Bearing vibration data acquisition method and system based on vibration sensor

Abstract

The invention relates to the technical field of data processing, in particular to a bearing vibration data acquisition method and system based on a vibration sensor, and the method comprises the steps: obtaining the vibration fluctuation difference of each piece of bearing vibration data through analyzing the distribution difference of bearing vibration data signals in each period; according to the vibration difference degree of the bearing vibration data between each collection time period and the adjacent collection time period, the vibration abnormal degree of each bearing vibration data is obtained; the vibration correction amplitude of the vibration data of each bearing is obtained according to the vibration abnormal degree; acquiring a vibration data correction factor of the bearing based on the vibration correction amplitude; and correcting the collected bearing vibration data according to the vibration data correction factor to obtain corrected bearing vibration data. According to the invention, the authenticity of the bearing vibration data collected by the vibration sensor can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method and system for collecting bearing vibration data based on vibration sensors. Background Art

[0002] As a core component of rotating machinery, the failure of bearings directly affects the safety and efficiency of equipment; according to statistics, about 30% of mechanical failures are related to bearing abnormalities, and vibration signals are key indicators reflecting the operating state of bearings; when analyzing the health status of bearings based on bearing vibration data signals, since the bearing vibration data signals collected under complex working conditions often contain multi-source mixed noise, resulting in chaotic and difficult-to-analyze bearing vibration data signals, existing signal denoising processing methods are prone to modal aliasing, resulting in signal distortion or loss of effective features after denoising, directly leading to poor authenticity of the collected bearing vibration data. Summary of the Invention

[0003] The present invention provides a method and system for collecting bearing vibration data based on vibration sensors to solve the existing problems: since the bearing vibration data signals collected under complex working conditions often contain multi-source mixed noise, resulting in chaotic and difficult-to-analyze bearing vibration data signals, existing signal processing methods are prone to modal aliasing, resulting in signal distortion or loss of effective features after denoising, directly leading to poor authenticity of the collected bearing vibration data.

[0004] The method and system for collecting bearing vibration data based on vibration sensors of the present invention adopt the following technical solutions: The present invention proposes a method for collecting bearing vibration data based on vibration sensors, and the method includes the following steps: Obtain bearing vibration data signals within a plurality of time periods; By analyzing the noise distribution in the bearing vibration data signals, obtain all the periods of the bearing vibration data signals in each acquisition time period; by analyzing the distribution difference of the bearing vibration data signals under each period, obtain the vibration fluctuation difference amount of each bearing vibration data. According to the difference in the vibration fluctuation difference amount between each bearing vibration data and other bearing vibration data, obtain the vibration difference degree of each bearing vibration data; according to the vibration difference degree of the bearing vibration data between each acquisition time period and the adjacent acquisition time period, obtain the vibration abnormality degree of each bearing vibration data; according to the vibration abnormality degree, obtain the vibration correction amplitude of each bearing vibration data. Obtain a vibration data correction factor for the bearing based on the vibration correction amplitude; correct the collected bearing vibration data according to the vibration data correction factor to obtain the corrected bearing vibration data.

[0005] Preferably, the specific method for obtaining all the periods of the bearing vibration data signal in each acquisition time period by analyzing the noise distribution in the bearing vibration data signal is as follows: Construct a rectangular coordinate system based on the acquisition time and the bearing vibration data; input the bearing vibration data signal in the th acquisition time period into the rectangular coordinate system to obtain several bearing vibration data points in the th acquisition time period; in the rectangular coordinate system, use the least squares method to perform curve fitting on all the bearing vibration data points in the th acquisition time period to obtain the bearing vibration data fluctuation curve in the th acquisition time period; Perform Fourier transform on the bearing vibration data fluctuation curve in the th acquisition time period, and take the reciprocal of the frequency with the largest amplitude in the frequency spectrum diagram as a period of the bearing vibration data fluctuation curve in the th acquisition time period, and denote it as the target period; according to the maximum amplitude and the frequency of the target period in the frequency spectrum diagram, the obtained curve is denoted as the fluctuation curve of the target period; denote the difference curve between the bearing vibration data fluctuation curve in the th acquisition time period and the fluctuation curve of the target period as the curve to be analyzed; use the EMD decomposition algorithm to decompose the curve to be analyzed to obtain several IMF components; For any one IMF component, use Fourier transform to obtain the frequency spectrum diagram of the IMF component; use the peak detection method to obtain the frequency corresponding to each peak in the frequency spectrum diagram, and denote it as the peak frequency; take the cumulative sum of the absolute values of the differences between the mean of all the peak frequencies of the IMF component and the mean of all the peak frequencies of all other IMF components as the possibility of the IMF component belonging to high-frequency noise; Denote the IMF component with the greatest possibility of belonging to high-frequency noise as the noise component, add the other IMF components and the residual term to obtain the curve to be analyzed after noise removal; perform Fourier transform on the curve to be analyzed after noise removal, and take the reciprocal of the frequency corresponding to each peak in the frequency spectrum diagram as a period of the bearing vibration data fluctuation curve in the th acquisition time period.

