A method, system, device and program for rotating machinery fault diagnosis

Abstract

The present invention discloses a method, system, device and program for diagnosing faults in rotating machinery. The method includes: acquiring sampling data; the sampling data includes a rotational speed pulse signal and a fault manifestation signal; resampling the sampling data into a rotational speed pulse signal and a fault manifestation signal at equal angular intervals; performing rotational speed fitting on the pulse signal at equal angular intervals to obtain a rotational speed signal; selecting the fault manifestation signal at equal angular intervals as reference axis analysis data based on the rotational speed signal; interpolating the reference axis analysis data to obtain non-reference axis analysis data based on the rotational speed signal and the rotational speed ratio between the reference axis and the non-reference axis; and obtaining the gear position where the fault occurs by performing synchronous channel analysis and mixed channel analysis on the reference axis analysis data and synchronous channel analysis on the non-reference axis analysis data. Through the processing solution of the present disclosure, the gear position where the fault occurs can be accurately identified.

Description

Technical Field

[0001] The present invention relates to the technical field of digital signal processing, and particularly to a method, system, device and program for diagnosing faults of rotating machinery. Background Art

[0002] Rotating mechanical structures that continuously rotate during operation, such as engines, motors, gearboxes, and drive shafts, are all rotating machinery. Vehicles, ships, aerospace vehicles, etc. all include a large number of rotating machinery, and the rotating machinery serving as the power source is often one of the core components of these products. Therefore, diagnosing faults of rotating machinery is of great significance in both product off-line inspection and real-time status monitoring.

[0003] Fault diagnosis of rotating machinery requires collecting signals during its operation. Vibration signals, noise signals, rotational speed signals, torque signals, temperature signals, etc. are all signal types commonly used for fault diagnosis. Different from general machinery, the characteristic of rotating machinery is that its fault manifestations are often related to the rotational speed.

[0004] Traditional methods for diagnosing faults of rotating machinery are to synchronously test the rotational speed signal and the fault manifestation signal. The fault manifestation signal can be different types of signals such as acceleration, sound, and temperature. Then, order spectrum analysis or ColorMap analysis is performed on the fault manifestation signal.

[0005] Among them, order spectrum analysis uses an equal-angle sampling method, that is, the time for the rotating machinery to rotate through a fixed angle is calculated through the rotational speed signal, so as to resample the fault manifestation signal. During the time between every two values in the adopted fault manifestation signal, the rotating machinery has rotated through the same angle. Performing Fourier transform analysis on this signal can obtain the order spectrum curve. By finding the order at which the peak occurs and corresponding to the structural characteristics of the rotating machinery, the faults of the rotating machinery can be diagnosed.

[0006] ColorMap analysis does not require equal-angle sampling. Instead, the fault manifestation signal is divided into small segments, and short-time Fourier transform is performed on each segment, and the average rotational speed of the rotating machinery during this time period is calculated. Plotting the rotational speed label, frequency label, and short-time Fourier transform result on one graph is the ColorMap graph of the signal. The order characteristics related to the rotational speed are shown as a straight line with a slope greater than 0 on the ColorMap graph. By observing the ColorMap graph, finding the rotational speed, frequency, and order corresponding to the fault signal and corresponding to the structural characteristics of the rotating machinery, the faults of the rotating machinery can be diagnosed.

[0007] However, the above traditional methods for diagnosing faults in rotating machinery have the drawback of being unable to locate faults, that is, they cannot perform automatic fault location diagnosis. After obtaining the problem order through traditional analysis methods, it is necessary to correspond to the structural characteristics of the rotating machinery itself to identify the fault location. If the structural parameters of the rotating machinery are unknown or the fault generation mechanism is unclear, fault location diagnosis cannot be carried out.

[0008] It can be seen that the above existing fault diagnosis methods are obviously still inconvenient and defective in use and urgently need to be further improved. How to create a new method for diagnosing faults in rotating machinery has become an urgent goal to be improved in the current industry. Summary of the Invention

[0009] In view of this, embodiments of the present disclosure provide a method for diagnosing faults in rotating machinery, which at least partially solves the problems existing in the prior art.

[0010] In a first aspect, embodiments of the present disclosure provide a method for diagnosing faults in rotating machinery, the method comprising the following steps:

[0011] Obtain sampling data; the sampling data includes a rotational speed pulse signal and a fault manifestation signal;

[0012] Resample the sampling data into a rotational speed pulse signal and a fault manifestation signal with equal angular intervals;

[0013] Perform rotational speed fitting on the pulse signal with equal angular intervals to obtain a rotational speed signal;

[0014] Based on the rotational speed signal, select the fault manifestation signal with equal angular intervals as the reference axis analysis data;

[0015] Based on the rotational speed signal and the rotational speed ratio between the reference axis and the non-reference axis, interpolate the reference axis analysis data to obtain non-reference axis analysis data;

[0016] By performing synchronous channel analysis, mixed channel analysis on the reference axis analysis data, and synchronous channel analysis on the non-reference axis analysis data, obtain the gear position where the fault occurs.

[0017] According to a specific implementation manner of the embodiments of the present disclosure, the resampling of the sampling data into a rotational speed pulse signal and a fault manifestation signal with equal angular intervals includes:

[0018] The host computer reads the sampling data one by one in real time; among them, the moment of reading the first sampling data is set to 0, and the time interval between any two adjacent sampling points is , f s is the sampling frequency;

[0019] When each rotational speed pulse signal is read, it is determined whether the sampling moment of the current rotational speed pulse signal is the pulse excitation moment; wherein, when the value of the current rotational speed pulse signal is greater than the preset value and the value of the previous pulse signal is less than the preset value, it is determined that the sampling moment of the current rotational speed pulse signal is at the pulse excitation moment, the corresponding moment of this sampling point is recorded, and the sampling moment of the current rotational speed pulse signal is written into the time series of equal-angle resampling of the reference axis; the fault manifestation signal data corresponding to this moment is written into the fault manifestation signal sequence of equal-angle resampling of the reference axis.

