CN113283153B - Ship vibration equipment service life prediction method under variable working conditions - Google Patents
Ship vibration equipment service life prediction method under variable working conditions Download PDFInfo
- Publication number
- CN113283153B CN113283153B CN202110661544.2A CN202110661544A CN113283153B CN 113283153 B CN113283153 B CN 113283153B CN 202110661544 A CN202110661544 A CN 202110661544A CN 113283153 B CN113283153 B CN 113283153B
- Authority
- CN
- China
- Prior art keywords
- ship
- working condition
- equipment
- vibration
- ship vibration
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/25—Design optimisation, verification or simulation using particle-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- 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
Abstract
The invention provides a life prediction method of ship vibration equipment under variable working conditions, which relates to the technical field of ship mechanical state monitoring and comprises the following steps: s1, acquiring acceleration data of historical ship vibration equipment, establishing a working condition classification and identification model, and further establishing a working condition classification and identification module; s2, acquiring acceleration data of ship vibration equipment to be predicted at the current moment, and outputting codes of the working condition types of the equipment at the current moment; and S3, carrying out feature extraction and fusion on vibration intensity data of the working condition of the ship vibration equipment to be predicted at the current moment to obtain an observation equation, obtaining a state equation by using the fatigue fracture expansion model, inputting the obtained observation equation and the state equation into a particle filter model, outputting the residual service life of the ship vibration equipment, and realizing the purpose of carrying out service life prediction on the ship vibration machinery with multiple working conditions.
Description
Technical Field
The invention relates to the technical field of ship mechanical state monitoring, in particular to a method for predicting service life of ship vibration equipment under variable working conditions.
Background
Shipping of ships becomes a main transportation way of world trade due to the advantages of large transportation amount, low transportation cost and the like. The ship needs a plurality of electromechanical devices to provide support for normal operation of the ship in the operation process, the operation of the ship devices is inevitably vibrated, the equipment wear is accelerated by the variable working conditions and the complex working environment where the devices are located, and the equipment faults are more easily caused by self-generation and superposition of ship body vibration. This means that continuous and accurate monitoring of the operating conditions of the ship equipment and prediction of the life of the ship equipment are required, so that reasonable and effective measures can be taken conveniently, and normal sailing of the ship is prevented from being influenced by equipment faults.
The existing commonly used life prediction method of the ship equipment mostly assumes that the working condition of the ship equipment is not changed when the ship equipment is operated, however, the life prediction based on the method has limitations and inaccuracy, and is not suitable for the ship machinery with the variable working condition operation characteristic. In view of the above, it is desirable to provide a method for predicting the life of marine equipment under conditions of varying operating conditions.
Disclosure of Invention
The invention provides a life prediction method of ship vibration equipment under variable working conditions, which solves the problem that the existing life prediction method of ship equipment cannot predict under variable working conditions.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a ship vibration equipment life prediction method under variable working conditions comprises the following steps:
s1, acquiring acceleration data of historical ship vibration equipment, calculating the historical acceleration data of the ship vibration equipment to obtain vibration intensity, establishing a working condition classification and identification model, and further establishing a working condition classification and identification module;
s2, acquiring acceleration data of the ship vibration equipment to be predicted at the current moment, calculating vibration intensity of the ship vibration equipment to be predicted at the current moment, taking the vibration intensity of the ship vibration equipment to be predicted at the current moment as input of a working condition classification and identification module, and outputting codes of working condition categories where the equipment at the current moment is located;
and S3, carrying out feature extraction and fusion on vibration intensity data of the working condition of the ship vibration equipment to be predicted at the current moment to obtain an observation equation, obtaining a state equation by using the fatigue fracture expansion model, inputting the obtained observation equation and state equation into a particle filter model, and outputting the residual life of the ship vibration equipment.
Preferably, the S1 includes:
s11, acquiring historical acceleration data of ship vibration equipment;
s12, calculating historical acceleration data of ship vibration equipment to obtain vibration intensity;
s13, carrying out parameter training on the vibration intensity data obtained in the S12 to obtain trained parameters;
s14, generating different working condition clusters by the trained parameters obtained in the step S13.
