CN111738068A - Transmission shaft fault diagnosis method and system under working condition of rotating speed fluctuation - Google Patents
Transmission shaft fault diagnosis method and system under working condition of rotating speed fluctuation Download PDFInfo
- Publication number
- CN111738068A CN111738068A CN202010401814.1A CN202010401814A CN111738068A CN 111738068 A CN111738068 A CN 111738068A CN 202010401814 A CN202010401814 A CN 202010401814A CN 111738068 A CN111738068 A CN 111738068A
- Authority
- CN
- China
- Prior art keywords
- signal
- transmission shaft
- time
- working condition
- rotating speed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 69
- 238000003745 diagnosis Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000000605 extraction Methods 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000006243 chemical reaction Methods 0.000 claims description 20
- 230000009467 reduction Effects 0.000 claims description 13
- 230000035772 mutation Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000005299 abrasion Methods 0.000 abstract description 4
- 238000009434 installation Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000005070 sampling Methods 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000012952 Resampling Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012887 quadratic function Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/028—Acoustic or vibration analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Artificial Intelligence (AREA)
- Acoustics & Sound (AREA)
- Algebra (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to a transmission shaft fault diagnosis method and a transmission shaft fault diagnosis system under a rotating speed fluctuation working condition, wherein firstly, a transmission shaft vibration signal under the rotating speed fluctuation working condition is obtained; secondly, extracting characteristics of the transmission shaft vibration signal under the working condition of speed fluctuation, and extracting a two-dimensional time-frequency ridge line of the vibration signal and characteristic parameters of the signal in an order domain; and then, taking the extracted characteristic parameters of the vibration signals in the order domain as input characteristics, and carrying out classification diagnosis on the characteristics of different vibration signals by using an artificial neural network to realize transmission shaft fault diagnosis. The invention utilizes the two-dimensional time-frequency ridge line of the signal, the order analysis method and the artificial neural network for diagnosis, is suitable for the rotating speed fluctuation working condition without tachometer installation, can improve the time-frequency ridge line extraction accuracy, can diagnose the faults of rotor unbalance, rotor misalignment, rotor collision and abrasion, rotor crack and the like, increases the accuracy and reliability of the transmission shaft fault diagnosis result, and solves the problems that the diagnosis result is difficult to be clear in general diagnosis and the like.
Description
Technical Field
The invention belongs to the field of vibration signal analysis processing and fault diagnosis, and particularly relates to a transmission shaft fault diagnosis method and system under a rotating speed fluctuation working condition.
Background
The rotating speed of mechanical equipment during working changes at any time along with working environment and working requirements, and the condition is called variable rotating speed working condition, also called rotating speed fluctuation working condition. Under the working condition of rotating speed fluctuation, the transmission shaft vibration signal acquired by signal sampling no longer has a periodic characteristic, so that the vibration analysis cannot be carried out by adopting the traditional vibration signal analysis method, and the fault signal cannot be accurately and efficiently diagnosed if the vibration analysis cannot be carried out, thereby greatly influencing the working stability of the transmission shaft and the overall safety of mechanical equipment. Therefore, the method has very important significance in the research of the transmission shaft fault diagnosis method under the working condition of speed fluctuation.
The main research technical route of the method for processing the signals with large fluctuation of the rotating speed and diagnosing the faults is mainly order analysis and a derivation method thereof. The order analysis method is provided by professor Randall of university of new south wales of australia and university of lyon of france, Antoni, and the order analysis substantially converts non-stationary time domain signals into stationary order domain signals which are used as judgment bases for fault diagnosis of variable-speed mechanical equipment.
The research on order analysis in China is gradually increased, for example, the planetary gearbox is analyzed by using an order analysis technology, and different order characteristics of local faults of the planetary gearbox are deeply analyzed; and if Hilbert envelope demodulation is used for demodulating the low-frequency fault signal from the high-frequency carrier signal, effectively extracting the fault characteristic frequency of the non-stationary vibration signal under the time-varying working condition by combining order tracking and judging the fault type. However, the order analysis method has a very obvious disadvantage that the dependence on sampling system hardware is extremely high. When the existing mechanical equipment is increasingly integrated, certain important parts of the mechanical equipment are not suitable for installing a tachometer, and under the condition of lacking vibration signals and rotating speed signal synchronous sampling equipment, order analysis and transmission shaft fault diagnosis under the working condition of rotating speed fluctuation are difficult to realize.
