Mechanical equipment operation state monitoring method based on vibration signal color visualization

Abstract

The invention belongs to the technical field of mechanical equipment operation state monitoring, and particularly relates to a mechanical equipment operation state monitoring method based on vibration signal color visualization. The method comprises the following steps: firstly, collecting vibration acceleration signals of mechanical equipment under various working conditions and different operation states to obtain a vibration acceleration signal sequence; performing time-frequency transformation on the vibration acceleration signal sequence to obtain a frequency spectrum of the vibration acceleration signal; then, calculating a spectrum amplitude mean value of the vibration acceleration signal; calculating the standard deviation between the mean value of the spectrum amplitude of the vibration acceleration signal in the current operation state under the same working condition and the mean value of the spectrum amplitude of the vibration acceleration signal in the normal operation state; performing normalization processing on the standard deviation, and taking the normalized standard deviation as a state characteristic value; and finally, mapping the state characteristic value to a range from 0 to 1, carrying out color self-definition, and further converting the state characteristic value into a color image. According to the method, the state characteristic value is mapped, and the color image reflecting the operation state is generated, so that the visual monitoring of the operation state is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of mechanical equipment operation status monitoring, and specifically is a mechanical equipment operation status monitoring method based on color visualization of vibration signals. It can be widely used in various mechanical equipment in industrial production, such as bearings, gears and other parts, wind turbines, rail transportation equipment, pumps and other equipment components, and is particularly suitable for scenarios that require real-time monitoring and efficient fault diagnosis. Background Art

[0002] Mechanical equipment is widely used in aerospace, petrochemical, precision machine tools, high-speed trains and many other fields. With the development of intelligent manufacturing technology, online monitoring and fault diagnosis of mechanical equipment have become the key to improving production efficiency and equipment reliability. Traditional fault diagnosis methods usually rely on the experience of professional technicians and complex analysis equipment, and the output signal is a data signal, which not only has certain limitations in real-time monitoring and rapid response, but also has a high operating threshold.

[0003] The present invention is committed to utilizing data analysis and visualization methods in intelligent manufacturing technology to provide a mechanical equipment operation status monitoring method based on color visualization of vibration signals, so as to help operators quickly understand the operation status of mechanical equipment and accurately identify and solve mechanical equipment failure problems. Summary of the invention

[0004] In view of the deficiencies in the prior art, the technical problem to be solved by the present invention is: a method for monitoring the operating status of mechanical equipment based on color visualization of vibration signals is proposed.

[0005] The present invention solves the technical problem by adopting the following technical solution:

[0006] A method for monitoring the operating status of mechanical equipment based on color visualization of vibration signals, characterized in that the method comprises the following steps:

[0007] S1: Collect vibration acceleration signals of mechanical equipment under various working conditions and different operating states to obtain vibration acceleration signal sequences;

[0008] S2: Perform time-frequency transformation on the vibration acceleration signal sequence to obtain the frequency spectrum of the vibration acceleration signal;

[0009] S3: Calculate the spectrum amplitude mean of the vibration acceleration signal; calculate the standard deviation between the spectrum amplitude mean of the vibration acceleration signal under the current operating state and the spectrum amplitude mean of the vibration acceleration signal under the normal operating state under the same working condition; normalize the standard deviation and use the normalized standard deviation as the state characteristic value;

[0010] S4: Map the state feature value to the range of 0 to 1, customize the color, and then convert the state feature value into a color image.

[0011] Furthermore, the time-frequency transform uses fast Fourier transform, and the calculation formula is as follows:

[0012]

[0013] Where: X(f k ) is the frequency domain representation of the vibration acceleration signal, which means that at frequency f k The amplitude and phase at x(t n ) is the time point t n The vibration acceleration signal at , N is the sequence length;

[0014] The calculation formula of the spectrum amplitude mean of the vibration acceleration signal is:

[0015]

[0016] In the formula, F K is the spectrum amplitude mean of the vibration acceleration signal, and K is the number of spectrum lines;

[0017] The formula for calculating the standard deviation is:

[0018]

[0019] Where σ is the standard deviation, F ik 、F 0k are the mean spectral amplitudes of the vibration acceleration signals under the current operating state and the normal operating state under the same working condition, respectively.