Preferably, the calculating the historical acceleration data of the ship vibration device to obtain the vibration intensity in S12 includes: let the historical acceleration data be x (n), the sampling frequency be f s Conversion to a frequency domain signal using discrete Fourier transformObtaining the single-side amplitude spectrum of the signal as +.>Harmonic frequency of +.>Then in the frequency range f a 、f b The vibration intensity is->
Wherein: k=0, 1,2, …, N, j is an imaginary unit, n=0, 1,2, …, N is a timing sequence number, f a For the lower sampling frequency limit, f b Is the upper sampling frequency limit.
Preferably, the step S13 of performing parameter training on the obtained vibration intensity data includes:
set up D dimension random observation variable x= (x) 1 ，x 2 ，...x D ) T The introduction of the hidden variable z, which is a set of discrete random variables, represents the gaussian distribution (C 1 ，C 2 ，...C k ) The gaussian mixture model expression comprising K components is as follows:
wherein: k is the number of single Gaussian models in the Gaussian mixture model, alpha k Weighting K Gaussian models in a Gaussian mixture model, N (x|Θ) k ) As a probability density function of sample x in the Kth Gaussian mixture model, Θ k To include the mean mu k Sum covariance matrix sigma k Is a parameter vector of (a);
obtaining data x i The probability generated by the jth gaussian mixture model is expressed as follows:
and carrying out iterative updating on parameters of the Gaussian mixture model through an EM algorithm until the parameters are converged, wherein the expression of each parameter is as follows:
wherein: x is x i Representing the i-th observed variable, i=1, 2, …, N, K is the number of gaussian models in the mixed model, k=1，2，…，K，μ j Is the mean value of the jth Gaussian model, sigma j Variance of mean value of jth Gaussian model, α j To observe the probability that a variable belongs to the jth Gaussian model, alpha j ≥0，
Preferably, the step of obtaining the code of the working condition class where the device at the current moment is located in S4 includes:
based on the identification of the log-likelihood estimation method, x belongs to the category in the Gaussian model, and the negative log-likelihood estimation is used as the judgment index because the log-likelihood value is smaller than 0:
NLLP＝-log p(x|Θ))
selecting the Gaussian component with the least negative likelihood as the working condition class code at the moment:
k＝argmin{-log p(x|Θ k )}
wherein: x is acceleration data at the current moment, k is the working condition category to which the variable at the current moment belongs, and Θ k To include the mean mu k Sum covariance matrix sigma k P (x|Θ) is the probability of variable x given the parameter Θ.
Preferably, the S3 includes:
for the evolution trend of the degradation of the vibration mechanical performance of the ship, 15 time domain features are extracted, the feature which can represent the trend is selected by comprehensively considering the monotonicity and the relativity of the evolution trend, and the monotonicity index is calculated by adopting two evaluation standards of the monotonicity and the relativity, wherein the formula is as follows:
the formula for calculating the correlation index is as follows:
wherein:X＝(x 1 ，x 2 ，...x N ) Is a characteristic parameter sequence; t= (T 1 ，t 2 ，...t N ) Is a time sequence of corresponding moments;
performing secondary feature processing on the high-dimensional feature vector meeting the requirements of the monotonicity and the relativity two evaluation standards by adopting a KPCA algorithm to obtain a fusion health index under the current moment determination working condition, and obtaining a measurement equation:
z t ＝y t +v t
wherein: z t Is the obtained health index; v t Is the measurement noise, y t Is a measurement equation;
and obtaining a state equation by using the fatigue fracture expansion model, and predicting the residual life of the mechanical equipment according to a particle filtering algorithm.
Preferably, the method for predicting the life of ship vibration equipment under the variable working condition is performed when the program runs.
Preferably, the electronic device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the method for predicting the service life of the ship vibration equipment under the variable working condition through the running of the computer program.
The invention has the beneficial effects that:
according to the invention, the historical data is modeled, and the data to be predicted is brought into the training parameters of the Gaussian mixture model, so that the purpose of predicting the service life of the ship vibration machinery with multiple working modes is realized.
