Gear fault diagnosis method, device and computer readable storage medium
By obtaining the original vibration data when the gear rotates for segmentation and correlation analysis, gear fault diagnosis is realized, solving the problem of high-cost speed sensors, improving diagnostic efficiency and accuracy, and reducing the risk of misjudgment.
Patent Information
- Application Number
- CN202210383899.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-12
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2042-04-12
AI Technical Summary
Existing gear fault diagnosis methods rely on high-cost speed sensors, resulting in high cost of use and installation, and the requirements for accurate speed measurement, affecting diagnostic efficiency and accuracy.
By obtaining the original vibration data when the gear rotates for no less than 1 turn, dividing and obtaining sub-vibration data, performing correlation analysis to determine the associated vibration interval, and performing time domain synchronous averaging to diagnose whether the gear has failed, avoiding accurate speed dependency.
It reduces the use and installation cost of speed sensors, improves diagnostic efficiency and accuracy, reduces the risk of misjudgment, and enhances the applicability of gear fault diagnosis.
Smart Images

Figure CN114755007B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of fault diagnosis, and in particular to a gear fault diagnosis method, device and computer-readable storage medium. Background Art
[0002] At present, the time domain synchronous averaging method is used to diagnose gear faults. The signal obtained by the time domain synchronous averaging method weakens the synchronous incoherent signal and noise signal, and retains the synchronous coherent signal.
[0003] In the related art, the gear needs to use a speed sensor to obtain the speed of the gear, and a time point is recorded for each rotation of the gear. The gear will rotate multiple times during the test period, and multiple time points can be recorded. These time points are generated into a time series. At the same time, during the rotation of the gear during the test period, it will mesh with another gear, generate an original vibration signal, and then record the original vibration signal. Next, the original vibration signal is processed according to the multiple time points in the time series, and the time domain average signal is subsequently obtained to diagnose whether the gear is faulty.
[0004] However, one rotation of the gear records a time point, and the original vibration signal must depend on the rotation speed of the gear, so the cost of the speed sensor is high and the installation cost of the speed sensor is high. Summary of the invention
[0005] The present application provides a gear fault diagnosis method, device and computer-readable storage medium, and the method can reduce the use cost and installation cost of the speed sensor.
[0006] The present application provides a gear fault diagnosis method, comprising:
[0007] Obtaining original vibration data of not less than one cycle generated when the gear rotates not less than one circle;
[0008] The original vibration data is segmented to obtain a plurality of sub-vibration data of not less than one cycle, wherein the sub-vibration data includes reference vibration data and comparative vibration data;
[0009] performing correlation analysis on the vibration data of a plurality of data comparison intervals of the comparison vibration data and the reference vibration data respectively, and determining the associated vibration intervals corresponding to the comparison vibration data and the reference vibration data;
[0010] Performing time-domain averaging on the vibration data in the associated vibration interval of the comparison vibration data and the vibration data in the corresponding interval of the reference vibration data to obtain time-domain synchronous average data; and
[0011] Whether the gear is faulty is diagnosed based on the time domain synchronous average data.
[0012] Furthermore, the data volume of the comparative vibration data is greater than that of the reference vibration data, and the data volume of the comparative vibration data is a positive integer multiple of the data volume of the reference vibration data, and adjacent sub-vibration data partially overlap.
[0013] Furthermore, the data of half a period of the adjacent sub-vibration data overlap.
[0014] Further, the data volumes of the plurality of data comparison intervals are respectively the same as the data volumes of the reference vibration data;
[0015] The performing correlation analysis on the vibration data of the multiple data comparison intervals of the comparison vibration data and the reference vibration data respectively to determine the associated vibration intervals corresponding to the comparison vibration data and the reference vibration data, comprises:
[0016] Determining a plurality of data comparison intervals for the comparison vibration data;
[0017] Determine the correlation between the vibration data of a plurality of data comparison intervals of the comparison vibration data and the reference vibration data;
[0018] The data comparison interval corresponding to the maximum correlation among the multiple correlations is determined as the associated vibration interval.
