Method, device and equipment for determining fault level of rotating equipment

Abstract

The invention relates to the technical field of vibration monitoring and fault diagnosis of rotating mechanical equipment, and discloses a method, a device and equipment for determining the fault level of rotating equipment, and the method comprises the steps: obtaining the vibration waveforms of a first part in to-be-detected equipment in different frequency domains; scanning the vibration waveform in a first sub-interval of the duration interval to obtain a first period; obtaining a second subinterval based on the first period, and scanning the vibration waveform in the second subinterval to obtain a second period; obtaining an inclusion relation between a period value corresponding to a peak value in the third sub-interval and a fourth sub-interval, and adjusting a counter to obtain a count value; and obtaining a target value based on the counting value, and obtaining a first fault level of the equipment when determining that the equipment has a fault based on the target value. By implementing the technical scheme of the invention, the equipment fault level can be determined under the unified equipment fault level evaluation standard, so that the standardized management of the equipment is realized.

Description

Technical Field

[0001] The present disclosure relates to the technical field of vibration monitoring and fault diagnosis of rotating machinery equipment, and particularly relates to a method, device and equipment for determining the fault level of rotating equipment. Background Art

[0002] The technology of vibration monitoring and fault diagnosis of rotating machinery equipment is mature and widely applied, and is an important means for carrying out predictive maintenance and management of equipment. After fault diagnosis of rotating machinery equipment, through fault level classification, the influence degree of the fault on equipment performance, operation safety and production process can be clearly judged.

[0003] Currently, the time-domain waveform self-diagnosis method is often used for fault diagnosis and fault level classification. The traditional time-domain waveform self-diagnosis method is based on equal-period vibration impact monitoring and scanning to judge whether there are typical fault characteristics such as gear, bearing damage or rotor rubbing with corresponding characteristic frequencies in the vibration waveform, and then refer to the recommended standards of the total vibration velocity and acceleration, and combine the empirical thresholds of impact coefficients such as peak factor and kurtosis to comprehensively evaluate the equipment fault level.

[0004] However, currently there are only recommended standards for the total vibration velocity and acceleration, and there is no recommended standard for impact vibration parameters such as peak factor and kurtosis, resulting in difficulty in uniformly evaluating the equipment fault level when conducting fault diagnosis on rotating machinery equipment based on abnormal vibration impact monitoring. Since a unified equipment fault level evaluation standard can improve equipment management level, ensure stable production and promote the standardized development of the industry, there is an urgent need to establish a unified evaluation standard for the fault level judgment of periodic vibration impact of rotating machinery equipment. Summary of the Invention

[0005] In view of this, the present disclosure provides a method, device and equipment for determining the fault level of rotating equipment to solve the problem of the lack of a unified equipment fault level evaluation standard.

[0006] In a first aspect, the present disclosure provides a method for determining the fault level of rotating equipment, the method comprising:

[0007] Obtaining vibration waveforms of a first component included in the equipment to be detected in different frequency domains, wherein the number of the first components is at least one;

[0008] Scanning the vibration waveforms within a first sub-interval of a time duration interval to obtain a first period, wherein the time duration interval is composed of the time duration periods of the vibration waveforms, the first sub-interval is used to represent that the probability of abnormal impact of the fault characteristic period of the vibration waveforms is greater than a first preset threshold, and the number of the first periods is at least one;

[0009] Obtain a second sub - interval based on the first period, and scan the vibration waveform within the second sub - interval to obtain a second period, where the second sub - interval is used to represent that the probability of the offset period of the fault - feature period of the vibration waveform is greater than a first preset threshold;

[0010] Obtain the inclusion relationship between the period value corresponding to the peak within a third sub - interval and a fourth sub - interval, and adjust a counter to obtain a count value, where the third sub - interval and the fourth sub - interval are obtained based on the first period, the second period, and a quasi - period fuzzy factor;

[0011] Obtain a target value based on the count value, and when it is determined that the device fails based on the target value, obtain a first fault level of the device, where the target value is used to represent the proportion of the maximum value in the count value to the quantity of the corresponding fourth sub - interval.

[0012] In the embodiments of the present disclosure, by obtaining the vibration waveforms of a first component included in a device to be detected in different frequency domains; scanning the vibration waveform within a first sub - interval of a time - length interval to obtain a first period; obtaining a second sub - interval based on the first period, and scanning the vibration waveform within the second sub - interval to obtain a second period; obtaining the inclusion relationship between the period value corresponding to the peak within a third sub - interval and a fourth sub - interval, and adjusting a counter to obtain a count value; obtaining a target value based on the count value, and when it is determined that the device fails based on the target value, obtaining a first fault level of the device. By implementing the technical solutions of the present disclosure, it is possible to determine the device fault level under a unified device fault - level evaluation standard, thereby realizing the standardized management of the device.

[0013] In an alternative implementation manner, before scanning the vibration waveform within the first sub - interval of the time - length interval to obtain a first period, the method further includes:

[0014] Obtain the fault - feature frequency order of the first component and the rotation frequency of the device;

[0015] Fuse the fault - feature frequency order and the rotation frequency to obtain a target frequency;

[0016] Obtain the reciprocal of the target frequency to obtain a third period;

[0017] Based on the third period and a period - scanning range factor, obtain the first sub - interval.

[0018] In the embodiments of the present disclosure, by fusing the fault - feature frequency order and the rotation frequency to obtain a target frequency, it is possible to obtain the theoretical fault - feature frequency of the first component, and further based on the target frequency and the period - scanning range factor to obtain the first sub - interval, it is possible to obtain the scanning range of the fault - feature period of the first component, improving the efficiency and accuracy of device fault detection.

[0019] In an alternative embodiment, obtaining the inclusion relationship between the period value corresponding to the peak within the third sub-interval and the fourth sub-interval includes:

[0020] Based on the first period, the second period, and the quasi-period fuzzy factor, obtain the third sub-interval and the fourth sub-interval;

[0021] Scan the vibration waveform within the third sub-interval to obtain the peak within the third sub-interval;

[0022] Based on the peak within the third sub-interval, obtain the period value corresponding to the peak within the third sub-interval;

[0023] Compare the period value with the fourth sub-interval to obtain the inclusion relationship between the period value and the fourth sub-interval.

[0024] In the embodiments of the present disclosure, by scanning the vibration waveform within the third sub-interval to obtain the peak within the third sub-interval and the period value corresponding to the peak, and obtaining the inclusion relationship between the period value and the fourth sub-interval, it is possible to determine whether the period value is a fault characteristic period, providing a reliable basis for subsequent adjustment of the counter and determination of equipment faults.