Drawings
For a clearer description of an embodiment of the invention or of the prior art, the drawings that are used in the description of the embodiment or of the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a block diagram of the residual life prediction structure of the ship vibration equipment.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
The relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise. Meanwhile, it should be clear that the dimensions of the respective parts shown in the drawings are not drawn in actual scale for convenience of description. Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
In the description of the present invention, it should be understood that the azimuth or positional relationships indicated by the azimuth terms such as "front, rear, upper, lower, left, right", "lateral, vertical, horizontal", and "top, bottom", etc., are generally based on the azimuth or positional relationships shown in the drawings, merely to facilitate description of the present invention and simplify the description, and these azimuth terms do not indicate and imply that the apparatus or elements referred to must have a specific azimuth or be constructed and operated in a specific azimuth, and thus should not be construed as limiting the scope of protection of the present invention: the orientation word "inner and outer" refers to inner and outer relative to the contour of the respective component itself.
Spatially relative terms, such as "above … …," "above … …," "upper surface at … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial location relative to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "above" or "over" other devices or structures would then be oriented "below" or "beneath" the other devices or structures. Thus, the exemplary term "above … …" may include both orientations of "above … …" and "below … …". The device may also be positioned in other different ways (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
In addition, the terms "first", "second", etc. are used to define the components, and are only for convenience of distinguishing the corresponding components, and the terms have no special meaning unless otherwise stated, and therefore should not be construed as limiting the scope of the present invention.
The invention provides a technical scheme that: a ship vibration equipment life prediction method under variable working conditions is shown in fig. 1, and comprises the following steps:
s1, acquiring acceleration data of historical ship vibration equipment, analyzing the historical acceleration data of the ship vibration equipment, and establishing a working condition classification and identification module;
s2, acquiring acceleration data of the ship vibration equipment to be predicted at the current moment, taking the acceleration data of the ship vibration equipment to be predicted at the current moment as input of a working condition classification and identification module, and outputting working condition data of the equipment at the current moment;
and S3, carrying out feature extraction and fusion on working condition data of the equipment at the current moment to obtain an observation equation, obtaining a state equation by using a fatigue fracture expansion model, and carrying the observation equation and the state equation into a particle filtering algorithm to obtain the residual life of the ship vibration equipment.
S1 comprises the following steps:
s11, acquiring historical acceleration data of ship vibration equipment;
s12, preprocessing historical acceleration data of ship vibration equipment;
s13, performing parameter training on the processed historical acceleration data of the ship vibration equipment;
s14, generating different working condition clusters by the parameters obtained in the step S13.
S12, preprocessing historical acceleration data of the ship vibration equipment, wherein the preprocessing comprises the following steps: let the historical acceleration data be x (n), the sampling frequency be f s Conversion to a frequency domain signal using discrete Fourier transformObtaining the single-side amplitude spectrum of the signal as +.>Harmonic frequency of +.>Then in the frequency range f a 、f b The intensity of vibration is
Wherein: k=0, 1,2, …, N, j is an imaginary unit, n=0, 1,2, …, N is a timing sequence number, f a For the lower sampling frequency limit, f b Is the upper sampling frequency limit.
