CN113610387B - Equipment service performance degradation evaluation method and system based on global spectrum feature fusion - Google Patents
Equipment service performance degradation evaluation method and system based on global spectrum feature fusion Download PDFInfo
- Publication number
- CN113610387B CN113610387B CN202110887378.8A CN202110887378A CN113610387B CN 113610387 B CN113610387 B CN 113610387B CN 202110887378 A CN202110887378 A CN 202110887378A CN 113610387 B CN113610387 B CN 113610387B
- Authority
- CN
- China
- Prior art keywords
- data file
- equipment
- amplitude
- ith
- representing
- 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
- 238000006731 degradation reaction Methods 0.000 title claims abstract description 83
- 230000015556 catabolic process Effects 0.000 title claims abstract description 82
- 238000001228 spectrum Methods 0.000 title claims abstract description 57
- 230000004927 fusion Effects 0.000 title claims abstract description 18
- 238000011156 evaluation Methods 0.000 title claims description 24
- 230000036541 health Effects 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 230000003595 spectral effect Effects 0.000 claims description 49
- 239000011159 matrix material Substances 0.000 claims description 25
- 238000005457 optimization Methods 0.000 claims description 19
- 238000005070 sampling Methods 0.000 claims description 9
- 238000013210 evaluation model Methods 0.000 claims description 5
- 238000011002 quantification Methods 0.000 claims description 4
- 230000003121 nonmonotonic effect Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000005315 distribution function Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/141—Discrete Fourier transforms
- G06F17/142—Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Pure & Applied Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Discrete Mathematics (AREA)
- Algebra (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a method and a system for evaluating equipment service performance degradation based on global spectrum feature fusion. According to the method, the global spectrum feature fusion strategy is adopted, the feature is extracted and screened without relying on expert knowledge, the spectrum feature is automatically screened, manual intervention is not needed, and the on-line equipment health detection and service performance degradation assessment are facilitated. By simultaneously considering the three-source characteristics of service performance degradation modeling to construct a performance degradation model, the health index can be simultaneously used for the tasks of early fault detection, monotonic degradation assessment and residual life prediction of equipment.
Description
Technical Field
The invention relates to the field of equipment service performance evaluation, in particular to an equipment service performance degradation evaluation method and system based on global spectrum feature fusion.
Background
The equipment service performance degradation assessment aims at collecting state data of equipment to monitor, assess and manage machine health states. Early fault monitoring and monotonic degradation assessment are two important tasks of equipment service performance degradation assessment. One of the most commonly used strategies at present is to construct a health index that characterizes and tracks the degradation process of the device to achieve a degradation assessment of the device's service performance. Because of the randomness of the equipment degradation track and the process, the influence of measurement uncertainty and environmental noise brings great challenges to the equipment service performance degradation evaluation.
In the chinese patent document with publication number CN107908864a, a method for predicting the residual life of complex equipment based on feature fusion is disclosed, and the method can accurately predict the residual life of equipment, but needs to manually extract features and screen features, and does not realize early fault monitoring of health index.
In chinese patent document with publication number CN110851980B, a method and system for predicting remaining lifetime of equipment are disclosed, the method comprising: establishing a device degradation mathematical model based on a nonlinear diffusion process; acquiring an estimated value of equipment degradation parameters under acceleration stress, wherein the estimated value is first data; calculating a degradation parameter value under normal working stress according to the first data to obtain second data; determining the distribution type of the second data through a fitting goodness test; obtaining a 2 nd page posterior distribution function and an expected value of the second data according to the distribution type of the second data; obtaining a first residual life probability density function according to the posterior distribution function, the expected value and the equipment degradation mathematical model; correcting the first residual life probability density function according to the full probability formula to obtain a second residual life probability density function; predicting the remaining life of the device according to the second remaining life probability density function. However, the parameters in this patent document need to be determined empirically by industry standards and expert experience, and require manual intervention.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a device service performance degradation evaluation method and system based on global spectrum feature fusion.