[0020] According to a specific implementation manner of the embodiment of the present disclosure, the fitting of the rotational speed to the pulse signals at equal-angle intervals includes the following steps:

[0021] Perform rotational speed fitting based on the following formula:

[0022] ;

[0023] Wherein, rpm is the rotational speed signal; PPR is the circumferential resolution; The function represents the staggered-phase subtraction function; is the slice of the time series corresponding to the rotational speed fitted this time T .

[0024] According to a specific implementation manner of the embodiment of the present disclosure, selecting the fault manifestation signals at equal-angle intervals based on the rotational speed signal as the reference axis analysis data includes:

[0025] When rpm reaches the preset minimum rotational speed, start collecting the fault manifestation signals at equal-angle intervals as the reference axis analysis data; when rpm reaches the preset maximum rotational speed, end the collection.

[0026] According to a specific implementation manner of the embodiment of the present disclosure, interpolating the reference axis analysis data to obtain the non-reference axis analysis data based on the rotational speed signal and the rotational speed ratio between the reference axis and the non-reference axis includes:

[0027] After each resampling of the reference axis, calculate the number of resamplings of the non-reference axis between the current resampling point and the previous resampling point of the reference axis in combination with the rotational speed ratio;

[0028] Perform linear interpolation on the times of two resampling points of the reference axis to obtain the resampling time of the non-reference axis; select the sampling point closest to the resampling time of the non-reference axis in the sampling data as the non-reference axis analysis data;

[0029] Calculate the non-reference axis resampling point based on the following formula:

[0030] ;

[0031] ;

[0032] wherein, is the serial number of non-reference axle weight resampling; is the th point of non-reference axle weight resampling; represents the serial number of the signal collected by the current signal acquisition device; is the coefficient of the recurrence relation formula of non-reference axle weight resampling; is the rotational speed ratio of the non-reference axle to the reference axle.

[0033] According to a specific implementation manner of an embodiment of the present disclosure, the method for obtaining the gear position where a fault occurs by performing synchronous channel analysis, mixed channel analysis, and synchronous channel analysis of non-reference axle analysis data on the reference axle analysis data includes:

[0034] The synchronous channel analysis includes:

[0035] Dividing the reference axle analysis data and the non-reference axle analysis data into different slice data, and each slice reflects the rotation condition of the rotating shaft within the time period of collecting the slice data;

[0036] Calculating the average value of multiple slice data of the rotating shaft;

[0037] Performing a fast Fourier transform on the averaged slice data, and then performing a self-spectrum linear spectrum calculation to obtain the synchronous channel analysis result;

[0038] The mixed channel analysis includes:

[0039] Dividing the reference axle analysis data into different slice data, which is the same as the synchronous channel reference axle slice data;

[0040] Performing a fast Fourier transform on all current slice data, calculating the self-spectrum linear spectrum, and taking the maximum value of all self-spectrums as the mixed channel analysis result.

[0041] According to a specific implementation manner of an embodiment of the present disclosure, the average value of multiple slice data of the rotating shaft in the synchronous channel analysis is calculated based on the following formula :

[0042] ;

[0043] wherein, is the th signal segment and the th data; represents the total number of signal segments;

[0044] Performing a fast Fourier transform on the averaged slice data based on the following formula :

[0045] ;

[0046] Among them, is the frequency components after Fourier transform; is the signal mean value of the th sampling point in the time domain; is the phase relationship of different frequency components; is the th frequency component in the frequency domain, 0 ≤ k ≤ ; is the total length of the signal.

[0047] According to a specific implementation manner of the embodiments of the present disclosure, the hybrid channel analysis includes:

[0048] Calculate the synchronous channel analysis result based on the following formula:

[0049] ;

[0050] Among them, is the synchronous channel analysis result;

[0051] The hybrid channel analysis includes:

[0052] Perform auto-spectrum linear spectrum calculation on the current all signal segmented data:

[0053] ;

[0054] Among them, is the th frequency component after Fourier transform of the th signal segment; is the th data of the th signal segment; is the phase relationship of different frequency components; is the th frequency component in the frequency domain, 0 ≤ k ≤ ; is the total length of the signal;

[0055] Perform hybrid channel calculation on the auto-spectrum linear spectrum calculation result:

[0056] ;

[0057] Among them, is the analysis result of the hybrid channel; is the total number of signal segments.

[0058] In a second aspect, an embodiment of the present disclosure provides a rotating machinery fault diagnosis system, the system comprising:

[0059] a data acquisition module configured to acquire sampling data; the sampling data includes a rotational speed pulse signal and a fault manifestation signal;

[0060] a resampling module configured to resample the sampling data into a rotational speed pulse signal and a fault manifestation signal with equal angular intervals;

[0061] a fitting module configured to perform rotational speed fitting on the pulse signal with equal angular intervals to obtain a rotational speed signal;

[0062] an analysis data module configured to select the fault manifestation signal with equal angular intervals as the reference axis analysis data based on the rotational speed signal; and, based on the rotational speed signal, the rotational speed ratio between the reference axis and the non-reference axis, interpolate the reference axis analysis data to obtain non-reference axis analysis data;

[0063] an analysis module configured to obtain the gear position where the fault occurs by performing synchronous channel analysis, mixed channel analysis on the reference axis analysis data, and synchronous channel analysis on the non-reference axis analysis data.