[0006] Preferably, the specific method for obtaining the vibration fluctuation difference amount of each bearing vibration data by analyzing the distribution difference of the bearing vibration data signal under each period is as follows: For the th period of the bearing vibration data signal in the th acquisition time period, arrange the bearing vibration data fluctuation curve in the th acquisition time period according to the The cycle is divided to obtain all the bands of the bearing vibration data fluctuation curve in the th cycle and the th acquisition time period; In the bearing vibration data fluctuation curve in the th acquisition time period, the band corresponding to the th bearing vibration data point is denoted as the target band; all the bands other than the target band are denoted as the reference bands; According to the similarity between the th bearing vibration data and other bearing vibration data, all the similar data of the th bearing vibration data are obtained; The position of the th bearing vibration data in the target band is denoted as the target position; the absolute value of the difference between the th bearing vibration data and the bearing vibration data at the target position in the th reference band is denoted as the data difference value between the target band and the th reference band; the DTW distance between the target band and the th reference band is denoted as the band difference value between the target band and the th reference band; the product of the data difference value and the band difference value is denoted as the corrected difference value between the target band and the th reference band; the sum of the corrected difference values between the target band and all the reference bands is denoted as the fluctuation difference factor of the th bearing vibration data; the ratio of the fluctuation difference factor to the number of all the similar data of the th bearing vibration data is used as the vibration fluctuation difference amount of the th bearing vibration data.

[0007] Preferably, the specific method for obtaining all the similar data of the th bearing vibration data according to the similarity between the th bearing vibration data and other bearing vibration data includes: A similarity threshold parameter is preset . If the absolute value of the difference between the th bearing vibration data and the bearing vibration data at the target position in the th reference band is less than or equal to the similarity threshold parameter , the bearing vibration data at the target position in the th reference band is used as the similar data of the th bearing vibration data.

[0008] Preferably, obtaining the vibration difference degree of each bearing vibration data according to the difference situation of the vibration fluctuation difference amount between each bearing vibration data and other bearing vibration data includes the following specific method: In the th acquisition time period, taking the cumulative sum of the absolute values of the differences between the vibration fluctuation difference amount of the th bearing vibration data and the vibration fluctuation difference amounts of other bearing vibration data as the vibration difference degree of the th bearing vibration data.

[0009] Preferably, obtaining the vibration abnormality degree of each bearing vibration data according to the vibration difference degree between each acquisition time period and the adjacent acquisition time period includes the following specific method: Preset a time period neighborhood parameter , and take the th acquisition time period, the acquisition time periods before it and the acquisition time periods after it as the reference acquisition time periods of the th acquisition time period; Take the absolute value of the difference between the vibration difference degree of the left adjacent bearing vibration data of the th bearing vibration data in the th reference acquisition time period of the th acquisition time period and the vibration difference degree of the right adjacent bearing vibration data of the th bearing vibration data in the th reference acquisition time period of the th acquisition time period, and denote it as the adjacent abnormality difference amount of the th reference acquisition time period; take the cumulative sum of the adjacent abnormality difference amounts of all reference acquisition time periods of the th acquisition time period, and denote it as the vibration abnormality correction factor of the th acquisition time period; take the product of the vibration abnormality correction factor and the vibration difference degree of the th bearing vibration data as the vibration abnormality degree of the th bearing vibration data.

[0010] Preferably, obtaining the vibration correction amplitude of each bearing vibration data according to the vibration abnormality degree includes the following specific method: Preset an acquisition neighborhood parameter , and in the th acquisition time period, denote the time series composed of the th bearing vibration data, the bearing vibration data before it and the bearing vibration data after it as the The neighborhood reference data sequence of the bearing vibration data; The mean value of all bearing vibration data in the neighborhood reference data sequence of the bearing vibration data of the th acquisition time period is denoted as the first mean value; the absolute value of the difference between the bearing vibration data of the th acquisition time period and the first mean value is denoted as the vibration correction factor; the normalized value of the product between the vibration abnormality degree of the bearing vibration data of the th bearing and the vibration correction factor is taken as the vibration correction amplitude of the bearing vibration data of the th bearing.