The invention provides a device service performance degradation evaluation method based on global spectrum feature fusion, which comprises the following steps:
step S1: obtaining time domain vibration data of a plurality of devices of the same type from normal operation to failure state;
step S2: converting the acquired time domain vibration data file into a frequency domain frequency spectrum amplitude based on fast Fourier transform;
step S3: defining a specific mathematical expression of a health index for equipment service performance degradation assessment;
step S4: constructing an equipment service performance degradation evaluation model for determining global spectrum characteristic amplitude weight;
step S5: according to step S3 and step S4, a health index of the device is calculated.
PreferablyIn step S1, the time domain vibration data is sequenced according to sampling time, and n is collected by the ith equipment i The number of vibration data files, i=1, 2 …, M and M are the number of devices, each data file contains M sampling points, and a data matrix acquired by the ith device is represented as follows:
wherein,representing collection of a data set from an ith device; x is x i,j,· ∈R 1×M Representing the collection of the jth data file from the ith device, j=1, 2, …, n i ；x i,j,k Representing the kth sample point in the jth data file acquired from the ith device, k=1, 2, …, M.
Preferably, in the step S2, spectrum amplitude data obtained by the ith device is expressed as follows:
wherein,representing a spectral amplitude matrix of the ith device; i f i,j,· I represents the spectral amplitude converted from the jth data file of the ith device, j=1, 2, …, n i ；f i,j,k Representing the spectral amplitude at the kth frequency from the jth data file of the ith device, k=1, 2, …, M; since the spectrum amplitude obtained by each data file is symmetrical, only the first half of the spectrum amplitude of each data file is taken as the input of the model, and therefore, the spectrum amplitude data finally obtained by the ith equipment is expressed as follows:
wherein s=m/2 when M is even; when M is an odd number, s= (m+1)/2.
Preferably, in the step S3, the health index of the ith device in the jth data file is calculated as follows:
wherein w is k A weight representing the magnitude of the spectrum at the kth frequency in the jth data file of the ith device, the health index at each data file being equal to the weighted sum of the global spectral feature magnitudes.
Preferably, the step S4 includes the following substeps:
step S4.1: constructing a monotone characteristic of the quantized health index of the optimization model according to the monotone degradation characteristic of the service performance of the equipment;
step S4.2: according to the uncertain characteristics of the early failure time of the equipment, constructing an optimization model to quantify the early failure detection characteristics of the health index;
step S4.3: constructing an optimization model quantification health index degradation track according to the random characteristics of the equipment degradation track;
step S4.4: according to the step S4.1, the step S4.2 and the step S4.3, constructing a performance degradation model considering the health index three-source characteristic of equipment service performance degradation evaluation;
step S4.5: and (4) solving a weight vector of the frequency spectrum amplitude according to the service performance degradation model considering the three-source characteristic in the step (S4.4).
The invention provides a device service performance degradation evaluation system based on global spectrum feature fusion, which comprises the following modules:
module M1: obtaining time domain vibration data of a plurality of devices of the same type from normal operation to failure state;
module M2: converting the acquired time domain vibration data file into a frequency domain frequency spectrum amplitude based on fast Fourier transform;
module M3: defining a specific mathematical expression of a health index for equipment service performance degradation assessment;
module M4: constructing an equipment service performance degradation evaluation model for determining global spectrum characteristic amplitude weight;
module M5: using the results in modules M3 and M4, a health index of the device is calculated.
Preferably, the time domain vibration data in the module M1 are ordered according to sampling time, and the ith equipment collects n i The number of vibration data files, i=1, 2 …, M and M are the number of devices, each data file contains M sampling points, and a data matrix acquired by the ith device is represented as follows:
wherein,representing collection of a data set from an ith device; x is x i,j,· ∈R 1×M Representing the collection of the jth data file from the ith device, j=1, 2, …, n i ；x i,j,k Representing the kth sample point in the jth data file acquired from the ith device, k=1, 2, …, M.
