CN117235643A - Early weak fault diagnosis method for rolling bearing - Google Patents
Early weak fault diagnosis method for rolling bearing Download PDFInfo
- Publication number
- CN117235643A CN117235643A CN202311147203.9A CN202311147203A CN117235643A CN 117235643 A CN117235643 A CN 117235643A CN 202311147203 A CN202311147203 A CN 202311147203A CN 117235643 A CN117235643 A CN 117235643A
- Authority
- CN
- China
- Prior art keywords
- dung
- fault
- modal
- follows
- optimal
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000005096 rolling process Methods 0.000 title claims abstract description 48
- 238000003745 diagnosis Methods 0.000 title claims abstract description 22
- 241000254173 Coleoptera Species 0.000 claims abstract description 94
- 210000003608 fece Anatomy 0.000 claims abstract description 94
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 63
- 238000001228 spectrum Methods 0.000 claims abstract description 21
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 70
- 239000013598 vector Substances 0.000 claims description 21
- 238000009395 breeding Methods 0.000 claims description 13
- 230000001488 breeding effect Effects 0.000 claims description 13
- 230000002431 foraging effect Effects 0.000 claims description 13
- 241001229848 Aphodius granarius Species 0.000 claims description 12
- 230000003044 adaptive effect Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 11
- 230000002441 reversible effect Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 7
- 230000000739 chaotic effect Effects 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 abstract description 2
- 238000012360 testing method Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 238000010183 spectrum analysis Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 241000218652 Larix Species 0.000 description 1
- 235000005590 Larix decidua Nutrition 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application discloses a method for diagnosing early weak faults of a rolling bearing, which comprises the following steps: collecting a fault bearing vibration signal; the method comprises the steps of guiding an improved dung beetle optimization algorithm based on a comprehensive fitness function integrating multiple domain indexes to adaptively determine the optimal decomposition layer number and penalty factor of a variational modal decomposition algorithm, and dividing an acquired fault bearing vibration signal into a series of modal components by utilizing the variational modal decomposition algorithm with optimized parameters; calculating the comprehensive fitness function value of each modal component, and selecting the modal component with the smallest comprehensive fitness function value as a main fault characteristic modal component; the early weak fault diagnosis of the rolling bearing is realized by extracting the fault characteristic frequency from the enhanced envelope spectrum of the main fault characteristic modal component. The application solves the problem that parameters are difficult to select in the existing variational modal decomposition, can extract useful periodic fault pulse information from a strong noise working environment, and realizes the accurate diagnosis of early weak faults of the rolling bearing.
Description
Technical Field
The application relates to the technical field of vibration signal processing and rotating machinery fault diagnosis, in particular to a method for diagnosing early weak faults of a rolling bearing.
Background
The rolling bearing has become one of the most important parts in the current rotary machinery due to the advantages of low friction moment, low power consumption and the like, is widely applied to the mechanical fields of energy power, aerospace, transportation and the like, and is a part with higher failure rate, and nearly 30% of mechanical failures are closely related to the rolling bearing. The method has important significance for early fault diagnosis of mechanical equipment in order to ensure normal operation and personal safety of the mechanical equipment. In practical engineering application, because of complex large-scale mechanical structure and severe working environment of the rolling bearing, the measured vibration signal has the characteristics of non-stability and non-linearity, and the impact component in the early failure bearing signal is weak and is easily covered by noise interference component, so how to accurately extract the early weak failure characteristic of the bearing is always a research difficulty and a hot spot in the field of mechanical failure diagnosis.
In recent years, the vibration signal analysis technology is widely applied to bearing fault diagnosis due to the advantages of convenience in data acquisition, intuitionistic and reliable samples, high measurement precision and the like. The methods can adaptively decompose the signal into a group of almost orthogonal modal components according to the inherent characteristics of the signal, but the methods lack strict mathematical basis, and have inherent defects such as end-point effect, modal aliasing and the like in the decomposition process, and still need to be further optimized and perfected. Compared with the algorithm, the variational modal decomposition algorithm is a brand-new vibration signal processing method, has stronger robustness, higher decomposition precision and better sparsity, can effectively avoid the occurrence of end-point effect and modal aliasing, has strong analysis processing capacity on complex nonlinear non-stationary signals, and can successfully solve the problem that early weak fault signals are difficult to find and diagnose. However, in the practical application process, the decomposition effect of the VMD is easily affected by two important parameters (namely, the decomposition layer number K and the penalty factor α). Therefore, the adaptive determination of the optimal parameter combination is important for the signal decomposition effect and the effective extraction of the early fault characteristic information of the bearing.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
Therefore, the application aims to provide a method for diagnosing early weak faults of a rolling bearing, which avoids the influence of parameters selected by experience or priori criteria required by the traditional variational modal decomposition algorithm and realizes accurate diagnosis of the early weak faults of the bearing.
In order to solve the technical problems, according to one aspect of the present application, the following technical solutions are provided:
a method for diagnosing early weak faults of a rolling bearing, comprising:
s10: collecting a fault bearing vibration signal by using a sensor;
s20: the method comprises the steps of guiding an improved dung beetle optimization algorithm based on a comprehensive fitness function integrating multiple domain indexes, adaptively determining the optimal decomposition layer number and penalty factor of a variational modal decomposition algorithm, and dividing an acquired fault bearing vibration signal into a series of modal components by utilizing the variational modal decomposition algorithm with optimized parameters, wherein the variational modal decomposition expression is as follows:
u＝VMD(x,α,tau,K,DC,init,tol)
in the formula, x is an original signal to be decomposed, tau is a noise margin, DC is a direct current component, init is an initialization center frequency, tol is convergence accuracy, K and alpha respectively represent an optimal decomposition layer number and a penalty factor, and VMD (·) is a variation mode decomposition function in a MATLAB kit.
S30: calculating the comprehensive fitness function value of each modal component, and selecting the modal component with the smallest comprehensive fitness function value as a main fault characteristic modal component;
s40: the early weak fault diagnosis of the rolling bearing is realized by extracting the fault characteristic frequency from the enhanced envelope spectrum of the main fault characteristic modal component.