[0011] Preferably, the method for obtaining the vibration data correction factor of the bearing based on the vibration correction amplitude specifically includes: The difference between the bearing vibration data of the th bearing in the th acquisition time period and the mean value of all bearing vibration data in the neighborhood reference data sequence of the bearing vibration data of the th acquisition time period is denoted as the first difference; the product of the first difference and the vibration correction amplitude of the bearing vibration data of the th bearing is taken as the vibration correction value of the bearing vibration data of the th bearing; If the first difference is greater than or equal to 0, the difference between the bearing vibration data of the th bearing and the vibration correction value is taken as the corrected vibration data of the bearing vibration data of the th bearing; if the first difference is less than 0, the sum of the bearing vibration data of the th acquisition and the vibration correction value is taken as the corrected vibration data of the bearing vibration data of the th bearing; The ratio between the mean value of the corrected vibration data of all bearing vibration data in all acquisition time periods under all cycles and the mean value of all bearing vibration data in all acquisition time periods under all cycles is taken as the vibration data correction factor of the bearing.

[0012] Preferably, the method for correcting the acquired bearing vibration data according to the vibration data correction factor to obtain the corrected bearing vibration data specifically includes: For the bearing vibration data acquired by the vibration sensor at any time, the sum value of the vibration data correction factor of the bearing and 1 is denoted as the vibration correction value; the product of the bearing vibration data acquired this time and the vibration correction value is taken as the optimized bearing vibration data acquired this time.

[0013] The present invention also provides a bearing vibration data acquisition system based on a vibration sensor, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the bearing vibration data acquisition methods based on the vibration sensor are implemented.

[0014] The beneficial effects of the technical solution of the present invention are as follows: By analyzing the distribution differences of the bearing vibration data signals in each period, the vibration fluctuation difference amount of each bearing vibration data is obtained; according to the vibration difference degree of the bearing vibration data between each acquisition time period and the adjacent acquisition time period, the vibration abnormality degree of each bearing vibration data is obtained; according to the vibration abnormality degree, the vibration correction amplitude of each bearing vibration data is obtained; based on the vibration correction amplitude, the vibration data correction factor of the bearing is obtained; according to the vibration data correction factor, the acquired bearing vibration data is corrected to obtain the corrected bearing vibration data; thereby, the authenticity of the bearing vibration data collected by the vibration sensor can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0016] Figure 1 It is a flowchart of the steps of the bearing vibration data acquisition method based on the vibration sensor of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following will, in conjunction with the accompanying drawings and preferred embodiments, describe in detail the specific implementation manner, structure, features, and effects of the bearing vibration data acquisition method based on the vibration sensor proposed by the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] The following will specifically describe the specific solution of the bearing vibration data acquisition method based on the vibration sensor provided by the present invention in conjunction with the accompanying drawings.

[0020] Please refer to Figure 1, which shows the step flow chart of the bearing vibration data acquisition method based on a vibration sensor provided by an embodiment of the present invention. The method includes the following steps: Step S001: Obtain the bearing vibration data signals within a number of time periods.

[0021] Specifically, first, it is necessary to collect the bearing vibration data signals within a number of time periods. The specific process is as follows: Fix the vibration sensor on the bearing or the bearing housing to collect the bearing vibration data. Take every 2 minutes as a collection time period, and collect for a total of 30 minutes. For any one collection time period, use the vibration sensor to collect the bearing vibration data for 2 minutes. The signal composed of the bearing vibration data of all the collection bags within the collection time period is used as the bearing vibration data signal within the collection time period.

[0022] Thus, the bearing vibration data signals within a number of time periods are obtained through the above method.

[0023] Step S002: By analyzing the noise distribution in the bearing vibration data signal, obtain all the periods of the bearing vibration data signal within each collection time period; by analyzing the distribution difference of the bearing vibration data signal under each period, obtain the vibration fluctuation difference amount of each bearing vibration data under each period.

[0024] 1. Obtain all the periods of the bearing vibration data signal within each time period.

[0025] It should be noted that since the interval of the collection time within the collection time period is fixed, and the bearing usually has periodicity during normal operation, under normal circumstances, the data fluctuation of the bearing vibration data within each collection time period shows a periodic characteristic. Since there may be high-frequency noise in the collected bearing vibration data, resulting in inaccurate acquisition of other periods, it is necessary to remove the high-frequency noise to obtain more accurate bearing vibration data.