Preferably, in the module M2, the spectrum amplitude data obtained by the ith device is represented as follows:
wherein,representing a spectral amplitude matrix of the ith device; i f i,j,· I represents the spectral amplitude converted from the jth data file of the ith device, j=1, 2, …, n i ；f i,j,k Representing the spectral amplitude at the kth frequency from the jth data file of the ith device, k=1, 2, …, M; the spectral amplitude due to each data fileSymmetrical, only the first half of the spectral amplitude of each data file is taken as the input of the model, so the final spectral amplitude data obtained by the ith device is represented as follows:
wherein s=m/2 when M is even; when M is an odd number, s= (m+1)/2.
Preferably, the health index of the ith device in the module M3 in the jth data file is calculated as follows:
wherein w is k A weight representing the magnitude of the spectrum at the kth frequency in the jth data file of the ith device, the health index at each data file being equal to the weighted sum of the global spectral feature magnitudes.
Preferably, the module M4 comprises the following sub-modules:
module M4.1: constructing a monotone characteristic of the quantized health index of the optimization model according to the monotone degradation characteristic of the service performance of the equipment;
module M4.2: according to the uncertain characteristics of the early failure time of the equipment, constructing an optimization model to quantify the early failure detection characteristics of the health index;
module M4.3: constructing an optimization model quantification health index degradation track according to the random characteristics of the equipment degradation track;
module M4.4: according to the results of the module M4.1, the module M4.2 and the module M4.3, constructing a performance degradation model considering the health index three-source characteristic of equipment service performance degradation evaluation;
module M4.5: and solving a weight vector of the frequency spectrum amplitude according to the service performance degradation model considering the three-source characteristic in the module M4.4.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, by adopting a strategy of global spectrum feature fusion, the feature is extracted and screened without relying on expert knowledge, so that the automatic spectrum feature screening is realized;
2. according to the invention, manual intervention is not needed, and the on-line equipment health detection and service performance degradation evaluation can be realized;
3. according to the invention, the performance degradation model is constructed by simultaneously considering the three-source characteristic of service performance degradation modeling, so that the health index can be simultaneously used for the tasks of early fault detection, monotonic degradation evaluation and residual life prediction of equipment.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a flowchart of an equipment service performance degradation evaluation method based on global spectral feature fusion in an embodiment of the invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present invention.
The invention provides a device service performance degradation evaluation method based on global spectrum feature fusion, which specifically comprises the following steps as shown in fig. 1:
step S1: obtaining time domain vibration data of m devices of the same type from normal operation to failure state, sequencing according to sampling time, and collecting n by the ith device i And a plurality of vibration data files, each data file containing M sampling points. The data matrix collected by the i (i=1, 2 …, m) th station apparatus is expressed as follows:
wherein the method comprises the steps of，Representing collection of a data set from an ith device; x is x i,j,· ∈R 1×M Representing the collection of the jth data file from the ith device, j=1, 2, …, n i ；x i,j,k Representing the kth sample point in the jth data file acquired from the ith device, k=1, 2, …, M.
Step S2: the spectral amplitude values from the acquired time domain vibration data file are converted to the frequency domain based on a fast fourier transform. Spectral amplitude data obtained by the i (i=1, 2 …, m) th station apparatus is expressed as follows:
wherein,representing a spectral amplitude matrix of the ith device; i f i,j,· I represents the spectral amplitude converted from the jth data file of the ith device, j=1, 2, …, n i ；f i,j,k Representing the spectral amplitude at the kth frequency from the jth data file of the ith device, k=1, 2, …, M. Since the spectral amplitude obtained for each data file is symmetrical, only the first half of the spectral amplitude of each data file is taken as input to the model. Thus, the spectrum amplitude data finally obtained by the i (i=1, 2 …, m) th station apparatus is expressed as follows:
wherein s=m/2 when M is even; when M is an odd number, s= (m+1)/2.
