Rotating machinery fault source positioning method based on optimal acquisition point of mobile robot

Abstract

The present application relates to the technical field of sound source positioning, and particularly relates to a rotating mechanical fault source positioning method based on optimal collection points of a mobile robot, which comprises the following steps: acquiring an initial sound signal; determining an optimal collection angle by comparing signal qualities at different positions; determining an optimal collection distance; determining an optimal collection height; acquiring a target frequency for fixed frequency band sound source positioning through fault feature analysis; and visually determining a fault source position through sound field imaging. The present application realizes sound signal collection through flexible movement of the robot, gradually adjusts collection parameters, compares signal qualities at different angles, distances and heights through a sound array, and determines an optimal collection position, so as to ensure adaptive detection of an object to be identified, ensure that the collected sound signal can reflect fault source features to the greatest extent, thereby improving positioning accuracy, visually display the fault source position through sound field imaging combined with a video image and a sound field image, and enhance the reliability and intuitiveness of positioning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sound source positioning, and particularly relates to a rotating mechanical fault source positioning method based on optimal collection points of a mobile robot. BACKGROUND

[0002] Rotating machinery is widely used in key technical equipment such as machining and manufacturing, automobile production, mining and transportation, high-speed motor train unit, nuclear power unit and the like. However, these important mechanical equipment often needs to serve in harsh and changeable working conditions for a long time, and is subjected to the continuous action of factors such as alternating load, impact load, speed fluctuation, etc., so that the rotating machinery system faults occur frequently. Once the rotating system fault occurs, it will cause a series of chain reactions, which may affect the normal operation of the whole machine, or even cause machine damage and human casualties, and lead to catastrophic safety accidents. Therefore, it is very important to carry out research on rotating machinery fault diagnosis and health state monitoring technology, to find potential early faults in the mechanical system as soon as possible, and to eliminate hidden dangers, so as to ensure the safe and reliable operation of the mechanical system, and to avoid major economic losses and personnel casualty accidents.

[0003] In modern factories, the application of automatic inspection robots is being popularized. The automatic inspection robot can provide equipment fault, environment safety judgment and automatic alarm for enterprises without human intervention, help enterprises better automate management, can significantly enhance the ability of remote collaborative work, and improve work efficiency. And it can avoid the carelessness of inspection personnel, reduce labor costs, greatly reduce safety hazards and reduce the occurrence of safety accidents. Looking at the current actual application of inspection robots in various industries, most of them use machine vision technology to obtain various information of equipment, so as to judge the running state of the equipment. However, using machine vision technology can only observe the surface information of the machine equipment, and when the fault is not on the surface of the equipment, this kind of inspection robot cannot well perform fault positioning and autonomous analysis.

[0004] Most of the traditional fault diagnosis systems obtain local vibration signals through acceleration sensors, but the installation position and precision of the acceleration sensor are poor due to the vibration of the mechanical equipment, and some equipment cannot provide suitable conditions for the installation of the vibration sensor, such as equipment in harsh environments such as high temperature, high corrosion and high humidity.

[0005] The patent document with the publication number CN112051063A discloses a device fault sound source positioning method and system. The patent takes the collected device sound signal as the signal to be analyzed, performs Fourier transform on the signal to be analyzed, calculates the fast spectral kurtosis index of the signal to be analyzed according to the transform result, and determines the fault feature frequency selection result according to the fast spectral kurtosis index. According to the fault feature frequency selection result and the signal to be analyzed, the cross-spectrum matrix and the delay sum steering response are calculated to obtain the delay sum beamforming imaging result of the fault frequency selection. The delay sum beamforming imaging result is input into the trained double-channel convolutional neural network to obtain the positioning information of the fault sound source point.

[0006] From this, the following problems are seen: in the prior art, when the actual sound field environment on site is complex and changeable, it will lead to poor and unstable sound signal quality and inaccurate fault positioning results. SUMMARY

[0007] To this end, the present application provides a rotating machine fault source positioning method based on the optimal collection point of a mobile robot, which uses the movement characteristics of the robot to determine the optimal position for sound signal collection to overcome the problem in the prior art that when the actual sound field environment on site is complex and changeable, it will lead to poor and unstable sound signal quality and inaccurate fault positioning results.

[0008] To achieve the above-mentioned purpose, the present application provides a rotating machine fault source positioning method based on the optimal collection point of a mobile robot, comprising:

[0009] Collecting sound information of the object to be identified using a sound array according to preset initial collection parameters to obtain an initial sound signal;

[0010] The collection parameters include an initial collection angle, an initial collection distance, and an initial collection height;

[0011] Step-by-step adjustment of the initial collection angle according to a preset angle adjustment step to obtain an adjusted collection angle;

[0012] Obtaining a first sound signal of the object to be identified based on the adjusted collection angle, the initial collection distance, and the initial collection height, and determining an optimal collection angle based on the initial sound signal and the first sound signal;

[0013] Step-by-step adjustment of the initial collection distance according to a preset distance adjustment step to obtain an adjusted collection distance;

[0014] Obtaining a second sound signal of the object to be identified based on the optimal collection angle, the adjusted collection distance, and the initial collection height, and determining an optimal collection distance based on the first sound signal and the second sound signal;