[0026] Preferably, in some implementation manners of the embodiments of the present invention, the specific method for obtaining all the periods of the bearing vibration data signal within each collection time period by analyzing the noise distribution in the bearing vibration data signal is as follows: Construct a rectangular coordinate system according to the collection time and the bearing vibration data; input the bearing vibration data signal within the th collection time period into the rectangular coordinate system to obtain a number of bearing vibration data points within the th collection time period; in the rectangular coordinate system, use the least squares method to perform curve fitting on all the bearing vibration data points within the th collection time period to obtain the bearing vibration data fluctuation curve within the th collection time period; Among them, the least squares method is a prior art and will not be elaborated here in this embodiment.

[0027] For the bearing vibration data fluctuation curve within the th acquisition time period, perform Fourier transform, and take the reciprocal of the frequency with the largest amplitude in the frequency spectrum diagram as one period of the bearing vibration data fluctuation curve within the th acquisition time period, and denote it as the target period; According to the maximum amplitude and the frequency of the target period in the frequency spectrum diagram, the obtained curve is denoted as the fluctuation curve of the target period; Take the difference curve between the bearing vibration data fluctuation curve within the th acquisition time period and the fluctuation curve of the target period, and denote it as the curve to be analyzed; Use the EMD decomposition algorithm to decompose the curve to be analyzed to obtain several IMF components and a residual term; For any one IMF component, use Fourier transform to obtain the frequency spectrum diagram of the IMF component; Use the peak detection method to obtain the frequency corresponding to each peak in the frequency spectrum diagram, and denote it as the peak frequency; Take the sum of the absolute values of the differences between the mean value of all peak frequencies of the IMF component and the mean value of all peak frequencies of all other IMF components as the possibility of the IMF component belonging to high-frequency noise; The specific formula is: In the formula, represents the possibility of the IMF component belonging to high-frequency noise; represents the total number of all IMF components; represents the mean value of all peak frequencies of the th IMF component; represents the mean value of all peak frequencies of the IMF component; represents taking the absolute value.

[0028] It should be noted that the larger the absolute value of the difference between the mean value of all peak frequencies of the IMF component and the mean value of all peak frequencies of all other IMF components, the greater the waveform difference between the IMF component and all other IMF components, and the greater the possibility of the IMF component belonging to high-frequency noise; Among them, Fourier transform is a prior art and will not be elaborated here in this embodiment; Denote the IMF component with the greatest possibility of belonging to high-frequency noise as the noise component, add the other IMF components and the residual term to obtain the curve to be analyzed after noise removal; Perform Fourier transform on the curve to be analyzed after noise removal, and take the reciprocal of the frequency corresponding to each peak in the frequency spectrum diagram as one period of the bearing vibration data fluctuation curve within the th acquisition time period.

[0029] So far, all the periods of the bearing vibration data signals in each time period have been obtained through the above method.

[0030] 2. Obtain the vibration fluctuation difference amount of each bearing vibration data in each cycle of each acquisition time period.

[0031] It should be noted that for any cycle in each acquisition time period, if the difference in the vibration fluctuation difference amount of the bearing vibration data between each acquisition moment and other acquisition moments is greater, it indicates that the vibration fluctuation difference amount of each bearing vibration data is greater, and then the degree of abnormality of each bearing vibration data is greater.

[0032] Preferably, for the th cycle of the bearing vibration data signal in the th acquisition time period, the bearing vibration data fluctuation curve in the th acquisition time period is segmented according to the th cycle to obtain all the wave bands of the bearing vibration data fluctuation curve in the th cycle of the th acquisition time period.

[0033] Preferably, in some implementation manners of the embodiments of the present invention, according to the difference between the corresponding wave band of each bearing vibration data and other wave bands, the specific method for obtaining the vibration fluctuation difference amount of each bearing vibration data in each cycle is as follows: In the bearing vibration data fluctuation curve in the th acquisition time period, the wave band corresponding to the th bearing vibration data point is recorded as the target wave band; all the wave bands other than the target wave band are recorded as reference wave bands; According to the similarity between the th bearing vibration data and other bearing vibration data, the specific method for obtaining all the similar data of the th bearing vibration data is as follows: Preset a similarity threshold parameter , where this embodiment is described by taking as an example, and this embodiment is not specifically limited, where is determined according to the specific implementation situation; If the absolute value of the difference between the th bearing vibration data and the bearing vibration data at the target position in the th reference wave band is less than or equal to the similarity threshold parameter , the bearing vibration data at the target position in the th reference wave band is used as the Similar data of the bearing vibration data.

