored are calculated using the correlation coefficient function to obtain each motion coordinate. Each motion coordinate is monitored and analyzed to achieve non-contact device vibration monitoring of the device to be monitored. This application achieves non-contact equipment vibration monitoring by acquiring video data of the device under test sent by a non-contact monitoring device. Based on the video data, the light intensity matrix information of each video frame is determined, and then the correlation between the light intensity matrix information of two adjacent video frames is calculated to obtain the correlation coefficient. A correlation coefficient matrix is ​​constructed based on the search range, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function. The correlation coefficient function is then used to calculate the coordinates of the device under test to obtain the motion coordinates, thereby improving the accuracy and efficiency of equipment vibration monitoring and avoiding misjudgment of actual working conditions and inaccurate calculation results.

[0092] See Figure 5 As shown, this embodiment of the invention discloses a non-contact equipment vibration monitoring device, which may specifically include:

[0093] The preprocessing module 11 is used to acquire video data sent by the non-contact monitoring device for the device to be monitored, and to preprocess the video data to obtain the processed video.

[0094] The correlation calculation module 12 is used to determine the light intensity matrix information of each video frame based on the processed video, calculate the correlation between the light intensity matrix information corresponding to two adjacent video frames, and calculate the correlation coefficient using the correlation.

[0095] The function determination module 13 is used to determine the search range for equipment vibration monitoring, construct a correlation coefficient matrix based on the search range, generate an initial correlation coefficient function using the correlation coefficient matrix and the correlation coefficients, calculate weight coefficients, and substitute the weight coefficients into the initial correlation coefficient function to obtain the correlation coefficient function.

[0096] The monitoring and analysis module 14 is used to calculate the coordinates of the device to be monitored using the correlation coefficient function, obtain each motion coordinate, and monitor and analyze each motion coordinate to realize non-contact equipment vibration monitoring of the device to be monitored.

[0097] In this embodiment, video data of the device to be monitored sent by a non-contact monitoring device is acquired, and the video data is preprocessed to obtain a processed video. Based on the processed video, the light intensity matrix information of each video frame is determined, and the correlation between the light intensity matrix information corresponding to two adjacent video frames is calculated. The correlation coefficient is calculated using the correlation coefficient. The search range for device vibration monitoring is determined, and a correlation coefficient matrix is ​​constructed based on the search range. An initial correlation coefficient function is generated using the correlation coefficient matrix and the correlation coefficients. Weight coefficients are calculated, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function. The coordinates of the device to be monitored are calculated using the correlation coefficient function to obtain each motion coordinate. Each motion coordinate is monitored and analyzed to achieve non-contact device vibration monitoring of the device to be monitored. This application achieves non-contact equipment vibration monitoring by acquiring video data of the device under test sent by a non-contact monitoring device. Based on the video data, the light intensity matrix information of each video frame is determined, and then the correlation between the light intensity matrix information of two adjacent video frames is calculated to obtain the correlation coefficient. A correlation coefficient matrix is ​​constructed based on the search range, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function. The correlation coefficient function is then used to calculate the coordinates of the device under test to obtain the motion coordinates, thereby improving the accuracy and efficiency of equipment vibration monitoring and avoiding misjudgment of actual working conditions and inaccurate calculation results.

[0098] In some specific embodiments, the preprocessing module 11 may specifically include:

[0099] A trimming module is used to read the video data and trim the video data to obtain trimmed video data;

[0100] The grayscale module is used to perform grayscale operations on the trimmed video data to obtain the processed video.

[0101] In some specific embodiments, the relevance calculation module 12 may specifically include:

[0102] The correlation calculation module is used to calculate the correlation between the light intensity matrix information corresponding to two adjacent video frames using the correlation coefficient method.

[0103] The correlation coefficient calculation module is used to calculate the correlation coefficient using the correlation degree and the device light intensity information matrix in the light intensity matrix information.

[0104] In some specific embodiments, the function determination module 13 may specifically include:

[0105] The correlation coefficient matrix construction module is used to construct the correlation coefficient matrix based on all search points in the search range and the corresponding correlation coefficients.

[0106] An initial correlation coefficient function generation module is used to generate the initial correlation coefficient function between the search point and the correlation coefficient using the correlation coefficient matrix.

[0107] In some specific embodiments, the function determination module 13 may specifically include:

[0108] The weight coefficient calculation module is used to calculate the weight coefficients using the radial basis function interpolation method.

[0109] In some specific embodiments, the function determination module 13 may specifically include:

[0110] An interpolation function construction module is used to construct an interpolation function using a Gaussian kernel function as a basis.

[0111] The interpolation function solving module is used to calculate the inverse matrix of the basis and use the inverse matrix to solve the interpolation function to obtain the weight coefficients.

[0112] In some specific embodiments, the monitoring and analysis module 14 may specifically include:

[0113] An extremum calculation module is used to calculate the partial derivative of the correlation coefficient function to obtain the extremum;

[0114] The coordinate calculation module is used to calculate the coordinates of the device to be monitored corresponding to the extreme value, so as to obtain each motion coordinate.