[0019] Further, the multiple data comparison intervals include an initial data comparison interval and multiple subsequent data comparison intervals;
[0020] The determining of a plurality of data comparison intervals for comparing vibration data includes:
[0021] Determine a starting data comparison interval for the comparison vibration data; the data volume of the starting data comparison area is the same as the data volume of the reference vibration data;
[0022] Based on the initial data comparison interval, the comparison vibration data is shifted by one vibration data each time to obtain a plurality of subsequent data comparison intervals, wherein the data amounts of the plurality of subsequent data comparison intervals are respectively the same as the data amount of the initial data comparison interval;
[0023] The determining of the correlation between the vibration data of the plurality of data comparison intervals of the comparison vibration data and the reference vibration data respectively includes:
[0024] Determine the correlation between the vibration data in the initial data comparison interval and the vibration data in the plurality of subsequent data comparison intervals and the reference vibration data.
[0025] Further, diagnosing whether the gear fails according to the time domain synchronous average data includes:
[0026] Determining a time-domain synchronous average characteristic value according to the time-domain synchronous average data;
[0027] Whether the gear fails is diagnosed based on the time domain synchronous average characteristic value.
[0028] Furthermore, the time-domain synchronous average characteristic value includes one or more of a peak-to-valley value, a root mean square value, a pulse factor, and a kurtosis.
[0029] The present application provides a gear fault diagnosis device, comprising:
[0030] A data acquisition module, used to acquire original vibration data of not less than one cycle generated when the gear rotates not less than one circle;
[0031] A data segmentation module, used for segmenting the original vibration data to obtain a plurality of sub-vibration data of not less than one cycle, wherein the sub-vibration data includes reference vibration data and comparative vibration data;
[0032] A correlation analysis module, used to perform correlation analysis on the vibration data of a plurality of data comparison intervals of the comparison vibration data and the reference vibration data respectively, and determine the associated vibration intervals corresponding to the comparison vibration data and the reference vibration data;
[0033] A time domain averaging module, used for performing time domain averaging on the vibration data in the associated vibration interval of the comparative vibration data and the vibration data in the corresponding interval of the reference vibration data to obtain time domain synchronous average data;
[0034] A fault diagnosis module is used to diagnose whether the gear has a fault based on the time domain synchronous average data.
[0035] The present application provides a gear fault diagnosis device, including a processor and a memory;
[0036] Memory, used to store computer programs;
[0037] The processor is used to implement any of the methods described above when executing a program stored in the memory.
[0038] The present application provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the method described in any one of the above items is implemented.
[0039] In some embodiments, the gear fault diagnosis method of the present application obtains original vibration data of not less than 1 cycle generated when the gear rotates not less than 1 circle, divides the original vibration data to obtain multiple sub-vibration data of not less than 1 cycle, and performs correlation analysis on the vibration data of multiple data comparison intervals of the comparison vibration data and the reference vibration data, respectively, to determine the associated vibration interval corresponding to the comparison vibration data and the reference vibration data, so as to obtain time domain synchronous average data, and diagnose whether the gear has a fault. In this way, the original vibration data of not less than 1 cycle generated when the gear rotates not less than 1 circle can be directly divided into the original vibration data to obtain multiple sub-vibration data of not less than 1 cycle, without the need for precise rotation speed, and without the need to install a rotation speed sensor, thereby reducing the use cost and installation cost of the rotation speed sensor. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 The figure is a schematic flow chart of a gear fault diagnosis method provided in an embodiment of the present application;
[0041] Figure 2 Shown Figure 1 A schematic diagram of the baseline vibration data and the comparative vibration data in the gear fault diagnosis method shown;
[0042] Figure 3 Shown Figure 1 A schematic diagram of an application example of obtaining sub-vibration data from any original vibration data in the gear fault diagnosis method shown;
[0043] Figure 4 Shown Figure 1 An example schematic diagram of a process for determining an associated vibration interval in a gear fault diagnosis method shown;
[0044] Figure 5 Shown Figure 1 An example schematic diagram of correlation analysis between reference vibration data and any comparative vibration data in the gear fault diagnosis method shown;
[0045] Figure 6 Shown Figure 5 An example schematic diagram of the associated vibration interval in the gear fault diagnosis method shown;
[0046] Figure 7 Shown is based on Figure 3 A schematic diagram of an application example of the associated vibration interval obtained by using the sub-vibration data shown;
[0047] Figure 8 Shown Figure 5 An example schematic diagram of an associated vibration interval in the gear fault diagnosis method and a corresponding interval in the reference vibration data with the associated vibration interval;
[0048] Fig. 9 Shown is based on Figure 3 A schematic diagram of an application example of time domain synchronous average data obtained from sub-vibration data shown;
[0049] Fig.10 Shown Figure 1 A schematic diagram of an application example of a time domain synchronous average eigenvalue obtained from raw vibration data in a gear fault diagnosis method shown;
[0050] Fig.11 The figure shows a module schematic diagram of a gear fault diagnosis device provided in an embodiment of the present application;
[0051] Fig.12 Shown is a schematic structural diagram of a gear fault diagnosis device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0052] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of the present specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of the present specification as detailed in the appended claims.