As a preferred scheme of the early weak fault diagnosis method for the rolling bearing, in the step S20, the improved dung beetle optimizing algorithm is guided based on a comprehensive fitness function fused with a multi-domain index, and the optimal decomposition layer number and penalty factor of the variation modal decomposition algorithm are determined in a self-adaptive manner, wherein the specific steps are as follows:
s201, initializing a group position vector of dung beetles by introducing a cubic chaotic map and a reverse learning strategy to form an evenly distributed initialized group, setting a group scale P, setting the number Pa of ball balls of the dung beetles, the breeding number Pr of the dung beetles, the foraging number Ps of the small dung beetles, the number Pt of the theft dung beetles and the maximum iteration number T max The upper and lower boundaries of the search are Ub and Lb respectively, and the dimension of the objective function is D;
s202, establishing a comprehensive fitness function with optimized parameters, wherein the expression is as follows:
wherein arg min {.cndot } represents a function for obtaining a minimum value, RIMI is a comprehensive fitness function value of a modal component, and K and alpha are a decomposition layer number and a penalty factor of variation modal decomposition respectively.
S203, processing the collected original vibration signals by using variational modal decomposition according to the position vector of each dung beetle, calculating the fitness function value corresponding to each dung beetle in the current population, and recording the current optimal fitness value and the corresponding position vector;
s204, updating individual positions of the dung beetles by utilizing four strategies of dung beetle rolling ball, dung beetle breeding, small dung beetle foraging and theft of the dung beetles, introducing a self-adaptive inertia weight strategy to improve a dung beetle rolling ball and theft dung beetle position updating rule, calculating and comparing global optimal values of individuals and groups, updating and storing global optimal individual positions of the dung beetles and optimal fitness function values;
s205, performing differential mutation operation on the globally optimal individuals and randomly selected individuals, calculating and comparing global optimal values of the individuals and the population, and updating and storing the globally optimal individual positions of the dung beetles and the optimal fitness function value;
s206, judging whether the maximum iteration times are reached. If so, the iteration is terminated, the optimal parameter combination [ K, alpha ] of the variation modal decomposition algorithm is obtained, otherwise, the step S204 is returned to for loop iteration until the maximum number of loops is met.
As a preferable mode of the early weak failure diagnosis method for a rolling bearing according to the present application, in step S202, the comprehensive fitness function is defined as:
where SEGI and IFCER are the square envelope base-Ni index of the signal and the improved fault signature energy ratio, respectively, and the calculation formulas are defined as follows:
wherein x is the original signal and x= (x) 1 ,x 2 ,…,x N ) N is the length of the signal, SE is the square envelope signal of the original signal x and se= [ SE ] (1) ,SE (2) ,…,SE (N) ]All elements being arranged in order from small to large, SE (1) ≤SE (2) ,…,≤SE (N) (1), (2), …, (N) is a new index of the index, SE 1 Is the L1 norm of the signal SE;
wherein FFT (·) is the Fourier transform function in MATLAB kit, M is the envelope spectrum of the signal x, f w For the fault characteristic frequency, q is the harmonic quantity, deltaf is the fault frequency deviation, g is the gravitational acceleration, E is the energy of fault related characteristic information, E * Is the total energy.
As a preferred scheme of the early weak fault diagnosis method for the rolling bearing, in the step S201, the specific steps of introducing the cubic chaotic map and the reverse learning strategy to initialize the group position vector of the dung beetle are as follows:
s201-1: mapping the cubic chaos sequence onto a dung beetle population, wherein the specific formula is as follows:
wherein y is i For the cubic sequence, ub and Lb are the upper and lower bounds of the search, X, respectively i Is the actual individual position of the dung beetles.
S201-2: generating a reverse solution population, wherein the specific formula is as follows: OS (operating System) i ＝k×(Lb+Ub)-X i Where k is a random number belonging to (0, 1).
S201-3: and combining and sequencing the cube mapping population and the reverse solution population, calculating the fitness function value of each individual, and selecting the top P dung beetles with better fitness function value as the initial population.
As a preferred scheme of the method for diagnosing early weak faults of rolling bearings, in step S204, the algorithm of updating the position of the ball of the dung beetle based on the adaptive inertia weight strategy is defined as follows:
where δ=rand (1), ST e (0.5, 1)]When delta is less than ST, the dung beetles roll in a targeted manner in a normal global exploration stage in a barrier-free mode, and when delta is more than or equal to ST, the dung beetles represent a barrier-free mode, no specific rolling target exists in the dung beetles, t is the current iteration times, and x i (t) represents position information of ith dung beetle in the t-th iteration, alpha is a natural coefficient with value of-1 or 1, 1 represents no deviation, -1 represents original direction deviation, X w Represents the global worst position, w t 、c t And r t Are all inertia weight coefficients, t is the current iteration number, wherein w is t And c t Non-linear decreasing function, r t A nonlinear increasing function, the formulas of which are respectively as follows:
wherein T is the current iteration number, T max Is the maximum number of iterations.
As a preferable scheme of the early weak fault diagnosis method for the rolling bearing, in the step S204, a position update formula for breeding the dung beetles is defined as follows:
wherein X is * Representing the current local best position, ub and Lb represent the upper and lower bounds of the search, respectively, where r=1-T/T max ，T max For maximum iteration number Ub * And Lb * Respectively represent the upper and lower bounds of spawning area, B i (t) is the position information of the ith breeding ball at the t-th iteration, b 1 And b 2 Representing two independent random vectors of size 1 x D, D representing the dimension of the optimization problem.
As a preferable scheme of the method for diagnosing early weak faults of rolling bearings, in step S204, the location update formula of foraging of the small dung beetles is defined as follows:
wherein X is b Indicating the global optimum position, ub and Lb respectively represent the upper and lower bounds of the search, where r=1-T/T max ，T max For maximum iteration number Ub b And Lb b Respectively representing the upper and lower bounds, x of the best foraging area i (t) represents the position information of the ith small dung beetle in the t-th iteration, C 1 Representing random numbers subject to normal distribution, C 2 Representing the random vector belonging to (0, 1).