[0015] adjusting the initial acquisition height step by step according to a preset height adjustment step to obtain an adjusted acquisition height;

[0016] acquiring a third sound signal of the to-be-identified object based on the optimal acquisition angle, the optimal acquisition distance and the adjusted acquisition height, and determining an optimal acquisition height based on the second sound signal and the third sound signal;

[0017] performing spectrum analysis on the sound signal of the best quality acquired based on the optimal acquisition angle, the optimal acquisition distance and the optimal acquisition height to obtain a target frequency;

[0018] sound source positioning with a fixed frequency band width;

[0019] acquiring a sound field image of the target frequency;

[0020] acquiring a video image of the to-be-identified object;

[0021] determining a fault source position based on the sound field image and the video image.

[0022] Further, the step of adjusting the initial acquisition angle step by step according to a preset angle adjustment step to obtain an adjusted acquisition angle comprises:

[0023] setting an angle adjustment step;

[0024] gradually increasing the initial acquisition angle according to the angle adjustment step in an adjustment period to obtain the adjusted acquisition angle.

[0025] Further, the step of determining an optimal acquisition angle based on the initial sound signal and the first sound signal comprises:

[0026] acquiring a first characteristic parameter of the first sound signal and an initial characteristic parameter of the initial sound signal;

[0027] calculating a first difference value by subtracting each initial characteristic parameter from each first characteristic parameter;

[0028] calculating a first difference ratio by dividing each first difference value by the corresponding initial characteristic parameter, and calculating a total first difference ratio by summing up all the first difference ratios;

[0029] comparing a plurality of total first difference ratios to determine the adjusted acquisition angle of the first sound signal when the total first difference ratio is the largest as the optimal acquisition angle.

[0030] Further, the step of adjusting the initial acquisition distance step by step according to a preset distance adjustment step to obtain an adjusted acquisition distance comprises:

[0031] setting a distance adjustment step;

[0032] According to the distance adjustment step, the initial acquisition distance is gradually increased according to an adjustment period to obtain the adjusted acquisition distance.

[0033] Further, the determining the optimal acquisition distance based on the first sound signal and the second sound signal comprises:

[0034] obtaining a second characteristic parameter of the second sound signal;

[0035] calculating a second difference value by subtracting each of the first characteristic parameters from each of the second characteristic parameters;

[0036] calculating a second difference value ratio by dividing the second difference value by the corresponding first characteristic parameter, and calculating a total second difference value ratio by summing up each of the second difference value ratios;

[0037] comparing a plurality of the total second difference value ratios, and determining the adjusted acquisition distance of the second sound signal when the total second difference value ratio is the largest as the optimal acquisition distance.

[0038] Further, the gradually adjusting the initial acquisition height according to the preset height adjustment step to obtain the adjusted acquisition height comprises:

[0039] setting a height adjustment step;

[0040] According to the height adjustment step, the initial acquisition height is gradually increased according to an adjustment period to obtain the adjusted acquisition height.

[0041] Further, the determining the optimal acquisition distance based on the second sound signal and the third sound signal comprises:

[0042] obtaining a third characteristic parameter of the third sound signal;

[0043] calculating a third difference value by subtracting each of the second characteristic parameters from each of the third characteristic parameters;

[0044] calculating a third difference value ratio by dividing the third difference value by the corresponding second characteristic parameter, and calculating a total third difference value ratio by summing up each of the third difference value ratios;

[0045] comparing a plurality of the total third difference value ratios, and determining the adjusted acquisition distance of the third sound signal when the total third difference value ratio is the largest as the optimal acquisition distance.

[0046] Further, the obtaining the sound field image of the target frequency comprises:

[0047] using a band-pass filter to filter out invalid frequencies in the target frequency to obtain valid target frequencies, and performing sound source positioning according to the valid target frequencies to obtain the sound field image of the fault source.

[0048] Further, the spectrum analysis of the optimal sound signal obtained according to the optimal collection angle, the optimal collection distance and the optimal collection height to obtain the target frequency comprises:

[0049] Obtaining a sound signal spectrum of the optimal sound signal;

[0050] Performing frequency domain analysis on the sound signal spectrum to determine a frequency with the maximum amplitude in the frequency domain as the target frequency.

[0051] Further, the determination of the fault source position based on the sound field image and the video image comprises:

[0052] Fusing the video image and the sound field image to obtain sound field imaging;

[0053] Determining the fault source position according to the sound field imaging.

[0054] Compared with the prior art, the present application has the beneficial effects that through systematic sound information collection and gradual adjustment of collection parameters, the sound array collects sound signals at different angles, distances and heights, ensuring comprehensive coverage and high sensitivity detection of the object to be identified, ensuring that the high-quality sound signal collected at the optimal collection point can reflect the characteristics of the fault source to the greatest extent, thereby improving the positioning accuracy, combining the video image and the sound field image, the fault source position can be intuitively displayed in space, the reliability and intuitiveness of positioning are enhanced, and the application is suitable for automatic monitoring in complex environments, facilitating early maintenance and replacement of equipment by workers, and avoiding greater losses.