[0115] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the non-contact device vibration monitoring method performed by the electronic device disclosed in any of the foregoing embodiments.

[0116] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0117] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0118] The operating system 221 manages and controls the various hardware devices on the electronic device 20 and the computer program 222 to enable the processor 21 to perform calculations and processing on the data 223 in the memory 22. The operating system can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the non-contact device vibration monitoring method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the non-contact device vibration monitoring device from external devices, as well as data collected by its own input / output interface 25.

[0119] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0120] Furthermore, embodiments of this application also disclose a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, it implements the steps of the non-contact equipment vibration monitoring method disclosed in any of the foregoing embodiments.

[0121] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0122] The present invention provides a detailed description of a non-contact equipment vibration monitoring method, apparatus, device, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A non-contact method for monitoring equipment vibration, characterized in that, include: Acquire video data sent by a non-contact monitoring device for the device to be monitored, and preprocess the video data to obtain the processed video; Based on the processed video, the light intensity matrix information of each video frame is determined, the correlation between the light intensity matrix information of two adjacent video frames is calculated, and the correlation coefficient is calculated using the correlation. The search range for equipment vibration monitoring is determined, a correlation coefficient matrix is ​​constructed based on the search range, an initial correlation coefficient function is generated using the correlation coefficient matrix and the correlation coefficients, weight coefficients are calculated, and the weight coefficients are substituted into the initial correlation coefficient function to obtain the correlation coefficient function. The correlation coefficient function is used to calculate the coordinates of the device to be monitored, and each motion coordinate is obtained. The motion coordinates are then monitored and analyzed to achieve non-contact equipment vibration monitoring of the device to be monitored. Calculating the weighting coefficients includes: calculating the weighting coefficients using radial basis function interpolation; The weight coefficients are calculated using the radial basis function interpolation method, which includes: using the Gaussian kernel function as a basis and constructing an interpolation function using the basis; calculating the inverse matrix of the basis and solving the interpolation function using the inverse matrix to obtain the weight coefficients; The coordinates of the monitored equipment are calculated using the correlation coefficient function to obtain each motion coordinate. This includes: calculating the partial derivative of the correlation coefficient function to obtain the extreme values; and calculating the coordinates of the monitored equipment corresponding to the extreme values ​​to obtain each motion coordinate.

2. The non-contact equipment vibration monitoring method according to claim 1, characterized in that, The preprocessing of the video data to obtain the processed video includes: Read the video data and trim the video data to obtain the trimmed video data; The trimmed video data is converted to grayscale to obtain the processed video.

3. The non-contact equipment vibration monitoring method according to claim 1, characterized in that, The step of calculating the correlation between the light intensity matrix information corresponding to two adjacent video frames, and using the correlation to calculate the correlation coefficient, includes: The correlation coefficient method is used to calculate the degree of correlation between the light intensity matrix information corresponding to two adjacent video frames; The correlation coefficient is calculated using the correlation degree and the device light intensity information matrix in the light intensity matrix information.

4. The non-contact equipment vibration monitoring method according to claim 1, characterized in that, The step of constructing a correlation coefficient matrix based on the search range, and generating an initial correlation coefficient function using the correlation coefficient matrix and the correlation coefficients, includes: The correlation coefficient matrix is ​​constructed based on all search points in the search range and their corresponding correlation coefficients. The initial correlation coefficient function between the search point and the correlation coefficient is generated using the correlation coefficient matrix.

5. A non-contact equipment vibration monitoring device, characterized in that, include: The preprocessing module is used to acquire video data sent by the non-contact monitoring device for the device to be monitored, and to preprocess the video data to obtain the processed video. The correlation calculation module is used to determine the light intensity matrix information of each video frame based on the processed video, calculate the correlation between the light intensity matrix information of two adjacent video frames, and use the correlation to calculate the correlation coefficient. The function determination module is used to determine the search range for equipment vibration monitoring, construct a correlation coefficient matrix based on the search range, generate an initial correlation coefficient function using the correlation coefficient matrix and the correlation coefficients, calculate weight coefficients, and substitute the weight coefficients into the initial correlation coefficient function to obtain the correlation coefficient function. The monitoring and analysis module is used to calculate the coordinates of the device to be monitored using the correlation coefficient function, obtain each motion coordinate, and monitor and analyze each motion coordinate to realize non-contact equipment vibration monitoring of the device to be monitored. Calculating the weighting coefficients includes: calculating the weighting coefficients using radial basis function interpolation; The weight coefficients are calculated using the radial basis function interpolation method, which includes: using the Gaussian kernel function as a basis and constructing an interpolation function using the basis; calculating the inverse matrix of the basis and solving the interpolation function using the inverse matrix to obtain the weight coefficients; The coordinates of the monitored equipment are calculated using the correlation coefficient function to obtain each motion coordinate. This includes: calculating the partial derivative of the correlation coefficient function to obtain the extreme values; and calculating the coordinates of the monitored equipment corresponding to the extreme values ​​to obtain each motion coordinate.

6. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the non-contact equipment vibration monitoring method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when the computer program is executed by a processor, it implements the non-contact equipment vibration monitoring method as described in any one of claims 1 to 4.

Images