S13 parameter training, comprising:
gaussian mixture (GMM) model is a linear combination of a plurality of Gaussian distribution functions, and is provided with D-dimensional random observation variable x= (x) 1 ，x 2 ，...x D ) T The introduction of the hidden variable z, which is a set of discrete random variables, represents the gaussian distribution (C 1 ，C 2 ，...C k ) The gaussian mixture model expression comprising K components is as follows:
wherein: k is the number of single Gaussian models in the Gaussian mixture model, alpha k Weighting K Gaussian models in a Gaussian mixture model, N (x|Θ) k ) As a probability density function of sample x in the Kth Gaussian mixture model, Θ k To include the mean mu k Sum covariance matrix sigma k Is a parameter vector of (a);
obtaining data x i The probability generated by the jth gaussian mixture model is expressed as follows:
and carrying out iterative updating on parameters of the Gaussian mixture model through an EM algorithm until the parameters are converged, wherein the expression of each parameter is as follows:
wherein: x is x i Representing the i-th observed variable, i=1, 2, …, N, K is the number of gaussian models in the mixed model, k=1, 2, …, K, μ j Is the mean value of the jth Gaussian model, sigma j Variance of mean value of jth Gaussian model, α j To observe the probability that a variable belongs to the jth Gaussian model, alpha j ≥0，
The step of obtaining the working condition data of the equipment at the current moment in S2 comprises the following steps:
based on the identification of the log-likelihood estimation method, x belongs to the category in the Gaussian model, and the negative log-likelihood estimation is used as the judgment index because the log-likelihood value is smaller than 0:
NLLP＝-log p(x|Θ)) (6)
selecting the Gaussian component with the least negative likelihood as the working condition category at the moment:
k＝argmin{-log p(x|Θ k )} (7)
wherein: x is acceleration data at the current moment, k is the working condition category to which the variable at the current moment belongs, and Θ k To include the mean mu k Sum covariance matrix sigma k Is used for the parameter vector of (a).
For the evolution trend of the degradation of the vibration mechanical performance of the ship, 15 time domain features are extracted, the feature which can represent the trend is selected by comprehensively considering the monotonicity and the relativity of the evolution trend, and the monotonicity index is calculated by adopting two evaluation standards of the monotonicity and the relativity, wherein the formula is as follows:
the formula for calculating the correlation index is as follows:
wherein:X＝(x 1 ，x 2 ，...x N ) Is a certain characteristic parameter sequence; t= (T 1 ，t 2 ，...t N ) Is a time sequence of corresponding moments;
performing secondary feature processing on the high-dimensional feature vector meeting the requirements by adopting a KPCA algorithm to obtain a fusion health index under the current moment determination working condition, and obtaining a measurement equation:
z t ＝y t +v t (10)
wherein: z t Is the obtained health index; v t Is measurement noise;
the fatigue fracture expansion model is utilized to obtain a state equation, which specifically comprises the following steps:
based on the Paris formula, a fatigue fracture expansion model based on a physical mechanism is given:
it is composed of:is the defect rate; parameters C and m and materialThe material characteristics are related; Δk is the stress intensity factor. For the case of defect expansion, it is difficult to estimate the stress intensity factor, express the defect size as the spalling area y, and build an empirical model:
after separating the variables, integrating, the model can be rewritten in the form of a state transfer function:
wherein: y is t Representing the degradation state of the machine, u t-1 State noise representing time t-1
Predicting the remaining life of the mechanical equipment according to a particle filtering algorithm, wherein the method specifically comprises the following steps of:
based on the measurement equation (10) state transition equation (13), the degradation state y for the 1-step advance prediction of the ship vibration machine is predicted given that all the measured values within the time step 1 are contained t+l And a posterior probability density function p (y t+l |z t ) The prediction can be made by:
it is composed of:is a weight based on the likelihood of the observed value at time t+l-1, and is expressed as
To avoid the occurrence of weight degradation, resampling of discrete approximations of the posterior probability density is required, defining the number of effective particles that undergo weight degradation as:
the number of effective particles is below a preset threshold N e At that time, resampling is performed.
The remaining service life (RUL) of the ship vibration machine is estimated according to the future degradation state, wherein the degradation state is defined as the remaining service time before the degradation state exceeds a preset threshold value;
RUL(t)＝t p -t d (16)
wherein: t is t p Is the current time, t d The time for the degradation state of the ship vibration machine to reach a preset threshold value is set to 0.7.
And obtaining a state equation by using the fatigue fracture expansion model, and predicting the residual life of the mechanical equipment according to a particle filtering algorithm.
The method for predicting the service life of the ship vibration equipment under the variable working condition can be accurately used for predicting the residual service life of the ship vibration equipment. Compared with the traditional residual life prediction method based on single working condition, the method has stronger self-adaptability and higher accuracy.