Step S3: defining a specific mathematical expression of the health index for equipment service performance degradation evaluation, and calculating the health index of the ith equipment in the jth data file as follows:
wherein w is k A weight representing the magnitude of the spectrum at the kth frequency in the jth data file of the ith device. From the definition, the health index at each data file is equal to the weighted sum of the global spectral feature magnitudes.
Step S4: constructing an equipment service performance degradation evaluation model for determining global spectral feature amplitude weight, and constructing an equipment performance degradation model based on mathematical optimization by considering the health index three-source characteristic of equipment service performance degradation evaluation.
Step S4.1: aiming at the monotonic degradation characteristic of the service performance of the equipment, the monotonic characteristic of the quantized health index of the following optimization model is constructed:
s.t.w′Μ′1＝r,Mw≥0，D i ω i ≥0,
ε i,j ≥0,i＝1,…,m,j＝1,…,n i
wherein m, n i And s is the number of the same type of equipment, the total number of the data files of the ith equipment and the number of the frequency spectrum amplitude contained in each data file respectively;
ε i,j representing a non-monotonically increasing difference in the health index at the jth data file of the ith device,
w' represents the transpose of the weight vector w of spectral magnitudes;
m' represents the transpose of the diagonal matrix M;
1 represents an all 1 vector, i.e. all vector elements are 1;
c i,j is the weighting coefficient of the non-monotonic quantity of the i-th equipment health index, which obeys the arithmetic progression;w∈R s×1 is a weight vector of spectral magnitudes; w (w) k The kth element representing w is the weight of the amplitude at the kth frequency; m epsilon R s×s Is a diagonal matrix representing the trend of amplitude over time at each frequency, e.g., if the spectral amplitude at a particular frequency has a trend of increasing or decreasing over time, then the corresponding diagonal element is 1 or-1. r is the sum of the weights of the global spectral feature magnitudes.Is a variable of the optimization model. />A spectrum difference matrix that is a global frequency feature, having the form:
step S4.2: aiming at the uncertain characteristic of the early failure time of equipment, the early failure detection characteristic of the quantitative health index of the following optimization model is constructed:
obj＝min w w′w
s.t.V i (U i w-C i )≥1,
i＝1,…,m,
given a data setWherein->Is a diagonal tag matrix corresponding to the j-th data file of the i-th device, if the j-th data file of the i-th device is a normal data file, the corresponding tag is-1, otherwise, the corresponding tag is 1; />Is a penalty term; />Is the spectrum amplitude data matrix of the ith device.
Step S4.3: aiming at the random characteristics of the equipment degradation track, the degradation track of the quantitative health index of the following optimization model is constructed:
wherein e i,k,j Is the fitting error of the spectral amplitude at the kth frequency in the jth data file of the ith device to the degradation model, e i,j,l Representing the fitting error, w, of the spectral amplitude at the ith frequency in the jth data file of the ith device to the degradation model l The first element representing w is the weight of the amplitude at the first frequency.
Step S4.4: according to step S4.1, step S4.2 and step S4.3, a performance degradation model can be constructed that considers the health index three-source characteristics of the equipment service performance degradation assessment:
s.t.w′Μ′1＝r,Mw≥0,D i ω i ≥0,V i (U i w-C i )≥1,
ε i,j ≥0,i＝1,…,m,j＝1,…,n i ,k＝1,…,s,l＝1,…,s
where μ and λ are the hyper-parameters of the model, determining the weight magnitude of the three source features of the health index. In practical applications, μ and λ can be set according to different requirements.
Step S4.5: according to the service performance degradation model considering the three-source characteristics in the step 3.4, a weight vector w E R of the frequency spectrum amplitude can be solved s×1 。
Step S5: based on the definition of the health index in step 3 and the weight vector solved in step 3.4, the health index of the device can be calculated. Early fault detection, monotonic degradation assessment and residual life prediction of the device can be achieved simultaneously by using the constructed health index.