[0064] In a third aspect, an embodiment of the present disclosure further provides a computer program product, the computer program product comprising a computing program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, causing the computer to execute a rotating machinery fault diagnosis method in the foregoing first aspect or any implementation manner of the first aspect.

[0065] A rotating machinery fault diagnosis method in an embodiment of the present disclosure divides the original time-domain signal into different intervals according to the rotational speeds of different rotating shafts of the rotating machinery. Each interval can accurately reflect the single rotation situation of the rotating shaft within a certain time. By performing synchronous rotational speed analysis to take the average value of the single rotation signal, signal components irrelevant to the rotating shaft will be suppressed, thereby obtaining the fault signal on the rotating shaft; for faults irrelevant to the rotational speed, the mixed channel is not averaged, and a fault signal irrelevant to all rotating shafts can be obtained from the mixed channel result.

[0066] The present invention has the following advantages:

[0067] (1) Accurately locate the faulty shaft based on the synchronous channel. By comparing the synchronous channels of the reference shaft and non-reference shafts, diagnose the shaft where the fault lies according to the fault order. This method utilizes the correlation between the rotational shaft synchronous signals, can effectively focus on faults related to rotational shaft synchronization, and accurately determine on which shaft the fault occurs. For multi-shaft equipment such as mechanical systems, quickly and accurately locating the faulty shaft can greatly reduce the maintenance time and cost, and avoid blindly inspecting multiple components.

[0068] (2) The synchronous channel effectively eliminates irrelevant noise interference. In the synchronous channel analysis, noises that are not synchronized with the rotational shaft (such as bearing noises) will be ignored. This enables the diagnostic process to focus on the key signals synchronized with the rotational shaft, avoids the interference of irrelevant noises on fault diagnosis, and thus improves the accuracy of fault diagnosis related to rotational shaft synchronization. In a complex mechanical operating environment, there are various noises, and this ability to specifically eliminate interference is very crucial.

[0069] (3) The hybrid channel complements the diagnosis of asynchronous faults. In addition to being able to diagnose faults synchronized with the rotational shaft, a hybrid channel is introduced to diagnose faults that are not synchronized with the rotational shaft. Since the noises generated by some faults are not synchronized with the rotational shaft, simply relying on synchronous channel analysis may miss these faults. The use of the hybrid channel exactly makes up for this defect, making the diagnostic method more comprehensive and capable of covering different types of faults, whether they are synchronized or not synchronized with the rotational shaft.

[0070] (4) The hybrid channel preserves the slice data features completely. The slice data used in the hybrid channel is the same as that in the synchronous channel, but in the processing method, instead of taking the average value, the maximum value is taken to preserve the noise features of all slice data. This data processing method can retain the information related to asynchronous faults to the greatest extent, and will not lose some key features that may imply faults due to operations such as taking the average. This helps to more keenly capture the fault signals that are not synchronized with the rotational shaft, and further improves the accuracy of asynchronous fault diagnosis.

[0071] (5) Standardization and potential for batch diagnosis. This diagnostic method provides a relatively standardized process for product quality inspection and fault diagnosis. Whether it is for quality inspection of newly produced products on the production line or for fault troubleshooting of multiple equipment of the same model during equipment maintenance, the same diagnostic steps and comparison criteria can be adopted. This enables batch fault diagnosis, improves the diagnostic efficiency, and also helps to ensure the consistency and reliability of the diagnostic results. Brief Description of the Drawings

[0072] The above is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, the following provides a more detailed description of the present invention in combination with the drawings and specific embodiments.

[0073] Figure 1 Schematic diagram of the process of a rotating machinery fault diagnosis method provided by an embodiment of the present disclosure;

[0074] Figure 2 Block diagram of the process of a rotating machinery fault diagnosis method provided by an embodiment of the present disclosure;

[0075] Figure 3 Schematic diagram of the rules of a pulse signal, a vibration signal, and resampling provided by an embodiment of the present disclosure;

[0076] Figure 4 Schematic diagram of a pulse signal provided by an embodiment of the present disclosure;

[0077] Figure 5 Schematic diagram of a rotational speed signal after pulse fitting provided by an embodiment of the present disclosure;

[0078] Figure 6 Schematic diagram of an angular domain analysis image of a synchronous channel of a reference shaft and a non-reference shaft provided by an embodiment of the present disclosure;

[0079] Figure 7 Schematic diagram of the structure of a rotating machinery fault diagnosis system provided by an embodiment of the present disclosure;

[0080] Figure 8 Schematic diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0081] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0082] The following uses specific specific examples to illustrate the implementation manners of the present disclosure. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts belong to the scope of protection of the present disclosure.

[0083] Note that the following description relates to various aspects of embodiments within the scope of the appended claims. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is illustrative only. Based on this disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of the aspects set forth herein can be used to implement an apparatus and / or practice a method. Additionally, this apparatus and / or method can be implemented using other structures and / or functionality in addition to one or more of the aspects set forth herein.

[0084] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the aspects can be practiced without these specific details.