Corresponding to the method for predicting the service life of the ship vibration equipment under the variable working condition, the embodiment of the invention also provides a computer readable storage medium, wherein the storage medium comprises a stored program, and the method for predicting the service life of the ship vibration equipment under the variable working condition is executed when the program runs.
Corresponding to the method for predicting the service life of the ship vibration equipment under the variable working condition, the embodiment of the invention also provides an electronic device which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor.
The invention provides a life prediction method of ship vibration equipment under variable working conditions, and aims to provide a life prediction method of ship vibration equipment under variable working conditions, which is high in self-adaptive capacity and accuracy. Comprising the following steps: collecting historical vibration data of vibration equipment under multiple working conditions, and performing GMM (Gaussian mixture model) unsupervised clustering on the data to obtain a clustering model of each working condition; for each given instant data point, adopting log likelihood estimation to determine the working condition of the instant data point to finish working condition identification; the state transition equation is a fatigue crack propagation model based on a physical mechanism and given based on a Paris formula; 15 time domain features are extracted from the instant vibration data, and dimension reduction processing is carried out on the high-dimensional data to obtain a measurement equation, so that life prediction can be carried out on the ship vibration machinery under multiple working conditions by the method.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (7)
1. The life prediction method of the ship vibration equipment under the variable working condition is characterized by comprising the following steps of:
s1, acquiring acceleration data of historical ship vibration equipment, calculating the historical acceleration data of the ship vibration equipment to obtain vibration intensity, establishing a working condition classification and identification model, and further establishing a working condition classification and identification module;
s2, acquiring acceleration data of the ship vibration equipment to be predicted at the current moment, calculating vibration intensity of the ship vibration equipment to be predicted at the current moment, taking the vibration intensity of the ship vibration equipment to be predicted at the current moment as input of a working condition classification and identification module, and outputting codes of working condition categories where the equipment at the current moment is located;
s3, carrying out feature extraction and fusion on vibration intensity data of the working condition of the ship vibration equipment to be predicted at the current moment to obtain an observation equation, obtaining a state equation by using a fatigue fracture expansion model, inputting the obtained observation equation and the state equation into a particle filter model, and outputting the residual service life of the ship vibration equipment, wherein the method specifically comprises the following steps:
for the evolution trend of the degradation of the vibration mechanical performance of the ship, 15 time domain features are extracted, the feature which can represent the trend is selected by comprehensively considering the monotonicity and the relativity of the evolution trend, and the monotonicity index is calculated by adopting two evaluation standards of the monotonicity and the relativity, wherein the formula is as follows:
the formula for calculating the correlation index is as follows:
wherein:X＝(x 1 ,x 2 ,...x N ) Is a characteristic parameter sequence; t= (T 1 ,t 2 ,...t N ) Is a time sequence of corresponding moments;
performing secondary feature processing on the high-dimensional feature vector meeting the requirements of the monotonicity and the relativity two evaluation standards by adopting a KPCA algorithm to obtain a fusion health index under the current moment determination working condition, and obtaining a measurement equation:
z t ＝y t +ν t
wherein: z t Is the obtained health index; v t Is the measurement noise, y t Is a measurement equation;
and obtaining a state equation by using the fatigue fracture expansion model, and predicting the residual life of the mechanical equipment according to a particle filtering algorithm.
2. The method for predicting the life of ship vibration equipment under variable working conditions according to claim 1, wherein S1 comprises:
s11, acquiring historical acceleration data of ship vibration equipment;
s12, calculating historical acceleration data of ship vibration equipment to obtain vibration intensity;
s13, carrying out parameter training on the vibration intensity data obtained in the S12 to obtain trained parameters;
s14, generating different working condition clusters by the trained parameters obtained in the step S13.
3. The method for predicting the life of a ship vibration device under variable working conditions according to claim 2, wherein S12 calculating the historical acceleration data of the ship vibration device to obtain the vibration intensity comprises: let the historical acceleration data be x (n), the sampling frequency be f s Conversion to a frequency domain signal using discrete Fourier transformObtaining the single-side amplitude spectrum of the signal as +.>Harmonic frequency of +.>Then in the frequency range f a 、f b The intensity of vibration is
Wherein: k=0, 1,2, …, N, j is an imaginary unit, n=0, 1,2, …, N is a timing sequence number, f a For the lower sampling frequency limit, f b Is the upper sampling frequency limit.