[0034] Denote the position of the th bearing vibration data in the target band as the target position; Denote the absolute value of the difference between the th bearing vibration data and the bearing vibration data at the target position in the th reference band as the data difference value between the target band and the th reference band; Denote the DTW distance between the target band and the th reference band as the band difference value between the target band and the th reference band; Denote the product of the data difference value and the band difference value as the corrected difference value between the target band and the th reference band; Denote the sum of the corrected difference values between the target band and all reference bands as the fluctuation difference factor of the th bearing vibration data; Denote the ratio between the fluctuation difference factor and the number of all similar data of the th bearing vibration data as the vibration fluctuation difference amount of the th bearing vibration data; The specific formula is: In the formula, represents the vibration fluctuation difference amount of the th acquisition time period under the th cycle for the th bearing vibration data; represents the number of all reference bands of the bearing vibration data fluctuation curve in the th cycle for the th acquisition time period; represents the th bearing vibration data in the th acquisition time period; represents the bearing vibration data at the target position in the th reference band in the th acquisition time period under the th cycle; represents the DTW distance between the band corresponding to the bearing vibration data point at the th acquisition moment in the th acquisition time period under the th cycle and the th reference band; represents the th cycle for the th acquisition time period for the The number of all similar data for each bearing vibration data; Indicates taking the absolute value.

[0035] It should be noted that Indicates the target band and The corrected difference between the reference bands; Indicates The fluctuation difference factor of the bearing vibration data; The larger the Within the collection time period The vibration data of the first bearing is compared with the The greater the difference between the bearing vibration data at the same position in other reference bands within the first acquisition period, the greater the difference between the bearing vibration data at the same position in the first acquisition period. The smaller the fluctuation difference factor, the greater the possibility of abnormal vibration data of the first bearing. The more the bearing vibration data in a collection period conform to the periodic distribution, the The smaller the possibility of abnormal bearing vibration data within a collection period; The larger the The smaller the fluctuation difference of the data points in the corresponding band of the bearing vibration data points at the first collection moment, the The smaller the anomaly in the vibration data of each bearing is likely to be.

[0036] At this point, the vibration fluctuation difference of each bearing vibration data in each cycle is obtained through the above method.

[0037] Step S003: Obtain the vibration difference of each bearing vibration data in each cycle according to the difference in vibration fluctuation between each bearing vibration data and other bearing vibration data; obtain the vibration abnormality degree of each bearing vibration data in each cycle according to the vibration difference of the bearing vibration data between each collection time period and the adjacent collection time periods; obtain the vibration correction amplitude of each bearing vibration data in each cycle.

[0038] 1. Obtain the vibration difference of each bearing vibration data in each cycle.

[0039] It should be noted that under normal circumstances, the bearing vibration data in each collection time period fluctuates uniformly and periodically. When an abnormality occurs, because the collection time interval is short, the abnormal collection time will not exist alone, and the abnormality will occur in the linked collection time. Therefore, the larger the abnormality, the greater the difference between the adjacent sampling times.

[0040] Preferably, in some implementations of the embodiments of the present invention, according to the difference in the vibration fluctuation difference between each bearing vibration data and other bearing vibration data, the specific method for obtaining the vibration difference of each bearing vibration data in each cycle is: In the During the collection period, The cumulative sum of the absolute values ​​of the differences between the vibration fluctuation difference of the first bearing vibration data and the vibration fluctuation difference of other bearing vibration data is taken as the The vibration difference of the bearing vibration data; The specific formula is: In the formula, Indicates The collection time period is The next cycle The vibration difference of the bearing vibration data; Indicates The number of all bearing vibration data in a collection period; Indicates The collection time period is The next cycle The difference in vibration fluctuations of the bearing vibration data; Indicates The collection time period is The next cycle The difference in vibration fluctuations of the bearing vibration data; Indicates taking the absolute value.

[0041] At this point, the vibration difference of each bearing vibration data in each cycle is obtained.

[0042] 2. Obtain the vibration abnormality degree of each bearing vibration data in each cycle.

[0043] It should be noted that since the abnormal collection moment does not exist alone, the collection moments at adjacent positions in adjacent collection time periods will be linked to abnormalities. Therefore, the vibration difference is corrected according to the difference in vibration difference of adjacent bearing vibration data in adjacent collection time periods to obtain the vibration abnormality degree of each bearing vibration data.