[0085] An embodiment of the present invention provides a method for diagnosing faults in a rotating machine. By synchronously sampling the rotational speed pulse and the original time-domain signal of the fault manifestation. The time-domain signal data at equal time intervals collected at the front end is resampled to obtain time-domain signal data at equal angular intervals. According to the time interval difference between the time-domain signals at equal angular intervals, the rotational speed corresponding to the sampling moment can be calculated; according to the resampled data at equal angular intervals, the fault manifestation signal resampled on the reference axis (the reference axis is the rotating axis for collecting the pulse signal) can be obtained; according to the resampled data on the reference axis and the speed ratio, the fault manifestation signal resampled on the non-reference axis (the non-reference axis is a gear shaft having a fixed speed ratio with the reference axis) can be calculated. By performing synchronous channel analysis and mixed channel analysis on the fault manifestation signals resampled on the reference axis and the non-reference axis, the gear position where the fault occurs can be comprehensively diagnosed.

[0086] Figure 1 It is a schematic diagram of the flow of a method for diagnosing faults in a rotating machine provided for an embodiment of the present disclosure.

[0087] Figure 2 For Figure 1 It is a flow block diagram of a method for diagnosing faults in a rotating machine corresponding thereto.

[0088] As Figure 1 shown, at step S110, sampling data is acquired; the sampling data includes a rotational speed pulse signal and a fault manifestation signal.

[0089] More specifically, the rotational speed sensor for collecting the pulse signal, the sensor for collecting the fault manifestation signal, and the front end of the data acquisition device are connected and debugged, and relevant parameters are set.

[0090] The set parameters include: different shaft speed ratios , sampling frequency 、Frequency resolution 、Window function 、Circumferential resolution 、Analysis frequency in the angular domain 、Angular resolution 、Analysis average rate in the angular domain 、Rotation speed fitting time interval And the zero reference value of the pulse signal 。The rotation speed ratio refers to the proportional relationship between the rotation speeds of the non-reference axis and the reference axis; the sampling frequency refers to the number of samplings per second; the frequency resolution refers to the minimum interval that can distinguish two different frequency components in the frequency domain; the average rate refers to the number of slice starting points included in the samples per second when the signal is sliced; the window function reduces the discontinuity of the signal at both ends of the slice by weighting the signal slices, thereby avoiding problems such as spectrum leakage and harmonic interference; the rotation speed fitting time interval is the length of the time interval defined manually. Every time the sampling time passes through a specified time interval, the pulse data sampled within this time interval is subjected to a rotation speed fitting once; the zero reference value of the pulse signal is the threshold value for pulse excitation. When the pulse signal passes through this value, it is considered that a pulse occurs.

[0091] More specifically, next, go to step S120.

[0092] At step S120, the sampling data is resampled into a rotation speed pulse signal and a fault manifestation signal with equal angular intervals.

[0093] In the embodiment of the present invention, the resampling of the sampling data into a rotation speed pulse signal and a fault manifestation signal with equal angular intervals includes:

[0094] The host computer reads the sampling data one by one in real time; among them, the moment of reading the first sampling data is set to 0, and the time interval between any two adjacent sampling points is , f s Is the sampling frequency;

[0095] Every time a rotation speed pulse signal is read, it is judged whether the sampling moment of the current rotation speed pulse signal is the pulse excitation moment; among them, when the value of the current rotation speed pulse signal is greater than the preset value and the value of the previous pulse signal is less than the preset value, it is judged that the sampling moment of the current rotation speed pulse signal is at the pulse excitation moment, record the corresponding moment of this sampling point, and write the sampling moment of the current rotation speed pulse signal into the time series of equal-angle resampling of the reference axis; write the data of the fault manifestation signal corresponding to this moment into the fault manifestation signal series of equal-angle resampling of the reference axis T 。

[0096] More specifically, the time domain signal with equal time intervals collected at the front end of the data acquisition device is processed into a time domain signal with equal angular intervals.

[0097] As shown Figure 3 in the figure, the pulses and fault manifestation signals collected at the front end of the data acquisition device are read by the host computer one by one in real time. The moment when the first data is read is set to 0, and the time interval between any two adjacent sampling points thereafter is , f s the sampling frequency, that is, the number of samples collected in 1 second, which is generally 12,800, 25,600 or 51,200, that is, the time interval for collecting data. Each time a pulse data is read, according to the set zero reference value of the pulse signal , it can be judged whether the current sampling moment of the pulse data is the pulse excitation moment. If the current pulse signal value is greater than , and the previous pulse signal value is less than , then it is the pulse excitation moment, and the corresponding moment of this sampling point will be recorded and written into the time series of equally angular resampling of the reference axis ; at the same time, the fault manifestation signal data corresponding to this moment will be recorded and written into the fault manifestation signal sequence of equally angular resampling of the reference axis .

[0098] Next, go to step S130.

[0099] At step S130, the equally angular interval pulse signals are subjected to rotational speed fitting to obtain rotational speed signals.

[0100] In the embodiment of the present invention, the rotational speed fitting of the equally angular interval pulse signals includes the following steps:

[0101] Perform rotational speed fitting based on the following formula:

[0102] ……Equation 1

[0103] where rpm is the rotational speed signal; PPR is the circumferential resolution; The function represents a staggered subtraction function; is the slice of the time series T corresponding to the rotational speed fitted this time.

[0104] More specifically, perform rotational speed fitting calculation on the obtained time series of equally angular resampling of the reference axis.

[0105] For the time series every time a new data is added, it is judged whether the newly added time data and the time of the previous rotational speed fitting reach the fitting time interval , if the condition is met, perform rotational speed fitting and record the current rotational speed fitting time. The rotational speed fitting calculation is to perform staggered subtraction on the time data within the time range before the current sampling moment to obtain . According to the rotational speed calculation formula, the rotational speeds at each sampling moment within the time range before the current sampling moment can be obtained, and the average value is taken as the fitted rotational speed within the time range before the current sampling moment rpm .