[0025] In an alternative embodiment, based on the first period, the second period, and the quasi-period fuzzy factor, obtaining the third sub-interval and the fourth sub-interval includes:

[0026] Fuse the first period and the quasi-period fuzzy factor to obtain the width of the fourth sub-interval;

[0027] Based on the first period, the second period, and the width of the fourth sub-interval, obtain the third sub-interval and the fourth sub-interval.

[0028] In the embodiments of the present disclosure, by fusing the first period and the quasi-period fuzzy factor to obtain the width of the fourth sub-interval, and based on the first period, the second period, and the width of the fourth sub-interval to obtain the third sub-interval and the fourth sub-interval, it is possible to obtain the scanning range of the possible fault offset period of the first component, improving the efficiency and accuracy of equipment fault detection.

[0029] In an alternative embodiment, obtaining the target value based on the count value includes:

[0030] Based on the first period and the duration of the vibration waveform of the vibration waveform, obtain the number of fourth sub-intervals;

[0031] Obtain the ratio of the maximum value of the count value to the number of corresponding fourth sub-intervals to obtain the target value.

[0032] In the embodiments of the present disclosure, by obtaining a target value based on the ratio of the maximum value of the count value to the number of corresponding fourth sub-intervals, the maximum value of the density of the fault characteristic period can be obtained, providing a basis for determining equipment faults subsequently.

[0033] In an alternative embodiment, when it is determined that the equipment has a fault based on the target value, obtaining the first fault level of the equipment includes:

[0034] Comparing the target value with a fault determination threshold to determine whether the equipment has a fault;

[0035] When it is determined that the equipment has a fault, obtaining target parameters corresponding to the target value of the vibration waveform, where the target parameters are used to characterize the state information of the vibration waveform;

[0036] Obtaining the comparison result between the target parameters and the fault level threshold;

[0037] Determining the first fault level of the equipment based on the comparison result.

[0038] In the embodiments of the present disclosure, by comparing the target value with the fault determination threshold to determine whether the equipment has a fault, the accuracy and reliability of equipment fault detection can be improved. By comparing the target parameters with the fault level threshold when the equipment has a fault to determine the first fault level of the equipment, a standardized evaluation of the degree of equipment fault can be achieved.

[0039] In an alternative embodiment, comparing the target value with the fault determination threshold to determine whether the equipment has a fault includes:

[0040] When the target value of any first component is greater than or equal to the corresponding fault determination threshold, it is determined that the equipment has a fault;

[0041] When the target values of all first components are less than the corresponding fault determination thresholds, it is determined that the equipment has no fault.

[0042] In the embodiments of the present disclosure, by comparing the target value with the fault determination threshold to determine whether the first component has a fault and then determining whether the equipment has a fault, the accuracy and reliability of equipment fault detection can be improved.

[0043] In an alternative embodiment, determining the first fault level of the equipment based on the comparison result includes:

[0044] Based on the comparison result, determining the second fault level of the first component;

[0045] Based on the second fault level, determining the third fault level of the second component where the first component is located, where the number of second components is at least one;

[0046] Based on the third failure level, determine the first failure level of the device where the second component is located.

[0047] In the embodiments of the present disclosure, by comparing the target parameter with the failure level threshold and the hierarchical relationship of components in the device, the first failure level of the device can be determined, thereby realizing a standardized evaluation of the degree of device failure.

[0048] In a second aspect, the present disclosure provides an apparatus for determining the failure level of a rotating device, the apparatus including:

[0049] A first acquisition module, configured to acquire vibration waveforms of a first component included in a device to be detected in different frequency domains, where the number of the first components is at least one;

[0050] A first obtaining module, configured to scan the vibration waveform within a first sub-interval of a time interval to obtain a first period, where the time interval is composed of the time periods of the vibration waveform, and the first sub-interval is used to represent that the probability of an abnormal impact of a failure characteristic period in the vibration waveform is greater than a first preset threshold, and the number of the first periods is at least one;

[0051] A second obtaining module, configured to obtain a second sub-interval based on the first period, and scan the vibration waveform within the second sub-interval to obtain a second period, where the second sub-interval is used to represent that the probability of a bias period of a failure characteristic period in the vibration waveform is greater than the first preset threshold;

[0052] A third obtaining module, configured to obtain the inclusion relationship between the period value corresponding to the peak value within a third sub-interval and a fourth sub-interval, adjust a counter, and obtain a count value, where the third sub-interval and the fourth sub-interval are obtained based on the first period, the second period, and a quasi-period ambiguity factor;

[0053] A second acquisition module, configured to obtain a target value based on the count value, and when it is determined that the device has a failure based on the target value, obtain the first failure level of the device, where the target value is used to represent the proportion of the maximum value in the count value to the number of corresponding fourth sub-intervals.

[0054] In a third aspect, the present disclosure provides a computer device, including: a memory and a processor, which are communicatively connected to each other, where the memory stores computer instructions, and the processor executes the computer instructions to execute the method for determining the failure level of a rotating device according to the first aspect or any corresponding embodiment thereof.

[0055] Fourthly, the present disclosure provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the method for determining the fault level of the rotating device according to the first aspect or any corresponding embodiment thereof as described above.

[0056] Fifthly, the present disclosure provides a computer program product, including computer instructions, and the computer instructions are used to cause a computer to execute the method for determining the fault level of the rotating device according to the first aspect or any corresponding embodiment thereof as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the following will briefly introduce the drawings required to be used in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0058] Figure 1 is a flowchart of the method for determining the fault level of the rotating device according to an embodiment of the present disclosure;

[0059] Figure 2 is a flowchart of the method for determining the fault level of another rotating device according to an embodiment of the present disclosure;

[0060] Figure 3 is a flowchart of the method for determining the fault level of yet another rotating device according to an embodiment of the present disclosure;

[0061] Figure 4 is a block diagram of the structure of the device for determining the fault level of the rotating device according to an embodiment of the present disclosure;

[0062] Figure 5 is a schematic diagram of the hardware structure of the computer device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] In order to make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present disclosure.

[0064] The vibration monitoring and fault diagnosis technology of rotating machinery and equipment is mature and widely used, which is an important means to carry out predictive maintenance and management of equipment. After diagnosing the faults of rotating machinery and equipment, through the fault level classification, the impact degree of the faults on equipment performance, operation safety and production process can be clearly judged.