[0053] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.
[0054] In order to solve the technical problem of high cost of speed sensors and high installation cost of speed sensors, the embodiment of the present application provides a gear fault diagnosis method, which obtains original vibration data of not less than 1 cycle generated when the gear rotates not less than 1 circle, divides the original vibration data to obtain multiple sub-vibration data of not less than 1 cycle, and performs correlation analysis on the vibration data of multiple data comparison intervals of the comparison vibration data and the reference vibration data respectively, determines the associated vibration interval corresponding to the comparison vibration data and the reference vibration data, so as to obtain time domain synchronous average data and diagnose whether the gear has a fault. In this way, the original vibration data of not less than 1 cycle generated when the gear rotates not less than 1 circle can be directly divided into the original vibration data to obtain multiple sub-vibration data of not less than 1 cycle, and no precise rotation speed is required, and no speed sensor needs to be installed, thereby reducing the use cost and installation cost of the speed sensor.
[0055] The gear fault diagnosis method of the present application can be applied to a gear fault diagnosis device. For example, the gear fault diagnosis device may include a gearbox. For the gearbox, the gearbox contains more than one set of gear meshing pairs. The original vibration signal of any test point of any gear of the gearbox contains not only the vibration signal of the corresponding gear meshing pair, but also the noise signal and the vibration signals of other gear meshing pairs, that is, synchronous incoherent signals. When studying whether any gear meshing pair has a fault, the vibration signals of other gear meshing pairs are equivalent to interference signals and need to be weakened, and the noise signals also need to be weakened. Alternatively, when studying whether any gear has a fault, the vibration signals of other gears are equivalent to interference signals and need to be weakened, and the noise signals also need to be weakened.
[0056] Based on this, the following gear fault diagnosis method of the present application can be executed to weaken the noise signal and interference signal, as described in detail below.
[0057] Figure 1 Shown is a flow chart of a gear fault diagnosis method provided in an embodiment of the present application.
[0058] like Figure 1 As shown, the gear fault diagnosis method may include the following steps 110 to 150:
[0059] Step 110, obtaining original vibration data of not less than one cycle generated when the gear rotates not less than one circle.
[0060] The above step 110 may further include obtaining data of a rotation time of not less than one circle when the gear rotates not less than one circle, as raw vibration data of not less than one cycle. In this way, the raw vibration data of not less than one cycle may include raw vibration data greater than or equal to one cycle, so that all information of one circle of the gear can be included to avoid missing information.
[0061] For example, the embodiment of the present application can obtain a reference speed range based on the engine power or the variable speed propeller stop system. The reference speed range is, for example, less than the maximum speed range of the gear or the gear is in the normal speed range.
[0062] The embodiment of the present application uses the vibration acceleration data of the high-speed shaft measuring point of a wind turbine gearbox as the original vibration data for illustration. The reference speed range is in the range of 1000 rpm to 2000 rpm. Thus, for 1000 rpm, the rotation time required for one revolution is 0.06s. For 2000 rpm, the rotation time required for one revolution is 0.03s. The reference speed range is approximately equal to 16.67 rpm to 33.33 rpm.