[0055] Further, through the preset step and period, the angle adjustment process can be effectively controlled, the comprehensive search in the angle dimension is ensured, the optimal angle is avoided to be missed, and the parameters can be adjusted according to actual conditions to adapt to different application scenarios.

[0056] Further, through the characteristic parameters and the difference, the characteristic change of the sound signal is quantified, comparison and optimization are facilitated, the change trend of the signal is focused on through comparison of the difference, the angle with the most obvious signal characteristic change can be quickly and effectively selected as the optimal angle, and the accuracy and reliability of fault source positioning are improved.

[0057] Further, through the setting of the distance adjustment step, different collection distances can be accurately controlled, and dynamic adaptation can be performed according to the sound field characteristics of the object to be identified and environmental changes, so that the optimal sound signal can be obtained under different working conditions, and flexibility is improved.

[0058] Further, by acquiring the second feature parameter of the second sound signal and comparing it with the feature parameter of the first sound signal, the change in the sound signal can be effectively identified, and by maximizing the second difference, it is ensured that the selected distance can reflect the acoustic characteristics of the object to be identified to the greatest extent during the sound signal collection process, improving the effectiveness of signal collection and helping to better capture the sound signal features related to the fault, thereby improving the accuracy of fault diagnosis.

[0059] Further, by setting the height adjustment step, accurate control of different collection heights can be achieved during the sound signal collection process, improving the accuracy of signal collection. Through meticulous height adjustment, the acoustic characteristics of the object to be identified at different heights can be more comprehensively captured, enhancing the identification ability of potential fault signals and improving the accuracy and reliability of fault source positioning.

[0060] Further, by accurately determining the optimal collection height, the sound signal features related to the fault can be obtained more quickly. By optimizing the collection height, the quality of the collected sound signal is ensured, thereby significantly improving the precision, efficiency and automation level of fault source positioning, thereby speeding up the fault diagnosis and facilitating the maintenance and management of rotating machinery equipment.

[0061] Further, by using a band-pass filter to filter out invalid frequencies in the sound signal and only retaining the signal part effective for fault positioning in the target frequency, the frequency selectivity is effectively improved, the signal clarity of the target frequency is enhanced, and the system can focus more accurately on the frequency components related to the fault source, avoiding misidentification caused by invalid frequency interference, making subsequent fault diagnosis more intuitive and accurate, thereby improving work efficiency.

[0062] Further, by performing frequency domain analysis on the sound signal spectrum of the optimal collection point, the frequency with the largest amplitude can be accurately extracted from the complex signal as the most representative target frequency. This process ensures that the system can automatically identify the frequency from among numerous frequency components, thereby effectively positioning the key signals related to the fault and avoiding interference from irrelevant frequencies, thereby improving the accuracy and reliability of fault source positioning.

[0063] Further, by fusing the sound field image with the video image, the spatial distribution of the acoustic signal can be effectively combined with the physical location in the visual image, thereby quickly and accurately marking the location of the fault source in the video image, improving the spatial precision of fault source positioning. The operator can visually see the fault source location and quickly make maintenance decisions, greatly improving the efficiency and timeliness of fault diagnosis. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1This is a flowchart of a rotating machinery fault source localization method based on the optimal acquisition points of a mobile robot, according to an embodiment of the present invention.

[0065] Figure 2 This is a logic diagram for determining the optimal sampling point in an embodiment of the present invention.

[0066] Figure 3 A flowchart for determining the optimal acquisition angle in an embodiment of the present invention;

[0067] Figure 4 This is a flowchart for determining the optimal acquisition distance in an embodiment of the present invention. Detailed Implementation

[0068] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0069] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0070] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0071] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0072] Please see Figure 1 ,like Figure 1 The diagram shown is a flowchart of a method for locating the fault source of rotating machinery based on the optimal collection point of a mobile robot, provided in an embodiment of the present invention.

[0073] Specifically, embodiments of the present invention provide a method for locating the fault source of rotating machinery based on the optimal acquisition points of a mobile robot, including:

[0074] Step S1, collecting sound information of the object to be identified using a sound array according to preset initial collection parameters to obtain an initial sound signal;

[0075] The collection parameters include an initial collection angle, an initial collection distance, and an initial collection height;

[0076] Step S2, gradually adjusting the initial collection angle according to a preset angle adjustment step to obtain an adjusted collection angle;

[0077] Based on the adjusted collection angle, the initial collection distance, and the initial collection height, a first sound signal of the object to be identified is obtained, and an optimal collection angle is determined based on the initial sound signal and the first sound signal;

[0078] Step S3, gradually adjusting the initial collection distance according to a preset distance adjustment step to obtain an adjusted collection distance;

[0079] Based on the optimal collection angle, the adjusted collection distance, and the initial collection height, a second sound signal of the object to be identified is obtained, and an optimal collection distance is determined based on the first sound signal and the second sound signal;

[0080] Step S5, gradually adjusting the initial collection height according to a preset height adjustment step to obtain an adjusted collection height;

[0081] Based on the optimal collection angle, the optimal collection distance, and the adjusted collection height, a third sound signal of the object to be identified is obtained, and an optimal collection height is determined based on the second sound signal and the third sound signal;

[0082] Performing frequency spectrum analysis on the sound signal obtained according to the optimal collection angle, the optimal collection distance, and the optimal collection height to obtain a target frequency;

[0083] Sound source positioning with a fixed frequency band width;

[0084] Step S6, obtaining a sound field image of the target frequency;

[0085] Obtaining a video image of the object to be identified;

[0086] Determining a fault source position based on the sound field image and the video image.