[0065] Currently, the time-domain waveform self-diagnosis method is often used for fault diagnosis and fault level classification. The traditional time-domain waveform self-diagnosis method is based on equal-period vibration impact monitoring and scanning to judge whether there are typical fault characteristics such as gear, bearing damage or rotor rubbing with corresponding characteristic periods in the vibration waveform, and then refer to the recommended standards of the total vibration velocity and acceleration, and combine the empirical thresholds of impact coefficients such as peak factor and kurtosis to comprehensively evaluate the equipment fault level.

[0066] However, there are currently only recommended standards for the total vibration velocity and acceleration, and there is no recommended standard for impact vibration parameters such as peak factor and kurtosis. As a result, it is difficult to uniformly evaluate the equipment fault level when diagnosing the faults of rotating machinery and equipment based on abnormal vibration impact monitoring. Since a unified equipment fault level evaluation standard can improve equipment management level, ensure production stability and promote the standardized development of the industry, there is an urgent need to establish a unified evaluation standard for the fault level judgment of periodic vibration impact of rotating machinery and equipment.

[0067] To solve the above problems, according to the embodiments of the present disclosure, an embodiment of a method for determining the fault level of a rotating device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0068] In this embodiment, a method for determining the fault level of a rotating device is provided, as Figure 1 shown, Figure 1 is a flowchart of a method for determining the fault level of a rotating device according to an embodiment of the present disclosure. This process can be applied to a server and includes the following steps:

[0069] Step S101, obtain the vibration waveforms of the first components included in the device to be detected in different frequency domains, where the number of the first components is at least one.

[0070] Optionally, in the embodiments of the present disclosure, the first components are the components included in the device. Taking a wind turbine as an example, the first components included in the device include front bearings, rear bearings, internal gear rings, planetary gears, sun gears, planetary frame bearings, low-speed shafts, low-speed shaft bearings, medium-speed shafts, medium-speed shaft bearings, high-speed shafts, high-speed shaft bearings, drive-end bearings and free-end bearings, etc.

[0071] The abscissa of the vibration waveform is time, and the ordinate is amplitude. The amplitude reflects the energy of the corresponding periodic component in the original vibration signal. The vibration waveform includes vibration waveforms of different physical quantities in different frequency domains. The physical quantities include vibration acceleration or vibration velocity, etc. Among them, the vibration velocity waveform is the integral form of the vibration acceleration waveform and has a good recognition effect on abnormal impacts generated under low speed and heavy load. The frequency domain includes high frequency (such as 10000 Hz), medium-high frequency (such as 5000 Hz), medium frequency (such as 2000 Hz), medium-low frequency (such as 1000 Hz), low frequency (such as 500 Hz), etc.

[0072] Specifically, the server can use a vibration sensor (such as an acceleration sensor, etc.) installed on the device to measure the vibration signals of the first component in different frequency domains, or use the sensor to measure the original vibration signal of the first component, and then perform signal resampling and digital integration on the original vibration signal to obtain vibration waveforms in different frequency domains.

[0073] In addition, after obtaining the vibration waveform, the server can preprocess it. Since the amplitudes of the vibration waveform are positive and negative, the server can square each amplitude point in the vibration waveform to enhance the impact peak characteristics and obtain the preprocessed vibration waveform.

[0074] Step S102, scan the vibration waveform within the first sub-interval of the duration interval to obtain the first period. The duration interval is composed of the duration periods of the vibration waveform. The first sub-interval is used to represent that the probability of an abnormal impact in the fault characteristic period of the vibration waveform is greater than the first preset threshold, and the number of the first periods is at least one.

[0075] It should be noted that when the device fails, it generally presents abnormal vibration impacts in the vibration waveform starting from the fault offset period and at intervals of the fault characteristic period, that is, the distribution position of the abnormal vibration impact is equal to the sum of the fault offset period and an integer multiple of the fault characteristic period. Among them, the fault offset period is the specific position where the first impact appears, and this position is not fixed and is determined by the acquisition start time. The actual impact form presents continuous or discontinuous distribution depending on the existence of the real rotational impact.

[0076] Optionally, in the embodiments of the present disclosure, the first preset threshold refers to the probability value that the first component may fail. When the probability of the vibration waveform appearing in the fault characteristic period is greater than the first preset threshold, it indicates that the first component may have failed. The first sub-interval is included in the duration interval of the vibration waveform, indicating the interval where the possible fault characteristic period exists. The first period is included in the first sub-interval, indicating the possible fault characteristic period.

[0077] Specifically, the server first obtains the first sub-interval, that is, the interval where the possible fault characteristic period exists. Then, the server scans the vibration spectrum within the first sub-interval of the duration interval to obtain the first period, that is, the possible fault characteristic period.

[0078] Step S103: Obtain a second sub-interval based on the first period, and scan the vibration waveform within the second sub-interval to obtain a second period, where the second sub-interval is used to represent that the probability of the offset period of the fault characteristic period in the vibration waveform is greater than the first preset threshold.

[0079] Optionally, in the embodiment of the present disclosure, the second sub-interval is included in the duration interval of the vibration waveform, representing the interval where the possible fault offset period exists. The second period is included in the second sub-interval, representing the possible fault offset period.

[0080] Specifically, the server first obtains the second sub-interval (such as [0, the first period]) based on the first period, that is, the interval where the possible fault offset period exists. Then, the server scans the vibration waveform within the second sub-interval of the duration interval to obtain the second period, that is, the possible fault offset period.

[0081] Step S104: Obtain the inclusion relationship between the period value corresponding to the peak within the third sub-interval and the fourth sub-interval, and adjust the counter to obtain a count value, where the third sub-interval and the fourth sub-interval are obtained based on the first period, the second period, and the quasi-period ambiguity factor.

[0082] Optionally, in the embodiment of the present disclosure, the third sub-interval is included in the duration interval of the vibration waveform, representing the first scanning range of the possible fault characteristic period. The fourth sub-interval is included in the duration interval of the vibration waveform, representing the second scanning range of the possible fault characteristic period. The quasi-period ambiguity factor is used to determine the width of the fourth sub-interval.

[0083] Specifically, the server first obtains the third sub-interval based on the first period and the second period, that is, the first scanning range of the possible fault characteristic period, and obtains the fourth sub-interval based on the first period, the second period, and the quasi-period ambiguity factor, that is, the second scanning range of the possible fault characteristic period.

[0084] Then, the server scans the vibration waveform within the third sub-interval of the duration interval, obtains the peak value within the third sub-interval and the corresponding period value of the peak value, determines the inclusion relationship between the period value and the fourth sub-interval, and adjusts the count value of the counter according to the inclusion relationship: If the period value is included in the fourth sub-interval, it indicates that the period value may be the fault characteristic period, and the count value of the counter is incremented by one; if the period value is not included in the fourth sub-interval, it indicates that the period value is not the fault characteristic period, and the count value of the counter remains unchanged. After the server finishes scanning, it obtains the count value of the counter and clears the counter.