Therefore, a new order analysis fault diagnosis method is urgently needed to be searched, so that the existing problems are solved, and the fault analysis and diagnosis can be better carried out on the transmission shaft signal under the working condition of rotating speed fluctuation.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to provide a transmission shaft fault diagnosis method and system under the working condition of rotating speed fluctuation, which can improve the accuracy and reliability of a transmission shaft fault diagnosis result.
The technical scheme is as follows: the invention relates to a transmission shaft fault diagnosis method under a rotating speed fluctuation working condition, which specifically comprises the following steps:
(1) acquiring a transmission shaft vibration signal under a rotating speed fluctuation working condition;
(2) carrying out time-frequency conversion, time-frequency ridge extraction, signal noise reduction, angle domain conversion and order domain conversion on a transmission shaft vibration signal under the working condition of rotating speed fluctuation, and extracting two-dimensional time-frequency ridges of the vibration signal and characteristic parameters of the signal in an order domain;
(3) and (3) taking the characteristic parameters extracted in the step (2) as input characteristics, and carrying out classification diagnosis on the characteristics of different vibration signals by using a fault diagnosis model trained by an artificial neural network to realize transmission shaft fault diagnosis under the working condition of rotating speed fluctuation.
Further, the time-frequency conversion in the step (2) is realized by short-time fourier transform in the formula (1):
wherein STFT (tau, omega) is the result of short-time Fourier transform analysis, f (t) is the signal to be analyzed, and g (t) is the STFT window function.
Further, the time-frequency ridge line extraction in the step (2) is realized by the following steps:
traversing a time axis in the time-frequency domain image, extracting the central main frequency of the signal from the highest point of the time-frequency energy, and obtaining a time-frequency ridge line; when a fault occurs, the local part of the ridge line generates mutation, and according to the ridge line generating the mutation, a time point at a ridge line mutation node is selected as a segmentation boundary, and the time-frequency domain signal is segmented along a time domain; dividing the extraction region according to time according to the signal division result, and respectively setting a target frequency f for each region, wherein the target frequency range is (f-delta f, f + delta f), and the delta f is set according to the signal frequency fluctuation range in the region; extracting curves in a target frequency range according to the highest energy point to obtain an optimal ridge line of each region; and (3) taking the ridge line coordinate at the moment when t is 0 as the Kalman filtering initial state, and fitting the optimal ridge line of each region into a ridge line by using a Kalman filter, wherein the ridge line is the optimal ridge line of the signal.
Further, the signal noise reduction implementation process in step (2) is as follows:
X(k|k-1)＝A*X(k-1|k-1)+B*U(k)+W(k) (2)
X(k|k)＝X(k|k-1)+Kg(k)*[Z(k)-H*X(k|k-1)](3)
wherein X (k-1) is the result of prediction using the previous state; x (k-1 | k-1) is the most optimal result for the previous state; u (k) is a control quantity of the current state; w (k) represents the noise of the process, with covariance Q; a and B are system parameters, Z (k) is the measured value at time k; h is a parameter of the measurement system; kg is the Kalman gain.
Further, the transmission shaft faults in the step (3) mainly comprise rotor unbalance, rotor misalignment, rotor collision and abrasion and rotor crack faults.
The invention also provides a transmission shaft fault diagnosis system under the working condition of rotating speed fluctuation, which comprises a sensor, a data acquisition module, a fault characteristic extraction module and a characteristic identification module; the sensor is used for collecting a transmission shaft vibration signal under the working condition of rotating speed fluctuation and converting the vibration signal into an analog electric signal; the data acquisition module converts the analog signals transmitted by the sensor into digital signals; the fault feature extraction module is used for extracting the features of the transmission shaft vibration signal sent by the data acquisition module under the working condition of rotating speed fluctuation, and extracting a two-dimensional time-frequency ridge line of the vibration signal and the feature parameters of the signal in an order domain; the characteristic identification module takes the characteristic parameters of the vibration signals in the order domain extracted by the fault characteristic extraction module as input characteristics, and classifies special diagnosis of different vibration signals by using a fault diagnosis model trained by an artificial neural network, so that the purpose of fault diagnosis of the transmission shaft under the working condition of rotating speed fluctuation is achieved.