[0063] Step 120 , dividing the original vibration data to obtain a plurality of sub-vibration data of not less than one cycle, wherein the sub-vibration data includes reference vibration data and comparative vibration data.
[0064] The sub-vibration data refers to the original vibration data after segmentation. The reference vibration data and the comparison vibration data are both the original vibration data after segmentation. The reference vibration data is used to use the original vibration data after segmentation as the basic data for subsequent correlation analysis, such as Figure 2 The comparative vibration data refers to data that can be matched with the benchmark vibration data based on the benchmark vibration data, such as Figure 2 The comparative vibration data shown. The comparative vibration data may include one comparative vibration data and two or more comparative vibration data.
[0065] There are many ways to obtain the sub-vibration data. One way to obtain the sub-vibration data is to divide the original vibration data into equal parts. Another way to obtain the sub-vibration data is to divide the original vibration data into unequal parts. The details are as follows.
[0066] In one method of obtaining sub-vibration data, the above step 120 may further include dividing the original vibration data into equal data volumes to obtain a plurality of sub-vibration data. In this way, the data volume of the reference vibration data is consistent with the data volume of the comparative vibration data, and the reference vibration data can be guaranteed to correspond to the comparative vibration data, so that the original vibration data can be quickly divided into equal parts, which is convenient for rapid division and does not require a speed sensor to measure the accurate speed, thereby reducing the cost of the speed sensor. In addition, the original vibration data is divided into equal data volumes, and then correlation analysis is used, so that no interpolation or fitting is required in the future, thereby improving the calculation efficiency.
[0067] In another method of obtaining sub-vibration data, the data volume of the comparison vibration data is greater than the data volume of the reference vibration data, and the data volume of the comparison vibration data is a positive integer multiple of the data volume of the reference vibration data, and the adjacent sub-vibration data partially overlap. This is equivalent to staggering the segmentation of the original vibration data, which can ensure that the comparison vibration data contains the reference vibration data, so that the comparison vibration data contains the vibration data of the same period, avoiding the loss of the vibration data of the same period, thereby avoiding misjudgment of the gear failure. In addition, the adjacent sub-vibration data partially overlap, avoiding omissions during segmentation, and improving the accuracy of the segmented data. At the same time, the data volume of the comparison vibration data is a positive integer multiple of the data volume of the reference vibration data, which provides more effective data for subsequent correlation analysis, so that the associated vibration interval corresponding to the comparison vibration data and the reference vibration data can be better determined later.
[0068] Wherein, the above-mentioned partial data overlap may include that the comparison vibration data may overlap with the end data of the reference vibration data. For the comparison vibration data, the adjacent sub-vibration data may overlap at the end, and the adjacent sub-vibration data may overlap at the beginning and the end, which is equivalent to expanding the data volume of the sub-vibration data forward and backward. Exemplarily, the data of half a cycle of adjacent sub-vibration data overlap. In this way, the data can be segmented more conveniently, the accuracy of the segmented data is improved, and most of the cycle is not overlapped, so as to achieve a balance between the amount of calculation and the accuracy of the segmented data, and reduce the amount of calculation of the overlapping data.
[0069] Figure 3 Shown Figure 1 Schematic diagram of an application example of obtaining sub-vibration data from any original vibration data in the gear fault diagnosis method shown in FIG. Figure 3 In the application example shown, the minimum speed of 1000 revolutions can be used as an example for explanation.
[0070] Assuming the sampling frequency is 51200 Hz and the single sampling time is 2.56 s, the total amount of raw vibration data sampled is 51200 2.56=131072, at this time the gear has rotated approximately 42.6752 times.
[0071] The original vibration signal is divided according to the minimum speed of 1000RPM. The data volume of the reference vibration data is 3072, and the data volume of the comparison vibration data is 6144. The sub-vibration data obtained from any original vibration signal is as follows: Figure 3 shown.
[0072] Step 130, performing correlation analysis on the vibration data of multiple data comparison intervals of the comparison vibration data and the reference vibration data, respectively, to determine the associated vibration intervals corresponding to the comparison vibration data and the reference vibration data. The data comparison intervals refer to multiple intervals selected from the comparison vibration data.