[0085] Step S105, obtain a target value based on the count value, and when it is determined that the device has a fault based on the target value, obtain the first fault level of the device, where the target value is used to represent the proportion of the maximum value in the count value to the number of corresponding fourth sub-intervals.

[0086] Optionally, in the embodiments of the present disclosure, the target value is the proportion of the maximum value in the count value to the number of corresponding fourth sub-intervals, which reflects the maximum value of the density of the fault characteristic periods. The first fault level refers to the fault level of the device.

[0087] Specifically, the server first obtains the maximum value of the count value, obtains the number of third sub-intervals corresponding to the count value, then calculates the proportion of the count value to the number of corresponding fourth sub-intervals to obtain the target value, then compares the target value with the corresponding fault determination threshold to determine whether the device has a fault, and finally compares the status information of the vibration waveform corresponding to the target value with the corresponding fault level threshold to determine the first fault level of the device.

[0088] It should be noted that the server can perform a two-layer nested loop scan on the vibration waveform by constructing a quasi-periodic abnormal shock searcher. The searcher consists of a bracket and several identical subnets evenly distributed on the bracket. The length of the bracket is the vibration waveform duration of the vibration waveform. The center of the first subnet is located at the left end of the searcher bracket. The subnet distribution interval is the first period. The number of subnets is determined by the bracket length and the subnet distribution interval. The subnet width is determined by the first period and the quasi-periodic ambiguity factor. The scanning range of the outer loop is the first sub-interval, the moving range of the searcher is the second sub-interval, and the scanning ranges of the inner loop are the third sub-interval and the fourth sub-interval.

[0089] The server performs a step-by-step scan of the first sub-interval through the outer loop to obtain the first period, steps the searcher within the second sub-interval through the inner loop, and step-by-step scans the third sub-interval and the fourth sub-interval. After each inner loop scan is completed, the count value of the counter is obtained and the counter is cleared. After the outer loop scan is completed, the maximum value of the count value is obtained, and a target value is obtained based on the count value. Finally, it is determined whether the device has a fault based on the target value.

[0090] In the embodiments of the present disclosure, by obtaining the vibration waveforms of the first component included in the device to be detected in different frequency domains; scanning the vibration waveforms in the first sub-interval of the time duration interval to obtain the first period; obtaining the second sub-interval based on the first period, and scanning the vibration waveforms in the second sub-interval to obtain the second period; obtaining the inclusion relationship between the period value corresponding to the peak value in the third sub-interval and the fourth sub-interval, adjusting the counter to obtain the count value; obtaining the target value based on the count value, and when determining that the device has a fault based on the target value, obtaining the first fault level of the device. By implementing the technical solution of the present disclosure, it is possible to determine the device fault level under a unified device fault level evaluation standard, thereby realizing the standardized management of the device.

[0091] In this embodiment, a method for determining the fault level of a rotating device is provided, as Figure 2 shown Figure 2 is a schematic flowchart of another method for determining the fault level of a rotating device according to an embodiment of the present disclosure. This process can be applied to a server and includes the following steps:

[0092] Step S201, obtain the vibration waveforms of the first component included in the device to be detected in different frequency domains, where the number of the first components is at least one. For details, please refer to Figure 1 step S101 of the embodiment shown, which will not be elaborated here.

[0093] Step S202, obtain the fault characteristic frequency order of the first component and the rotation frequency of the device.

[0094] Optionally, in the embodiments of the present disclosure, the server first obtains a plurality of large components included in the rotating mechanical equipment, and obtains the key components (i.e., the first components) included in each large component, and then queries or calculates the fault characteristic frequency order of the first component according to the transmission parameters of the first component, such as the gearbox structure type and number of teeth, belt transmission ratio, bearing model, etc.

[0095] After that, the server can obtain the rotation frequency of the device through an external tachometer, or can calculate the rotation frequency of the device by using the real-time vibration signals collected by the vibration sensor.

[0096] Step S203, fuse the fault characteristic frequency order and the rotation frequency to obtain the target frequency.

[0097] Optionally, in the embodiments of the present disclosure, the target frequency represents the theoretical fault characteristic frequency of the first component.

[0098] Specifically, the server multiplies the fault characteristic frequency order of the first component by the rotation frequency of the device to calculate the target frequency, that is, the theoretical fault characteristic frequency of the first component.

[0099] Step S204: Obtain the reciprocal of the target frequency to get the third period.

[0100] Optionally, in the embodiments of the present disclosure, the third period is the interval center of the first sub-interval, that is, the theoretical fault characteristic period of the first component.

[0101] Specifically, the server calculates the reciprocal of the target frequency to obtain the third period.

[0102] Step S205: Based on the third period and the period scanning range factor, obtain the first sub-interval.

[0103] Optionally, in the embodiments of the present disclosure, the period scanning range factor is used to determine the width of the first sub-interval.

[0104] Specifically, the server multiplies the third period by the period scanning range factor to calculate the width of the first sub-interval, and based on this width and the third period, calculates the first sub-interval. For example: if the third period is 100 seconds and the period scanning range factor is 0.2, then the interval center of the first sub-interval is 100 seconds, the interval width is 20 seconds, and the first sub-interval is [90 seconds, 110 seconds].

[0105] Step S206: Scan the vibration waveform within the first sub-interval of the duration interval to obtain the first period. Here, the duration interval is composed of the duration periods of the vibration waveform, and the first sub-interval is used to characterize that the probability of an abnormal impact with the fault characteristic period in the vibration waveform is greater than the first preset threshold, and the number of the first periods is at least one. For details, please refer to Figure 1 Step S102 of the illustrated embodiment, which will not be elaborated here.

[0106] Step S207: Based on the first period, obtain the second sub-interval, and scan the vibration waveform within the second sub-interval to obtain the second period. Here, the second sub-interval is used to characterize that the probability of the offset period with the fault characteristic period in the vibration waveform is greater than the first preset threshold. For details, please refer to Figure 1 Step S103 of the illustrated embodiment, which will not be elaborated here.

[0107] Step S208: Obtain the inclusion relationship between the period value corresponding to the peak within the third sub-interval and the fourth sub-interval, and adjust the counter to obtain the count value, where the third sub-interval and the fourth sub-interval are obtained based on the first period, the second period, and the quasi-period ambiguity factor.

[0108] Specifically, obtaining the inclusion relationship between the period value corresponding to the peak within the third sub-interval and the fourth sub-interval in the above step S208 includes:

[0109] Step S2081: Obtain a third sub-interval and a fourth sub-interval based on the first period, the second period, and the quasi-period fuzzy factor.

