Equipment micro-vibration real-time monitoring method and system based on vision enhancement

Abstract

The invention discloses an equipment micro-vibration real-time monitoring method and system based on visual enhancement, and belongs to the field of equipment micro-vibration monitoring, and the method comprises the following steps: S1, collecting a high-frame-rate video, and recording collection parameters in real time; s2, constructing a Gaussian pyramid, constructing a Laplacian pyramid through adjacent layer image difference of the Gaussian pyramid, and decomposing the collected video into different spatial frequency bands; s3, designing a band-pass filter to extract a specific frequency band where the equipment vibration signal is located, and enhancing and reconstructing the micro vibration signal; s4, carrying out region selection from the enhanced image frame, calculating an optical flow in a selected region through an optical flow method, and extracting a characteristic frequency of vibration; and S5, performing data visualization, and generating a vibration signal image in real time to display the motion characteristics of the target area. According to the invention, the problems of insufficient sensitivity and poor real-time performance of small vibration detection of equipment in a traditional vibration monitoring method can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment micro-vibration monitoring, and in particular to a method and system for real-time monitoring of equipment micro-vibration based on vision enhancement. Background Art

[0002] Equipment micro-vibration monitoring is a technology used to detect and analyze the subtle vibrations generated by mechanical equipment during operation. This technology is very important in the industrial field because it can help identify the health of equipment and predict potential failures, thereby improving the reliability of equipment and extending its service life. Existing equipment micro-vibration monitoring methods include acceleration sensor measurement, laser displacement sensor measurement, eddy current sensor measurement, etc., all of which have defects and shortcomings:

[0003] 1) Acceleration sensor measurement method

[0004] Accelerometers work based on the piezoelectric effect or capacitance principle. When the device vibrates, the sensitive elements inside the sensor will produce charge changes (piezoelectric) or capacitance changes (capacitive) due to the inertial force. These changes are proportional to the acceleration of the vibration. By measuring the changes in these physical quantities, the acceleration information of the device vibration can be obtained, thereby detecting whether the vibration frequency of the device is normal.

[0005] Disadvantages: When installing the sensor, you may need to drill holes, stick or fix it with a clamp on the surface of the device. These operations will change the local mass distribution and structural stiffness of the device, which may cause new vibration modes or change the original vibration characteristics. Due to the working mode based on the piezoelectric effect or capacitance principle, the accelerometer has certain requirements for the working environment. When there are a large number of electromagnetic devices in the scene where the accelerometer is applied, these devices will generate complex electromagnetic fields. The output signal of the accelerometer may be affected by electromagnetic interference, and the electromagnetic interference is superimposed on the vibration signal, which eventually causes the measurement signal to be distorted. In a high temperature environment, the performance of the piezoelectric material may drift, resulting in deviations in the measurement results. A high humidity environment may cause the internal circuit of the sensor to become damp, affecting its electrical performance. Especially for accelerometers containing electronic components, humidity may cause problems such as short circuits, leakage or component aging.

[0006] 2) Laser displacement sensor measurement method

[0007] The laser displacement sensor emits a laser beam to the surface of the device being measured and then receives the reflected light. The distance between the device surface and the sensor is calculated based on the laser propagation time or the phase change of the reflected light. When the device vibrates, this distance will change, and the vibration information of the device can be obtained by continuously measuring the change in distance.

[0008] Disadvantages: Too high requirements on the surface of the object being measured. Objects of different materials have very different reflection and absorption characteristics for lasers. Materials with strong light absorption will absorb most of the laser beam energy, resulting in a weak reflected light signal that is difficult to measure accurately; and objects with strong reflective or mirror-reflective properties may cause the light to return vertically without forming diffuse reflection, resulting in unstable or inaccurate received signals. If the object being measured has deep grooves, complex curved surfaces or obstructions, the optical path will be blocked, causing part of the light to be unable to be reflected normally to the receiver, and thus unable to measure or the measurement results will be inaccurate. Temperature changes can cause changes in the wavelength, output power and beam quality of the laser, thereby affecting the measurement accuracy.

[0009] 3) Eddy current sensor measurement method

[0010] The eddy current sensor uses the principle of electromagnetic induction. When it is close to a metal object, the sensor coil will generate an alternating magnetic field. Eddy currents will be generated on the surface of the object, which will generate a magnetic field opposite to the original magnetic field, thereby changing the electrical parameters of the sensor coil, such as inductance and impedance. The change of these parameters is related to the change of the distance between the object and the sensor, and the vibration of the device will cause the change of this distance, and then the vibration of the device can be detected by measuring the electrical parameters.