[0087] The object to be identified is a rotating mechanical equipment in the field of a factory workshop, such as a water pump, a compressor, a motor and the like driving equipment, which is a motor in the embodiment, the sound array is a device equipped with a robot to obtain a sound signal, which can be different types of microphone array as long as real-time sound field data can be collected, which is a 16-element MEMS digital silicon microphone rectangular array UMA-16v2 in the embodiment, the video image of the object to be identified can be various cameras as long as the video image of the field can be collected in real time, which is a camera of IMX294USB in the embodiment, the initial sound signal is the sound signal obtained by the sound array according to the initial collection parameters, the first sound signal is the best sound signal collected according to the best collection angle, the second sound signal is the best sound signal collected according to the best collection angle and the best collection distance, the third sound signal is the best sound signal collected according to the best collection angle, the best collection distance and the best collection height, the initial collection angle is the initial angle between the sound collection direction of the sound array and the object to be identified, which is generally set between 0°-30°, which is set to 0° in the embodiment, the initial collection distance is the initial distance between the sound collection place of the sound array and the object to be identified, which is generally set between 0.5-1m, which is set to 0.5m in the embodiment, and the initial collection height is the height difference between the sound collection place of the sound array and the object to be identified, which is generally set between 1-1.5m, and the initial collection height is 1m in the embodiment.

[0088] The best collection angle is the angle between the sound collection place with the best sound signal quality obtained by the sound array and the object to be identified, the best collection distance is the distance between the sound collection place with the best sound signal quality obtained by the sound array and the object to be identified, the best collection height is the height between the sound collection place with the best sound signal quality obtained by the sound array and the object to be identified, the adjustment collection angle is the amplitude of the angle adjustment between the sound array and the object to be identified each time, which is generally set between 0-60°, which is set to 45° in the embodiment, the adjustment collection distance is the amplitude of the distance adjustment between the sound array and the object to be identified each time, which is generally set between 0m-1m, which is set to 0.5m in the embodiment, the adjustment collection height is the amplitude of the height adjustment between the sound array and the object to be identified each time, which is generally set between 0m-0.5m, which is set to 0.25m in the embodiment, the first characteristic parameter, the second characteristic parameter and the third characteristic parameter refer to parameters such as signal-to-noise ratio and fault characteristic amplitude ratio which can determine the sound signal quality, which refer to four sound signal quality evaluation indexes such as root mean square, sound pressure level, signal-to-noise ratio and fault characteristic amplitude ratio in the embodiment.

[0089] Root mean square value, also known as effective value, represents the energy size of the sound signal generated by rotating machinery. When the bearing is not faulty, it runs smoothly and the sound is small, and the corresponding RMS value is also relatively small. As the fault gradually intensifies, the RMS will also increase. As shown in formula (1):

[0090]

[0091] Sound pressure level, the "effective sound pressure" measured in logarithmic scale, describes the overall noise level of the sound source. The reference sound pressure Pref is the minimum sound pressure value 20μPa that the human ear can hear at 1000Hz. The larger the detected sound source noise, the larger the overall sound pressure level. As shown in formula (2):

[0092]

[0093] Signal-to-noise ratio, which represents the ratio of the power of the useful signal to the power of the background noise, is an important parameter for measuring signal quality. Where Ps is the effective signal power and Pn is the noise signal power. High SNR value means good signal quality and less noise interference to the signal. Low SNR value indicates that the signal has more noise components and the signal quality is poor. As shown in formula (3):

[0094]

[0095] Fault characteristic amplitude ratio can quantitatively evaluate the fault information in the signal envelope spectrum. Fcf is the theoretically calculated fault characteristic frequency, i is the i-th harmonic, l is the number of harmonics to be analyzed, df is the frequency resolution, Fi represents the deviation between the theoretical Fcf and the actual Fcf due to gear speed instability, the deviation range is [Fcf-4×df, Fcf+4×df], and Hes represents the Hilbert envelope spectrum; The higher the RFCA value, the more bearing fault diagnosis information contained in the frequency spectrum. As shown in formula (4):

[0096]

[0097] Specifically, the determination of the best collection angle, the determination of the best collection distance, and the determination of the best collection height are three determinations of the collection parameters of the best collection point, which can be combined and exchanged in order according to actual needs. In this embodiment, the determination order is to determine the best collection angle, determine the best collection distance, and determine the best collection height. First, control the robot to move and gradually adjust the collection angle, the collection distance and the collection height to determine the best collection angle, the best collection distance and the best collection height to obtain the best position for acquiring the sound signal of the object to be identified. Then, high-quality sound signals of the object to be identified are obtained, frequency domain analysis is performed to determine the target frequency with the most obvious difference, sound source positioning of the target frequency is performed, and the acquired video stream image is further fused into a sound field image to visually analyze the actual position of the fault source.