Those skilled in the art will appreciate that the invention provides a system and its individual devices, modules, units, etc. that can be implemented entirely by logic programming of method steps, in addition to being implemented as pure computer readable program code, in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Therefore, the system and various devices, modules and units thereof provided by the invention can be regarded as a hardware component, and the devices, modules and units for realizing various functions included in the system can also be regarded as structures in the hardware component; means, modules, and units for implementing the various functions may also be considered as either software modules for implementing the methods or structures within hardware components.
The foregoing describes specific embodiments of the present invention. It is to be understood that the invention is not limited to the particular embodiments described above, and that various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the invention. The embodiments of the present application and features in the embodiments may be combined with each other arbitrarily without conflict.
Claims (6)
1. The equipment service performance degradation evaluation method based on global spectrum feature fusion is characterized by comprising the following steps of:
step S1: obtaining time domain vibration data of a plurality of devices of the same type from normal operation to failure state;
step S2: converting the acquired time domain vibration data file into a frequency domain frequency spectrum amplitude based on fast Fourier transform;
step S3: defining a specific mathematical expression of a health index for equipment service performance degradation assessment;
in the step S3, the health index of the ith device in the jth data file is calculated as follows:
wherein w is k A weight representing the magnitude of the spectrum at the kth frequency in the jth data file of the ith device, the health index at each data file being equal to the weighted sum of the global spectral feature magnitudes, f i,j,k Representing the spectral amplitude at the kth frequency from the jth data file of the ith device, k=1, 2, …, M;
step S4: constructing an equipment service performance degradation evaluation model for determining global spectrum characteristic amplitude weight;
step S5: according to the step S3 and the step S4, calculating the health index of the equipment;
said step S4 comprises the sub-steps of:
step S4.1: constructing a monotone characteristic of the quantized health index of the optimization model according to the monotone degradation characteristic of the service performance of the equipment;
s.t.w′Μ′1＝r,Mw≥0，D i ω i ≥0,
ε i,j ≥0,i＝1,…,m,j＝1,…,n i
wherein m, n i And s is the number of the same type of equipment, the total number of the data files of the ith equipment and the number of the frequency spectrum amplitude contained in each data file respectively;
ε i,j representing a non-monotonically increasing difference in the health index at the jth data file of the ith device,
w' represents the transpose of the weight vector w of spectral magnitudes;
m' represents the transpose of the diagonal matrix M;
1 represents an all 1 vector, i.e. all vector elements are 1;
c i,j is the weighting coefficient of the non-monotonic quantity of the i-th equipment health index, which obeys the arithmetic progression; w is E R s×1 Is a weight vector of spectral magnitudes; w (w) k The kth element representing w is the weight of the amplitude at the kth frequency; m epsilon R s×s Is a diagonal matrix representing the trend of the amplitude at each frequency over time, r is the sum of the weights of the global spectral feature amplitudes;is a variable of the optimization model; />A spectrum difference matrix that is a global frequency feature, having the form:
step S4.2: according to the uncertain characteristics of the early failure time of the equipment, constructing an optimization model to quantify the early failure detection characteristics of the health index;
obj＝min w w′w
s.t.V i (U i w-C i )≥1,
i＝1,…,m,
given a data setWherein->Is a diagonal tag matrix corresponding to the j-th data file of the i-th device, if the j-th data file of the i-th device is a normal data file, the corresponding tag is-1, otherwise, the corresponding tag is 1; />Is a penalty term; />Is the frequency spectrum amplitude data matrix of the ith equipment;
step S4.3: constructing an optimization model quantification health index degradation track according to the random characteristics of the equipment degradation track;
wherein e i,k,j Is the fitting error of the spectral amplitude at the kth frequency in the jth data file of the ith device to the degradation model, e i,j,l Representing the fitting error, w, of the spectral amplitude at the ith frequency in the jth data file of the ith device to the degradation model l The first element representing w is the weight of the amplitude at the first frequency;
step S4.4: according to the step S4.1, the step S4.2 and the step S4.3, constructing a performance degradation model considering the health index three-source characteristic of equipment service performance degradation evaluation;
s.t.w′Μ′1＝r,Mw≥0,D i ω i ≥0,V i (U i w-C i )≥1,
ε i,j ≥0,i＝1,…,m,j＝1,…,n i ,k＝1,…,s,l＝1,…,s
where μ and λ are the hyper-parameters of the model;
step S4.5: according to the service performance degradation model considering the three-source characteristic in the step S4.4, solving a weight vector w E R of the frequency spectrum amplitude s×1 。
2. The equipment service performance degradation evaluation method based on global spectrum feature fusion according to claim 1, wherein the method is characterized by comprising the following steps: sequencing the time domain vibration data in the step S1 according to sampling time, wherein n is collected by the ith equipment i A number of vibration data files, i=1, 2 …, M, M being the number of devices, each data file containing M samplesThe data matrix collected by the ith device is represented as follows:
wherein,representing collection of a data set from an ith device; x is x i,j,· ∈R 1×M Representing the collection of the jth data file from the ith device, j=1, 2, …, n i ；x i,j,k Representing the kth sample point in the jth data file acquired from the ith device, k=1, 2, …, M.