Furthermore, the system also comprises a display module for realizing signal loading, artificial neural network model loading, signal time domain image display, signal order domain image display and signal fault diagnosis result display.
Has the advantages that: compared with the prior art, the invention has the beneficial effects that: the method and the system can be suitable for the rotating speed fluctuation working condition without installing a tachometer, can improve the two-dimensional time-frequency ridge line extraction accuracy of the variable-rotating-speed rotating mechanical vibration signal under noise interference, are simple to operate and easy to realize, can diagnose the faults of rotor unbalance, rotor misalignment, rotor collision and abrasion, rotor cracks and the like, increase the accuracy and reliability of the fault diagnosis result of the transmission shaft under the rotating speed fluctuation working condition, and solve the problem that the diagnosis result is difficult to determine in general diagnosis.
Drawings
FIG. 1 is a general flowchart of a transmission shaft fault diagnosis method under a condition of rotating speed fluctuation;
FIG. 2 is a block diagram of a transmission shaft fault diagnosis system under a condition of rotating speed fluctuation;
FIG. 3 is a diagram of a transmission shaft fault diagnosis system software interface under a condition of rotating speed fluctuation;
FIG. 4 is a graph of 20 diagnostic accuracy results for a normal condition transmission shaft according to the method of the present invention;
FIG. 5 is a graph of 20 diagnostic accuracy results for an unbalanced failed drive shaft according to the present invention;
FIG. 6 is a graph of 20 diagnosis accuracy results of the method of the present invention for a misaligned faulty transmission shaft.
Detailed Description
The present invention is described in further detail below with reference to the attached drawing figures.
As shown in FIG. 1, the invention provides a transmission shaft fault diagnosis method under a rotating speed fluctuation working condition, which specifically comprises the following steps:
step 1: and acquiring a transmission shaft vibration signal under the working condition of rotating speed fluctuation.
The sensor is used for collecting a transmission shaft vibration signal under the working condition of rotating speed fluctuation, the vibration signal is converted into an analog electric signal, and then the analog signal is converted into a digital signal.
Step 2: and carrying out time-frequency conversion, time-frequency ridge extraction, signal noise reduction, angle domain conversion and order domain conversion on the transmission shaft vibration signal under the working condition of rotating speed fluctuation, and extracting the two-dimensional time-frequency ridge of the vibration signal and the characteristic parameters of the signal in the order domain.
Time-frequency conversion: short-time Fourier transform (STFT) of formula (1) is utilized to map the time domain signal to a time-frequency domain signal, which is convenient for subsequent ridge extraction:
where STFT (τ, ω) is the short-time Fourier transform analysis result, f (t) is the signal to be analyzed, and g (t) is the STFT window function.
And (3) time-frequency ridge line extraction:
after the signal is subjected to STFT, curves related to the dynamic characteristics of the mechanical system parts appear clearly or invisibly, and the distribution form of the curves in a three-dimensional space is similar to a ridge, namely a ridge line mark or a line extending along the ridge top. Therefore, in the time-frequency diagram, the line extending along the highest power point in the three-dimensional space is called a time-frequency ridge line, which is represented on a time-frequency surface, is a line with different brightness degrees and trends, and can represent various modes of signal frequency change. The energy of the signal in the time and frequency domains can be expressed as:
wherein | x (t) & ltnon | & gt2、|X(v)|2The energy density of the signal in the time domain and the frequency domain, respectively. Similarly, the energy of the signal in the time-frequency domain is:
in the formula (I), the compound is shown in the specification,
which is the joint time-frequency density of a signal, is a quadratic function of the signal, and the time-frequency energy usually has the form of a quadratic form. The energy distribution also satisfies the marginal properties:
in the absence of a synchronous sampling device for the vibration signal and the rotation speed signal, order analysis is difficult to realize. The time-frequency ridge line represents various modes of signal frequency change, the frequency change is rotation speed change, and in the mapping process and the ridge line extraction process, the time relation of the signals is synchronous, so the time-frequency ridge line can be used as synchronous rotation speed information of the vibration signals. And under the condition that only the vibration signal is acquired, carrying out ridge line extraction on the vibration signal, and taking the time-frequency ridge line as a synchronous rotating speed signal required by the order analysis method, thereby realizing the order analysis method without installing a tachometer.