[0098] Specifically, through systematic sound information collection and gradual adjustment of collection parameters, the sound array collects sound signals at different angles, distances and heights, ensuring comprehensive coverage and high sensitivity detection of the object to be identified, ensuring that the collected sound signals can reflect the characteristics of the fault source to the greatest extent, thereby improving the positioning accuracy, combining video images and sound field images, the fault source position can be intuitively displayed in space, enhancing the reliability and intuitiveness of positioning, suitable for automated monitoring in complex environments, facilitating early maintenance and replacement of equipment by workers, avoiding greater losses.

[0099] Please continue to refer to Figure 2 As shown in the flow chart for determining the optimal collection angle of the embodiment of the application, Figure 2

[0100] Specifically, the initial collection angle is gradually adjusted according to the preset angle adjustment step to obtain an adjusted collection angle.

[0101] The angle adjustment step is set.

[0102] The initial collection angle is gradually increased according to the adjustment period according to the angle adjustment step to obtain the adjusted collection angle.

[0103] Specifically, the adjustment period is the interval time for the robot to move and adjust, which is generally set to 0-3s, and in this embodiment, the adjustment period is 2s.

[0104] In the specific implementation process, the motor with a rotating speed of 2400r / min and a load of 0% is positioned for the fault source, the initial collection angle is 0°, the angle adjustment step is 45°, the sound signal of the object to be identified is collected at the initial collection angle of 0°, and then the collection angle is increased by 45° every 2s to obtain a new adjusted collection angle. The adjustment step is 3 times, and the collection time at the initial angle and each adjusted angle is 5s.

[0105] Specifically, by presetting the step and period, the angle adjustment process can be effectively controlled to ensure comprehensive search in the angle dimension, avoid missing the optimal angle, and adjust the parameters according to the actual situation to adapt to different application scenarios.

[0106] Specifically, the optimal collection angle is determined based on the initial sound signal and the first sound signal.

[0107] The first characteristic parameters of the first sound signal and the initial characteristic parameters of the initial sound signal are obtained.

[0108] The first difference value is obtained by subtracting the corresponding initial characteristic parameters from each first characteristic parameter.​

[0109] The ratio of the first difference value to the corresponding initial characteristic parameter is calculated to obtain a first difference value ratio, and the sum of each first difference value ratio is calculated to obtain a total first difference value ratio;

[0110] By comparing several total first difference value ratios, the adjustment collection angle of the first sound signal when the total first difference value ratio is the largest is determined as the optimal collection angle.

[0111] Table 1 Characteristic parameter values at different angles

[0112]

[0113]

[0114] Specifically, the first characteristic parameters (the four index values of the characteristic parameters corresponding to 45°, 90° and 135°) are subtracted by the initial characteristic parameters (the four index values of the characteristic parameters corresponding to 0°) to obtain respective difference values, and then the respective difference values are divided by the index values corresponding to the initial characteristic parameters to obtain respective difference value ratios. The sum of the difference value ratios of the four indexes is obtained to obtain the total first difference value ratio of the three adjusted collection angles, i.e. the above-mentioned total first difference value ratio. As shown in Table 1, the specific characteristic parameter values, difference values and difference value ratios at different angles are shown. The SNR value in the table is only a linear ratio, not a logarithm. It is convenient for calculating the difference value ratio.

[0115] By comparing three total first difference value ratios, the adjustment collection angle 0° of the first sound signal when the total first difference value ratio is the largest is determined as the optimal collection angle. (The first difference value ratio is 0 at 0°, and the other three angles are negative values, so the signal quality is worse than that at the initial angle) In the specific implementation process, according to the initial collection angle 0°, the initial collection distance 0.5m and the initial collection height 1m, the initial characteristic parameters of the initial sound signal collected are RMS0=0.295Pa, SPL0=83.025dB, SNR0=0.672 and RFCA0=4.475. The specific index values of the adjusted parameters after adjustment at the adjusted collection angles of 45°, 90° and 135° are shown in Table 1. Then the respective first difference value ratios are determined as -23.05%, -73.62% and -118.08%, and the optimal collection angle is determined as 0°.

[0116] Specifically, by using characteristic parameters and difference values, the characteristic change amount of the sound signal is quantified, which is convenient for comparison and optimization. By comparing the difference values, the change trend of the signal is focused on, so that the angle with the most obvious signal characteristic change can be quickly and effectively selected as the optimal angle, thereby improving the accuracy and reliability of fault source positioning.

[0117] Please continue to refer to Figure 3 For example Figure 3As shown, it is a flow chart for determining the optimal collection distance by the embodiment of the present application;

[0118] Specifically, the initial collection distance is adjusted step by step according to the preset distance adjustment step to obtain the adjusted collection distance.

[0119] The distance adjustment step is set.

[0120] The initial collection distance is gradually increased according to the adjustment period according to the distance adjustment step to obtain the adjusted collection distance.