3. The equipment service performance degradation evaluation method based on global spectrum feature fusion according to claim 1, wherein the method is characterized by comprising the following steps: in the step S2, spectrum amplitude data obtained by the ith device is represented as follows:
wherein,representing a spectral amplitude matrix of the ith device; i f i,j,· I represents the spectral amplitude converted from the jth data file of the ith device, j=1, 2, …, n i ；f i,j,k Representing the spectral amplitude at the kth frequency from the jth data file of the ith device, k=1, 2, …, M; since the spectrum amplitude obtained by each data file is symmetrical, only the first half of the spectrum amplitude of each data file is taken as the input of the model, and therefore, the spectrum amplitude data finally obtained by the ith equipment is expressed as follows:
wherein s=m/2 when M is even; when M is an odd number, s= (m+1)/2.
4. The equipment service performance degradation evaluation system based on global spectrum feature fusion is characterized by comprising the following modules:
module M1: obtaining time domain vibration data of a plurality of devices of the same type from normal operation to failure state;
module M2: converting the acquired time domain vibration data file into a frequency domain frequency spectrum amplitude based on fast Fourier transform;
module M3: defining a specific mathematical expression of a health index for equipment service performance degradation assessment;
the health index of the ith device in the module M3 in the jth data file is calculated as follows:
wherein w is k A weight representing the magnitude of the spectrum at the kth frequency in the jth data file of the ith device, the health index at each data file being equal to the weighted sum of the global spectral feature magnitudes, f i,j,k Representing the spectral amplitude at the kth frequency from the jth data file of the ith device, k=1, 2, …, M;
module M4: constructing an equipment service performance degradation evaluation model for determining global spectrum characteristic amplitude weight;
module M5: calculating a health index of the device using the results in modules M3 and M4;
the module M4 comprises the following sub-modules:
module M4.1: constructing a monotone characteristic of the quantized health index of the optimization model according to the monotone degradation characteristic of the service performance of the equipment;
s.t.w′Μ′1＝r,Mw≥0，D i ω i ≥0,
ε i,j ≥0,i＝1,…,m,j＝1,…,n i
wherein m, n i And s is the number of the same type of equipment, the total number of the data files of the ith equipment and the number of the frequency spectrum amplitude contained in each data file respectively;
ε i,j representing a non-monotonically increasing difference in the health index at the jth data file of the ith device,
w' represents the transpose of the weight vector w of spectral magnitudes;
m' represents the transpose of the diagonal matrix M;
1 represents an all 1 vector, i.e. all vector elements are 1;
c i,j is the weighting coefficient of the non-monotonic quantity of the i-th equipment health index, which obeys the arithmetic progression; w is E R s×1 Is a weight vector of spectral magnitudes; w (w) k The kth element representing w is the weight of the amplitude at the kth frequency; m epsilon R s×s Is a diagonal matrix representing the trend of the amplitude at each frequency over time, r is the sum of the weights of the global spectral feature amplitudes;is a variable of the optimization model; />A spectrum difference matrix that is a global frequency feature, having the form:
module M4.2: according to the uncertain characteristics of the early failure time of the equipment, constructing an optimization model to quantify the early failure detection characteristics of the health index;
obj＝min w w′w
s.t.V i (U i w-C i )≥1,
i＝1,…,m,
given a data setWherein->Is a diagonal tag matrix corresponding to the j-th data file of the i-th device, if the j-th data file of the i-th device is a normal data file, the corresponding tag is-1, otherwise, the corresponding tag is 1; />Is a penalty term; />Is the frequency spectrum amplitude data matrix of the ith equipment;