[0106] The calculation method of the fitted rotational speed is as follows:

[0107] ;

[0108] In the formula, PPR represents the circular resolution, the function represents the staggered subtraction function, represents the time series slice corresponding to the fitted rotational speed this time.

[0109] Next, go to step S140.

[0110] At step S140, select the fault manifestation signals at equal angular intervals based on the rotational speed signal as the reference axis analysis data.

[0111] In the embodiment of the present invention, selecting the fault manifestation signals at equal angular intervals based on the rotational speed signal as the reference axis analysis data includes:

[0112] When rpm reaches the preset minimum rotational speed, start collecting the fault manifestation signals at equal angular intervals as the reference axis analysis data; when rpm reaches the preset maximum rotational speed, end the collection.

[0113] More specifically, as Figure 4 shown, if rpm meets the minimum rotational speed requirement for collection rpm min , then start collecting the reference axis analysis data in step S120. If rpm reaches the maximum rotational speed for collection rpm max , then end the collection.

[0114] Next, go to step S150.

[0115] At step S150, based on the rotational speed signal and the rotational speed ratio between the reference axis and the non-reference axis, interpolate the reference axis analysis data to obtain the non-reference axis analysis data.

[0116] In the embodiments of the present invention, based on the rotational speed signal and the rotational speed ratio between the reference axis and the non-reference axis, interpolating the reference axis analysis data to obtain non-reference axis analysis data includes:

[0117] After each resampling of the reference axis, calculate the number of resamplings of the non-reference axis between the current resampling point and the previous resampling point of the reference axis in combination with the rotational speed ratio;

[0118] Perform linear interpolation on the times of two resampling points of the reference axis to obtain the resampling time of the non-reference axis; select the sampling point closest to the resampling time of the non-reference axis from the sampling data as the non-reference axis analysis data;

[0119] Calculate the non-reference axis resampling point based on the following formula:

[0120] …… Equation 2

[0121] …… Equation 3

[0122] Wherein, is the serial number of the non-reference axis resampling; is the th point of the non-reference axis resampling; represents the serial number of the signal collected by the current signal acquisition device; is the coefficient of the recurrence relation of the non-reference axis resampling; is the rotational speed ratio between the non-reference axis and the reference axis.

[0123] More specifically, while performing equal-angle resampling of the reference axis (selecting points from ), perform equal-angle resampling of the non-reference axis.

[0124] Since there is no corresponding pulse signal for the non-reference axis, the resampling of the non-reference axis fault manifestation signal should be based on the reference axis resampling data. Therefore, after each resampling of the reference axis, it is necessary to combine the rotational speed ratio to calculate the number of resamplings required for the non-reference axis between the current resampling point and the previous resampling point of the reference axis. Perform linear interpolation on the times of these two resampling points of the reference axis to obtain the resampling time of the non-reference axis, and select the sampling point closest to the resampling time of the non-reference axis from the sampling data as the resampling data of the non-reference axis.

[0125] The calculation method of the non-reference axis resampling point is:

[0126] ;

[0127] ;

[0128] In the formula, Indicates the serial number of non-reference axis resampling, Indicates the th point of non-reference axis resampling; Indicates the serial number of the signal collected by the current data acquisition device, Is a coefficient of a recurrence relation for non-reference axis resampling Is the rotational speed ratio of the non-reference axis to the reference axis. Multiplying by 1 / fs gives the resampled point time.

[0129] Next, go to step S160.

[0130] At step S160, by performing synchronous channel analysis, mixed channel analysis on the reference axis analysis data, and synchronous channel analysis on the non-reference axis analysis data, the gear position where the fault occurs is obtained.

[0131] In the embodiment of the present invention, the method of obtaining the gear position where the fault occurs by performing synchronous channel analysis, mixed channel analysis on the reference axis analysis data, and synchronous channel analysis on the non-reference axis analysis data includes:

[0132] The synchronous channel analysis includes:

[0133] Dividing the reference axis analysis data and the non-reference axis analysis data into different slice data, each slice reflecting the rotation of the rotating shaft within the time range of collecting the slice data; the slice length is several PPR , that is, the slice data is the data of several complete rotations of the shaft where it is located; for example, the slice length is a multiple of PPR, generally taking 2, 4, or 8 times.

[0134] Calculating the average value of the multiple slice data of the rotating shaft;

[0135] Performing a fast Fourier transform on the averaged slice data, and then calculating the auto-spectrum linear spectrum to obtain the synchronous channel analysis result;

[0136] The mixed channel analysis includes:

[0137] Dividing the reference axis analysis data into different slice data, which is the same as the synchronous channel reference axis slice data;

[0138] Taking the maximum value of all current slice data and then performing a fast Fourier transform, calculating the auto-spectrum linear spectrum, and taking the maximum value of all auto-spectrums as the mixed channel analysis result.

[0139] In the embodiment of the present invention, the average value of the multiple slice data of the rotating shaft in the synchronous channel analysis is calculated based on the following formula :

[0140] …… Equation 4

[0141] Among them, is the th data of the th signal segment; represents the total number of signal segments;

[0142] Perform a fast Fourier transform on the averaged slice data based on the following formula :

[0143] ... Equation 5

[0144] Among them, are the frequency components after Fourier transform; is the signal mean value of the th sampling point in the time domain; is the phase relationship of different frequency components; is the th frequency component in the frequency domain, 0 ≤ k ≤ ; is the total length of the signal.