[0121] In the specific implementation process, the initial collection distance is 0.5m, the distance adjustment step is 0.5m, the initial collection distance of 0.5m is used to collect the sound signal of the target to be identified, and then the collection distance is increased by 0.5m every 2s to obtain a new adjusted collection distance. The adjustment number is 3 times, and the collection time at the initial distance and each adjusted distance is 5s.

[0122] Specifically, by setting the distance adjustment step, the initial collection distance can be accurately controlled, and the sound field characteristics of the object to be identified and the environmental changes can be dynamically adapted, so that the best sound signal can be obtained under different working conditions, and the flexibility is improved.

[0123] Specifically, the optimal collection distance is determined based on the first sound signal and the second sound signal.

[0124] The second feature parameter of the second sound signal is obtained.

[0125] The difference between each second feature parameter and each first feature parameter is calculated to obtain a second difference value.

[0126] The ratio of the second difference value to the corresponding first feature parameter is calculated to obtain a second difference ratio, and the sum of each second difference ratio is calculated to obtain a total second difference ratio.

[0127] By comparing a plurality of total second difference ratios, the adjusted collection distance of the second sound signal when the total second difference ratio is the largest is determined as the optimal collection distance.

[0128] Table 2: Feature parameter values at different distances

[0129]

[0130] Specifically, the second characteristic parameters (1m, 1.5m and 2m corresponding characteristic parameter four index values) are subtracted by the first characteristic parameters (0°, 0.5m corresponding characteristic parameter four index values, due to the complexity of the actual sound field and measurement error, the values are slightly different from the first characteristic parameter index values in Table 1) to obtain the respective differences, and then the respective differences are divided by the index values corresponding to the first characteristic parameters to obtain the respective difference ratios. Then, the difference ratios of the four indexes are summed to obtain the total second difference ratio of the three adjusted collection distances, that is, the above-mentioned total second difference ratio. As shown in Table 2, the specific characteristic parameter values, differences and difference ratios at different distances. The SNR value in the table is only a linear ratio, not taking the logarithm. Facilitate the calculation of the difference ratio.

[0131] By comparing the three total second difference ratios, the adjusted collection distance 1.5m of the second sound signal when the total second difference ratio is maximum is determined as the optimal collection distance.

[0132] In the specific implementation process, according to the optimal collection angle 0°, the initial collection distance 0.5m and the initial collection height 1m, the first characteristic parameters of the sound signal collected are RMS1=0.27Pa, SPL1=82.825dB, SNR1=0.507 and RFCA1=4.425. The adjusted parameters of the adjusted collection distances of 1m, 1.5m and 2m are shown in Table 2. Then, the second difference ratios are determined as -89.11%, -10.91% and -108.19%, and the optimal collection distance is determined as 1.5m.

[0133] Specifically, by obtaining the second characteristic parameters of the second sound signal and comparing them with the characteristic parameters of the first sound signal, the changes in the sound signal can be effectively identified. By maximizing the second difference ratio, it is ensured that the selected distance can reflect the acoustic characteristics of the object to be identified to the greatest extent during sound signal collection, improving the effectiveness of signal collection and helping to better capture the sound signal features related to the fault, thereby improving the accuracy of fault diagnosis.

[0134] Please continue to refer to Figure 4 As Figure 4 shown, it is a flow chart for determining the optimal collection height according to the embodiment of the application;

[0135] Specifically, the step of gradually adjusting the initial collection height according to the preset height adjustment step to obtain the adjusted collection height comprises:

[0136] Setting a height adjustment step;

[0137] According to the height adjustment step, gradually increase the initial collection height according to the adjustment period to obtain the adjusted collection height.

[0138] In the specific implementation process, the initial acquisition height is 1 m, the height adjustment step is 0.25 m, the sound signal of the to-be-identified target is acquired according to the initial acquisition height of 1 m, and then the acquisition height is increased by 0.25 m every 2 s to obtain a new adjusted acquisition height. The adjustment number is 3 times, and the acquisition time at the initial height and each adjusted height is 5 s.

[0139] Specifically, by setting the height adjustment step, the initial acquisition height can be accurately controlled during the sound signal acquisition process, improving the accuracy of signal acquisition. Through detailed height adjustment, the acoustic characteristics of the to-be-identified object at different heights can be more comprehensively captured, enhancing the identification ability of potential fault signals and improving the accuracy and reliability of fault source positioning.

[0140] Specifically, the determination of the optimal acquisition height based on the second sound signal and the third sound signal comprises:

[0141] obtaining a third feature parameter of the third sound signal;

[0142] calculating a third difference value by subtracting each second feature parameter from each third feature parameter;

[0143] calculating a third difference ratio by dividing the third difference value by the corresponding second feature parameter, and calculating a total third difference ratio by summing up each third difference ratio;

[0144] comparing a plurality of total third difference ratios to determine the optimal acquisition height as the adjusted acquisition height of the third sound signal when the total third difference ratio is maximum.