Firstly, ridge line initial extraction: and traversing a time axis in the time-frequency domain image, and extracting the central main frequency of the signal from the highest point of the time-frequency energy to obtain a time-frequency ridge line. When a fault occurs, the ridge line can generate a local sudden change, so that the ridge line cannot be used as the rotating speed information, but the ridge line shows the energy change of the rotating speed fluctuation signal, and provides a basis for dividing the signal along the time domain at the later time.
Then, signal division is carried out: and according to the ridge line generating the mutation, selecting the time point at the mutation node of the ridge line as a segmentation boundary, and segmenting the time-frequency domain signal along the time domain.
And finally, realizing the optimal ridge line extraction: and dividing the extraction region according to time according to the signal division result, and respectively setting a target frequency f for each region, wherein the target frequency range is (f-delta f, f + delta f), and the delta f is set according to the signal frequency fluctuation range in the region. And extracting curves in the target frequency range according to the highest energy point to obtain the optimal ridge line of each region. And (3) taking the ridge line coordinate at the moment when t is 0 as the Kalman filtering initial state, and fitting the optimal ridge line of each region into a ridge line by using a Kalman filter, wherein the ridge line is the optimal ridge line of the signal.
Signal noise reduction: carrying out noise reduction pretreatment on the signals by using Kalman filtering in formulas (6) and (7);
X(k|k-1)＝A*X(k-1|k-1)+B*U(k)+W(k) (6)
X(k|k)＝X(k|k-1)+Kg(k)*[Z(k)-H*X(k|k-1)](7)
wherein X (k-1) is the result of prediction using the previous state; x (k-1 | k-1) is the most optimal result for the previous state; u (k) is a control quantity of the current state; w (k) represents the noise of the process, with covariance Q; a and B are system parameters, Z (k) is the measured value at time k; h is a parameter of the measurement system; kg is the Kalman gain
And (3) angle domain conversion: converting the time domain signal subjected to noise reduction into an angle domain signal by using equal-angle resampling in combination with the rotating speed signal of the signal;
order domain conversion: and mapping the angle domain signal to an order domain to obtain an order domain signal, and taking the order domain signal as a signal characteristic.
And step 3: and (3) taking the characteristic parameters extracted in the step (2) as input characteristics, and carrying out classification diagnosis on the characteristics of different vibration signals by using a fault diagnosis model trained by an artificial neural network to realize the fault diagnosis of the transmission shaft under the working condition of rotating speed fluctuation.
And (3) carrying out feature extraction on normal and fault transmission shaft rotation speed fluctuation signals under a large number of rotation speed fluctuation working conditions, and sending the feature parameters into an artificial neural network with well-set parameters such as learning rate, iteration times, training target errors and the like for training, thereby obtaining an artificial neural network fault diagnosis model.
The invention also provides a transmission shaft fault diagnosis system under the working condition of rotating speed fluctuation, as shown in fig. 2, comprising: the sensor is used for collecting a transmission shaft vibration signal under the working condition of rotating speed fluctuation and converting the vibration signal into an analog electric signal; the data acquisition module is used for converting the analog signals transmitted by the sensor into digital signals; the fault feature extraction module is used for extracting the features of the transmission shaft vibration signal under the working condition of rotating speed fluctuation sent by the data acquisition module and extracting a two-dimensional time-frequency ridge line of the vibration signal and the feature parameters of the signal in an order domain; and the characteristic identification module is used for taking the characteristic parameters of the vibration signals in the order domain extracted by the fault characteristic extraction module as input characteristics and classifying special diagnoses of different vibration signals by utilizing an artificial neural network so as to achieve the purpose of diagnosing the faults of the transmission shaft under the working condition of rotating speed fluctuation.