[0011] Disadvantages: Sensitive to the material properties of the object being measured. The working principle of the eddy current sensor is based on electromagnetic induction. The electrical conductivity and magnetic permeability of the object being measured will significantly affect the sensitivity and measurement accuracy of the sensor. When the object being measured is a magnetic conductive material, the eddy current effect and the magnetic effect exist at the same time. The magnetic effect will react on the eddy current effect, weakening the eddy current effect, thereby reducing the sensitivity of the sensor. It is also very sensitive to temperature changes. The electrical conductivity and magnetic permeability of the object being measured will also change with temperature changes, which further affects the eddy current effect and the measurement accuracy of the sensor. Although the eddy current sensor itself has a certain ability to resist electromagnetic interference, in some strong electromagnetic field environments, such as near large motors, transformers and other equipment, the magnetic field may change the magnetic field distribution generated by the sensor probe, thereby affecting the generation and detection of eddy currents. Summary of the invention

[0012] The purpose of the present invention is to provide a method and system for real-time monitoring of equipment micro-vibration based on visual enhancement, so as to solve the problems of insufficient sensitivity and poor real-time performance in detecting equipment micro-vibration in traditional vibration monitoring methods.

[0013] To achieve the above object, the present invention provides a method for real-time monitoring of equipment micro-vibration based on visual enhancement, comprising the following steps:

[0014] Step S1, collecting high frame rate video, and selecting key parts of the target device as the collection area through manual calibration, and recording the collection parameters in real time, the collection parameters including frame rate, resolution and number of frames;

[0015] Step S2, constructing a Gaussian pyramid to perform layer-by-layer sampling and blurring processing on the image, constructing a Laplacian pyramid through the image differences of adjacent layers of the Gaussian pyramid, and decomposing the collected video into different spatial frequency bands;

[0016] Step S3, designing a bandpass filter to extract the specific frequency band of the device vibration signal, performing time domain bandpass filtering on the time-varying signal of each pixel point in the Laplace pyramid, and enhancing and reconstructing the micro-vibration signal;

[0017] Step S4, selecting a region from the enhanced image frame, calculating the optical flow in the selected region by the Farneback optical flow method in OpenCV, and extracting the characteristic frequency of the vibration;

[0018] Step S5, data visualization is performed, a vibration signal image is generated in real time to display the motion characteristics of the target area, and the dynamic changes of the vibration signal amplitude and characteristic frequency are monitored and recorded.

[0019] Preferably, in step S1, tiny vibrations of the target device are captured by a high frame rate industrial camera device, and the video frame rate captured by the high frame rate industrial camera device is not less than 120fps, and the video resolution is 720p or 1080p.

[0020] Preferably, step S2 includes step S21 and step S22,

[0021] Step S21, constructing a Gaussian pyramid:

[0022] Step S211, Gaussian blur:

[0023] Assume the input image is I0(x, y), and its resolution is W×H;

[0024] For image I i (x, y) is blurred using a Gaussian kernel to filter out high-frequency information:

[0025] I′ i (x, y) = I i (x, y)*G(x, y);

[0026] Among them, G(x, y) is the standard Gaussian kernel,

[0027]

[0028] x, y represent the position in the two-dimensional image coordinate system, and σ represents the standard deviation of the Gaussian distribution;

[0029] Step S212, image downsampling:

[0030] The blurred image I′i (x, y) is downsampled by 1 / 2 to get the next layer image I i+1 (x, y),

[0031] I i+1 (x, y) = I′ i (2x, 2y);

[0032] During downsampling, the resolution is halved until a predetermined minimum size is reached;

[0033] Repeat the above steps to build a multi-layer Gaussian pyramid until the target size is reached. The result is:

[0034] Gaussian Pyramid={I0,I1,I2,...,I n};

[0035] I n is the lowest resolution image.