[0073] Figure 4 Shown Figure 1 FIG. 1 is a schematic diagram showing an example of the process of determining the associated vibration range in the gear fault diagnosis method. Figure 4 As shown, the data volumes of the multiple data comparison intervals are respectively the same as the data volumes of the reference vibration data. The above step 130 may further include the first step of determining the multiple data comparison intervals of the comparison vibration data. The second step of determining the correlations between the vibration data of the multiple data comparison intervals of the comparison vibration data and the reference vibration data. The third step of determining the data comparison interval corresponding to the maximum correlation among the multiple correlations as the associated vibration interval. The associated vibration interval in the comparison vibration data having the highest matching degree with the reference vibration data is obtained in this way, which can best reflect the matching degree of the comparison vibration data and extract the smallest amount of data.
[0074] The multiple data comparison intervals include a starting data comparison interval and multiple subsequent data comparison intervals. The above-mentioned first step may further include determining the starting data comparison interval of the comparison vibration data; the data volume of the starting data comparison area is the same as the data volume of the benchmark vibration data; based on the starting data comparison interval, the comparison vibration data is offset by one vibration data each time to obtain multiple subsequent data comparison intervals, and the data volume of the multiple subsequent data comparison intervals is the same as the data volume of the starting data comparison interval. The above-mentioned second step may further include determining the correlation between the vibration data in the starting data comparison interval and the vibration data in the multiple subsequent data comparison intervals and the benchmark vibration data. In this way, based on the starting data comparison interval with the same data volume as the benchmark vibration data, all the comparison vibration data can be offset and compared to avoid missing the comparison vibration data and improve the accuracy of the correlation analysis. In addition, the associated vibration interval with the same data volume as the benchmark vibration data can be obtained, which provides a basis for the data volume for the subsequent time domain average, does not require interpolation or fitting, is convenient for direct calculation, and reduces the amount of data calculated.
[0075] Figure 5 Shown Figure 1 An example schematic diagram of the correlation analysis between the baseline vibration data and any comparative vibration data in the gear fault diagnosis method shown is shown. Figure 6 Shown Figure 5 An example schematic diagram of associated vibration intervals in the gear fault diagnosis method is shown. Figure 7 Shown is based on Figure 3 Schematic diagram of an application example of the associated vibration intervals obtained by sub-vibration data shown. Figure 8 Shown Figure 5 An exemplary schematic diagram of an associated vibration interval in a gear fault diagnosis method and a corresponding interval in reference vibration data to the associated vibration interval is shown. Fig. 9 Shown is based on Figure 3Schematic diagram of an application example of time-domain synchronous average data obtained from sub-vibration data shown.
[0076] like Figure 5 , Figure 6 and Figure 8 As shown, the original vibration data is divided into one reference vibration data and five comparative vibration data, and the data volume of the comparative vibration data is twice that of the reference vibration data.
[0077] Assuming that the left side of any comparative vibration data is taken as a starting point, a data comparison section in the comparative vibration data having the same data amount as that of the reference vibration data is obtained as a start data comparison section.
[0078] Then, the vibration data is gradually moved to the right for comparison, one data amount at a time, to obtain the subsequent data comparison interval.
[0079] Next, during the movement, correlations between the vibration data in the initial data comparison interval and the vibration data in a plurality of subsequent data comparison intervals and the reference vibration data are calculated respectively.
[0080] Furthermore, using the above correlation, the data comparison interval with the highest correlation with the reference vibration data is determined as the associated vibration interval, such as Figure 6 As shown. Combined Figure 3 The application example shown in the figure, accordingly, the associated vibration range can be as follows Figure 7 shown.
[0081] Finally, the associated vibration interval of the comparison vibration data is determined, the associated vibration interval is aligned with the reference vibration data, and the time domain average of the following step 140 is subsequently performed to obtain the time domain synchronous average data, and the corresponding intervals of the associated vibration interval and the reference vibration data are as follows: Figure 8 As shown. Combined Figure 3 The application example shown in Figure 2 is that the time domain synchronous average data can be obtained as follows: Fig. 9 shown.