Wherein the feature extraction module includes: the time-frequency conversion module is used for receiving the digital signals of the data acquisition module and mapping the time-domain signals into time-frequency domain signals by using short-time Fourier transform; the time-frequency ridge line extraction module is used for receiving the time-frequency domain signal of the time-frequency conversion module, obtaining a time-frequency ridge line by using a peak ridge line extraction method, and taking the time-frequency ridge line as a rotating speed signal of the transmission shaft vibration signal under the working condition of rotating speed fluctuation; the signal noise reduction module is used for receiving the digital signal of the data acquisition module and performing noise reduction pretreatment on the signal by using Kalman filtering; the angle domain conversion module is used for receiving the rotating speed signal of the time-frequency ridge line extraction module and the noise reduction signal of the signal noise reduction module and converting the time domain signal subjected to noise reduction into an angle domain signal by utilizing equal-angle resampling; and the order domain conversion module is used for receiving the angle domain signal of the angle domain conversion module, mapping the angle domain signal to an order domain, and obtaining the order domain signal which is used as the signal characteristic.
And the characteristic identification module receives the signal characteristics of the order domain conversion module, sends the signal characteristics to the artificial neural network for training, and obtains a fault diagnosis model, so that multi-class diagnosis of the transmission shaft faults is realized.
The transmission shaft fault diagnosis system under the working condition of rotating speed fluctuation further comprises a display module, as shown in fig. 3, which is a software interface diagram of the transmission shaft fault diagnosis system under the working condition of rotating speed fluctuation, and the realizable functions of the transmission shaft fault diagnosis system comprise: signal loading, artificial neural network model loading, signal time domain image display, signal order domain image display, signal fault diagnosis and the like. The software completes interface design through the GUI function of MATLAB software, embeds a transmission shaft fault diagnosis system algorithm program under the condition of rotating speed fluctuation in an interface function button, and finally uses the Compiler function to package and integrate into independent software. The software is an interface for displaying the diagnosis result and facilitating human-computer interaction.
The transmission shaft fault diagnosis method under the working condition of rotating speed fluctuation provided by the invention is used for experimental verification. Vibration signals of the transmission shaft in the speed increasing and reducing processes are collected to serve as experimental data, the experimental data comprise three signals of normal transmission shaft fault, unbalanced transmission shaft fault and misalignment fault, and a data set is shown in table 1. The sampling point number of each sample is 4096, the data set contains 1200 samples in total, 600 samples are randomly selected as a training sample set, the rest 600 samples are selected as a testing sample set, and the condition class labels are set to be 1, 2 and 3 for convenience of representation.
Table 1 data set description
Setting parameters of an artificial neural network, a middle result period of 50, a maximum iteration number of 500, a training target error of 0.001 and a learning rate of 0.001. To eliminate the effect of randomness, each set of experiments was performed 20 times.
The 20-time diagnosis accuracy results of the order analysis method are shown in fig. 4 to 6, and it can be seen that the training accuracy of the data set is 100%, the test accuracy exceeds 99%, which indicates that the order analysis method can accurately diagnose the health state of the rotating shaft in the speed increasing and decreasing process.
In order to illustrate the effectiveness of the order analysis method, the conventional method is verified as a comparison method, the method also uses the data set shown in table 1, and the feature extraction method extracts a frequency spectrum for kalman filtering denoising and short-time fourier transform. The average training accuracy and the average test accuracy of the two methods were calculated as shown in table 2. It can be seen that the test accuracy of the order analysis method is stabilized between 99.62% -100%, and the standard deviation is less than 0.09%, both of which are superior to those of the comparison method. Therefore, the transmission shaft fault diagnosis method under the working condition of rotating speed fluctuation can obtain ideal application effect.
TABLE 2 comparison of the order of analysis with the conventional method
The invention combines the two-dimensional time-frequency ridge line with the order analysis method, utilizes the artificial neural network to carry out fault diagnosis, improves the accuracy and reliability of the fault diagnosis result of the vehicle transmission shaft under the working condition of rotating speed fluctuation, can diagnose the faults of rotor unbalance, rotor misalignment, rotor collision and abrasion, rotor crack and the like, and has very important significance.
It should be noted that, the steps in the method for diagnosing a failure of a transmission shaft under a condition of rotating speed fluctuation provided by the present invention may be implemented by using corresponding modules, devices, units, etc. in the system for diagnosing a failure of a transmission shaft under a condition of rotating speed fluctuation, and those skilled in the art may refer to the technical scheme of the system to implement the steps of the method, that is, the embodiments in the system may be understood as preferred examples for implementing the method, and will not be described herein again.