[0145] In the embodiment of the present invention, the hybrid channel analysis includes:

[0146] Calculate the synchronous channel analysis result based on the following formula:

[0147] ... Equation 6

[0148] Among them, is the synchronous channel analysis result, and the synchronous channel analysis results of the reference axis and the non-reference axis can be calculated from this step;

[0149] The hybrid channel analysis includes:

[0150] Calculate the auto-spectrum linear spectrum based on all the current signal segment data:

[0151] ... Equation 7

[0152] Among them, are the frequency components after Fourier transform of the th signal segment; is the th data of the th signal segment; is the phase relationship of different frequency components; is the th frequency component in the frequency domain, 0 ≤ k ≤ ; is the total length of the signal;

[0153] Perform mixed-channel calculation on the self-spectrum linear spectrum calculation result:

[0154] …… Equation 8

[0155] wherein, is the analysis result of the mixed channel; is the total number of signal segments.

[0156] More specifically, as shown in Figure 5 and Figure 6 , the reference axis (selected from ) and the resampled fault manifestation signal H of the non-reference axis are respectively subjected to synchronous channel analysis and mixed channel analysis of the reference axis and the non-reference axis.

[0157] According to the angular domain analysis frequency and the angular resolution , the analysis bandwidth can be obtained. For each newly added data of the fault manifestation signal, it is judged whether the difference in the length of the fault manifestation signal from the length of the previous synchronous channel analysis (same as the mixed channel analysis) reaches (if it is the first time to perform synchronous channel analysis (or mixed channel analysis), it is judged whether the length reaches ). If it reaches, the slices of a total of data including the current sampling point and the previous sampling point are subjected to synchronous channel analysis and mixed channel analysis (the non-reference axis only performs synchronous channel analysis and does not perform mixed channel analysis).

[0158] Furthermore, the resampled slices of the reference axis and non-reference axis data obtained represent the rotation condition of the rotating shaft within the sampling time range of the slice, and the analyzed slice data represents the rotation condition of the rotating shaft within the acquisition time range of the segment slice, that is, the mean value of all current slice data is taken and then subjected to FFT (Fast Fourier Transform) processing, and its effective value is calculated as the synchronous channel analysis result.

[0159] Mixed channel analysis is to take the maximum value of all current slice data and then perform FFT processing, and calculate its effective value as the mixed channel analysis result. Taking the mean value in the synchronous channel can eliminate the interference caused by other channels; taking the maximum value in the mixed channel retains the signal characteristics of all channels through peak holding.

[0160] The resampled signal of each rotating shaft is segmented into different slice data. Each slice contains one or more rotations of the reference shaft. Each slice can accurately reflect the rotation of the rotating shaft within the time period of collecting this point, including all noise components. By calculating the average value of the multiple slice data of the rotating shaft, the noise components that are not synchronized with the rotating shaft are suppressed. After performing FFT processing on the averaged slice data, the synchronous channel analysis result can be obtained. By comparing the synchronous channels of the reference shaft and the non-reference shaft, the faulty shaft can be diagnosed according to the fault order. Some noises are not synchronized with the rotating shaft (such as bearing noise). Using synchronous channel analysis, such noises will be ignored. Therefore, a mixed channel is used to diagnose the noise that is not synchronized with the rotating shaft. The slice data used in the mixed channel is the same as that in the synchronous channel, but the average value is not taken. By taking the maximum value, the noise characteristics of all slice data are retained. By comparing the mixed channels of the reference shafts of different products of the same model, it can be diagnosed whether there is a fault.

[0161] The calculation method of synchronous channel analysis is as follows:

[0162] The time window used in FFT is the Hanning window, and the coefficient multiplied by each element of the signal can be calculated by the formula where, represents the length of the signal segment, represents the coefficient multiplied by the th element in the signal;

[0163] The mean value of the synchronous channel signal is calculated as follows:

[0164] ;

[0165] In the formula, is the th data of the th signal segment; represents the total number of signal segments.

[0166] The Fourier transform needs to be calculated for each slice. The calculation method of the Fourier transform is as follows:

[0167] ;

[0168] In the formula, represents the th frequency component after Fourier transform of the th signal segment; is the mean value of the signal at the th sampling point in the time domain; describes the phase relationship of different frequency components; represents the th frequency component in the frequency domain, 0 ≤ k ≤ ; represents the total length of the signal.

[0169] The hybrid channel analysis includes: calculating the synchronous channel analysis result based on the following formula:

[0170] ;

[0171] where is the synchronous channel analysis result;

[0172] The hybrid channel analysis includes: calculating the auto-spectrum linear spectrum based on the current all signal segmented data:

[0173] ;

[0174] where is the th frequency component after Fourier transform of the th signal segment; is the th data of the th signal segment; is the phase relationship of different frequency components; is the th frequency component in the frequency domain, 0 ≤ k ≤ ; is the total length of the signal;

[0175] Perform hybrid channel calculation on the auto-spectrum linear spectrum calculation result:

[0176] ;

[0177] where is the analysis result of the hybrid channel; is the total number of signal segments.

[0178] Diagnostic method: By comparing the synchronous channels of the reference axis and the non-reference axis, the faulty axis can be diagnosed according to the fault order. Some noises are not synchronized with the rotating shaft (such as bearing noise). Using synchronous channel analysis, such noises will be ignored. Therefore, use the hybrid channel to diagnose the noises that are not synchronized with the rotating shaft. The sliced data used in the hybrid channel is the same as that in the synchronous channel, but the average value is not taken. By taking the maximum value, the noise characteristics of all sliced data are retained. By comparing the hybrid channels of the reference axes of different products of the same model, it can be diagnosed whether there are faults that are not synchronized with the rotating shaft.