[0044] Preferably, in some implementations of the embodiments of the present invention, according to the difference in vibration difference between each acquisition time period and the adjacent acquisition time period, the specific method for obtaining the vibration abnormality degree of each bearing vibration data in each cycle is: Preset a time range neighborhood parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation; The first Before the collection period The subsequent acquisition time periods, along with the previous acquisition time periods, are all used as the reference acquisition time periods for the nth acquisition time period; For the nth acquisition time period, the absolute value of the difference between the vibration difference degree of the left adjacent bearing vibration data and the vibration difference degree of the right adjacent bearing vibration data for the nth bearing vibration data within the nth reference acquisition time period is denoted as the adjacent anomaly difference quantity for the nth reference acquisition time period; The cumulative sum of the adjacent anomaly difference quantities for all reference acquisition time periods of the nth acquisition time period is denoted as the vibration anomaly correction factor for the nth acquisition time period; The product of the vibration anomaly correction factor and the vibration difference degree of the nth bearing vibration data is used as the vibration anomaly degree of the nth bearing vibration data; The specific formula is as follows: Specifically, the formula is: In the formula, represents the vibration anomaly degree of the nth acquisition time period for the mth cycle and the kth bearing vibration data; represents the vibration difference degree of the nth acquisition time period for the mth cycle and the kth bearing vibration data; represents the number of all reference acquisition time periods for the nth acquisition time period; represents the vibration difference degree of the left adjacent bearing vibration data for the nth reference acquisition time period of the nth acquisition time period for the mth cycle and the kth bearing vibration data; represents the vibration difference degree of the right adjacent bearing vibration data for the nth reference acquisition time period of the nth acquisition time period for the mth cycle and the kth bearing vibration data; represents taking the absolute value.

[0045] It should be noted that Indicates the vibration anomaly correction factor.

[0046] Thus, the vibration anomaly degree of the vibration data of each bearing in each period is obtained.

[0047] 3. The vibration correction amplitude of the vibration data of each bearing in each period.

[0048] Preferably, in some implementation manners of the embodiments of the present invention, according to the difference in the vibration anomaly degree between the vibration data of each bearing and the vibration data of the surrounding bearings, the specific method for obtaining the vibration correction amplitude of the vibration data of each bearing in each period is as follows: Preset a collection neighborhood parameter , where in this embodiment, is taken as an example for description, and this embodiment does not make specific limitations, where is determined according to the specific implementation situation; In the th collection time period, the time series composed of the first bearing vibration data before the th bearing vibration data and the last bearing vibration data is recorded as the neighborhood reference data series of the th bearing vibration data; The mean value of all the bearing vibration data in the neighborhood reference data series of the th bearing vibration data is recorded as the first mean value; the absolute value of the difference between the th bearing vibration data in the th collection time period and the first mean value is recorded as the vibration correction factor; the normalized value of the product between the vibration anomaly degree of the th bearing vibration data and the vibration correction factor is used as the vibration correction amplitude of the th bearing vibration data; The specific formula is: In the formula, represents the vibration correction amplitude of the th bearing vibration data in the th period in the th collection time period; represents the vibration anomaly degree of the th bearing vibration data in the th period in the th collection time period; represents the th bearing vibration data in the th collection time period; represents the th collection time period and the The number of all bearing vibration data in the neighborhood reference data sequence of bearing vibration data; Denote the th bearing vibration data in the th neighborhood reference data sequence of bearing vibration data within the th acquisition time period; Denote taking the absolute value;

[0049] It should be noted that denotes the vibration correction factor.

[0050] Thus far, the vibration correction amplitude of each bearing vibration data under each period is obtained through the above method.

[0051] Step S004: Obtain the vibration data correction factor of the bearing based on the vibration correction amplitude; correct the acquired bearing vibration data according to the vibration data correction factor to obtain the corrected bearing vibration data.

[0052] Preferably, in some implementation manners of the embodiments of the present invention, the specific method for obtaining the vibration data correction factor of the bearing according to the vibration correction amplitudes of all bearing vibration data in all acquisition time periods under all cycles is as follows: Denote the difference between the th bearing vibration data in the th acquisition time period and the mean value of all bearing vibration data in the neighborhood reference data sequence of the th bearing vibration data in the th acquisition time period as the first difference; Multiply the first difference by the vibration correction amplitude of the th bearing vibration data as the vibration correction value of the th bearing vibration data; If the first difference is greater than or equal to 0, denote the difference between the th bearing vibration data and the vibration correction value as the corrected vibration data of the th bearing vibration data; If the first difference is less than 0, denote the sum of the th bearing vibration data and the vibration correction value as the corrected vibration data of the th bearing vibration data; Denote the ratio between the mean value of the corrected vibration data of all bearing vibration data in all acquisition time periods under all cycles and the mean value of all bearing vibration data in all acquisition time periods under all cycles as the vibration data correction factor of the bearing.

[0053] Preferably, the specific method for optimizing the collected bearing vibration data according to the vibration data correction factor is as follows: For the bearing vibration data collected by the vibration sensor at any time, the sum of the bearing vibration data correction factor and 1 is recorded as the vibration correction value; the product of the bearing vibration data collected this time and the vibration correction value is used as the optimized bearing vibration data collected this time.