[0036] Preferably, step S22, constructing a Laplacian pyramid:

[0037] Step S221, Laplace layer calculation:

[0038] For each layer of Gaussian image I i (x, y) and its underlying image I i+1 The upsampling result of (x, y) is I′ i+1 (x, y) to find the difference and get the Laplace layer L i (x, y):

[0039] L i (x, y) = I i (x, y)-I′ i+1 (x, y);

[0040] Among them, I′ i+1 (x, y) is I i+1 Upsampled image of (x, y);

[0041] Step S222, retaining the underlying Gaussian image:

[0042] Lowest resolution image I n (x, y) is used as the bottom layer of the Laplacian pyramid, and the detailed information is added to obtain the Laplacian pyramid:

[0043] Laplacian Pyramid={L0, L1, L2,...,I n}.

[0044] Preferably, step S3 includes step S31 and step S32,

[0045] Step S31, bandpass filter design:

[0046] Step S311, designing a dual IIR low-pass filter:

[0047] Set the vibration frequency range [f low , f high ], perform time domain bandpass filtering on the time-varying signal of each pixel of the Laplace pyramid, and select two IIR low-pass filters LPF with different cutoff frequencies low and LPF high For each frame of video image, first use LPF low Filter out high-frequency components, retain low-frequency signals, and then use LPF high Filter out the signal with wide frequency band;

[0048] Step S312, filter difference:

[0049] By LPF high Subtract LPF from the filtered result low Filtering results:

[0050] BandPass=LPF high (Frame)-LPF low (Frame);

[0051] Frame represents a single static image in a video stream.

[0052] Preferably, step S32, vibration signal enhancement and reconstruction:

[0053] Step S321, enhancing the signal:

[0054] The separated vibration signal L k , apply the gain factor α to amplify:

[0055] L′ k =L k ×α;

[0056] Step S322, reconstructing the enhanced signal:

[0057] By reconstructing the Laplacian pyramid layer by layer, the video frame with enhanced micro-vibration signal is obtained:

[0058] I′ i (x, y) = L′ i (x,y)+Upsample(I′ i+1 (x, y));

[0059] The enhanced video frame is upsampled and image fused using OpenCV functions to achieve layer-by-layer reconstruction, and the reconstructed image I′0(x, y) is the enhanced result frame.

[0060] Preferably, step S4 includes step S41 and step S42,

[0061] Step S41, region selection and optical flow calculation:

[0062] Step S411, ROI area selection:

[0063] Manually or automatically select the region of interest (ROI) from the enhanced image frame;

[0064] Step S412, optical flow calculation:

[0065] The Farneback optical flow method in OpenCV is used to calculate the optical flow in the ROI area for motion analysis. Multi-resolution block matching is used to optimize the optical flow vector of each pixel point, and the output optical flow field flow(x,y)=(u,v), where u and v are the displacement components of the target device in the horizontal and vertical directions;

[0066] Calculate the motion amplitude and convert the optical flow field into polar coordinates:

[0067]

[0068] The average value of the motion amplitude is calculated for the selected area, and the vibration signal amplitude and pixel motion direction of each frame are extracted.

[0069] Preferably, step S42, vibration frequency extraction:

[0070] Step S421, vibration signal construction:

[0071] The average value of the optical flow motion amplitude of each frame is connected in frame sequence to obtain the time domain vibration signal sequence:

[0072]

[0073] Where N is the number of valid pixels in the target area;

[0074] Step S422, Fourier transform analysis:

[0075] Perform fast Fourier transform FFT on the vibration signal sequence to convert the time domain signal into a frequency domain signal:

[0076]

[0077] Where t represents the time of each moment or frame, j represents the index of the spatial pixel, f represents the frequency describing the micro-vibration of the device, and T represents the total duration of the video;

[0078] Step S423, characteristic frequency extraction:

[0079] Find the frequency component f with the largest amplitude in the frequency domain signal max , as the characteristic vibration frequency of the device:

[0080] f max =arg max|F(f)|.

[0081] Preferably, in step S5, based on the dynamic changes of the vibration signal amplitude and characteristic frequency, a threshold range is set to detect when the vibration frequency deviates from the normal value range, trigger an alarm, and record the video and analysis data of the abnormal period;

[0082] The vibration signal time domain waveform, frequency domain vibration spectrum, and optical flow field animation are generated in real time to display the motion characteristics of the target area.