[0110] Specifically, the server first obtains the width of the fourth sub-interval based on the first period and the quasi-period fuzzy factor, and then obtains at least one third sub-interval and at least one fourth sub-interval based on the first period, the second period, and the width of the fourth sub-interval.

[0111] In some alternative embodiments, the above step S2081 includes:

[0112] Step a1: Fuse the first period and the quasi-period fuzzy factor to obtain the width of the fourth sub-interval.

[0113] Step a2: Obtain the third sub-interval and the fourth sub-interval based on the first period, the second period, and the width of the fourth sub-interval.

[0114] Specifically, the server first multiplies the first period and the quasi-period fuzzy factor to calculate the width value of the fourth sub-interval. For example, if the first period is 100 seconds and the quasi-period fuzzy factor is 0.2, then the interval width of the fourth sub-interval is 20 seconds.

[0115] Then, the server calculates the interval width and the interval center of each third sub-interval based on the first period, the second period, and the width of the fourth sub-interval, thereby calculating each third sub-interval. Among them, the interval width of each third sub-interval is the same, which is the difference between twice the first period and the interval width of the corresponding fourth sub-interval. The interval center of the first third sub-interval is the second period, and the distance between the interval centers of each third sub-interval is the same, which is the first period.

[0116] It should be noted that the lower limit of the interval of each third sub-interval is greater than or equal to 0 seconds, and the upper limit of the interval is less than or equal to the maximum value of the abscissa of the vibration waveform.

[0117] For example, if the first period is 100 seconds, the second period is 90 seconds, and the width of the fourth sub-interval is 20 seconds, then the interval width of each third sub-interval is 180 seconds, and the interval centers of the third sub-intervals are 90 seconds, 190 seconds, 290 seconds,... in sequence, and so on. The third sub-intervals are [0 seconds, 180 seconds], [100 seconds, 280 seconds], [200 seconds, 380 seconds],... in sequence, and so on.

[0118] After that, the server calculates the interval center of each fourth sub-interval based on the first period, the second period, and the width of the fourth sub-interval, and calculates each fourth sub-interval in combination with the interval width of the fourth sub-interval. Among them, the interval center of the first fourth sub-interval is the second period, and the distance between the interval centers of each fourth sub-interval is the same, which is the first period.

[0119] It should be noted that the lower limit of each fourth sub-interval is greater than or equal to 0 seconds, and the upper limit of the interval is less than or equal to the maximum value of the abscissa of the vibration waveform.

[0120] For example: if the first period is 100 seconds, the second period is 90 seconds, and the width of the fourth sub-interval is 20 seconds, then the centers of the fourth sub-intervals are 90 seconds, 190 seconds, 290 seconds, and so on. By analogy, the fourth sub-intervals are [80 seconds, 100 seconds], [180 seconds, 200 seconds], [280 seconds, 300 seconds], and so on. By analogy.

[0121] In the above embodiment, the width of the fourth sub-interval is obtained by fusing the first period and the quasi-periodic fuzzy factor, and the third sub-interval and the fourth sub-interval are obtained based on the first period, the second period, and the width of the fourth sub-interval, so as to obtain the scanning range of the possible fault offset period of the first component, improving the efficiency and accuracy of equipment fault detection.

[0122] Step S2082: Scan the vibration waveform within the third sub-interval to obtain the peak value within the third sub-interval.

[0123] Specifically, the server scans the vibration waveform within the third sub-interval of the time duration interval to obtain the maximum value of the ordinate (amplitude) within the third sub-interval, that is, the peak value.

[0124] Step S2083: Based on the peak value within the third sub-interval, obtain the period value corresponding to the peak value within the third sub-interval.

[0125] Specifically, the server obtains the value of the abscissa (i.e., time) corresponding to the maximum value of the ordinate (i.e., the peak value) within the third sub-interval based on the peak value within the third sub-interval.

[0126] Step S2084: Compare the period value with the fourth sub-interval to obtain the inclusion relationship between the period value and the fourth sub-interval.

[0127] Specifically, the server compares the period value with the fourth sub-interval to determine the inclusion relationship between the period value and the fourth sub-interval, that is, the period value is included in the fourth sub-interval, or the period value is not included in the fourth sub-interval.

[0128] Step S209: Obtain the target value based on the count value, and when it is determined that the device has a fault based on the target value, obtain the first fault level of the device, where the target value is used to represent the proportion of the maximum value in the count value to the number of corresponding fourth sub-intervals. For details, please refer to Figure 1 Step S105 of the illustrated embodiment, which will not be elaborated here.

[0129] In the embodiments of the present disclosure, by fusing the fault characteristic frequency order and the rotation frequency to obtain the target frequency, the theoretical fault characteristic frequency of the first component can be obtained. Furthermore, based on the target frequency and the period scanning range factor, the first sub-interval can be obtained, and the scanning range of the fault characteristic period of the first component can be obtained, improving the efficiency and accuracy of equipment fault detection. By scanning the vibration waveform in the third sub-interval, the peak value in the third sub-interval and the period value corresponding to the peak value are obtained, and the inclusion relationship between the period value and the fourth sub-interval is obtained, so as to determine whether the period value is a fault characteristic period, providing a reliable basis for subsequent adjustment of the counter and determination of equipment faults.

[0130] In this embodiment, a method for determining the fault level of a rotating device is provided, as Figure 3 shown, Figure 3 is a schematic flowchart of another method for determining the fault level of a rotating device according to the embodiments of the present disclosure. This process can be applied to a server and includes the following steps:

[0131] Step S301, obtain the vibration waveforms of the first component included in the device to be detected in different frequency domains, where the number of the first components is at least one. For details, please refer to Figure 2 step S201 of the embodiment shown herein, which will not be elaborated herein.

[0132] Step S302, scan the vibration waveform in the first sub-interval of the time duration interval to obtain the first period, where the time duration interval is composed of the time duration periods of the vibration waveform, and the first sub-interval is used to represent that the probability of abnormal impact of the fault characteristic period in the vibration waveform is greater than the first preset threshold, and the number of the first periods is at least one. For details, please refer to Figure 2 step S206 of the embodiment shown herein, which will not be elaborated herein.

[0133] Step S303, obtain the second sub-interval based on the first period, and scan the vibration waveform in the second sub-interval to obtain the second period, where the second sub-interval is used to represent that the probability of the offset period of the fault characteristic period in the vibration waveform is greater than the first preset threshold. For details, please refer to Figure 2 step S207 of the embodiment shown herein, which will not be elaborated herein.