As a preferred scheme of the method for diagnosing early weak faults of rolling bearings according to the present application, in step S204, the method for updating the position of the theft dung beetle based on the adaptive inertia weight strategy is defined as follows:
wherein S is max And S is min Represent S t Maximum and minimum of S max Taking 1, S min Taking 0, T to represent the current iteration number, T max Represents the maximum iteration number S t The linear decaying inertia weight coefficient, ζ, is a random vector of 1×d that satisfies a normal distribution with a mean value of 0 and a variance of 1.
As a preferable embodiment of the method for diagnosing early weak failure of a rolling bearing according to the present application, in step S205, the formula of the differential mutation operation is defined as follows:
wherein X is b (t) is the optimal position, X, in the t-th iteration population r1 (t) and X r2 (t) is the individual position of the dung beetle selected randomly in the t-th iteration, lambda is the scaling factor,is the new individual position generated in the t-th iteration.
As a preferable scheme of the method for diagnosing early weak faults of the rolling bearing, the calculation formula of the enhanced envelope spectrum is defined as follows:
wherein u is a main fault characteristic modal component of the original vibration signal x after VMD decomposition, xcorr (·) is an autocorrelation transformation function in MATLAB kit, R xx For the autocorrelation noise reduction signal of signal u, FFT (·) is the Fourier transform function in MATLAB kit, PF is signal R xx Std (·) is the standard deviation calculation function in MATLAB kit and v is the standard deviation of the square envelope spectrum amplitude PF.
Compared with the prior art, the application has the following beneficial effects:
1. the Improved Fault Characteristic Energy Ratio (IFCER) and the average Fang Baolao base Ni index (SEGI) are used for jointly constructing the VMD parameter optimized comprehensive fitness function RIMI, so that the time domain impact and the frequency domain cyclostationarity of the obtained mode are fully ensured. Experiments prove that compared with the existing fitness function (such as kurtosis, envelope spectrum peak value factors and weighted synthesis kurtosis), the comprehensive fitness function RIMI has better impact sensitivity and noise robustness, and can better solve the problem of VMD priori parameter selection.
2. The optimizing capability of the original dung beetle algorithm is improved by fusing the initializing population strategy, the self-adaptive inertia weight factor and the differential evolution algorithm, and the global exploration and local development capability are balanced well. Experiments prove that compared with other similar meta-heuristic algorithms (such as SSA, GWO, WOA), the improved dung beetle optimizing algorithm has higher convergence accuracy and higher convergence speed in the VMD parameter optimizing process.
3. The enhanced envelope spectrum analysis method combines the self-correlation noise reduction technology of the signals and the inherent characteristics between the envelope spectrum amplitude and the standard deviation, and performs operation processing through an extended exponential function, so that compared with the traditional spectrum analysis method, the enhanced envelope spectrum analysis method can effectively inhibit the interference frequency in the signals, amplify the fault characteristics and improve the accuracy of fault diagnosis.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following detailed description will be given with reference to the accompanying drawings and detailed embodiments, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive faculty for a person skilled in the art. Wherein:
FIG. 1 is a flowchart of an overall implementation of a fault diagnosis method according to an embodiment of the present application;
FIG. 2 is a flow chart of a method of decomposing a parameter adaptive variation modality according to an embodiment of the present application;
FIG. 3 is a fault bearing vibration signal and its envelope spectrum according to an embodiment of the present application;
FIG. 4 is a graph of the result of parameter optimization of a decomposition algorithm of a variation mode according to an embodiment of the present application;
FIG. 5 is a graph of decomposition results of a parameter optimized variational modal decomposition versus a fault bearing vibration signal in accordance with an embodiment of the present application;
FIG. 6 is a graph of the RIMI values of the integrated fitness function for each modal component according to an embodiment of the present application;
fig. 7 is a graph of the principal fault signature mode component and its enhancement envelope spectrum in accordance with an embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the application will be readily understood, a more particular description of the application will be rendered by reference to the appended drawings.
Next, the present application will be described in detail with reference to the drawings, wherein the sectional view of the device structure is not partially enlarged to general scale for the convenience of description, and the drawings are only examples, which should not limit the scope of the present application. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The application provides a method for diagnosing early weak faults of a rolling bearing, which avoids the influence of the traditional variational modal decomposition algorithm that an experience or priori criterion is required to select parameters and realizes accurate diagnosis of the early weak faults of the bearing.
Referring to fig. 1, a method for diagnosing early weak faults of a rolling bearing based on parameter adaptive variation modal decomposition provided by an embodiment of the application comprises the following steps:
s10: collecting a fault bearing vibration signal by using a sensor;
s20: the method comprises the steps of guiding an improved dung beetle optimization algorithm based on a comprehensive fitness function integrating multiple domain indexes to adaptively determine the optimal decomposition layer number and penalty factor of a variational modal decomposition algorithm, and dividing an acquired fault bearing vibration signal into a series of modal components by utilizing the variational modal decomposition algorithm with optimized parameters;
s30: calculating the comprehensive fitness function value of each modal component, and selecting the modal component with the smallest comprehensive fitness function value as a main fault characteristic modal component;
s40: the early weak fault diagnosis of the rolling bearing is realized by extracting the fault characteristic frequency from the enhanced envelope spectrum of the main fault characteristic modal component.
According to the diagnosis method, an optimal decomposition layer number and a penalty factor of a variation modal decomposition algorithm are adaptively determined by establishing a comprehensive fitness function RIMI to guide an improved dung beetle optimization algorithm, so that a parameter adaptive variation modal decomposition algorithm is formed, and the accurate diagnosis of early weak faults of the rolling bearing is realized.
In one embodiment of the present application, in step S20, the specific steps of adaptively determining the decomposition layer number and the penalty factor of the variational modal decomposition algorithm based on the improved dung beetle optimization algorithm guided by the comprehensive fitness function fusing the multiple domain indexes are as follows:
s201: and initializing a population position vector of the dung beetles by introducing a cubic chaotic map and a reverse learning strategy to form an initialized population with uniform distribution. Setting the population number P, the number Pa of the rolling balls of the dung beetles, the breeding number Pr of the dung beetles, the foraging number Ps of the dung beetles, the number Pt of the larch dung beetles and the maximum iteration number T max The upper and lower boundaries of the search are Ub and Lb respectively, and the dimension of the objective function is D;
s202: and establishing a comprehensive fitness function with optimized parameters, wherein the expression is as follows:
wherein arg min {.cndot } represents a function for obtaining a minimum value, RIMI is a comprehensive fitness function value of a modal component, and K and alpha are a decomposition layer number and a penalty factor of variation modal decomposition respectively.