[0083] The present invention also provides a system for real-time monitoring of equipment micro-vibration based on visual enhancement, comprising:

[0084] Video acquisition module, used to acquire high frame rate video of micro-vibration of target equipment and record acquisition parameters in real time;

[0085] The signal enhancement module is used to input the original video frame, separate the vibration signal and background information through the Laplacian pyramid, enhance the signal after filter difference, and reconstruct the enhanced signal;

[0086] The region selection and optical flow calculation module is used for selecting the ROI region of the enhanced image frame and calculating the optical flow within the ROI region;

[0087] Vibration frequency extraction module, used for vibration signal construction, transformation and characteristic frequency extraction;

[0088] The real-time monitoring and data output module is used for real-time monitoring of vibration signals, process status evaluation and early warning, and for visualization of vibration signal data to display the motion characteristics of the target area.

[0089] Therefore, the present invention adopts the above-mentioned method and system for real-time monitoring of equipment micro-vibration based on visual enhancement, which has the following beneficial effects:

[0090] The present invention adopts a non-contact optical imaging and vision enhancement method, avoiding the problems of mass distribution change and poor environmental adaptability caused by the need for the acceleration sensor to physically contact the device, and is not affected by electromagnetic interference or high humidity. In terms of signal extraction, the present invention uses a bandpass filter and Laplace pyramid decomposition to enhance the micro-vibration signal of a specific frequency band, eliminates background noise, overcomes the high requirements of the laser displacement sensor on the target surface material and reflection characteristics, and adapts to complex surfaces and environmental changes. The motion analysis based on the optical flow method of the present invention avoids the dependence of the eddy current sensor on the electromagnetic characteristics of the material of the object being measured, and improves the adaptability and accuracy of the measurement. The present invention extracts the vibration frequency in real time through Fourier transform, provides an efficient solution for equipment status monitoring and fault warning, and has significant technical advantages of strong environmental adaptability, high measurement accuracy and excellent anti-interference ability.

[0091] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] Figure 1 A schematic diagram of a method flow of an embodiment of the present invention;

[0093] Figure 2 Schematic diagram of a Gaussian pyramid according to an embodiment of the present invention. DETAILED DESCRIPTION

[0094] In order to make the purpose, technical scheme and advantages disclosed in the embodiments of the present invention clearer, the embodiments of the present invention are further described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention and are not intended to limit the embodiments of the present invention. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions.

[0095] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products or devices.

[0096] Like reference numerals and letters denote similar items in the following drawings, and thus, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0097] In the description of the present invention, it should be noted that the terms "upper", "lower", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, or are directions or positional relationships in which the product of the invention is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation on the present invention.

[0098] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "setting", "installation" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0099] Example

[0100] like Figure 1 As shown, the method for real-time monitoring of equipment micro-vibration based on visual enhancement described in the present invention comprises the following steps:

[0101] Step S1, collect high frame rate video, select key parts of the target device as the collection area through manual calibration, and record the collection parameters in real time, including frame rate, resolution and number of frames.

[0102] ①High frame rate video acquisition

[0103] High frame rate industrial camera equipment (frame rate not less than 120fps) is used to ensure that the tiny vibrations of the target equipment are fully captured. The video resolution is 720p or 1080p so that the spatial resolution meets the real-time requirements.

[0104] ② Collection target setting

[0105] The key parts of the target device are selected as the acquisition area through manual calibration, and the acquisition parameters, including frame rate, resolution and number of frames, are recorded in real time.

[0106] Step S2, constructing a Gaussian pyramid to perform layer-by-layer sampling and blurring processing on the image, constructing a Laplacian pyramid through the image differences of adjacent layers of the Gaussian pyramid, and decomposing the collected video into different spatial frequency bands.

[0107] After inputting the original video frame, the core of Laplacian pyramid decomposition is to separate the vibration signal and background information through multi-scale image representation to highlight the micro-vibration characteristics of the target area. The specific decomposition process is as follows:

[0108] Step S21, constructing a Gaussian pyramid:

[0109] The construction of Gaussian pyramid is the basis of Laplacian pyramid decomposition, which is achieved by downsampling and blurring the image layer by layer. The process is as follows:

[0110] Assume that the input image is I0(x, y) and its resolution is W×H.

[0111] Step S211, Gaussian blur:

[0112] For image I i (x, y) is blurred using a Gaussian kernel to filter out high-frequency information:

[0113] I′ i (x, y) = I i (x, y)*G(x, y);

[0114] Among them, G(x, y) is the standard Gaussian kernel,

[0115]

[0116] x, y represent the position in the two-dimensional image coordinate system, and σ represents the standard deviation of the Gaussian distribution. This operation is implemented with the help of the cv2.GaussianBlur function in OpenCV.