[0020] Furthermore, the calculation formula for normalization is:

[0021]

[0022] Where: max and σ min are the maximum and minimum values ​​of the standard deviation, respectively.

[0023] Furthermore, for color customization, 0 corresponds to green, 1 corresponds to red, and the intermediate value between 0 and 1 corresponds to the yellow gradient color.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] The present invention realizes online monitoring and fault diagnosis of the operating status of mechanical equipment based on the frequency spectrum change of the vibration acceleration signal, and realizes visual monitoring of the operating status by mapping the state characteristic value and generating a color image reflecting the operating status. The present invention has the characteristics of simple principle, easy implementation, dynamic, real-time monitoring and visualization. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is the overall flow chart of the present invention;

[0027] Figure 2 The figure is a visualization result of the bearing operating status of the embodiment. DETAILED DESCRIPTION

[0028] Specific embodiments are given below in conjunction with the accompanying drawings. The specific embodiments are only used to introduce the technical solutions of the present invention in detail and are not intended to limit the protection scope of the present application.

[0029] The present invention provides a method for monitoring the operation status of mechanical equipment based on color visualization of vibration signals (hereinafter referred to as method, see Figures 1-2 ), including the following steps:

[0030] S1: Use acceleration sensors to collect vibration acceleration signals of mechanical equipment under various working conditions and different operating states (including healthy, faulty, etc.). Multiple vibration acceleration signal sequences under a certain working condition and operating state constitute a vibration acceleration signal set. A total of multiple vibration acceleration signal data sets are obtained; among them, x i is the i-th vibration acceleration signal sequence, C is the number of sequences, and D is the number of data points contained in the sequence;

[0031] S2: Use fast Fourier transform (FFT) to perform time-frequency transformation on the vibration acceleration signal sequence to obtain the spectrum of the vibration acceleration signal; the formula of fast Fourier transform is as follows:

[0032]

[0033] Where: X(f k ) is the frequency domain representation of the vibration acceleration signal, which means that at frequency f k The amplitude and phase at is the discrete frequency on the frequency axis, f s is the sampling frequency; x(t n ) is the time point t n The vibration acceleration signal at , N is the sequence length;

[0034] S3: Calculate the spectrum amplitude mean of the vibration acceleration signal. The calculation formula is:

[0035]

[0036] In the formula, F K is the spectrum amplitude mean of the vibration acceleration signal, and K is the number of spectrum lines;

[0037] Calculate the standard deviation between the mean spectral amplitude of the vibration acceleration signal under the current operating state and the mean spectral amplitude of the vibration acceleration signal under the normal operating state under the same working condition. The calculation formula is:

[0038]

[0039] Where σ is the standard deviation, F ik 、F 0k are the mean values ​​of the spectral amplitude of the vibration acceleration signal under the current operating state and the normal operating state of the same working condition respectively;

[0040] The standard deviation is normalized and the normalized standard deviation is used as the state characteristic value to reflect the state of the mechanical equipment; the normalization formula is:

[0041]

[0042] Where: max and σ min are the maximum and minimum values ​​of the standard deviation, respectively.

[0043] Repeat the above process to obtain the state characteristic values ​​under different operating states of various working conditions, and store them in the operating state database. The database includes detailed data such as timestamp, state characteristic value, amplitude mean of vibration acceleration signal and acquisition time, so as to call the state characteristic values ​​therein.

[0044] S4: Map the state characteristic value to the range of 0 to 1, and customize the color, for example, 0 corresponds to green, 1 corresponds to red, and the middle value corresponds to a gradient of yellow, and then convert the state characteristic value into a color image. The closer the color of the color image is to red, the more serious the mechanical equipment failure is. Therefore, the color image can intuitively display the operating status of the mechanical equipment, realize the visualization of the operating status, and facilitate rapid diagnosis and analysis; while outputting the color image, it also outputs information such as the state characteristic value, operating time, and fault degree, which is used to comprehensively characterize the operating status of the mechanical equipment.