S203: processing the collected original vibration signals by using variational modal decomposition according to the position vector of each dung beetle, calculating the fitness function value corresponding to each dung beetle in the current population, and recording the current optimal fitness value and the corresponding position vector;
s204: the individual position of the dung beetles is updated by utilizing four strategies of dung beetle rolling balls, dung beetle breeding, small dung beetle foraging and theft dung beetle, and the position updating rule of the dung beetle rolling balls and the theft dung beetles is improved by introducing a self-adaptive inertia weight strategy. Calculating and comparing global optimal values of individuals and populations, and updating and storing the global optimal individual positions of the dung beetles and the optimal fitness function values;
s205: performing differential mutation operation on the globally optimal individuals and randomly selected individuals, calculating and comparing global optimal values of the individuals and the population, and updating and storing the globally optimal individual positions of the dung beetles and the optimal fitness function values;
s206: and judging whether the maximum iteration times are reached. If so, the iteration will be terminated, obtaining the optimal parameter combination [ K, alpha ] of the variant mode decomposition algorithm. Otherwise, returning to the step S204 for loop iteration until the maximum number of loops is met.
In one embodiment of the present application, in step S202, the comprehensive fitness function is defined as:
where SEGI and IFCER are the square envelope base-Ni index of the signal and the improved fault signature energy ratio, respectively, and the calculation formulas are defined as follows:
wherein x is the original signal and x= (x) 1 ,x 2 ,…,x N ) N is the length of the signal, SE is the square envelope signal of the original signal x and se= [ SE ] (1) ,SE (2) ,…,SE (N) ]All elements being arranged in order from small to large, SE (1) ≤SE (2) ,…,≤SE (N) (1), (2), …, (N) is a new index of the index, SE 1 Is the L1 norm of the signal SE.
Wherein FFT (·) is the Fourier transform function in MATLAB kit, M is the envelope spectrum of the signal x, f w For the fault characteristic frequency, q is the harmonic quantity, deltaf is the fault frequency deviation, g is the gravitational acceleration, E is the energy of fault related characteristic information, E * Is the total energy.
In one embodiment of the present application, in step S201, the specific steps of introducing the cubic chaotic map and the inverse learning strategy to initialize the population position vector of the dung beetle are as follows:
s201-1: mapping the cubic chaos sequence to a dung beetle population;
s201-2: generating a reverse solution population;
s201-3: and combining and sequencing the cube mapping population and the reverse solution population, calculating the fitness function value of each individual, and selecting the top P dung beetles with better fitness function value as the initial population.
In one embodiment of the present application, in step S401, the formula for mapping the cubic chaos sequence onto the dung beetle population is as follows:
wherein y is i For the cubic sequence, ub and Lb are the upper and lower bounds of the search, X, respectively i Is the actual individual position of the dung beetles.
In one embodiment of the present application, in step S402, the formula for generating the inverse solution population is as follows:
OS i ＝k×(Lb+Ub)-X i
where k is a random number belonging to (0, 1).
In one embodiment of the present application, in step S204, the formula of the method for updating the position of the ball of the dung beetle based on the adaptive inertia weight strategy is defined as follows:
where δ=rand (1), ST e (0.5, 1)]. When delta is less than ST, the dung beetles roll in a targeted mode, and are in a normal global exploration stage, and when delta is more than or equal to ST, the dung beetles represent a barrier mode, and no specific rolling target exists. t is the current iteration number, x i (t) represents position information of ith dung beetle in the t-th iteration, alpha is a natural coefficient with value of-1 or 1, 1 represents no deviation, -1 represents original direction deviation, X w Representing the global worst position. w (w) t 、c t And r t Are all inertia weight coefficients, t is the current iteration number, wherein w is t And c t Non-linear decreasing function, r t A nonlinear increasing function, the formulas of which are respectively as follows:
wherein T is the current iteration number, T max Is the maximum number of iterations.
In one embodiment of the present application, in step S204, the location update formula for the dung beetle breeding is defined as follows:
wherein X is * Representing the current local best position, ub and Lb represent the upper and lower bounds of the search, respectively, where r=1-T/T max ，T max For maximum iteration number Ub * And Lb * Representing the upper and lower bounds, respectively, of the spawning area. B (B) i (t) is the position information of the ith breeding ball at the t-th iteration, b 1 And b 2 Representing two independent random vectors of size 1 x D, D representing the dimension of the optimization problem.
In one embodiment of the present application, in step S204, the location update formula for foraging of the small dung beetles is defined as follows:
wherein X is b Indicating the global optimum position, ub and Lb respectively represent the upper and lower bounds of the search, where r=1-T/T max ，T max For maximum iteration number Ub b And Lb b Representing the upper and lower bounds, respectively, of the optimal foraging area. X is x i (t) represents the position information of the ith small dung beetle in the t-th iteration, C 1 Representing random numbers subject to normal distribution, C 2 Representing the random vector belonging to (0, 1).
In one embodiment of the present application, in step S204, the following formula is defined for the theft dung beetle location updating rule based on the adaptive inertia weight policy improvement:
wherein S is max And S is min Represent S t Maximum and minimum of S max Taking 1, S min Taking 0, T to represent the current iteration number, T max Represents the maximum iteration number S t Is a linearly decaying inertial weight coefficient. ζ is a random vector of 1×d size satisfying a normal distribution with a mean value of 0 and a variance of 1.
In one embodiment of the present application, in step S205, the formula of the differential mutation operation is defined as follows:
wherein X is b (t) is the optimal position, X, in the t-th iteration population r1 (t) and X r2 (t) is the dung beetle number randomly selected in the t-th iterationThe volume position, lambda, is the scaling factor,is the new individual position generated in the t-th iteration.