[0179] Compared with the traditional angular domain analysis method, the synchronous channel and hybrid channel angular domain analysis technical methods of the present invention have the following advantages:

[0180] (1) According to the rotational speeds of different rotating shafts of a rotating machine, the present invention divides the original time-domain signal into different intervals. Each interval can accurately reflect the single rotation condition of the rotating shaft within a certain time. By performing synchronous rotational speed analysis to take the average value of the single rotation signal, the signal components unrelated to the rotating shaft will be suppressed, thereby obtaining the fault signal on the rotating shaft.

[0181] (2) For faults unrelated to the rotational speed, the mixed channels are not averaged, and the fault signals unrelated to all rotating shafts can be obtained from the results of the mixed channels.

[0182] Figure 7 Fig. 7 shows a rotating machine fault diagnosis system 700 provided by the present invention, which includes a data acquisition module 710, a resampling module 720, a fitting module 730, an analysis data module 740, and an analysis module 750.

[0183] The data acquisition module 710 is used to acquire sampling data; the sampling data includes rotational speed pulse signals and fault manifestation signals.

[0184] The resampling module 720 is used to resample the sampling data into rotational speed pulse signals and fault manifestation signals with equal angular intervals.

[0185] The fitting module 730 is used to perform rotational speed fitting on the pulse signals with equal angular intervals to obtain rotational speed signals.

[0186] The analysis data module 740 is used to select the fault manifestation signals with equal angular intervals as the reference axis analysis data based on the rotational speed signals; and, based on the rotational speed signals, the rotational speed ratio between the reference axis and the non-reference axis, interpolate the reference axis analysis data to obtain non-reference axis analysis data.

[0187] The analysis module 750 is used to obtain the gear position where the fault occurs by performing synchronous channel analysis, mixed channel analysis on the reference axis analysis data, and synchronous channel analysis on the non-reference axis analysis data.

[0188] Refer to Figure 8 , the present disclosure embodiment also provides an electronic device 80, which includes:

[0189] At least one processor; and,

[0190] A memory communicatively connected to the at least one processor; wherein,

[0191] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor can execute a rotating machine fault diagnosis method in the foregoing method embodiment.

[0192] An embodiment of the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute a rotary machinery fault diagnosis method in the foregoing method embodiments.

[0193] An embodiment of the present disclosure also provides a computer program product including a computing program stored on a non-transitory computer-readable storage medium, the computer program including program instructions that, when executed by a computer, cause the computer to execute a rotary machinery fault diagnosis method in the foregoing method embodiments.

[0194] Reference is made below Figure 8 to FIG. [not provided in the original, assuming it should be filled in later], which shows a schematic structural diagram of an electronic device 80 suitable for implementing embodiments of the present disclosure. The electronic device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The electronic device shown is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0195] As Figure 8 shown, the electronic device 80 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 801, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 80 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0196] Generally, the following devices may be connected to the I / O interface 805: an input device 806 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 808 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 809. The communication device 809 may allow the electronic device 80 to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows an electronic device 80 having various devices, it should be understood that it is not required to implement or include all the shown devices. More or fewer devices may be alternatively implemented or included.

[0197] In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by a processing device 801, the above-described functions defined in the methods of the embodiments of the present disclosure are performed.

[0198] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0199] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; or it can exist separately without being assembled into the electronic device.

[0200] The above computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: obtain at least two Internet Protocol addresses; send a node evaluation request including the at least two Internet Protocol addresses to a node evaluation device, wherein the node evaluation device selects an Internet Protocol address from the at least two Internet Protocol addresses and returns it; receive the Internet Protocol address returned by the node evaluation device; wherein the obtained Internet Protocol addresses indicate edge nodes in a content delivery network.

[0201] Alternatively, the above computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: receive a node evaluation request including at least two Internet Protocol addresses; select an Internet Protocol address from the at least two Internet Protocol addresses; return the selected Internet Protocol address; wherein the received Internet Protocol addresses indicate edge nodes in a content delivery network.

[0202] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0203] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or by a combination of dedicated hardware and computer instructions.

[0204] The units involved in the embodiments described in the present disclosure can be implemented in software or in hardware. Among them, the name of the unit does not constitute a limitation on the unit itself in some cases. For example, the first acquisition unit can also be described as "the unit for acquiring at least two Internet protocol addresses".

[0205] It should be understood that the various parts of the present disclosure can be implemented by hardware, software, firmware, or a combination thereof.

[0206] As described above, the above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present disclosure should be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for diagnosing a rotating machinery fault, characterized in that: The method comprises the following steps: Acquiring sampling data; the sampling data includes a speed pulse signal and a fault performance signal; Resampling the sampled data into speed pulse signals and fault manifestation signals at equal angle intervals; Performing speed fitting on the pulse signals with equal angle intervals to obtain a speed signal; Selecting fault manifestation signals with equal angle intervals as reference shaft analysis data based on the rotation speed signal; Based on the speed signal and the speed ratio of the reference shaft to the non-reference shaft, interpolating the reference shaft analysis data to obtain the non-reference shaft analysis data; The gear position where the fault occurs is obtained by performing synchronous channel analysis, mixed channel analysis and synchronous channel analysis on the reference axis analysis data and non-reference axis analysis data.