[0082] After determining the associated vibration interval in step 130, in some embodiments, the method further includes cutting the associated vibration interval in the comparison vibration data. For example, when the comparison vibration data is a plurality of comparison vibration data, the associated vibration interval corresponding to each comparison vibration data is cut out. In other embodiments, the method further includes separately recording the associated vibration interval of the comparison data for subsequent time domain averaging.
[0083] Step 140, time-domain averaging is performed on the vibration data in the associated vibration interval of the comparison vibration data and the vibration data in the corresponding interval of the associated vibration interval in the reference vibration data to obtain time-domain synchronous average data. Among them, the time-domain synchronous average data is extremely similar to the vibration data in the associated vibration interval and the vibration data in the corresponding interval of the associated vibration interval in the reference vibration data. In this way, because the rotation period of this gear is different from that of other gears, and the rotation period of multiple rotations of this gear is the same, the vibration data in the associated vibration interval of this gear and the corresponding interval of the associated vibration interval in the reference vibration data are averaged in the time domain, which can enhance the vibration signal of this gear and weaken the vibration signals of other gears. In addition, the noise signal is a Gaussian white noise signal, which has positive and negative values, so the noise signal can be weakened during the time-domain averaging process.
[0084] The time domain averaging in the above step 140 may include time domain averaging of vibration data corresponding to multiple associated vibration regions in a plurality of comparative vibration data and vibration data in a corresponding interval of the associated vibration interval in the reference vibration data. Alternatively, the time domain averaging in the above step 140 may include time domain averaging of vibration data corresponding to one associated vibration region in a comparative vibration data and vibration data in a corresponding interval of the associated vibration interval in the reference vibration data. This is not limited here.
[0085] Exemplarily, the above step 140 can adopt the following steps to obtain the time domain synchronous average data: :
[0086] in, Represents the associated vibration area of the baseline vibration data or the comparative vibration data, Represents the total number of sub-vibration data, Represents the serial number of the sub-vibration data, Can represent baseline vibration data, Can represent the associated vibration area of the comparative vibration data, Represents the location of specific data.
[0087] Step 150, diagnose whether the gear is faulty based on the time domain synchronous average data.
[0088] The above step 150 may further include a first step of determining a time domain synchronous average characteristic value based on the time domain synchronous average data. The time domain synchronous average characteristic value may characterize the degree of gear failure. The second step of diagnosing whether the gear fails based on the time domain synchronous average characteristic value. In this way, the gear failure may be diagnosed more accurately through the time domain synchronous average characteristic value. The time domain synchronous average characteristic value may include one or more of the peak-to-valley value, the root mean square value, the pulse factor and the kurtosis. In this way, the degree of gear failure may be reflected through multiple time domain synchronous average characteristic values, and multiple time domain synchronous average characteristic values may simultaneously reflect the degree of failure of the same gear, thereby improving the accuracy of gear failure determination.
[0089] Combination Figure 3 As shown, the original vibration data of the embodiment of the present application may include one or more vibration acceleration data. Exemplarily, 195 vibration acceleration data are obtained before a gear in a gearbox fails. Each of the 195 vibration acceleration data before the gear fails can be used as any of the above-mentioned original vibration data. The process of the gear fault diagnosis method of the embodiment of the present application is executed on each of the 195 vibration acceleration data before the gear fails, so as to perform time-domain synchronous averaging to obtain 195 time-domain synchronous average data. Based on each of the 195 time-domain synchronous average data, a group of time-domain average eigenvalues of each vibration acceleration data is extracted. Each group of time-domain average eigenvalues may include at least the above-mentioned 4 time-domain synchronous average eigenvalues, that is, 195 time-domain synchronous average data correspond to at least 195 times 4 time-domain synchronous average eigenvalues.
[0090] Fig.10 Shown Figure 1 Schematic diagram of an application example of the time domain synchronous average eigenvalue obtained from the original vibration data in the gear fault diagnosis method shown in FIG. Fig.10 As shown, 195 time-domain synchronous average data corresponding to at least 195 times 4 time-domain synchronous average characteristic value points are connected into a line to analyze the gear fault.
[0091] Before September 25, 2017, the fluctuations in these time-domain synchronous average characteristic values were relatively stable, indicating that the diagnostic gear was not faulty. On September 25, 2017, the fluctuations in these time-domain synchronous average characteristic values increased significantly, indicating that the diagnostic gear was faulty.