It is to be noted that the population number M, the number Pa of ball balls of the dung beetles, the breeding number Pr of the dung beetles, the foraging number Ps of the small dung beetles, the number Pt of the stealing dung beetles and the maximum iteration number T of variation modal decomposition of the improved dung beetle optimization algorithm max Depending on the size of the calculation task, preferably m=30, pa=6, pr=6, ps=7, pt=11, t are chosen max ＝20。
In one embodiment of the present application, in step S20, the expression of the variant modal decomposition is:
u＝VMD(x,α,tau,K,DC,init,tol)
in the formula, x is an original signal to be decomposed, tau is a noise margin, DC is a direct current component, init is an initialization center frequency, tol is convergence accuracy, K and alpha respectively represent an optimal decomposition layer number and a penalty factor, and VMD (·) is a variation mode decomposition function in a MATLAB kit.
In one embodiment of the present application, in step S40, the calculation formula of the enhanced envelope spectrum is defined as follows:
wherein u is a main fault characteristic modal component of the original vibration signal x after VMD decomposition, xcorr (·) is an autocorrelation transformation function in MATLAB kit, R xx Is the autocorrelation noise reduction signal of signal u. FFT (·) is the Fourier transform function in MATLAB kit, PF is the signal R xx Is a square envelope spectrum of (c). std (·) is the standard deviation calculation function in the MATLAB kit and v is the standard deviation of the square envelope spectral amplitude PF.
The specific implementation cases are as follows:
the test uses XJTU-SY rolling bearing test data (XJTU-SY) of the XAn university of transportation and Shengyang science and technology joint laboratory to verify the method of the applicationEffectiveness. The bearing test platform consists of an alternating current motor, a motor rotating speed controller, a rotating shaft, a supporting bearing, a hydraulic loading system, a test bearing and the like, and can be used for carrying out accelerated life tests of various rolling bearings or sliding bearings under different working conditions to obtain the full life cycle monitoring data of the test bearing. The test designs 3 kinds of working conditions altogether, and 5 test bearings are arranged under each kind of working condition. The test bearing model was LDKUER204, roller diameter 7.92mm, pitch diameter 34.55mm, number of rollers 8, contact angle 0 °. During the running of the test bearing, an angular velocity sensor is arranged on the bearing seat in a horizontal direction for vibration data acquisition. In the application, during test verification, test vibration data of early weak failure of the outer ring of the bearing 3 under the working condition 1 is adopted at 70 minutes. In the experimental process, the radial load applied to the fault bearing is 12kN, the motor rotating speed is 2100rpm (which is equivalent to 35Hz of rotating frequency), the sampling frequency is 25.6kHz, and the sampling point number is 8192 points. According to the theoretical calculation formula of the fault bearing, the theoretical fault frequencies of the bearing outer ring, the bearing inner ring, the bearing rolling bodies and the bearing retainer are respectively f o ＝107.91Hz、f i ＝172.09Hz、f b =72.33 Hz and f c =13.49 Hz. FIG. 3 is an acquired fault bearing vibration signal and its envelope spectrum. Although it can be seen from fig. 3 that the bearing failure cycle transient pulses have been masked by background noise, the bearing outer race failure characteristic frequency f can be extracted from the envelope spectrum o However, other harmonic frequencies cannot be found, spectral lines are disordered, a large amount of interference frequencies and noise exist, and the outer ring faults cannot be accurately identified.
The fault bearing vibration signal is processed and analyzed by adopting the method. Firstly, an optimal parameter combination of a variation modal decomposition algorithm is adaptively found by utilizing an improved dung beetle algorithm based on a comprehensive fitness function RIMI, and the obtained parameter optimization result is shown in a figure 4. From the results of fig. 4, the optimal number of decomposition layers k=4 and penalty factor α=2000 can be determined. Second, the fault bearing vibration signal is decomposed into 4 modal components using a variational modal decomposition algorithm containing an optimal combination of parameters, as shown in fig. 5. The RIMI values for the 4 modal components are then calculated separately, as shown in fig. 6. As is apparent from FIG. 6, the 3 rd dieThe state component has the smallest RIMI value. Thus, the 3 rd modality component is selected as the main fault signature modality component. Finally, fig. 7 shows the principal fault signature modal component and its enhanced envelope spectrum. The periodic impact characteristic of the fault vibration signal is apparent from FIG. 7, and the outer ring fault characteristic frequency f o Frequency multiplication nf o (n=2, 3, …, 8) has a relatively pronounced spectral line, which dominates the whole spectrum and the interference noise is attenuated considerably. Therefore, the fault of the outer ring of the bearing can be accurately judged, which is consistent with experimental setting, and the effectiveness of the method in early weak fault diagnosis of the bearing is verified.
While the exemplary embodiment of the method for diagnosing early weak faults of a rolling bearing based on modal decomposition of adaptive variation of parameters according to the present application has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various modifications and adaptations can be made to the specific embodiments described above without departing from the concept of the present application, and various technical features and structures of the present application can be combined without departing from the scope of the application, which is defined in the appended claims.
Claims (10)
1. The method for diagnosing the early weak fault of the rolling bearing is characterized by comprising the following steps of:
s10: collecting a fault bearing vibration signal by using a sensor;
s20: the method comprises the steps of guiding an improved dung beetle optimization algorithm based on a comprehensive fitness function integrating multiple domain indexes, adaptively determining the optimal decomposition layer number and penalty factor of a variational modal decomposition algorithm, and dividing an acquired fault bearing vibration signal into a series of modal components by utilizing the variational modal decomposition algorithm with optimized parameters, wherein the variational modal decomposition expression is as follows:
u＝VMD(x,α,tau,K,DC,init,tol)
wherein x is an original signal to be decomposed, tau is a noise margin, DC is a direct current component, init is an initialization center frequency, tol is convergence accuracy, K and alpha respectively represent an optimal decomposition layer number and a penalty factor, and VMD (·) is a variation mode decomposition function in a MATLAB kit;
s30: calculating the comprehensive fitness function value of each modal component, and selecting the modal component with the smallest comprehensive fitness function value as a main fault characteristic modal component;
s40: the early weak fault diagnosis of the rolling bearing is realized by extracting the fault characteristic frequency from the enhanced envelope spectrum of the main fault characteristic modal component.