module M4.3: constructing an optimization model quantification health index degradation track according to the random characteristics of the equipment degradation track;
wherein e i,k,j Is the fitting error of the spectral amplitude at the kth frequency in the jth data file of the ith device to the degradation model, e i,j,l Representing the fitting error, w, of the spectral amplitude at the ith frequency in the jth data file of the ith device to the degradation model l The first element representing w is the weight of the amplitude at the first frequency;
module M4.4: according to the module M4.1, the module M4.2 and the module M4.3, constructing a performance degradation model considering the health index three-source characteristic of equipment service performance degradation evaluation;
s.t.w′Μ′1＝r,Mw≥0,D i ω i ≥0,V i (U i w-C i )≥1,
ε i,j ≥0,i＝1,…,m,j＝1,…,n i ,k＝1,…,s,l＝1,…,s
where μ and λ are the hyper-parameters of the model;
module M4.5: according to the service performance degradation model considering the three-source characteristic in the module M4.4, solving a weight vector w E R of the frequency spectrum amplitude s×1 。
5. The equipment service performance degradation evaluation system based on global spectral feature fusion according to claim 4, wherein: ordering the time domain vibration data in the module M1 according to sampling time, wherein n is collected by the ith equipment i The number of vibration data files, i=1, 2 …, M and M are the number of devices, each data file contains M sampling points, and a data matrix acquired by the ith device is represented as follows:
wherein,representing collection of a data set from an ith device; x is x i,j,· ∈R 1×M Representing the collection of the jth data file from the ith device, j=1, 2, …, n i ；x i,j,k Representing the kth sample point in the jth data file acquired from the ith device, k=1, 2, …, M.
6. The equipment service performance degradation evaluation system based on global spectral feature fusion according to claim 4, wherein: in the module M2, spectrum amplitude data obtained by the ith device is represented as follows:
wherein,representing a spectral amplitude matrix of the ith device; i f i,j,· I represents the spectral amplitude converted from the jth data file of the ith device, j=1, 2, …, n i ；f i,j,k Representing the spectral amplitude at the kth frequency from the jth data file of the ith device, k=1, 2, …, M; since the spectrum amplitude obtained by each data file is symmetrical, only the first half of the spectrum amplitude of each data file is taken as the input of the model, and therefore, the spectrum amplitude data finally obtained by the ith equipment is expressed as follows:
wherein s=m/2 when M is even; when M is an odd number, s= (m+1)/2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110887378.8A CN113610387B (en) | 2021-08-03 | 2021-08-03 | Equipment service performance degradation evaluation method and system based on global spectrum feature fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110887378.8A CN113610387B (en) | 2021-08-03 | 2021-08-03 | Equipment service performance degradation evaluation method and system based on global spectrum feature fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113610387A CN113610387A (en) | 2021-11-05 |
| CN113610387B true CN113610387B (en) | 2024-04-09 |
Family
ID=78306649
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110887378.8A Active CN113610387B (en) | 2021-08-03 | 2021-08-03 | Equipment service performance degradation evaluation method and system based on global spectrum feature fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610387B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908864A (en) * | 2017-11-14 | 2018-04-13 | 中国科学院空间应用工程与技术中心 | A kind of complex device remaining life Forecasting Methodology of feature based fusion |
| CN110851980A (en) * | 2019-11-11 | 2020-02-28 | 中国人民解放军火箭军工程大学 | Method and system for predicting residual life of equipment |