[0117] Step S212, image downsampling:

[0118] The blurred image I′ i (x, y) is downsampled by 1 / 2 to get the next layer image I i+1 (x, y),

[0119] I i+1 (x, y) = I′ i (2x, 2y)

[0120] This process is implemented by the OpenCV function cv2.pyrDown. During the downsampling process, the resolution is halved until the predetermined minimum size is reached;

[0121] Repeat the above steps to build a multi-layer Gaussian pyramid until the target size is reached. The result is:

[0122] Gaussian Pyramid={I0,I1,I2,...,I n};

[0123] I n is the lowest resolution image, such as Figure 2 It is a multi-layer Gaussian pyramid.

[0124] Step S22, constructing a Laplacian pyramid:

[0125] The Laplacian pyramid is constructed by the image difference of adjacent layers of the Gaussian pyramid, retaining the detailed information of each layer. The specific process is as follows:

[0126] Step S221, Laplace layer calculation:

[0127] For each layer of Gaussian image I i (x, y) and its underlying image I i+1 The upsampling result of (x, y) is I′ i+1 (x, y) to find the difference and get the Laplace layer L i (x, y):

[0128] L i (x, y) = I i (x, y)-I′ i+1 (x, y);

[0129] Among them, I′ i+1 (x, y) is I i+1 The upsampled image of (x, y) is implemented by the OpenCV function cv2.pyrUp.

[0130] Step S222, retaining the underlying Gaussian image:

[0131] Lowest resolution image I n (x, y) is used as the bottom layer of the Laplace pyramid, and detailed information is added to finally obtain the Laplace pyramid:

[0132] Laplacian Pyramid={L0, L1, L2,...,I n}.

[0133] Step S3, designing a bandpass filter to extract the specific frequency band of the device vibration signal, performing time domain bandpass filtering on the time variation signal of each pixel point of the Laplace pyramid, and enhancing and reconstructing the micro-vibration signal.

[0134] Step S31, bandpass filter design:

[0135] According to the vibration characteristics of the target device, a bandpass filter is designed to extract the specific frequency band of the device vibration signal to obtain a clearer input signal and set its vibration frequency range [f low , f high ], perform time domain bandpass filtering on the time-varying signal of each pixel of the Laplace pyramid. The specific steps are as follows:

[0136] Step S311, designing a dual IIR low-pass filter:

[0137] Select two IIR low pass filters LPF with different cutoff frequencies low and LPF high For each frame of video image, first use LPF low Filter out high-frequency components, retain lower-frequency signals, and then use LPF high Filter out higher frequencies to obtain a wider bandwidth signal.

[0138] Step S312, filter difference:

[0139] By LPF high Filter result minus LPF low Filtering results:

[0140] BandPass=LPF high (Frame)-LPF low (Frame);

[0141] Frame represents a single static image in a video stream. After filtering, the remaining pixel vibration signal represents the motion change within the corresponding frequency range.

[0142] Step S32, vibration signal enhancement and reconstruction:

[0143] Step S321, enhancing the signal:

[0144] The specific frequency component related to the micro-vibration signal, i.e., the separated vibration signal L k , apply the gain factor α to amplify:

[0145] L′ k =L k ×α;

[0146] The Laplace layer L′ after gain processing k The amplified vibration signal characteristics are preserved, while the other layers remain unchanged.

[0147] Step S322, reconstructing the enhanced signal:

[0148] By reconstructing the Laplacian pyramid layer by layer, the video frame with enhanced micro-vibration signal is obtained:

[0149] I′ i (x, y) = L′ i (x,y)+Upsample(I′ i+1 (x, y));

[0150] Use OpenCV functions cv2.add and cv2.pyrUp to perform upsampling and image fusion on the enhanced video frame to achieve layer-by-layer reconstruction. Finally, the reconstructed image I′0(x, y) is the enhanced result frame.

[0151] Step S4, selecting a region from the enhanced image frame, calculating the optical flow in the selected region by the Farneback optical flow method in OpenCV, and extracting the characteristic frequency of the vibration.

[0152] Step S41, region selection and optical flow calculation:

[0153] Step S411, ROI area selection:

[0154] From the enhanced image frame, a region of interest (ROI) is manually or automatically selected to ensure that the moving area of ​​the target device is focused on while avoiding interference from non-target areas.