2. The method for diagnosing early weak faults of a rolling bearing according to claim 1, wherein in step S20, the specific steps of adaptively determining the optimal decomposition layer number and penalty factor of the variation modal decomposition algorithm based on an improved dung beetle optimization algorithm guided by a comprehensive fitness function fused with a multi-domain index are as follows:
s201, initializing a group position vector of dung beetles by introducing a cubic chaotic map and a reverse learning strategy to form an evenly distributed initialized group, setting a group scale P, setting the number Pa of ball balls of the dung beetles, the breeding number Pr of the dung beetles, the foraging number Ps of the small dung beetles, the number Pt of the theft dung beetles and the maximum iteration number T max The upper and lower boundaries of the search are Ub and Lb respectively, and the dimension of the objective function is D;
s202, establishing a comprehensive fitness function with optimized parameters, wherein the expression is as follows:
wherein arg min {.cndot } represents a function for obtaining a minimum value, RIMI is a comprehensive fitness function value of a modal component, and K and alpha are a decomposition layer number and a penalty factor of variation modal decomposition respectively;
s203, processing the collected original vibration signals by using variational modal decomposition according to the position vector of each dung beetle, calculating the fitness function value corresponding to each dung beetle in the current population, and recording the current optimal fitness value and the corresponding position vector;
s204, updating individual positions of the dung beetles by utilizing four strategies of dung beetle rolling ball, dung beetle breeding, small dung beetle foraging and theft of the dung beetles, introducing a self-adaptive inertia weight strategy to improve a dung beetle rolling ball and theft dung beetle position updating rule, calculating and comparing global optimal values of individuals and groups, updating and storing global optimal individual positions of the dung beetles and optimal fitness function values;
s205, performing differential mutation operation on the globally optimal individuals and randomly selected individuals, calculating and comparing global optimal values of the individuals and the population, and updating and storing the globally optimal individual positions of the dung beetles and the optimal fitness function value;
s206, judging whether the maximum iteration times are reached, if so, ending the iteration, obtaining the optimal parameter combination [ K, alpha ] of the variation modal decomposition algorithm, otherwise, returning to the step S204 for loop iteration until the maximum loop times are met.
3. The method according to claim 2, wherein in step S202, the integrated fitness function is defined as:
where SEGI and IFCER are the square envelope base-Ni index of the signal and the improved fault signature energy ratio, respectively, and the calculation formulas are defined as follows:
wherein x is the original signal and x= (x) 1 ,x 2 ,…,x N ) N is the length of the signal, SE is the square envelope signal of the original signal x and se= [ SE ] (1) ,SE (2) ,…,SE (N) ]All elements being arranged in order from small to large, SE (1) ≤SE (2) ,…,≤SE (N) (1), (2), …, (N) is the new index, SE 1 For letterThe L1 norm of the number SE;
wherein FFT (·) is the Fourier transform function in MATLAB kit, M is the envelope spectrum of the signal x, f w For the fault characteristic frequency, q is the harmonic quantity, deltaf is the fault frequency deviation, g is the gravitational acceleration, E is the energy of fault related characteristic information, E * Is the total energy.
4. The method for diagnosing early weak faults of rolling bearings according to claim 2, wherein in step S201, the specific steps of introducing the cubic chaotic map and the reverse learning strategy to initialize the group position vector of the dung beetles are as follows:
s201-1: mapping the cubic chaos sequence onto a dung beetle population, wherein the specific formula is as follows:
wherein y is i For the cubic sequence, ub and Lb are the upper and lower bounds of the search, X, respectively i The individual position of the actual dung beetles;
s201-2: generating a reverse solution population, wherein the specific formula is as follows: OS (operating System) i ＝k×(Lb+Ub)-X i Wherein k is a random number belonging to (0, 1);
s201-3: and combining and sequencing the cube mapping population and the reverse solution population, calculating the fitness function value of each individual, and selecting the top P dung beetles with better fitness function value as the initial population.
5. The method for diagnosing early weak failure of a rolling bearing according to claim 4, wherein in step S204, the algorithm is defined as follows, based on the algorithm for updating the position of the ball of the dung beetle after the adaptive inertia weight strategy is improved:
where δ=rand (1), ST e (0.5, 1)]When delta is less than ST, the dung beetles roll in a targeted manner in a normal global exploration stage in a barrier-free mode, and when delta is more than or equal to ST, the dung beetles represent a barrier-free mode, no specific rolling target exists in the dung beetles, t is the current iteration times, and x i (t) represents position information of ith dung beetle in the t-th iteration, alpha is a natural coefficient with value of-1 or 1, 1 represents no deviation, -1 represents original direction deviation, X w Represents the global worst position, w t 、c t And r t Are all inertia weight coefficients, t is the current iteration number, wherein w is t And c t Non-linear decreasing function, r t A nonlinear increasing function, the formulas of which are respectively as follows:
wherein T is the current iteration number, T max Is the maximum number of iterations.
6. The method for diagnosing early weak faults of rolling bearings according to claim 1, wherein in step S204, the position update formula for the dung beetle breeding is defined as follows:
wherein X is * Representing the current local best position, ub and Lb represent the upper and lower bounds of the search, respectively, where r=1-T/T max ，T max For maximum iteration number, Ub * And Lb * Respectively represent the upper and lower bounds of spawning area, B i (t) is the position information of the ith breeding ball at the t-th iteration, b 1 And b 2 Representing two independent random vectors of size 1 x D, D representing the dimension of the optimization problem.
7. The method for diagnosing early weak failure of a rolling bearing according to claim 1, wherein in step S204, the position update formula of foraging of the small dung beetles is defined as follows:
wherein X is b Indicating the global optimum position, ub and Lb respectively represent the upper and lower bounds of the search, where r=1-T/T max ，T max For maximum iteration number Ub b And Lb b Respectively representing the upper and lower bounds, x of the best foraging area i (t) represents the position information of the ith small dung beetle in the t-th iteration, C 1 Representing random numbers subject to normal distribution, C 2 Representing the random vector belonging to (0, 1).