[0054] Through the above steps, the bearing vibration data acquisition method based on the vibration sensor is completed.

[0055] Another embodiment of the present invention provides a bearing vibration data acquisition system based on a vibration sensor. The system includes a memory and a processor. When the processor executes the computer program stored in the memory, it executes the above method steps S001 to step S004.

[0056] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A bearing vibration data acquisition method based on a vibration sensor, characterized in that: The method comprises the following steps: Acquire bearing vibration data signals within several time periods; By analyzing the noise distribution in the bearing vibration data signal, all cycles of the bearing vibration data signal in each acquisition time period are obtained; by analyzing the distribution difference of the bearing vibration data signal in each cycle, the vibration fluctuation difference of each bearing vibration data is obtained; According to the difference in the vibration fluctuation difference between each bearing vibration data and other bearing vibration data, the vibration difference degree of each bearing vibration data is obtained; according to the vibration difference degree of the bearing vibration data between each collection time period and the adjacent collection time period, the vibration abnormality degree of each bearing vibration data is obtained; according to the vibration abnormality degree, the vibration correction amplitude of each bearing vibration data is obtained; The vibration data correction factor of the bearing is obtained based on the vibration correction amplitude; the collected bearing vibration data is corrected according to the vibration data correction factor to obtain the corrected bearing vibration data.

2. The bearing vibration data acquisition method based on a vibration sensor according to claim 1 is characterized in that: The specific method of obtaining all cycles of the bearing vibration data signal in each acquisition time period by analyzing the noise distribution in the bearing vibration data signal includes: Construct a rectangular coordinate system based on the acquisition time and bearing vibration data; The bearing vibration data signal within the acquisition time period is input into the rectangular coordinate system to obtain the Several bearing vibration data points within a collection period; in the rectangular coordinate system, the least squares method is used to transform the All the bearing vibration data points in the acquisition time period are curve fitted to obtain the The fluctuation curve of bearing vibration data within a collection period; For The bearing vibration data fluctuation curve within the acquisition time period is Fourier transformed, and the inverse of the frequency with the largest amplitude in the spectrum is taken as the A cycle of the fluctuation curve of the bearing vibration data within the acquisition time period is recorded as the target cycle; according to the maximum amplitude in the spectrum diagram and the frequency of the target cycle, the obtained curve is recorded as the fluctuation curve of the target cycle; The difference curve between the fluctuation curve of the bearing vibration data in a collection time period and the fluctuation curve of the target period is recorded as the curve to be analyzed; the EMD decomposition algorithm is used to decompose the curve to be analyzed to obtain several IMF components; For any IMF component, a spectrum of the IMF component is obtained by Fourier transform; the frequency corresponding to each peak in the spectrum is obtained by peak detection method and recorded as peak frequency; the sum of the absolute values ​​of the difference between the mean of all peak frequencies of the IMF component and the mean of all peak frequencies of all other IMF components is taken as the possibility that the IMF component belongs to high-frequency noise; The IMF component with the highest probability of being high-frequency noise is recorded as the noise component, and the other IMF components and the residual term are added to obtain the curve to be analyzed after the noise is removed; the curve to be analyzed after the noise is removed is subjected to Fourier transform, and the inverse of the frequency corresponding to each peak in the spectrum is taken as the first One cycle of the bearing vibration data fluctuation curve within a collection time period.

3. The bearing vibration data acquisition method based on a vibration sensor according to claim 1 is characterized in that: The specific method of obtaining the vibration fluctuation difference of each bearing vibration data by analyzing the distribution difference of the bearing vibration data signal in each cycle is as follows: For The bearing vibration data signal within the acquisition time period cycle, the The fluctuation curve of bearing vibration data within the collection time period is calculated according to The cycle is divided into The next cycle All bands of the bearing vibration data fluctuation curve within a collection time period; In the In the fluctuation curve of bearing vibration data within a collection period, The band corresponding to the bearing vibration data point is recorded as the target band; all bands except the target band are recorded as reference bands; According to The similarity between the vibration data of the first bearing and other bearings is obtained. All similar data of bearing vibration data; The first The position of the bearing vibration data in the target band is recorded as the target position; The vibration data of the first bearing is compared with the The absolute value of the difference between the bearing vibration data at the target position in the first reference band is recorded as the difference between the target band and the The data difference between the reference bands; the target band and the The DTW distance between the reference bands is recorded as the DTW distance between the target band and the The band difference value between the reference bands; the product of the data difference value and the band difference value is recorded as the difference between the target band and the The corrected difference between the reference bands; The cumulative sum of the corrected difference values ​​between the target band and all reference bands is recorded as The fluctuation difference factor of the bearing vibration data is The ratio of the number of all similar data of the bearing vibration data is taken as the The difference in vibration fluctuations of the bearing vibration data.