[0155] Step S412, optical flow calculation:

[0156] The Farneback optical flow method (cv2.calcOpticalFlowFarneback) in OpenCV is used to calculate the optical flow in the ROI area for motion analysis:

[0157] The optical flow vector of each pixel is optimized by multi-resolution block matching, and the optical flow field flow(x, y) = (u, v) is output, where u and v are the displacement components of the target device in the horizontal and vertical directions;

[0158] Calculate the motion amplitude and convert the optical flow field into polar coordinates:

[0159]

[0160] The average value of the motion amplitude is calculated for the selected area, and the vibration signal amplitude and pixel motion direction of each frame are extracted.

[0161] Step S42, vibration frequency extraction:

[0162] Step S421, vibration signal construction:

[0163] The average value of the optical flow motion amplitude of each frame is connected in frame sequence to obtain the time domain vibration signal sequence:

[0164]

[0165] Where N is the number of valid pixels in the target area;

[0166] Step S422, Fourier transform analysis:

[0167] Perform fast Fourier transform (FFT) on the vibration signal sequence to convert the time domain signal into a frequency domain signal:

[0168]

[0169] Where t represents the time of each moment or frame, j represents the index of the spatial pixel, f represents the frequency describing the micro-vibration of the device, and T represents the total duration of the video.

[0170] Step S423, characteristic frequency extraction:

[0171] Find the frequency component f with the largest amplitude in the frequency domain signal max , as the main vibration frequency of the equipment:

[0172] f max = arg max|F(f)|;

[0173] Eigenfrequencies correspond to the physical properties of equipment vibration and can be used for monitoring and fault diagnosis.

[0174] Step S5, data visualization is performed, a vibration signal image is generated in real time to display the motion characteristics of the target area, and the dynamic changes of the vibration signal amplitude and characteristic frequency are monitored and recorded.

[0175] ① Status assessment and early warning

[0176] Based on the dynamic changes of vibration signal amplitude and characteristic frequency, the threshold range is set. Once the detected vibration frequency deviates from the normal value range, the system triggers an alarm and records the video and analysis data of the abnormal period.

[0177] ②Data Visualization

[0178] The vibration signal time domain waveform, frequency domain vibration spectrum, and optical flow field animation are generated in real time to display the motion characteristics of the target area.

[0179] The system of the present invention is a method for real-time monitoring of equipment micro-vibration based on visual enhancement, comprising:

[0180] Video acquisition module, used to acquire high frame rate video of micro-vibration of target equipment and record acquisition parameters in real time;

[0181] The signal enhancement module is used to input the original video frame, separate the vibration signal and background information through the Laplacian pyramid, enhance the signal after filter difference, and reconstruct the enhanced signal;

[0182] The region selection and optical flow calculation module is used for selecting the ROI region of the enhanced image frame and calculating the optical flow within the ROI region;

[0183] Vibration frequency extraction module, used for vibration signal construction, transformation and characteristic frequency extraction;

[0184] The real-time monitoring and data output module is used for real-time monitoring of vibration signals, process status evaluation and early warning, and for visualization of vibration signal data to display the motion characteristics of the target area.

[0185] The system of the present invention first decomposes the input video sequence into different spatial frequency bands by constructing a Laplacian pyramid, and applies the same temporal bandpass filter to all frequency bands. Then, the filtered spatial frequency band is amplified by a given factor to obtain an enhanced image frame, which is then added to the original signal to fold and generate an output video after vibration amplification. The amplitude of the vibration signal of each frame of the image will be enhanced after the above method, realizing vibration visualization, and the equipment vibration spectrum can be obtained by performing optical flow calculation on the enhanced image frame, so as to perform equipment fault analysis on the spectrum.

[0186] Through the optimization design of the system and the improvement of the methods, the following advantages and effects are mainly reflected:

[0187] ① High-sensitivity extraction of micro-vibration signals

[0188] Bandpass filter design:

[0189] A dual IIR filter is used to perform time-domain bandpass filtering on the video frame signal to effectively extract the frequency components of micro-vibrations, eliminate low-frequency interference (such as changes in device background light) and high-frequency noise, and ensure the high quality of the input signal.

[0190] Signal boost module:

[0191] The signal extracted by Laplace pyramid decomposition, that is, filtering, is amplified to amplify the subtle vibration signal to an observable range, while suppressing interference from background irrelevant areas.

[0192] ②Efficient motion feature analysis

[0193] Optical flow combined with visual enhancement:

[0194] The optical flow method is used on the enhanced image to analyze the vibration amplitude and direction, avoiding the problem of insufficient sensitivity of the traditional optical flow method in subtle motion detection, thereby accurately capturing the dynamic changes of the target area.