8. The method for diagnosing early weak failure of a rolling bearing according to claim 1, wherein in step S204, the adaptive inertia weight policy-based improved positioning rule of the theft dung beetle is defined as follows:
wherein S is max And S is min Represent S t Maximum and minimum of S max Taking 1, S min Taking 0, T to represent the current iteration number, T max Represents the maximum iteration number S t The linear attenuation inertial weight coefficient is that xi is normal distribution with 0 as mean and 1 as variance and 1×A random vector of D.
9. The method according to claim 1, wherein in step S205, the formula of the differential mutation operation is defined as follows:
wherein X is b (t) is the optimal position, X, in the t-th iteration population r1 (t) and X r2 (t) is the individual position of the dung beetle selected randomly in the t-th iteration, lambda is the scaling factor,is the new individual position generated in the t-th iteration.
10. The method for diagnosing early weak failure of a rolling bearing according to claim 1, wherein the calculation formula of the enhanced envelope spectrum is defined as follows:
wherein u is a main fault characteristic modal component of the original vibration signal x after VMD decomposition, xcorr (·) is an autocorrelation transformation function in MATLAB kit, R xx For the autocorrelation noise reduction signal of signal u, FFT (·) is the Fourier transform function in MATLAB kit, PF is signal R xx Std (·) is the standard deviation calculation function in MATLAB kit and v is the standard deviation of the square envelope spectrum amplitude PF.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311147203.9A CN117235643B (en) | 2023-09-06 | 2023-09-06 | Early weak fault diagnosis method for rolling bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311147203.9A CN117235643B (en) | 2023-09-06 | 2023-09-06 | Early weak fault diagnosis method for rolling bearing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117235643A true CN117235643A (en) | 2023-12-15 |
| CN117235643B CN117235643B (en) | 2024-03-22 |
Family
ID=89083615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311147203.9A Active CN117235643B (en) | 2023-09-06 | 2023-09-06 | Early weak fault diagnosis method for rolling bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117235643B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117692914A (en) * | 2024-02-02 | 2024-03-12 | Ut斯达康通讯有限公司 | Service function chain mapping method, system, electronic equipment and storage medium |
| CN117743835A (en) * | 2024-02-20 | 2024-03-22 | 齐鲁工业大学(山东省科学院) | Underwater sound signal noise reduction method based on improved dung beetle algorithm optimization variational modal decomposition |
| CN117851872A (en) * | 2024-03-07 | 2024-04-09 | 唐智科技湖南发展有限公司 | High-frequency vibration treatment diagnosis method and system for aero-engine |
| CN117909795A (en) * | 2024-01-31 | 2024-04-19 | 昆明理工大学 | Water pump unit fault diagnosis method based on EEMD (EEMD) and LCTDBO-BP fusion |
| CN117928951A (en) * | 2024-03-21 | 2024-04-26 | 安徽大学 | Fault diagnosis method based on improved empirical wavelet transformation and envelope spectrum energy ratio |
| CN117970864A (en) * | 2024-04-02 | 2024-05-03 | 万科思自动化(上海)有限公司 | Petroleum and natural gas PLC control monitoring system and method based on electric signal analysis |
| CN118294144A (en) * | 2024-06-04 | 2024-07-05 | 苏州长城精工科技股份有限公司 | Rolling bearing fault diagnosis method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108426715A (en) * | 2018-06-13 | 2018-08-21 | 福州大学 | Rolling bearing Weak fault diagnostic method based on PSO-VMD-MCKD |
| CN113418705A (en) * | 2021-07-23 | 2021-09-21 | 燕山大学 | Early fault diagnosis method for rolling bearing |
| CN113468688A (en) * | 2021-07-05 | 2021-10-01 | 西安交通大学 | Bearing fault diagnosis method based on parameter optimization VMD and weighted Gini index |
| CN114742111A (en) * | 2022-05-24 | 2022-07-12 | 南京林业大学 | Fault diagnosis method and system based on parameter adaptive characteristic modal decomposition |
| CN115062665A (en) * | 2022-06-30 | 2022-09-16 | 太原理工大学 | Rolling bearing early fault diagnosis method based on self-adaptive variational modal decomposition |
| CN115628906A (en) * | 2022-10-08 | 2023-01-20 | 北京理工大学 | Bearing fault diagnosis method based on GA-VMD and self-adaptive stochastic resonance |
| CN115876476A (en) * | 2023-02-16 | 2023-03-31 | 山东科技大学 | Rolling bearing fault diagnosis method, system, computer device and storage medium |
| CN116028844A (en) * | 2022-12-13 | 2023-04-28 | 西安交通大学 | Rolling bearing weak fault enhancement diagnosis method, device, equipment and storage medium |
| CN116610907A (en) * | 2023-05-27 | 2023-08-18 | 哈尔滨理工大学 | Gear vibration signal characteristic extraction method based on variational modal decomposition |
-
2023
- 2023-09-06 CN CN202311147203.9A patent/CN117235643B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108426715A (en) * | 2018-06-13 | 2018-08-21 | 福州大学 | Rolling bearing Weak fault diagnostic method based on PSO-VMD-MCKD |
| CN113468688A (en) * | 2021-07-05 | 2021-10-01 | 西安交通大学 | Bearing fault diagnosis method based on parameter optimization VMD and weighted Gini index |
| CN113418705A (en) * | 2021-07-23 | 2021-09-21 | 燕山大学 | Early fault diagnosis method for rolling bearing |
| CN114742111A (en) * | 2022-05-24 | 2022-07-12 | 南京林业大学 | Fault diagnosis method and system based on parameter adaptive characteristic modal decomposition |
| CN115062665A (en) * | 2022-06-30 | 2022-09-16 | 太原理工大学 | Rolling bearing early fault diagnosis method based on self-adaptive variational modal decomposition |
| CN115628906A (en) * | 2022-10-08 | 2023-01-20 | 北京理工大学 | Bearing fault diagnosis method based on GA-VMD and self-adaptive stochastic resonance |
| CN116028844A (en) * | 2022-12-13 | 2023-04-28 | 西安交通大学 | Rolling bearing weak fault enhancement diagnosis method, device, equipment and storage medium |