4. The bearing vibration data acquisition method based on a vibration sensor according to claim 3 is characterized in that: According to the The similarity between the vibration data of the first bearing and other bearings is obtained. All similar data of bearing vibration data, including the specific method is: Preset a similarity threshold parameter , The vibration data of the first bearing is compared with the The absolute value of the difference between the bearing vibration data at the target position in the reference band is less than or equal to the similarity threshold parameter , will The bearing vibration data at the target position in the first reference band is used as the Similar data for the vibration data of the bearings.

5. The bearing vibration data acquisition method based on a vibration sensor according to claim 1 is characterized in that: The specific method of obtaining the vibration difference degree of each bearing vibration data according to the difference in the vibration fluctuation difference between each bearing vibration data and other bearing vibration data is as follows: In the During the collection period, The cumulative sum of the absolute values ​​of the differences between the vibration fluctuation difference of the first bearing vibration data and the vibration fluctuation difference of other bearing vibration data is taken as the The vibration difference of the bearing vibration data.

6. The bearing vibration data acquisition method based on a vibration sensor according to claim 1 is characterized in that: The specific method of obtaining the vibration abnormality degree of each bearing vibration data according to the vibration difference degree of the bearing vibration data between each collection time period and the adjacent collection time period is as follows: Preset a time range neighborhood parameter , will Before the collection period The collection period and The collection time periods are all taken as A reference collection time period for a collection time period; The first The first The first The vibration difference between the left adjacent bearing vibration data of the first bearing and the The first The first The absolute value of the difference between the vibration difference of the right adjacent bearing vibration data of the bearing vibration data is recorded as The adjacent abnormal difference of the reference acquisition time period; The cumulative sum of the adjacent abnormal differences of all reference collection time periods in the collection time period is recorded as Vibration anomaly correction factor for each acquisition period; The vibration abnormality correction factor and The product of the vibration difference between the vibration data of the first bearing is taken as the The vibration abnormality degree of each bearing vibration data.

7. The bearing vibration data acquisition method based on a vibration sensor according to claim 1 is characterized in that: The specific method of obtaining the vibration correction amplitude of each bearing vibration data according to the vibration abnormality degree includes: Preset a collection neighborhood parameter , in During the collection period, bearing vibration data bearing vibration data and the The time sequence composed of bearing vibration data is recorded as A neighborhood reference data sequence of bearing vibration data; The first The mean of all bearing vibration data in the neighborhood reference data sequence of the bearing vibration data is recorded as the first mean; Within the collection time period The absolute value of the difference between the vibration data of the first bearing and the first mean is recorded as the vibration correction factor; The normalized value of the product of the vibration abnormality degree and the vibration correction factor of the first bearing vibration data is taken as the The vibration correction amplitude of each bearing vibration data.

8. The bearing vibration data acquisition method based on a vibration sensor according to claim 1 is characterized in that: The specific method of obtaining the vibration data correction factor of the bearing based on the vibration correction amplitude includes: The first Within the collection time period The vibration data of the first bearing is compared with the Within the collection time period The difference between the mean values ​​of all bearing vibration data in the neighborhood reference data sequence of the bearing vibration data is recorded as the first difference; the first difference is added to the The product of the vibration correction amplitudes of the bearing vibration data is used as the Vibration correction value of each bearing vibration data; If the first difference is greater than or equal to 0, The difference between the vibration data of the first bearing and the vibration correction value is taken as the The corrected vibration data of the bearing vibration data; if the first difference is less than 0, the The sum of the bearing vibration data and the vibration correction value is taken as the Corrected vibration data of each bearing vibration data; The ratio between the mean of the corrected vibration data of all bearing vibration data in all cycles of all acquisition time periods and the mean of all bearing vibration data in all cycles of all acquisition time periods is used as the vibration data correction factor of the bearing.

9. The bearing vibration data acquisition method based on a vibration sensor according to claim 1 is characterized in that: The method of correcting the collected bearing vibration data according to the vibration data correction factor to obtain the corrected bearing vibration data includes the following specific methods: For any bearing vibration data collected by the vibration sensor, the sum of the bearing vibration data correction factor and 1 is recorded as the vibration correction value; the product of the bearing vibration data collected this time and the vibration correction value is used as the optimized bearing vibration data collected this time.

10. A bearing vibration data acquisition system based on a vibration sensor, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the bearing vibration data acquisition method based on a vibration sensor as described in any one of claims 1 to 9 are implemented.

Images