[0092] In the embodiment of the present application, the original vibration data of not less than 1 cycle generated when the gear rotates not less than 1 circle can be directly divided to obtain multiple sub-vibration data of not less than 1 cycle. It does not require precise rotation speed, and does not require the installation of a rotation speed sensor, thereby reducing the use cost and installation cost of the rotation speed sensor, and also avoiding the influence of the rotation speed sensor on the diagnosis of gear faults when there is a deviation. In addition, the vibration data of multiple data comparison intervals of the comparison vibration data are subsequently correlated with the reference vibration data to realize gear fault diagnosis. At the same time, for gears that do not use rotation speed sensors, it is possible to diagnose whether the gear has a fault, which can enhance the applicability of gear fault diagnosis.
[0093] Fig.11 Shown is a module schematic diagram of a gear fault diagnosis device provided in an embodiment of the present application.
[0094] like Fig.11 As shown, the gear fault diagnosis device comprises:
[0095] The data acquisition module 31 is used to acquire the original vibration data of not less than one cycle generated when the gear rotates not less than one circle;
[0096] A data segmentation module 32 is used to segment the original vibration data to obtain a plurality of sub-vibration data of not less than one cycle, wherein the sub-vibration data includes reference vibration data and comparative vibration data;
[0097] A correlation analysis module 33, used to perform correlation analysis on the vibration data of multiple data comparison intervals of the comparison vibration data and the reference vibration data respectively, and determine the associated vibration intervals corresponding to the comparison vibration data and the reference vibration data;
[0098] A time domain averaging module 34 is used to perform time domain averaging on the vibration data in the associated vibration interval of the comparison vibration data and the vibration data in the corresponding interval of the reference vibration data to obtain time domain synchronous average data;
[0099] The fault diagnosis module 35 is used to diagnose whether a gear fault occurs based on the time domain synchronous average data.
[0100] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.
[0101] Fig.12The structure diagram of the gear fault diagnosis device 40 provided by the embodiment of the present application is shown. The gear fault diagnosis device 40 may include a processor 41, a memory 43 storing machine executable instructions, and a communication interface 42. The processor 41 and the memory 43 may communicate via a system bus 44. In addition, by reading and executing the machine executable instructions corresponding to the data pull or data return logic in the memory 43, the processor 41 may execute the method described above.
[0102] The memory 43 mentioned herein may be any electronic, magnetic, optical or other physical storage device that may contain or store information, such as executable instructions, data, etc. For example, the machine-readable storage medium may be: RAM (RadomAccess Memory, random access memory), volatile memory, non-volatile memory, flash memory, storage drive (such as hard disk drive), solid state drive, any type of storage disk (such as optical disk, DVD, etc.), or similar storage medium, or a combination thereof.
[0103] In some embodiments, a machine-readable storage medium is also provided. Fig.12 The memory 43 in the machine readable storage medium stores machine executable instructions, and the method described above is implemented when the machine executable instructions are executed by the processor. For example, the machine readable storage medium can be ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
[0104] The present application also provides a computer program stored in a machine-readable storage medium, such as Fig.12 The computer program is stored in the memory 43, and when the processor executes the computer program, the processor 41 is prompted to execute the method described above.
[0105] The above are only preferred embodiments of this specification and are not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.
[0106] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
Claims
1. A gear fault diagnosis method, It is characterized in that include: Obtaining original vibration data of not less than one cycle generated when the gear rotates not less than one circle; The original vibration data is segmented to obtain a plurality of sub-vibration data of not less than one cycle, wherein the sub-vibration data includes reference vibration data and comparative vibration data; Performing correlation analysis on the vibration data of multiple data comparison intervals of the comparison vibration data and the benchmark vibration data respectively, and determining the associated vibration intervals corresponding to the comparison vibration data and the benchmark vibration data; wherein, performing correlation analysis on the vibration data of multiple data comparison intervals of the comparison vibration data and the benchmark vibration data respectively, and determining the associated vibration intervals corresponding to the comparison vibration data and the benchmark vibration data, comprises: determining multiple data comparison intervals of the comparison vibration data; determining the correlations between the vibration data of multiple data comparison intervals of the comparison vibration data and the benchmark vibration data respectively; determining the data comparison interval corresponding to the maximum correlation among the multiple correlations as the associated vibration interval; Performing time-domain averaging on the vibration data in the associated vibration interval of the comparison vibration data and the vibration data in the corresponding interval of the reference vibration data to obtain time-domain synchronous average data; and Whether the gear is faulty is diagnosed based on the time domain synchronous average data.