| CN115876476A (en) * | 2023-02-16 | 2023-03-31 | 山东科技大学 | Rolling bearing fault diagnosis method, system, computer device and storage medium |
| CN116610907A (en) * | 2023-05-27 | 2023-08-18 | 哈尔滨理工大学 | Gear vibration signal characteristic extraction method based on variational modal decomposition |
Non-Patent Citations (4)
| Title |
|---|
| JIANKAI XUE ET AL.: "Dung beetle optimizer: a new meta‑heuristic algorithm for global optimization", 《THE JOURNAL OF SUPERCOMPUTING 》, 27 November 2022 (2022-11-27), pages 7305 - 7336 * |
| QICHEN SHAO ET AL.: "A Novel Coupled Optimization Prediction Model for Air Quality", 《IEEE ACCESS》, vol. 11, 13 July 2023 (2023-07-13), pages 69667 - 69685 * |
| RAN WANG ET AL.: "Cyclic correlation density decomposition based on a sparse and low-rank model for weak fault feature extraction of rolling bearings", 《MEASUREMENT》, 30 May 2022 (2022-05-30), pages 1 - 17 * |
| 刘迎松 等: "基于参数自适应VMD和MCKD的 滚动轴承微弱故障特征提取", 《噪声与振动控制》, vol. 43, no. 3, 30 June 2023 (2023-06-30), pages 102 - 109 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117909795A (en) * | 2024-01-31 | 2024-04-19 | 昆明理工大学 | Water pump unit fault diagnosis method based on EEMD (EEMD) and LCTDBO-BP fusion |
| CN117692914A (en) * | 2024-02-02 | 2024-03-12 | Ut斯达康通讯有限公司 | Service function chain mapping method, system, electronic equipment and storage medium |
| CN117743835A (en) * | 2024-02-20 | 2024-03-22 | 齐鲁工业大学(山东省科学院) | Underwater sound signal noise reduction method based on improved dung beetle algorithm optimization variational modal decomposition |
| CN117743835B (en) * | 2024-02-20 | 2024-04-30 | 齐鲁工业大学(山东省科学院) | Underwater sound signal noise reduction method based on improved dung beetle algorithm optimization variational modal decomposition |
| CN117851872A (en) * | 2024-03-07 | 2024-04-09 | 唐智科技湖南发展有限公司 | High-frequency vibration treatment diagnosis method and system for aero-engine |
| CN117851872B (en) * | 2024-03-07 | 2024-05-31 | 唐智科技湖南发展有限公司 | High-frequency vibration treatment diagnosis method and system for aero-engine |
| CN117928951A (en) * | 2024-03-21 | 2024-04-26 | 安徽大学 | Fault diagnosis method based on improved empirical wavelet transformation and envelope spectrum energy ratio |
| CN117928951B (en) * | 2024-03-21 | 2024-06-11 | 安徽大学 | Fault diagnosis method based on improved empirical wavelet transformation and envelope spectrum energy ratio |
| CN117970864A (en) * | 2024-04-02 | 2024-05-03 | 万科思自动化(上海)有限公司 | Petroleum and natural gas PLC control monitoring system and method based on electric signal analysis |
| CN117970864B (en) * | 2024-04-02 | 2024-05-31 | 万科思自动化(上海)有限公司 | Petroleum and natural gas PLC control monitoring system and method based on electric signal analysis |
| CN118294144A (en) * | 2024-06-04 | 2024-07-05 | 苏州长城精工科技股份有限公司 | Rolling bearing fault diagnosis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117235643B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117235643B (en) | Early weak fault diagnosis method for rolling bearing | |
| CN107560849B (en) | Wind turbine generator bearing fault diagnosis method of multichannel deep convolutional neural network | |
| Aye et al. | An integrated Gaussian process regression for prediction of remaining useful life of slow speed bearings based on acoustic emission | |
| Chelidze et al. | A dynamical systems approach to damage evolution tracking, part 1: description and experimental application | |
| CN100568271C (en) | A kind of Methods of Chaotic Forecasting of corrosion depth | |
| CN112347898B (en) | Rolling bearing health index construction method based on DCAE neural network | |
| US12045047B2 (en) | Fault diagnostics systems and methods | |
| CN108760310A (en) | Accidental resonance Fault Diagnosis of Roller Bearings based on novel signal-to-noise ratio index | |
| CN114896559B (en) | Self-adaptive noise complete set empirical mode decomposition method based on permutation entropy | |
| CN115901249B (en) | Rolling bearing performance degradation evaluation method combining feature optimization and multi-strategy optimization SVDD | |
| CN112364706A (en) | Small sample bearing fault diagnosis method based on class imbalance | |
| Yu et al. | Machine fault diagnosis based on Gaussian mixture model and its application | |
| CN115238736A (en) | Method for identifying early fault of rotary machine | |
| Ding et al. | Deep time–frequency learning for interpretable weak signal enhancement of rotating machineries | |
| CN106126801A (en) | Rolling bearing friction torque parameter uncertainty evaluation method | |
| CN113281047A (en) | Bearing inner and outer ring fault quantitative trend diagnosis method based on variable-scale Lempel-Ziv | |
| CN117473872A (en) | Rolling bearing fault diagnosis method based on FFT (fast Fourier transform) coding and L-CNN (linear-to-CNN) | |
| Moazenahmadi et al. | Defect size estimation and analysis of the path of rolling elements in defective bearings with respect to the operational speed | |
| CN105631238A (en) | Method and system for detecting vibration performance variation of antifriction bearing | |
| CN114894481B (en) | Rolling bearing fault diagnosis method and system based on deconvolution algorithm | |
| CN116401950A (en) | Rolling bearing performance degradation prediction method based on time chart convolution neural network | |
| Fu et al. | Intelligent fault diagnosis of rolling bearings based on an improved empirical wavelet transform and ResNet under variable conditions | |
| CN112613573B (en) | Rolling bearing fault diagnosis method based on self-adaptive termination criterion OMP | |
| CN111368379B (en) | Rolling bearing reliability evaluation method and system for improving HWPSO-WPHM model | |
| Liu et al. | Periodic impact feature extraction for bearings fault based on envelope correlation kurtosis of singular value components |
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 |