4. A method for predicting the life of a ship vibration device under variable working conditions according to claim 3, wherein the step S13 of performing parameter training on the obtained vibration intensity data comprises the steps of:
set up D dimension random observation variable x= (x) 1 ,x 2 ,...x D ) T The introduction of the hidden variable z, which is a set of discrete random variables, represents the gaussian distribution (C 1 ,C 2 ,...C k ) The gaussian mixture model expression comprising K components is as follows:
wherein: k is the number of single Gaussian models in the Gaussian mixture model, alpha k Weighting K Gaussian models in a Gaussian mixture model, N (x|Θ) k ) As a probability density function of sample x in the Kth Gaussian mixture model, Θ k To include the mean mu k Sum covariance matrix sigma k Is a parameter vector of (a);
obtaining data x i The probability generated by the jth gaussian mixture model is expressed as follows:
and carrying out iterative updating on parameters of the Gaussian mixture model through an EM algorithm until the parameters are converged, wherein the expression of each parameter is as follows:
wherein: x is x i Representing the i-th observed variable, i=1, 2, …, N, K is the number of gaussian models in the mixed model, k=1, 2, …, K, μ j For the mean value of the jth gaussian model Σ j Variance of mean value of jth Gaussian model, α j To observe the probability that a variable belongs to the jth Gaussian model, alpha j ≥0，
5. The method for predicting the life of ship vibration equipment under variable working conditions according to claim 4, wherein the step of obtaining the code of the working condition class in which the equipment is located at the current moment in S2 comprises the following steps:
based on the identification of the log-likelihood estimation method, x belongs to the category in the Gaussian model, and the negative log-likelihood estimation is used as the judgment index because the log-likelihood value is smaller than 0:
NLLP＝-log p(x|Θ))
selecting the Gaussian component with the least negative likelihood as the working condition class code at the moment:
k＝argmin{-log p(x|Θ k )}
wherein: x is acceleration data at the current moment, k is the working condition category to which the variable at the current moment belongs, and Θ k To include the mean mu k Sum covariance matrix Σ k P (x|Θ) is the probability of variable x given the parameter Θ.
6. A computer-readable storage medium, characterized by: the storage medium includes a stored program, wherein the program, when run, performs the variable operating condition marine vessel vibration equipment life prediction method of any one of claims 1 to 5.
7. An electronic device, characterized in that: a method of predicting the life of a ship vibration device under variable conditions according to any one of claims 1 to 5, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor being operable by the computer program to perform the method of predicting the life of a ship vibration device under variable conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110661544.2A CN113283153B (en) | 2021-06-15 | 2021-06-15 | Ship vibration equipment service life prediction method under variable working conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110661544.2A CN113283153B (en) | 2021-06-15 | 2021-06-15 | Ship vibration equipment service life prediction method under variable working conditions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113283153A CN113283153A (en) | 2021-08-20 |
| CN113283153B true CN113283153B (en) | 2023-08-25 |
Family
ID=77284612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110661544.2A Active CN113283153B (en) | 2021-06-15 | 2021-06-15 | Ship vibration equipment service life prediction method under variable working conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113283153B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114489167B (en) * | 2021-12-17 | 2023-04-18 | 中国船舶重工集团公司第七一九研究所 | Warship rotary mechanical equipment feedforward vibration control system based on supervised learning |
| CN114692302B (en) * | 2022-03-28 | 2023-08-25 | 中南大学 | Fatigue crack detection method and system based on Gaussian mixture model |
| CN114547760B (en) * | 2022-04-27 | 2022-07-01 | 江苏南通冠仟新材料科技有限公司 | High-rise building shock insulation damping life management method based on data design optimization processing |