[0134] Step S304, obtain the inclusion relationship between the period value corresponding to the peak value in the third sub-interval and the fourth sub-interval, and adjust the counter to obtain the count value, where the third sub-interval and the fourth sub-interval are obtained based on the first period, the second period, and the quasi-period ambiguity factor. For details, please refer to Figure 2 step S208 of the embodiment shown herein, which will not be elaborated herein.

[0135] Step S305: Obtain a target value based on the count value, and when it is determined that the device has a fault based on the target value, obtain the first fault level of the device, where the target value is used to represent the proportion of the maximum value in the count value to the number of corresponding fourth sub-intervals.

[0136] Specifically, the above-mentioned step S305 includes:

[0137] Step S3051: Obtain the number of fourth sub-intervals based on the first period and the vibration waveform duration of the vibration waveform.

[0138] Specifically, the server first obtains the vibration waveform duration of the vibration waveform, and then calculates the number of fourth sub-intervals based on the first period and the vibration waveform duration of the vibration waveform. For example: The server can use the floor function to calculate the number of fourth sub-intervals, that is, the number of fourth sub-intervals = floor(vibration waveform duration / first period) + 1.

[0139] Step S3052: Obtain the proportion of the maximum value in the count value to the number of corresponding fourth sub-intervals to obtain the target value.

[0140] Specifically, the server first obtains the maximum value of the count value, and then calculates the proportion of this count value to the number of corresponding fourth sub-intervals to obtain the target value.

[0141] Step S3053: Compare the target value with the fault determination threshold to determine whether the device has a fault.

[0142] Specifically, the server compares the target value with the fault determination threshold to obtain a comparison result, and determines whether the device has a fault according to this comparison result, where the value range of the fault determination threshold can be [0.05, 0.5].

[0143] In some alternative embodiments, the above-mentioned step S3053 includes:

[0144] Step b1: When the target value of any first component is greater than or equal to the corresponding fault determination threshold, determine that the device has a fault.

[0145] Step b2: When the target values of all first components are less than the corresponding fault determination thresholds, determine that the device has no fault.

[0146] Specifically, if the target value of any first component is greater than or equal to the corresponding fault determination threshold, it means that there is a fault in the first component in the device, then the server determines that the device has a fault; if the target values of all first components are less than the corresponding fault determination thresholds, it means that all first components in the device have no faults, then the server determines that the device has no fault.

[0147] In the above embodiments, by comparing the target value with the fault determination threshold, it is determined whether the first component fails, and then whether the device fails, which can improve the accuracy and reliability of device fault detection.

[0148] Step S3054, when it is determined that the device fails, obtain the target parameter corresponding to the target value of the vibration waveform, where the target parameter is used to characterize the state information of the vibration waveform.

[0149] Optionally, in the embodiments of the present disclosure, the target parameters include the effective value of the vibration velocity, the effective value of the vibration acceleration, the peak factor, and the kurtosis, etc. within the fault characteristic period interval of the vibration waveform.

[0150] Specifically, the server first obtains the target parameters within the fault characteristic period interval corresponding to the target value of the vibration waveform, and then uses the root mean square formula to calculate the amplitude within the fault characteristic period interval, that is, the effective value of the vibration velocity or the effective value of the vibration acceleration, calculates the peak value through the peak formula, and calculates the kurtosis through the kurtosis formula.

[0151] Step S3055, obtain the comparison result between the target parameter and the fault level threshold.

[0152] Optionally, in the embodiments of the present disclosure, the number of fault level thresholds is at least one, and the number of fault levels of the first component is at least two, such as four levels: attention, warning, alarm, and danger.

[0153] Specifically, the server compares the target parameter and the fault level threshold to obtain the comparison result, that is, the target parameter is greater than the corresponding fault level threshold, the target parameter is equal to the corresponding fault level threshold, or the target parameter is less than the corresponding fault level threshold.

[0154] It should be noted that the server can pre-determine the fault level threshold: first obtain the vibration acceleration waveform and vibration velocity waveform of the first component corresponding to the relatively normal and stable time periods in each frequency band, with a long time span (such as 3 months) and a large number of data records (such as 100), and then calculate the mathematical expectations and standard deviations of the target parameters such as the effective value of the vibration acceleration, the effective value of the vibration velocity, the peak factor, and the kurtosis of these vibration waveforms. Finally, calculate the fault level threshold based on the mathematical expectations and standard deviations of these target parameters, such as: fault level threshold = mathematical expectation + k * standard deviation, where k is a real number, and the k value corresponds to different fault levels.

[0155] Step S3056, determine the first fault level of the device based on the comparison result.

[0156] Specifically, when the target parameter is greater than or equal to the corresponding fault level threshold, the server determines the fault level of the first component as a higher level; when the target parameter is less than the corresponding fault level threshold, the server determines the fault level of the first component as a lower level.

[0157] In some alternative embodiments, step S3056 includes:

[0158] Step c1, determining the second fault level of the first component based on the comparison result.

[0159] Step c2, determining the third fault level of the second component where the first component is located based on the second fault level, where the number of second components is at least one.

[0160] Step c3, determining the first fault level of the device where the second component is located based on the third fault level.

[0161] Optionally, in the embodiments of the present disclosure, the device includes at least one large component, that is, the second component. Each large component includes at least one component part, that is, the first component. Taking a wind turbine as an example, the second components included in the device include a main bearing, a gearbox, and an engine, etc. The first components included in the main bearing include a front bearing and a rear bearing, etc. The first components included in the gearbox include an internal gear ring, planet gears, a sun gear, a planet carrier bearing, a low-speed shaft, a low-speed shaft bearing, a medium-speed shaft, a medium-speed shaft bearing, a high-speed shaft, and a high-speed shaft bearing, etc. The first components included in the engine include a drive-end bearing and a free-end bearing, etc. The first fault level is the fault level of the device, the second fault level is the fault level of the first component, and the third fault level is the fault level of the second component.

[0162] Specifically, first, when the target parameter is greater than or equal to the corresponding fault level threshold, the server determines the fault level of the first component as a higher level; when the target parameter is less than the corresponding fault level threshold, the server determines the fault level of the first component as a lower level, and obtains the second fault level of each first component.

[0163] Then, the server obtains the maximum value, minimum value, or average value, etc. of the second fault levels of all the first components included in the second component, and determines it as the corresponding third fault level of the second component, and obtains the third fault level of each second component.

[0164] Finally, the server obtains the maximum value, minimum value, or average value, etc. of the third fault levels of all the second components included in the device, and determines it as the first fault level of the device.