[0195] ③Accurate frequency characteristics extraction

[0196] Frequency Domain Analysis:

[0197] By extracting the spectral characteristics of the vibration signal through Fourier transform, the vibration frequency of the target device can be accurately calculated, providing the core indicators of the device status.

[0198] Combining time domain and frequency domain:

[0199] The dual methods of time domain filtering and frequency domain analysis are adopted to enhance the distinguishability of signals and ensure the accuracy and reliability of vibration characteristic extraction.

[0200] ④Equipment safety and fault warning

[0201] Based on the detection results of real-time vibration characteristics, this system can quickly determine the operating status of the equipment and issue early warning signals, thereby greatly improving the safety of equipment operation and maintenance efficiency.

[0202] The present invention adopts the above-mentioned real-time monitoring method and system for equipment micro-vibration based on visual enhancement, which can solve the problems of insufficient sensitivity and poor real-time performance in detecting equipment micro-vibration in traditional vibration monitoring methods.

[0203] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A real-time monitoring method for equipment micro-vibration based on visual enhancement, characterized in that: The following steps are involved: Step S1, collecting high frame rate video, and selecting key parts of the target device as the collection area through manual calibration, and recording the collection parameters in real time, the collection parameters including frame rate, resolution and number of frames; Step S2, constructing a Gaussian pyramid to perform layer-by-layer sampling and blurring processing on the image, constructing a Laplacian pyramid through the image differences of adjacent layers of the Gaussian pyramid, and decomposing the collected video into different spatial frequency bands; Step S3, designing a bandpass filter to extract the specific frequency band of the device vibration signal, performing time domain bandpass filtering on the time-varying signal of each pixel point in the Laplace pyramid, and enhancing and reconstructing the micro-vibration signal; Step S4, selecting a region from the enhanced image frame, calculating the optical flow in the selected region by the Farneback optical flow method in OpenCV, and extracting the characteristic frequency of the vibration; Step S5, data visualization is performed, a vibration signal image is generated in real time to display the motion characteristics of the target area, and the dynamic changes of the vibration signal amplitude and characteristic frequency are monitored and recorded.

2. The method for real-time monitoring of equipment micro-vibration based on visual enhancement according to claim 1 is characterized in that: In step S1, the tiny vibration of the target device is captured by a high frame rate industrial camera device. The video frame rate captured by the high frame rate industrial camera device is not less than 120fps, and the video resolution is 720p or 1080p.

3. The method for real-time monitoring of equipment micro-vibration based on visual enhancement according to claim 1 is characterized in that: Step S2 includes step S21 and step S22, Step S21, constructing a Gaussian pyramid: Step S211, Gaussian blur: Assume the input image is I0(x,y), and its resolution is W×H; For image I i (x,y) is blurred using a Gaussian kernel to filter out high-frequency information: I′ i (x,y)=I i (x,y)*G(x,y); Among them, G(x,y) is the standard Gaussian kernel, x, y represent the position in the two-dimensional image coordinate system, and σ represents the standard deviation of the Gaussian distribution; Step S212, image downsampling: The blurred image I' i (x,y) is downsampled by 1 / 2 to get the next layer image I i+1 (x,y), I i+1 (x,y)=I′ i (2x,2y); During downsampling, the resolution is halved until a predetermined minimum size is reached; Repeat the above steps to build a multi-layer Gaussian pyramid until the target size is reached. The result is: Gaussian Pyramid={I0,I1,I2,…,I n }; I n is the lowest resolution image.