| CN116842381A (en) * | 2023-06-13 | 2023-10-03 | 青岛哈尔滨工程大学创新发展中心 | Ship motion extremely-short-term prediction model generalization optimization method based on data fusion |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1298511A1 (en) * | 2001-09-27 | 2003-04-02 | Reliance Electric Technologies, LLC | Motorized system integrated control and diagnostics using vibration, pressure, temperature, speed, and/or current analysis |
| CN108108588A (en) * | 2014-12-30 | 2018-06-01 | 江苏理工学院 | A kind of ship conflict method for early warning of Rolling Planning |
| CN111832125A (en) * | 2020-06-18 | 2020-10-27 | 东南大学 | Method for predicting fatigue crack propagation life of metal structure of metallurgical crane |
-
2021
- 2021-06-15 CN CN202110661544.2A patent/CN113283153B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1298511A1 (en) * | 2001-09-27 | 2003-04-02 | Reliance Electric Technologies, LLC | Motorized system integrated control and diagnostics using vibration, pressure, temperature, speed, and/or current analysis |
| CN108108588A (en) * | 2014-12-30 | 2018-06-01 | 江苏理工学院 | A kind of ship conflict method for early warning of Rolling Planning |
| CN111832125A (en) * | 2020-06-18 | 2020-10-27 | 东南大学 | Method for predicting fatigue crack propagation life of metal structure of metallurgical crane |
Non-Patent Citations (1)
| Title |
|---|
| 基于HMM-SVR的船舶动力设备故障模式识别与状态预测研究;杨奕飞;冯静;;船舶工程(03);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113283153A (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113283153B (en) | Ship vibration equipment service life prediction method under variable working conditions | |
| EP3680639A1 (en) | Abnormal sound detecting device, abnormality model learning device, abnormality detecting device, abnormal sound detecting method, abnormal sound generating device, abnormal data generating device, abnormal sound generating method, and program | |
| CN111199270B (en) | Regional wave height forecasting method and terminal based on deep learning | |
| CN107316046A (en) | A kind of method for diagnosing faults that Dynamic adaptiveenhancement is compensated based on increment | |
| CN115060497B (en) | Bearing fault diagnosis method based on CEEMD energy entropy and optimized PNN | |
| CN108805142A (en) | A kind of crime high-risk personnel analysis method and system | |
| CN110175541B (en) | Method for extracting sea level change nonlinear trend | |
| CN113239624A (en) | Short-term load prediction method, equipment and medium based on neural network combination model | |
| CN109623489B (en) | Improved machine tool health state evaluation method and numerical control machine tool | |
| CN114282571B (en) | Method, system, equipment and medium for constructing multidimensional health index of bearing | |
| CN113314144A (en) | Voice recognition and power equipment fault early warning method, system, terminal and medium | |
| CN112200114A (en) | Fault diagnosis model training method and device, electronic equipment and storage medium | |
| CN111753751A (en) | Fan fault intelligent diagnosis method for improving firework algorithm | |
| CN111383217A (en) | Visualization method, device and medium for evaluation of brain addiction traits | |
| CN116720101A (en) | On-line intelligent monitoring method and device for propeller faults of underwater propeller | |
| Zhou et al. | On the use of hidden Markov modeling and time-frequency features for damage classification in composite structures | |
| CN116152146A (en) | Cast aluminum cylinder cover mechanical property prediction method based on GAN and CNN | |
| CN115409050A (en) | Bearing fault diagnosis method, device and system | |
| CN115186574A (en) | Tool residual life prediction method based on gated cyclic residual error network | |
| Chen et al. | A New Approach for Power Signal Disturbances Classification Using Deep Convolutional Neural Networks | |
| Shin et al. | Markov chain-based mass estimation method for loose part monitoring system and its performance | |
| CN114061956A (en) | Rolling bearing composite fault feature separation method under strong noise interference | |
| CN113159419A (en) | Group feature portrait analysis method, device and equipment and readable storage medium | |
| CN107608333B (en) | A kind of diagnosticability appraisal procedure based on equivalent depression of order | |
| CN112200546A (en) | Intelligent government examination and approval screening method based on bayes cross model |
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 |