[0165] In the above embodiments, by comparing the target parameter with the fault level threshold and based on the hierarchical relationship of components in the device, the first fault level of the device can be determined, thus realizing a standardized evaluation of the degree of device failure.

[0166] In the embodiments of the present disclosure, by obtaining a target value based on the ratio of the maximum value of the count value to the number of corresponding fourth sub-intervals, the maximum value of the density of the fault characteristic period can be obtained, providing a judgment basis for subsequent determination of device faults. By comparing the target value with the fault determination threshold to determine whether the device has a fault, the accuracy and reliability of device fault detection can be improved. By comparing the target parameter with the fault level threshold in the case of device failure to determine the first fault level of the device, a standardized evaluation of the degree of device failure can be realized.

[0167] In this embodiment, a device for determining the fault level of a rotating device is also provided. This device is used to implement the above embodiments and preferred embodiments, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0168] This embodiment provides a device for determining the fault level of a rotating device, as Figure 4 shown, including:

[0169] A first acquisition module 401, configured to acquire vibration waveforms of a first component included in a device to be detected in different frequency domains, where the number of first components is at least one;

[0170] A first obtaining module 402, configured to scan the vibration waveform in a first sub-interval of a time duration interval to obtain a first period, where the time duration interval is composed of the time duration period of the vibration waveform, and the first sub-interval is used to represent that the probability of an abnormal impact of a fault characteristic period in the vibration waveform is greater than a first preset threshold, and the number of first periods is at least one;

[0171] A second obtaining module 403, configured to obtain a second sub-interval based on the first period, and scan the vibration waveform in the second sub-interval to obtain a second period, where the second sub-interval is used to represent that the probability of a bias period of a fault characteristic period in the vibration waveform is greater than a first preset threshold;

[0172] A third obtaining module 404, configured to obtain the inclusion relationship between the period value corresponding to the peak value in a third sub-interval and a fourth sub-interval, and adjust a counter to obtain a count value, where the third sub-interval and the fourth sub-interval are obtained based on the first period, the second period, and a quasi-period ambiguity factor;

[0173] A second acquisition module 405, configured to obtain a target value based on a count value, and when it is determined that the device has a fault based on the target value, obtain a first fault level of the device, where the target value is used to represent the ratio of the maximum value in the count value to the number of corresponding fourth sub-intervals.

[0174] In an embodiment of the present disclosure, by acquiring vibration waveforms of a first component included in a device to be detected in different frequency domains; scanning the vibration waveforms in a first sub-interval of a time duration interval to obtain a first period; obtaining a second sub-interval based on the first period, and scanning the vibration waveforms in the second sub-interval to obtain a second period; acquiring an inclusion relationship between a period value corresponding to a peak value in a third sub-interval and a fourth sub-interval, adjusting a counter to obtain a count value; obtaining a target value based on the count value, and when it is determined that the device has a fault based on the target value, obtaining a first fault level of the device. By implementing the technical solution of the present disclosure, it is possible to determine the device fault level under a unified device fault level evaluation standard, thereby realizing the standardized management of the device.

[0175] In some alternative embodiments, the apparatus further includes:

[0176] A third acquisition module, configured to acquire a fault characteristic frequency order of the first component and a rotation frequency of the device;

[0177] A fourth obtaining module, configured to fuse the fault characteristic frequency order and the rotation frequency to obtain a target frequency;

[0178] A fifth obtaining module, configured to obtain a reciprocal of the target frequency to obtain a third period;

[0179] A sixth obtaining module, configured to obtain a first sub-interval based on the third period and a period scanning range factor.

[0180] In some alternative embodiments, the third obtaining module 404 includes:

[0181] A first obtaining sub-module, configured to obtain a third sub-interval and a fourth sub-interval based on the first period, the second period, and a quasi-periodic fuzzy factor;

[0182] A second obtaining sub-module, configured to scan the vibration waveforms in the third sub-interval to obtain a peak value in the third sub-interval;

[0183] A third obtaining sub-module, configured to obtain a period value corresponding to the peak value in the third sub-interval based on the peak value in the third sub-interval;

[0184] A fourth obtaining sub-module, configured to compare the period value with the fourth sub-interval to obtain an inclusion relationship between the period value and the fourth sub-interval.

[0185] In some alternative embodiments, the first obtaining sub-module includes:

[0186] A first obtaining unit, configured to fuse the first period and the quasi-periodic ambiguity factor to obtain the width of the fourth sub-interval;

[0187] A second obtaining unit, configured to obtain the third sub-interval and the fourth sub-interval based on the first period, the second period, and the width of the fourth sub-interval.

[0188] In some alternative embodiments, the second obtaining module 405 includes:

[0189] A fifth obtaining sub-module, configured to obtain the number of fourth sub-intervals based on the first period and the vibration waveform duration of the vibration waveform;

[0190] A sixth obtaining sub-module, configured to obtain the ratio of the maximum value of the count value to the number of corresponding fourth sub-intervals to obtain a target value.

[0191] In some alternative embodiments, the second obtaining module 405 includes:

[0192] A first determining sub-module, configured to compare the target value with a fault determination threshold to determine whether the device has a fault;

[0193] A first obtaining sub-module, configured to obtain a target parameter corresponding to the target value of the vibration waveform in the case of determining that the device has a fault, where the target parameter is used to characterize the state information of the vibration waveform;

[0194] A second obtaining sub-module, configured to obtain a comparison result between the target parameter and a fault level threshold;

[0195] A second determining sub-module, configured to determine a first fault level of the device based on the comparison result.

[0196] In some alternative embodiments, the first determining sub-module includes:

[0197] A first determining unit, configured to determine that the device has a fault in the case where the target value of any first component is greater than or equal to the corresponding fault determination threshold;

[0198] A second determining unit, configured to determine that the device has no fault in the case where the target values of all first components are less than the corresponding fault determination thresholds.

[0199] In some alternative embodiments, the second determining sub-module includes:

[0200] A third determining unit, configured to determine a second fault level of the first component based on the comparison result;

[0201] A fourth determination unit, configured to determine a third failure level of a second component where a first component is located based on the second failure level, where the number of second components is at least one;

[0202] A fifth determination unit, configured to determine a first failure level of a device where the second component is located based on the third failure level.

[0203] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding embodiments above, and will not be elaborated here.

[0204] The device for determining the failure level of the rotating device in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0205] This disclosure embodiment also provides a computer device having the Figure 4 device for determining the failure level of the rotating device as shown above.