4. The method for real-time monitoring of equipment micro-vibration based on visual enhancement according to claim 3 is characterized in that: Step S22, constructing a Laplacian pyramid: Step S221, Laplace layer calculation: For each layer of Gaussian image I i (x,y) and its underlying image I i+1 The upsampling result of (x,y) is I' i+1 (x, y) to find the difference and get the Laplace layer L i (x,y): L i (x,y)=I i (x,y)-I' i+1 (x,y); Among them, I' i+1 (x,y) is I i+1 (x,y) upsampled image; Step S222, retaining the underlying Gaussian image: Lowest resolution image I n (x,y) is used as the bottom layer of the Laplace pyramid, and detailed information is added to obtain the Laplace pyramid: Laplacian Pyramid={L0,L1,L2,…,I n }。 5. The method for real-time monitoring of equipment micro-vibration based on visual enhancement according to claim 1 is characterized in that: Step S3 includes step S31 and step S32, Step S31, bandpass filter design: Step S311, designing a dual IIR low-pass filter: Set the vibration frequency range [f low ,f high ], perform time domain bandpass filtering on the time-varying signal of each pixel of the Laplace pyramid, and select two IIR low-pass filters LPF with different cutoff frequencies low and LPF high For each frame of video image, first use LPF low Filter out high-frequency components, retain low-frequency signals, and then use LPF high Filter out the signal with wide frequency band; Step S312, filter difference: By LPF high Filter result minus LPF low Filtering results: BandPass=LPF high (Frame)-LPF low (Frame); Frame represents a single static image in a video stream.

6. The method for real-time monitoring of equipment micro-vibration based on visual enhancement according to claim 5 is characterized in that: Step S32, vibration signal enhancement and reconstruction: Step S321, enhancing the signal: The separated vibration signal L k , apply the gain factor α to amplify: L' k =L k ×α; Step S322, reconstructing the enhanced signal: By reconstructing the Laplacian pyramid layer by layer, the video frame with enhanced micro-vibration signal is obtained: YO' i (x,y)=L' i (x,y)+Upsample(I' i+1 (x,y)); The enhanced video frame is upsampled and image fused using OpenCV functions to achieve layer-by-layer reconstruction, and the reconstructed image I'0(x,y) is the enhanced result frame.

7. The method for real-time monitoring of equipment micro-vibration based on visual enhancement according to claim 1 is characterized in that: Step S4 includes step S41 and step S42, Step S41, region selection and optical flow calculation: Step S411, ROI area selection: Manually or automatically select the region of interest (ROI) from the enhanced image frame; Step S412, optical flow calculation: The Farneback optical flow method in OpenCV is used to calculate the optical flow in the ROI area for motion analysis. Multi-resolution block matching is used to optimize the optical flow vector of each pixel point, and the output optical flow field flow(x,y)=(u,v), where u and v are the displacement components of the target device in the horizontal and vertical directions; Calculate the motion amplitude and convert the optical flow field into polar coordinates: The average value of the motion amplitude is calculated for the selected area, and the vibration signal amplitude and pixel motion direction of each frame are extracted.

8. The method for real-time monitoring of equipment micro-vibration based on visual enhancement according to claim 7 is characterized in that: Step S42, vibration frequency extraction: Step S421, vibration signal construction: The average value of the optical flow motion amplitude of each frame is connected in frame sequence to obtain the time domain vibration signal sequence: Where N is the number of valid pixels in the target area; Step S422, Fourier transform analysis: Perform fast Fourier transform FFT on the vibration signal sequence to convert the time domain signal into a frequency domain signal: Where t represents the time of each moment or frame, j represents the index of the spatial pixel, f represents the frequency describing the micro-vibration of the device, and T represents the total duration of the video; Step S423, characteristic frequency extraction: Find the frequency component f with the largest amplitude in the frequency domain signal max , as the characteristic vibration frequency of the device: f max =arg max|F(f)|。 9. The method for real-time monitoring of equipment micro-vibration based on visual enhancement according to claim 1, characterized in that: In step S5, based on the dynamic changes of the vibration signal amplitude and characteristic frequency, a threshold range is set to detect when the vibration frequency deviates from the normal value range, trigger an alarm, and record the video and analysis data of the abnormal period; The vibration signal time domain waveform, frequency domain vibration spectrum, and optical flow field animation are generated in real time to display the motion characteristics of the target area.

10. A system for real-time monitoring of equipment micro-vibration based on visual enhancement according to any one of claims 1 to 9, characterized in that: include Video acquisition module, used to acquire high frame rate video of micro-vibration of target equipment and record acquisition parameters in real time; The signal enhancement module is used to input the original video frame, separate the vibration signal and background information through the Laplacian pyramid, enhance the signal after filter difference, and reconstruct the enhanced signal; The region selection and optical flow calculation module is used for selecting the ROI region of the enhanced image frame and calculating the optical flow within the ROI region; Vibration frequency extraction module, used for vibration signal construction, transformation and characteristic frequency extraction; The real-time monitoring and data output module is used for real-time monitoring of vibration signals, process status evaluation and early warning, and for visualization of vibration signal data to display the motion characteristics of the target area.

Images