[0145] Table 3: Characteristic parameter values at different heights

[0146]

[0147] Specifically, the third feature parameter (four index values of the characteristic parameters corresponding to 1.25 m, 1.5 m and 1.75 m) is subtracted from the second feature parameter (four index values of the characteristic parameters corresponding to 1 m, which are slightly different from the second feature parameter in Table 2 due to the complexity of the actual sound field and measurement error) to obtain a respective difference value, and then the respective difference value is divided by the index value corresponding to the second feature parameter to obtain a respective difference ratio. Then, the total third difference ratio of the three adjusted acquisition heights is obtained by summing up the difference ratios of the four indexes, i.e., the above-mentioned total third difference ratio. As shown in Table 3, the characteristic parameter values, differences and difference ratios at different heights are shown. The SNR value in the table is only a linear ratio, not a logarithm. It is convenient for calculating the difference ratio.

[0148] By comparing a plurality of total third difference ratios, it is determined that the optimal acquisition height is 1.25 m, which is the adjusted acquisition height of the third sound signal when the total third difference ratio is maximum.

[0149] In the specific implementation process, according to the best acquisition angle 0°, the best acquisition distance 1.5 m, and the initial acquisition height 1 m, the second characteristic parameter of the sound signal collected is RMS2=0.2575 Pa, SPL2=82.425 dB, SNR2=0.589, and RFCA2=4.9. The adjustment parameters of the adjusted acquisition heights of 1.25 m, 1.5 m, and 1.75 m are shown in Table 3. The third difference ratios are 68.47%, 22.11%, and -44.5%, respectively. The best acquisition height is determined to be 1.25 m.

[0150] Specifically, by accurately determining the best acquisition height, the sound signal features related to the fault can be quickly obtained. By optimizing the acquisition height, the quality of the collected sound signal is ensured, thereby significantly improving the accuracy, efficiency, and automation degree of the fault source positioning, and further accelerating the fault diagnosis speed, which is beneficial to the maintenance and management of the rotating machinery equipment.

[0151] Specifically, the sound field image of the target frequency includes:

[0152] The invalid frequencies in the target frequency are filtered out using a band-pass filter to obtain valid target frequencies, and the sound source positioning is performed according to the valid target frequencies to obtain the sound field image of the fault source.

[0153] Specifically, the band-pass filter is a filter that can filter out invalid frequency signals other than valid target frequencies, which can be an elliptical band-pass filter, a Butterworth band-pass filter, etc. In this embodiment, it is a Butterworth band-pass filter, and the sound field imaging function is used to perform sound field imaging on the sound information of the valid target frequencies to obtain the sound field image.

[0154] Specifically, by using the band-pass filter to filter out the invalid frequencies in the sound signal, only the signal part effective for fault positioning in the target frequency is retained, the frequency selectivity is effectively improved, the signal clarity of the target frequency is enhanced, the system can focus more accurately on the frequency components related to the fault source, the misrecognition caused by invalid frequency interference is avoided, the subsequent fault diagnosis is more intuitive and accurate, and the work efficiency is improved.

[0155] Specifically, the spectrum analysis of the sound signal of the best acquisition angle, the best acquisition distance, and the best acquisition height to obtain the target frequency includes:

[0156] Obtaining the sound signal spectrum of the best sound signal;

[0157] Performing frequency domain analysis on the sound signal spectrum to determine the frequency with the maximum amplitude in the frequency domain as the target frequency.

[0158] In the specific implementation process, the amplitude of the 12th frequency in the sound signal frequency of the optimal sound signal is the largest, and the 12th frequency of the object to be identified is taken as the target frequency.

[0159] Specifically, by performing frequency domain analysis on the sound signal spectrum of the optimal sound signal, the frequency with the largest amplitude can be accurately extracted from the complex signal as the most representative target frequency. This process ensures that the system can automatically identify the frequency from among numerous frequency components, thereby effectively locating the key signal related to the fault and avoiding interference from irrelevant frequencies, thereby improving the accuracy and reliability of fault source diagnosis.

[0160] Specifically, determining the fault source position based on the sound field image and the video image comprises:

[0161] Fusing the video image and the sound field image to obtain a sound field imaging;

[0162] Determining the fault source position according to the sound field imaging.

[0163] Specifically, the sound field image of the target frequency is determined, the video image is fused with the sound field image, and the position of the sound source located by the sound field image in the video image is determined as the fault source position.

[0164] Specifically, by fusing the sound field image and the video image, the spatial distribution of the acoustic signal can be effectively combined with the physical position in the visual image, thereby quickly and accurately marking the position of the fault source in the video image, improving the spatial accuracy of fault source positioning. The operator can intuitively see the fault source position and quickly make maintenance decisions, greatly improving the efficiency of fault diagnosis.

[0165] So far, the technical solutions of the present application have been described in conjunction with the preferred embodiments shown in the drawings, but those skilled in the art will readily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to related technical features without departing from the principles of the present application, and the technical solutions after such changes or replacements will fall within the protection scope of the present application.