[0206] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of a computer device provided by an optional embodiment of this disclosure. As shown in Figure 5 , the computer device includes: one or more processors 10, a memory 20, and an interface for connecting each component, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional implementation manners, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Figure 5 In

[0207] Processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, processor 10 can further include a hardware chip. The above-mentioned hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The above-mentioned programmable logic device can be a complex programmable logic device, a field programmable gate array, a general array logic, or any combination thereof.

[0208] Among them, the memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.

[0209] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0210] The memory 20 may include a volatile memory, for example, a random access memory; the memory may also include a non-volatile memory, for example, a flash memory, a hard disk, or a solid-state drive; the memory 20 may further include a combination of the above types of memories.

[0211] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0212] The embodiments of the present disclosure also provide a computer-readable storage medium. The method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processed on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0213] A part of the present disclosure can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the present disclosure through the operations of the computer. Those skilled in the art should understand that the forms of existence of computer program instructions in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways for a computer to execute computer program instructions include, but are not limited to: the computer directly executes the instructions, or the computer compiles the instructions and then executes the corresponding compiled program, or the computer reads and executes the instructions, or the computer reads and installs the instructions and then executes the corresponding installed program. Herein, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0214] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for determining the fault level of a rotating device, characterized in that, The method includes: Obtaining vibration waveforms of a first component included in a device to be detected in different frequency domains, where the number of the first components is at least one; Scanning the vibration waveforms within a first sub-interval of a time duration interval to obtain a first period, where the time duration interval is composed of the time duration periods of the vibration waveforms, the first sub-interval is used to represent that the probability of an abnormal impact of a fault characteristic period in the vibration waveforms is greater than a first preset threshold, and the number of the first periods is at least one; Obtaining a second sub-interval based on the first period, and scanning the vibration waveforms within the second sub-interval to obtain a second period, where the second sub-interval is used to represent that the probability of a bias period of a fault characteristic period in the vibration waveforms is greater than the first preset threshold; Obtaining the inclusion relationship between the period value corresponding to the peak within a third sub-interval and a fourth sub-interval, and adjusting a counter to obtain a count value, where the third sub-interval and the fourth sub-interval are obtained based on the first period, the second period, and a quasi-periodic fuzzy factor; Obtaining a target value based on the count value, and when determining that the device has a fault based on the target value, obtaining a first fault level of the device, where the target value is used to represent the proportion of the maximum value in the count value to the number of corresponding fourth sub-intervals.

2. The method according to claim 1, wherein Before scanning the vibration waveforms within the first sub-interval of the time duration interval to obtain the first period, the method further includes: Obtaining the fault characteristic frequency order of the first component and the rotation frequency of the device; Fusing the fault characteristic frequency order and the rotation frequency to obtain a target frequency; Obtaining the reciprocal of the target frequency to obtain a third period; Obtaining the first sub-interval based on the third period and a period scanning range factor.

3. The method according to claim 1, wherein The obtaining the inclusion relationship between the period value corresponding to the peak within the third sub-interval and the fourth sub-interval includes: Obtaining the third sub-interval and the fourth sub-interval based on the first period, the second period, and the quasi-periodic fuzzy factor; Scanning the vibration waveforms within the third sub-interval to obtain the peak within the third sub-interval; Obtaining the period value corresponding to the peak within the third sub-interval based on the peak within the third sub-interval; Comparing the period value with the fourth sub-interval to obtain the inclusion relationship between the period value and the fourth sub-interval.

4. The method according to claim 3, characterized in that, The obtaining the third sub-interval and the fourth sub-interval based on the first period, the second period, and the quasi-periodic fuzzy factor includes: Fusing the first period and the quasi-periodic fuzzy factor to obtain the width of the fourth sub-interval; Obtaining the third sub-interval and the fourth sub-interval based on the first period, the second period, and the width of the fourth sub-interval.

5. The method according to claim 1, wherein The obtaining the target value based on the count value includes: Obtaining the number of the fourth sub-intervals based on the first period and the time duration of the vibration waveforms; Obtaining the proportion of the maximum value in the count value to the number of corresponding fourth sub-intervals to obtain the target value.

6. The method according to claim 1, wherein When it is determined that the device has a fault based on the target value, obtaining a first fault level of the device includes: Comparing the target value with a fault determination threshold to determine whether the device has a fault; When it is determined that the device has a fault, obtaining a target parameter corresponding to the target value of the vibration waveform, where the target parameter is used to characterize the state information of the vibration waveform; Obtaining a comparison result between the target parameter and a fault level threshold; Determining the first fault level of the device based on the comparison result.

7. The method according to claim 6, characterized in that, The comparing the target value with the fault determination threshold to determine whether the device has a fault includes: When the target value of any one of the first components is greater than or equal to the corresponding fault determination threshold, determining that the device has a fault; When the target values of all the first components are less than the corresponding fault determination thresholds, determining that the device has no fault.

8. The method according to claim 6, characterized in that, The determining the first fault level of the device based on the comparison result includes: Determining a second fault level of the first component based on the comparison result; Determining a third fault level of a second component where the first component is located based on the second fault level, where the number of the second components is at least one; Determining the first fault level of the device where the second component is located based on the third fault level.

9. A device for determining the fault level of a rotating device, characterized in that, The apparatus includes: A first obtaining module, configured to obtain vibration waveforms of first components included in a device to be detected in different frequency domains, where the number of the first components is at least one; A first obtaining module, configured to scan the vibration waveform within a first sub-interval of a time duration interval to obtain a first period, where the time duration interval is composed of time duration periods of the vibration waveform, the first sub-interval is used to characterize that the probability of an abnormal impact in a fault feature period of the vibration waveform is greater than a first preset threshold, and the number of the first periods is at least one; A second obtaining module, configured to obtain a second sub-interval based on the first period, and scan the vibration waveform within the second sub-interval to obtain a second period, where the second sub-interval is used to characterize that the probability of a bias period in a fault feature period of the vibration waveform is greater than the first preset threshold; A third obtaining module, configured to obtain an inclusion relationship between a period value corresponding to a peak value within a third sub-interval and a fourth sub-interval, and adjust a counter to obtain a count value, where the third sub-interval and the fourth sub-interval are obtained based on the first period, the second period, and a quasi-period fuzzy factor; A second obtaining module, configured to obtain a target value based on the count value, and when it is determined that the device has a fault based on the target value, obtain a first fault level of the device, where the target value is used to characterize a ratio of a maximum value in the count value to a number of corresponding fourth sub-intervals.

10. A computer device, characterized in that, including: A memory and a processor, which are communicatively connected to each other. Computer instructions are stored in the memory, and the processor executes the computer instructions to execute the method for determining the fault level of the rotating device according to any one of claims 1 to 8.

Images