2. The gear fault diagnosis method according to claim 1, It is characterized in that The data volume of the comparative vibration data is larger than that of the reference vibration data, and the data volume of the comparative vibration data is a positive integer multiple of the data volume of the reference vibration data, and the adjacent sub-vibration data partially overlap.
3. The gear fault diagnosis method according to claim 2, It is characterized in that The data of half a period of the adjacent sub-vibration data overlap.
4. The gear fault diagnosis method according to claim 1, It is characterized in that The multiple data comparison intervals include a starting data comparison interval and multiple subsequent data comparison intervals; The determining of a plurality of data comparison intervals for comparing vibration data includes: Determine a starting data comparison interval for the comparison vibration data; the data volume of the starting data comparison area is the same as the data volume of the reference vibration data; Based on the initial data comparison interval, the comparison vibration data is shifted by one vibration data each time to obtain a plurality of subsequent data comparison intervals, wherein the data amounts of the plurality of subsequent data comparison intervals are respectively the same as the data amount of the initial data comparison interval; The determining of the correlation between the vibration data of the plurality of data comparison intervals of the comparison vibration data and the reference vibration data respectively includes: Determine the correlation between the vibration data in the initial data comparison interval and the vibration data in the plurality of subsequent data comparison intervals and the reference vibration data.
5. The gear fault diagnosis method according to claim 1, It is characterized in that The step of diagnosing whether the gear fails according to the time domain synchronous average data comprises: Determining a time-domain synchronous average characteristic value according to the time-domain synchronous average data; Whether the gear fails is diagnosed based on the time domain synchronous average characteristic value.
6. The gear fault diagnosis method according to claim 5, It is characterized in that The time-domain synchronous average characteristic value includes one or more of a peak-to-valley value, a root mean square value, a pulse factor, and a kurtosis.
7. A gear fault diagnosis device, It is characterized in that A gear fault diagnosis method for implementing any one of claims 1 to 6, wherein the gear fault diagnosis device comprises: A data acquisition module, used to acquire original vibration data of not less than one cycle generated when the gear rotates not less than one circle; A data segmentation module, used for segmenting the original vibration data to obtain a plurality of sub-vibration data of not less than one cycle, wherein the sub-vibration data includes reference vibration data and comparative vibration data; A correlation analysis module is used to perform correlation analysis on the vibration data of multiple data comparison intervals of the comparison vibration data and the benchmark vibration data, respectively, to determine the associated vibration intervals corresponding to the comparison vibration data and the benchmark vibration data; wherein, performing correlation analysis on the vibration data of multiple data comparison intervals of the comparison vibration data and the benchmark vibration data, respectively, to determine the associated vibration intervals corresponding to the comparison vibration data and the benchmark vibration data, comprises: determining multiple data comparison intervals of the comparison vibration data; determining the correlations between the vibration data of multiple data comparison intervals of the comparison vibration data and the benchmark vibration data, respectively; determining the data comparison interval corresponding to the maximum correlation among the multiple correlations as the associated vibration interval; A time domain averaging module, used for performing time domain averaging on the vibration data in the associated vibration interval of the comparative vibration data and the vibration data in the corresponding interval of the reference vibration data to obtain time domain synchronous average data; A fault diagnosis module is used to diagnose whether the gear has a fault based on the time domain synchronous average data.
8. A gear fault diagnosis device, It is characterized in that including a processor and a memory; Memory, used to store computer programs; A processor, for implementing the method according to any one of claims 1 to 6 when executing a program stored in a memory.
9. A computer-readable storage medium, It is characterized in that A program is stored thereon, and when the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