Those skilled in the art will appreciate that, in addition to implementing the system and its various devices provided by the present invention in purely computer readable program code means, the method steps can be fully programmed to implement the same functions by implementing the system and its various devices in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system and various devices thereof provided by the present invention can be regarded as a hardware component, and the devices included in the system and various devices thereof for realizing various functions can also be regarded as structures in the hardware component; means for performing the functions may also be regarded as structures within both software modules and hardware components for performing the methods.
It should be noted that the description of the present invention and the accompanying drawings illustrate preferred embodiments of the present invention, but the present invention may be embodied in many different forms and is not limited to the embodiments described in the present specification, which are provided as additional limitations to the present invention, and the present invention is provided for understanding the present disclosure more fully. Furthermore, the above-mentioned technical features are combined with each other to form various embodiments which are not listed above, and all of them are regarded as the scope of the present invention described in the specification; further, modifications and variations will occur to those skilled in the art in light of the foregoing description, and it is intended to cover all such modifications and variations as fall within the true spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. A transmission shaft fault diagnosis method under the working condition of rotating speed fluctuation is characterized by comprising the following steps:
(1) acquiring a transmission shaft vibration signal under a rotating speed fluctuation working condition;
(2) carrying out time-frequency conversion, time-frequency ridge extraction, signal noise reduction, angle domain conversion and order domain conversion on a transmission shaft vibration signal under the working condition of rotating speed fluctuation, and extracting two-dimensional time-frequency ridges of the vibration signal and characteristic parameters of the signal in an order domain;
(3) and (3) taking the characteristic parameters extracted in the step (2) as input characteristics, and carrying out classification diagnosis on the characteristics of different vibration signals by using a fault diagnosis model trained by an artificial neural network to realize transmission shaft fault diagnosis under the working condition of rotating speed fluctuation.
2. The method for diagnosing the fault of the transmission shaft under the working condition of the fluctuation of the rotating speed according to claim 1, wherein the time-frequency conversion in the step (2) is realized by short-time Fourier transform in an expression (1):
wherein STFT (tau, omega) is the result of short-time Fourier transform analysis, f (t) is the signal to be analyzed, and g (t) is the STFT window function.
3. The method for diagnosing the fault of the transmission shaft under the working condition of the fluctuation of the rotating speed according to claim 1, wherein the time-frequency ridge line extraction in the step (2) is realized by the following steps:
traversing a time axis in the time-frequency domain image, extracting the central main frequency of the signal from the highest point of the time-frequency energy, and obtaining a time-frequency ridge line; when a fault occurs, the local part of the ridge line generates mutation, and according to the ridge line generating the mutation, a time point at a ridge line mutation node is selected as a segmentation boundary, and the time-frequency domain signal is segmented along a time domain; dividing the extraction region according to time according to the signal division result, and respectively setting a target frequency f for each region, wherein the target frequency range is (f-delta f, f + delta f), and the delta f is set according to the signal frequency fluctuation range in the region; extracting curves in a target frequency range according to the highest energy point to obtain an optimal ridge line of each region; and (3) taking the ridge line coordinate at the moment when t is 0 as the Kalman filtering initial state, and fitting the optimal ridge line of each region into a ridge line by using a Kalman filter, wherein the ridge line is the optimal ridge line of the signal.
4. The method for diagnosing the fault of the transmission shaft under the working condition of rotating speed fluctuation according to claim 1, wherein the signal noise reduction implementation process in the step (2) is as follows:
X(k|k-1)＝A*X(k-1|k-1)+B*U(k)+W(k) (6)
X(k|k)＝X(k|k-1)+Kg(k)*[Z(k)-H*X(k|k-1)](7)
wherein X (k-1) is the result of prediction using the previous state; x (k-1 | k-1) is the most optimal result for the previous state; u (k) is a control quantity of the current state; w (k) represents the noise of the process, with covariance Q; a and B are system parameters, Z (k) is the measured value at time k; h is a parameter of the measurement system; kg is the Kalman gain.