2. A rotating machinery fault diagnosis method according to claim 1, characterized in that: The step of resampling the sampled data into speed pulse signals and fault manifestation signals at equal angle intervals includes: The host computer reads the sampled data one by one in real time; the time when the first sampled data is read is set to 0, and the time interval between any two adjacent sampling points is 1 / f s , f s is the sampling frequency; Each time a speed pulse signal is read, it is determined whether the current speed pulse signal sampling moment is the pulse excitation moment; wherein, when the current speed pulse signal value is greater than the preset value and the previous pulse signal value is less than the preset value, it is determined that the current speed pulse signal sampling moment is at the pulse excitation moment, the moment corresponding to the sampling point is recorded, and the current speed pulse signal sampling moment is written into the time series of the reference axis equiangular resampling; the fault manifestation signal data corresponding to the moment is written into the fault manifestation signal sequence of the reference axis equiangular resampling.

3. A rotating machinery fault diagnosis method according to claim 1, characterized in that: The speed fitting of the pulse signals at equal angle intervals comprises the following steps: The speed fitting is based on the following formula: Among them, rpm is the speed signal; PPR is the circumferential resolution; diff function represents the offset subtraction function; T′ is the slice of the time series T corresponding to the fitting speed this time.

4. A rotating machinery fault diagnosis method according to claim 2, characterized in that: Selecting fault manifestation signals at equal angle intervals based on the speed signal as reference shaft analysis data includes: When the rpm reaches the preset minimum speed, the fault performance signals at equal angle intervals are collected as reference axis analysis data; when the rpm reaches the preset maximum speed, the collection is terminated.

5. A rotating machinery fault diagnosis method according to claim 1, characterized in that: Based on the speed signal and the speed ratio of the reference shaft to the non-reference shaft, the reference shaft analysis data is interpolated to obtain the non-reference shaft analysis data, including: After each resampling of the reference axis, the number of resamplings of the non-reference axis between the current resampling point and the previous resampling point of the reference axis is calculated in combination with the speed ratio; Perform linear interpolation on the two resampling point times of the reference axis to obtain the resampling time of the non-reference axis; select the sampling point closest to the resampling time of the non-reference axis from the sampling data as the non-reference axis analysis data; The non-reference axis resampling points are calculated based on the following formula: H(j)=H(j-1)+k×(iH(j-1)); Among them, j is the serial number of the non-reference axis resampling; H(j) is the jth point of the non-reference axis resampling; i represents the serial number of the signal collected by the current signal acquisition device; k is the recursive relationship coefficient of the non-reference axis resampling; R is the speed ratio of the non-reference axis to the reference axis.

6. A rotating machinery fault diagnosis method according to claim 1, characterized in that: The method of obtaining the gear position where the fault occurs by performing synchronous channel analysis, mixed channel analysis and synchronous channel analysis on the reference shaft analysis data, includes: The synchronous channel analysis of the reference axis analysis data comprises: The reference axis analysis data is divided into different slice data, each slice reflects the rotation of the axis within the time period of collecting the slice data; Calculate the average value of multiple slice data of the rotation axis; The averaged slice data is subjected to fast Fourier transformation, and then the autospectral linear spectrum is calculated to obtain the synchronous channel analysis results; The synchronous channel analysis step for analyzing the non-reference axis data is consistent with the synchronous channel analysis for the reference axis; The mixed channel analysis comprises: The reference axis analysis data is divided into different slice data, which are consistent with the reference axis slice data of the synchronous channel; Perform fast Fourier transform on all current slice data, calculate the self-spectrum linear spectrum, and take the maximum value of all self-spectra as the mixed channel analysis result.

7. A rotating machinery fault diagnosis method according to claim 6, characterized in that: The average value f(n) of multiple slice data of the rotating axis in the synchronous channel analysis is calculated based on the following formula: Among them, f s (n) is the nth data of the sth signal segment; S represents the total number of signal segments; The averaged slice data is fast Fourier transformed based on the following formula y fft [k]: Among them, y fft [k] is the k frequency components after Fourier transform; f(n) is the signal mean of the nth sampling point in the time domain; is the phase relationship between different frequency components; k is the kth frequency component in the frequency domain, 0≤k≤N-1; N is the total length of the signal; The synchronous channel analysis results are calculated based on the following formula: Among them, sync is the analysis result of the synchronization channel; The mixed channel analysis comprises: Based on the calculation of the autospectral linear spectrum of all current signal segment data: Among them, y fft,s [k] is the k frequency components after Fourier transform of the sth signal segment; f s (n) is the nth data of the sth signal segment; is the phase relationship between different frequency components; k is the kth frequency component in the frequency domain, 0≤k≤N-1; N is the total length of the signal; Perform mixed channel calculation on the autospectral linear spectrum calculation result: Wherein, mix is ​​the analysis result of the mixed channel; S is the total number of signal segments.

8. A rotating machinery fault diagnosis system, characterized in that: The system comprises: A data acquisition module is configured to acquire sampled data; the sampled data includes a speed pulse signal and a fault manifestation signal; A resampling module, configured to resample the sampled data into a rotation speed pulse signal and a fault manifestation signal at equal angle intervals; A fitting module is configured to perform speed fitting on the pulse signals with equal angle intervals to obtain a speed signal; an analysis data module configured to select fault manifestation signals with equal angle intervals as reference axis analysis data based on the rotation speed signal; and interpolate the reference axis analysis data to obtain non-reference axis analysis data based on the rotation speed signal and the rotation speed ratio of the reference axis to the non-reference axis; The analysis module is configured to obtain the gear position where the fault occurs by performing synchronous channel analysis, mixed channel analysis and synchronous channel analysis on the reference shaft analysis data and the non-reference shaft analysis data.

9. An electronic device, characterized in that: The electronic device includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor executes a rotating machinery fault diagnosis method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes a rotating machinery fault diagnosis method as described in any one of claims 1 to 7.

Images