| CN112182912A (en) * | 2020-10-27 | 2021-01-05 | 南京航空航天大学 | Manufacturing equipment main shaft bearing health assessment method based on probability description and spectrum analysis |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8103463B2 (en) * | 2006-09-21 | 2012-01-24 | Impact Technologies, Llc | Systems and methods for predicting failure of electronic systems and assessing level of degradation and remaining useful life |
| US11042145B2 (en) * | 2018-06-13 | 2021-06-22 | Hitachi, Ltd. | Automatic health indicator learning using reinforcement learning for predictive maintenance |
-
2021
- 2021-08-03 CN CN202110887378.8A patent/CN113610387B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908864A (en) * | 2017-11-14 | 2018-04-13 | 中国科学院空间应用工程与技术中心 | A kind of complex device remaining life Forecasting Methodology of feature based fusion |
| CN110851980A (en) * | 2019-11-11 | 2020-02-28 | 中国人民解放军火箭军工程大学 | Method and system for predicting residual life of equipment |
| CN112182912A (en) * | 2020-10-27 | 2021-01-05 | 南京航空航天大学 | Manufacturing equipment main shaft bearing health assessment method based on probability description and spectrum analysis |
Non-Patent Citations (1)
| Title |
|---|
| Tongtong Yan等.《Mechanical Systems and Signal Processing》.2021,第1-20页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113610387A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117495210B (en) | Highway concrete construction quality management system | |
| Entezami et al. | Structural health monitoring by a new hybrid feature extraction and dynamic time warping methods under ambient vibration and non-stationary signals | |
| CN111310981B (en) | Reservoir water level trend prediction method based on time series | |
| Alqahtani et al. | Artificial neural networks incorporating cost significant items towards enhancing estimation for (life-cycle) costing of construction projects | |
| Ni et al. | Strain monitoring based bridge reliability assessment using parametric Bayesian mixture model | |
| Pachauri et al. | Modeling optimal release policy under fuzzy paradigm in imperfect debugging environment | |
| CN111143981A (en) | Virtual test model verification system and method | |
| CN107679756B (en) | Soil suitability evaluation method and device | |
| JP2009086896A (en) | Failure prediction system and failure prediction method for computer | |
| Isaev et al. | Application of time series analysis for structural and parametric identification of fuzzy cognitive models | |
| CN115618269A (en) | Big data analysis method and system based on industrial sensor production | |
| CN104022899A (en) | Three-dimensional assessment method for network management system and system | |
| Soofi et al. | Output-only entropy-based damage detection using transmissibility function | |
| Silik et al. | Dynamic wavelet neural network model for damage features extraction and patterns recognition | |
| CN113610387B (en) | Equipment service performance degradation evaluation method and system based on global spectrum feature fusion | |
| CN113505980A (en) | Reliability evaluation method, device and system for intelligent traffic management system | |
| CN111158918B (en) | Supporting point parallel enumeration load balancing method, device, equipment and medium | |
| CN112580254A (en) | Multi-dimensional analysis and early warning method for converter transformer based on multi-level decision fusion | |
| Kim et al. | A study toward appropriate architecture of system-level prognostics: physics-based and data-driven approaches | |
| CN114528707A (en) | Equipment performance degradation evaluation method and system based on sparse degradation modeling | |
| CN115860263A (en) | Power grid infrastructure planning project construction period prediction method and prediction system | |
| Vachtsevanos | Corrosion diagnostic and prognostic technologies | |
| CN111160419B (en) | Deep learning-based electronic transformer data classification prediction method and device | |
| Cheraghzade et al. | Incorporating Uncertainty in Mechanics-Based Synthetic Data Generation for Deep Learning–Based Structural Monitoring | |
| CN117035559B (en) | Electrical equipment multi-parameter transmitter simulation installation evaluation method and system |
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 |