5. The method for diagnosing the faults of the transmission shaft under the working condition of rotating speed fluctuation according to claim 1, wherein the faults of the transmission shaft in the step (3) mainly comprise rotor unbalance, rotor misalignment, rotor rubbing and rotor crack faults.
6. A transmission shaft fault diagnosis system under the working condition of rotating speed fluctuation by adopting the method of claim 1 is characterized by comprising a sensor, a data acquisition module, a fault characteristic extraction module and a characteristic identification module; the sensor is used for collecting a transmission shaft vibration signal under the working condition of rotating speed fluctuation and converting the vibration signal into an analog electric signal; the data acquisition module converts the analog signals transmitted by the sensor into digital signals; the fault feature extraction module is used for extracting the features of the transmission shaft vibration signal sent by the data acquisition module under the working condition of rotating speed fluctuation, and extracting a two-dimensional time-frequency ridge line of the vibration signal and the feature parameters of the signal in an order domain; the characteristic identification module takes the characteristic parameters of the vibration signals in the order domain extracted by the fault characteristic extraction module as input characteristics, and classifies special diagnosis of different vibration signals by using a fault diagnosis model trained by an artificial neural network, so that the purpose of fault diagnosis of the transmission shaft under the working condition of rotating speed fluctuation is achieved.
7. The transmission shaft fault diagnosis system under the working condition of rotation speed fluctuation according to claim 6, wherein the system further comprises a display module for realizing signal loading, artificial neural network model loading, signal time domain image display, signal order domain image display and signal fault diagnosis result display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010401814.1A CN111738068B (en) | 2020-05-13 | 2020-05-13 | Transmission shaft fault diagnosis method and system under rotating speed fluctuation working condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010401814.1A CN111738068B (en) | 2020-05-13 | 2020-05-13 | Transmission shaft fault diagnosis method and system under rotating speed fluctuation working condition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111738068A true CN111738068A (en) | 2020-10-02 |
| CN111738068B CN111738068B (en) | 2024-04-02 |
Family
ID=72647147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010401814.1A Active CN111738068B (en) | 2020-05-13 | 2020-05-13 | Transmission shaft fault diagnosis method and system under rotating speed fluctuation working condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738068B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112665851A (en) * | 2020-10-28 | 2021-04-16 | 西安交通大学 | Key-free phase change rotating speed gearbox fault diagnosis method |
| CN112668417A (en) * | 2020-12-17 | 2021-04-16 | 武汉理工大学 | Rolling bearing intelligent fault diagnosis method based on vibration signals |
| CN113093709A (en) * | 2021-04-08 | 2021-07-09 | 重庆理工大学 | Active vehicle-mounted running state monitoring and fault forecasting method |
| CN114235137A (en) * | 2021-11-30 | 2022-03-25 | 江铃汽车股份有限公司 | Abnormal sound diagnosis method based on time-frequency analysis of vibration signals inside engine cylinder |
| CN118167570A (en) * | 2024-05-11 | 2024-06-11 | 国电联合动力技术有限公司 | Wind turbine shafting centering detection method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105547698A (en) * | 2015-12-31 | 2016-05-04 | 新疆金风科技股份有限公司 | Fault diagnosis method and apparatus for rolling bearing |
| CN109668733A (en) * | 2018-12-21 | 2019-04-23 | 苏州大学 | Variation nonlinear model decomposes variable speed Method for Bearing Fault Diagnosis |
| CN110487547A (en) * | 2019-07-31 | 2019-11-22 | 中国特种设备检测研究院 | Fault Diagnosis of Roller Bearings under variable working condition based on vibrorecord and transfer learning |
| CN110702411A (en) * | 2019-09-23 | 2020-01-17 | 武汉理工大学 | Residual error network rolling bearing fault diagnosis method based on time-frequency analysis |
-
2020
- 2020-05-13 CN CN202010401814.1A patent/CN111738068B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105547698A (en) * | 2015-12-31 | 2016-05-04 | 新疆金风科技股份有限公司 | Fault diagnosis method and apparatus for rolling bearing |