[0045] Example

[0046] This embodiment takes a bearing as an example, and the data set used is the full-cycle data of vibration acceleration signals of three bearings under three different working conditions, as shown in Table 1. The sampling frequency of the acceleration sensor is 25.6kHz, and the data is collected once every 10 seconds, with a collection time of 0.1s, and the data length of each vibration acceleration signal sequence is 2560 data points.

[0047] Table 1 Vibration acceleration signal data set of each bearing

[0048]

[0049] According to the above steps, use Python 3.7 to perform FFT on each segment of vibration acceleration data to obtain the spectrum; calculate the amplitude mean of each spectrum, and output the amplitude mean of each bearing over time; calculate the standard deviation between the spectrum amplitude mean and the spectrum amplitude mean of the initial spectrum under the same working condition, and normalize the standard deviation as the fault feature; use custom color mapping to map the normalized standard deviation value in the range of 0 to 1. According to experience, the bearing status is divided into five types: healthy, normal, slightly abnormal, dangerous, and faulty, and the corresponding status characteristic value ranges are 0-0.15, 0.15-0.35, 0.35-0.55, 0.55-0.75, and 0.75-1.

[0050] Figure 2 Color images are generated for the state characteristic values ​​of each bearing. The state characteristic value 0 corresponds to green, 1 corresponds to red, and the intermediate value corresponds to a gradient of yellow. The closer the color of the color image is to red, the more serious the bearing fault is. The color image can intuitively display the operating status of the bearing, which is convenient for rapid diagnosis and analysis.

[0051] Any matters not described in the present invention are applicable to the prior art.

Claims

1. A method for monitoring the operating status of mechanical equipment based on color visualization of vibration signals, characterized in that: The method comprises the following steps: S1: Collect vibration acceleration signals of mechanical equipment under various working conditions and different operating states to obtain vibration acceleration signal sequences; S2: Perform time-frequency transformation on the vibration acceleration signal sequence to obtain the frequency spectrum of the vibration acceleration signal; S3: Calculate the spectrum amplitude mean of the vibration acceleration signal; calculate the standard deviation between the spectrum amplitude mean of the vibration acceleration signal under the current operating state and the spectrum amplitude mean of the vibration acceleration signal under the normal operating state under the same working condition; normalize the standard deviation and use the normalized standard deviation as the state characteristic value; S4: Map the state feature value to the range of 0 to 1, customize the color, and then convert the state feature value into a color image.

2. The method for monitoring the operation status of mechanical equipment based on color visualization of vibration signals according to claim 1 is characterized in that: The time-frequency transform uses fast Fourier transform, and the calculation formula is as follows: Where: X(f k ) is the frequency domain representation of the vibration acceleration signal, which means that at frequency f k The amplitude and phase at x(t n ) is the time point t n The vibration acceleration signal at , N is the sequence length; The calculation formula of the spectrum amplitude mean of the vibration acceleration signal is: In the formula, F K is the spectrum amplitude mean of the vibration acceleration signal, and K is the number of spectrum lines; The formula for calculating the standard deviation is: Where σ is the standard deviation, F ik 、F 0k are the mean spectral amplitudes of the vibration acceleration signals under the current operating state and the normal operating state under the same working condition, respectively.

3. The method for monitoring the operation status of mechanical equipment based on color visualization of vibration signals according to claim 1 or 2, characterized in that: The calculation formula for normalization is: Where: max and σ min are the maximum and minimum values ​​of the standard deviation, respectively.

4. The method for monitoring the operation status of mechanical equipment based on color visualization of vibration signals according to claim 1 is characterized in that: For color customization, 0 corresponds to green, 1 corresponds to red, and the intermediate value between 0 and 1 corresponds to the yellow gradient.

Images