[0166] The above description is only the preferred embodiments of the present application and is not intended to limit the present application; for those skilled in the art, the present application can have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

Claims

1. A rotating machinery fault source positioning method based on optimal acquisition points of a mobile robot, characterized in that, The method comprises the following steps: acquiring initial sound signals of the object to be identified according to preset initial acquisition parameters using a sound array; the acquisition parameters include initial acquisition angle, initial acquisition distance and initial acquisition height; adjusting the initial acquisition angle step by step according to preset angle adjustment step to obtain adjusted acquisition angle; acquiring first sound signals of the object to be identified based on the adjusted acquisition angle, the initial acquisition distance and the initial acquisition height, and determining the best acquisition angle based on the initial sound signals and the first sound signals; adjusting the initial acquisition distance step by step according to preset distance adjustment step to obtain adjusted acquisition distance; acquiring second sound signals of the object to be identified based on the best acquisition angle, the adjusted acquisition distance and the initial acquisition height, and determining the best acquisition distance based on the first sound signals and the second sound signals; adjusting the initial acquisition height step by step according to preset height adjustment step to obtain adjusted acquisition height; acquiring third sound signals of the object to be identified based on the best acquisition angle, the best acquisition distance and the adjusted acquisition height, and determining the best acquisition height based on the second sound signals and the third sound signals; performing frequency spectrum analysis on the sound signals acquired according to the best acquisition angle, the best acquisition distance and the best acquisition height to obtain target frequency; sound source positioning with fixed frequency band width; acquiring sound field image of the target frequency; acquiring video image of the object to be identified; determining the location of the fault source based on the sound field image and the video image. 2.The rotating machinery fault source positioning method based on mobile robot optimal collection point according to claim 1, wherein, The step of adjusting the initial acquisition angle step by step according to preset angle adjustment step to obtain adjusted acquisition angle comprises: setting angle adjustment step; gradually increasing the initial acquisition angle according to the angle adjustment step in adjustment period to obtain the adjusted acquisition angle. 3.The rotating machinery fault source positioning method based on mobile robot optimal collection point according to claim 2, wherein, The step of determining the best acquisition angle based on the initial sound signals and the first sound signals comprises: acquiring first characteristic parameters of the first sound signals and initial characteristic parameters of the initial sound signals; calculating the difference between each first characteristic parameter and corresponding initial characteristic parameter to obtain first difference value; calculating the ratio of the first difference value to corresponding initial characteristic parameter to obtain first difference value ratio, and calculating the sum of each first difference value ratio to obtain total first difference value ratio; comparing the total first difference value ratios to determine the adjusted acquisition angle of the first sound signals when the total first difference value ratio is the largest as the best acquisition angle. 4.The rotating machinery fault source positioning method based on mobile robot optimal collection point according to claim 3, wherein, The step of adjusting the initial acquisition distance step by step according to preset distance adjustment step to obtain adjusted acquisition distance comprises: setting distance adjustment step; gradually increasing the initial acquisition distance according to the distance adjustment step in adjustment period to obtain the adjusted acquisition distance. 5.The rotating machinery fault source locating method based on mobile robot optimal collection point according to claim 4, wherein, The step of determining the best acquisition distance based on the first sound signals and the second sound signals comprises: acquiring second characteristic parameters of the second sound signals; calculating the difference between each second characteristic parameter and each first characteristic parameter to obtain second difference value; calculating the ratio of the second difference value to corresponding first characteristic parameter to obtain second difference value ratio, and calculating the sum of each second difference value ratio to obtain total second difference value ratio; The adjustment collection distance of the second sound signal when the total second difference value ratio is the largest is determined as the optimal collection distance by comparing the total second difference value ratios. 6.The rotating machinery fault source positioning method based on mobile robot optimal collection point according to claim 5, wherein, The step of adjusting the initial collection height according to the preset height adjustment step to obtain the adjustment collection height comprises: setting a height adjustment step; gradually increasing the initial collection height according to the height adjustment step in an adjustment period to obtain the adjustment collection height. 7.The rotating machinery fault source locating method based on mobile robot optimal collection point according to claim 6, wherein, The step of determining the optimal collection height based on the second sound signal and the third sound signal comprises: obtaining a third characteristic parameter of the third sound signal; calculating a third difference value by subtracting each second characteristic parameter from each third characteristic parameter; calculating a third difference value ratio by dividing the third difference value by the corresponding second characteristic parameter, and calculating a total third difference value ratio by summing up all the third difference value ratios; the adjustment collection height of the third sound signal when the total third difference value ratio is the largest is determined as the optimal collection height by comparing the total third difference value ratios. 8.The rotating machinery fault source locating method based on mobile robot optimal collection point according to claim 7, wherein, The step of obtaining the sound field image of the target frequency comprises: using a band-pass filter to filter out invalid frequencies in the target frequency to obtain valid target frequencies, and performing sound source positioning according to the valid target frequencies to obtain the sound field image of the fault source. 9.The rotating machinery fault source positioning method based on mobile robot optimal collection point according to claim 8, wherein, The step of performing frequency spectrum analysis on the quality-optimal sound signal obtained according to the optimal collection angle, the optimal collection distance and the optimal collection height to obtain the target frequency comprises: obtaining a sound signal spectrum of the optimal sound signal; performing frequency domain analysis on the sound signal spectrum to determine the frequency with the largest amplitude in the frequency domain as the target frequency. 10.The rotating machinery fault source positioning method based on mobile robot optimal collection point according to claim 9, wherein, The step of determining the fault source position based on the sound field image and the video image comprises: fusing the video image and the sound field image to obtain a sound field image; determining the fault source position according to the sound field image.

Images