| CN109668733A (en) * | 2018-12-21 | 2019-04-23 | 苏州大学 | Variation nonlinear model decomposes variable speed Method for Bearing Fault Diagnosis |
| CN110487547A (en) * | 2019-07-31 | 2019-11-22 | 中国特种设备检测研究院 | Fault Diagnosis of Roller Bearings under variable working condition based on vibrorecord and transfer learning |
| CN110702411A (en) * | 2019-09-23 | 2020-01-17 | 武汉理工大学 | Residual error network rolling bearing fault diagnosis method based on time-frequency analysis |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112665851A (en) * | 2020-10-28 | 2021-04-16 | 西安交通大学 | Key-free phase change rotating speed gearbox fault diagnosis method |
| CN112668417A (en) * | 2020-12-17 | 2021-04-16 | 武汉理工大学 | Rolling bearing intelligent fault diagnosis method based on vibration signals |
| CN112668417B (en) * | 2020-12-17 | 2023-02-03 | 武汉理工大学 | Rolling bearing intelligent fault diagnosis method based on vibration signals |
| CN113093709A (en) * | 2021-04-08 | 2021-07-09 | 重庆理工大学 | Active vehicle-mounted running state monitoring and fault forecasting method |
| CN114235137A (en) * | 2021-11-30 | 2022-03-25 | 江铃汽车股份有限公司 | Abnormal sound diagnosis method based on time-frequency analysis of vibration signals inside engine cylinder |
| CN118167570A (en) * | 2024-05-11 | 2024-06-11 | 国电联合动力技术有限公司 | Wind turbine shafting centering detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111738068B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111738068A (en) | Transmission shaft fault diagnosis method and system under working condition of rotating speed fluctuation | |
| Zhao et al. | Fault diagnosis of wind turbine bearing based on variational mode decomposition and Teager energy operator | |
| CN108106830B (en) | A kind of Variable Speed Rotating Machinery method for diagnosing faults based on time-frequency spectrum segmentation | |
| CN113125179B (en) | Keyless phase order tracking method for rotating speed fluctuation of rotary machine | |
| Lei et al. | EEMD method and WNN for fault diagnosis of locomotive roller bearings | |
| Tang et al. | IoT-based signal enhancement and compression method for efficient motor bearing fault diagnosis | |
| CN110617964A (en) | Synchronous compression transformation order ratio analysis method for fault diagnosis of rolling bearing | |
| CN111665051A (en) | Bearing fault diagnosis method under strong noise variable-speed condition based on energy weight method | |
| CN103308152B (en) | Based on the characteristic of rotating machines vibration signal angular domain method for resampling of instantaneous Frequency Estimation | |
| CN105784366A (en) | Wind turbine generator bearing fault diagnosis method under variable speed | |
| CN103884502A (en) | Method for diagnosing faults of planetary gear system of wind driven generator under variable rotating speed | |
| CN105929331A (en) | Double-fed aerogenerator stator/rotor fault analysis diagnosis apparatus and method | |
| CN109883706A (en) | A kind of rolling bearing local damage Weak fault feature extracting method | |
| CN103900815A (en) | Rolling bearing fault diagnosis method based on EEMD and distribution fitting testing | |
| CN111879508B (en) | Method and device for estimating instantaneous rotating speed of rotating machine based on time-frequency transformation and storage medium | |
| Lin et al. | A review and strategy for the diagnosis of speed-varying machinery | |
| CN108278184B (en) | Wind turbine generator impeller imbalance monitoring method based on empirical mode decomposition | |
| CN103267652B (en) | Intelligent online diagnosis method for early failures of equipment | |
| Sun et al. | A novel rolling bearing vibration impulsive signals detection approach based on dictionary learning | |
| CN114742111B (en) | Fault diagnosis method and system based on parameter adaptive characteristic modal decomposition | |
| CN112733612A (en) | Cross-domain rotating machinery fault diagnosis model establishing method and application thereof | |
| CN114486263B (en) | Noise reduction demodulation method for vibration signal of rolling bearing of rotary machine | |
| CN111855208A (en) | Rotary machine weak fault signal extraction method based on order analysis and sparse coding | |
| Liu et al. | Two-step adaptive chirp mode decomposition for time-varying bearing fault diagnosis | |
| CN102778354A (en) | Method for diagnosing failure of wind-powered rotary support based on wavelet analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |