CN113688904B - Method for extracting dynamic characteristic parameters of intelligent ship system equipment - Google Patents
Method for extracting dynamic characteristic parameters of intelligent ship system equipment Download PDFInfo
- Publication number
- CN113688904B CN113688904B CN202110976013.2A CN202110976013A CN113688904B CN 113688904 B CN113688904 B CN 113688904B CN 202110976013 A CN202110976013 A CN 202110976013A CN 113688904 B CN113688904 B CN 113688904B
- Authority
- CN
- China
- Prior art keywords
- data
- matrix
- calculating
- value
- characteristic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims abstract description 65
- 238000004364 calculation method Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 238000000513 principal component analysis Methods 0.000 claims abstract description 6
- 238000013507 mapping Methods 0.000 claims description 24
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000003416 augmentation Effects 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000009467 reduction Effects 0.000 abstract description 4
- 230000036541 health Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- 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 method for extracting dynamic characteristic parameters of intelligent ship system equipment. The method of the invention comprises the following steps: processing the original data by utilizing a dynamic fractal theory, and constructing an optimal time-lag matrix; performing kernel principal component analysis on the constructed optimal time-lag matrix, calculating a centralized matrix, and screening data by using characteristic values; and analyzing and calculating the centralization matrix, calculating to obtain the numerical value of the principal component characteristic parameter by using a fractal theory, and constructing the principal component characteristic parameter matrix. According to the characteristic that the system equipment operates in different time and different states, the dynamic characteristic parameter information of the equipment can be screened and extracted, and the whole health state of the system can be evaluated by using the selected principal element characteristic data. According to the method, the dimension reduction processing is carried out on the multi-parameter data of the system equipment, the calculation of redundant data is reduced, meanwhile, the timeliness and the effectiveness of equipment monitoring can be guaranteed through dynamic feature extraction, and the intelligent operation and maintenance efficiency of the system equipment is improved.
Description
Technical Field
The invention relates to the technical field of intelligent ships, in particular to a method for extracting dynamic characteristic parameters of intelligent ship system equipment.
Background
With the further development of modern intelligent sensing, the internet of things and big data technology, the intelligent and autonomous degree of ships is gradually improved, ship systems and equipment can provide richer state information, measured data volume can be expanded rapidly, data types become more diversified, and how to realize health management of mechanical equipment by using detection data and related knowledge information is a problem that needs to be mainly solved in current intelligent operation and maintenance of ships. The ship system equipment has the characteristics of multiple perception variables, multiple working modes and non-unique fault modes, and usually lacks dominant characteristic parameters. Meanwhile, due to the influence of external factors, such as wind, wave and current, working environment and the like; the values of the dominant characteristic parameters also change under the combined action of intrinsic factors, such as the operating conditions and maintenance conditions of the ship system equipment.
At present, the selection of the characteristic values has the methods of corresponding principal component analysis, linear discriminant analysis, recursive characteristic elimination and the like. Principal component analysis is to convert a set of variables that may have correlation into a set of linearly uncorrelated variables by direct-to-alternating conversion, and the converted set of variables become principal components of the data. The linear discriminant analysis method utilizes dimension reduction processing to realize screening of data principal components. The recursive feature elimination method is to eliminate feature values smaller than the assigned weight through continuous recursion, and to circularly recursion until the number of the feature values reaches a certain degree. The method still has the defect of extracting the characteristics of dynamic nonlinear data, and is difficult to meet the analysis requirement of multi-parameter data of ship system equipment.
Disclosure of Invention
According to the technical problems, the method for extracting the dynamic characteristic parameters of the intelligent ship system equipment is provided. The invention can select the dynamic characteristic parameter information of the equipment according to the characteristics of the system equipment running at different times and under different states, and can evaluate the whole health state of the system by using the selected principal component characteristic parameters. According to the method, the dimension reduction processing is carried out on the multi-parameter data of the system equipment, the calculation of redundant data is reduced, meanwhile, the timeliness and the effectiveness of equipment monitoring can be guaranteed through dynamic feature extraction, and the intelligent operation and maintenance efficiency of the system equipment is improved.
The invention adopts the following technical means:
a method for extracting dynamic characteristic parameters of intelligent ship system equipment comprises the following steps:
s1, processing original data by utilizing a dynamic fractal theory, and constructing an optimal time-lag matrix;
s2, performing kernel principal component analysis on the constructed optimal time-lag matrix to obtain a mapping matrix, and solving eigenvalues and eigenvectors of a covariance matrix of the mapping matrix;
s3, analyzing and calculating the screened matrix, calculating to obtain the numerical value of the principal component characteristic parameter by using a fractal theory, and constructing a principal component characteristic parameter matrix.
Further, the specific implementation process of the step S1 is as follows:
s11, acquiring state data of a detected ship system and equipment through a ship monitor and a sensor, and taking the state data as a sample XE R N×m ;
S12, carrying out standardized processing on the data in the sample X, converting each column of monitoring element data into dimensionless evaluation values, wherein all index values are in the same magnitude, and calculating the selected state data by using the following formula:
wherein x represents standardized data; x is x i Data representing each column;mean value of each column of data; s represents the variance of each column of data; n represents the dimension of each column of input data row;
s13, assuming that the initial value of the hysteresis time l is 0, calculating the correlation dimension CDim when l=0 by using a fractal theory formula, wherein the calculation formula of the correlation dimension is as follows:
wherein N represents the number of measurements; delta ij Euclidean representing row and row state vectors within a data matrixA distance; distance parameter epsilon and delta ij In relation, H represents a step function, satisfyingCD (epsilon) and epsilon follow CD (epsilon) -epsilon as epsilon values become smaller CDim The relation, taking logarithm to both sides at the same time, obtains the association dimension as follows:
s14, carrying the calculated correlation dimension CDim into the following formula to calculate and obtain a circulation function r n Is a value of (2);
s15, sequentially selecting different values of hysteresis time l, and repeatedly executing the steps S13-S14 until r is obtained n Stopping calculation when the time is less than or equal to 0, selecting the most suitable delay time l, and constructing an augmentation matrix with minimized autocorrelation and cross-correlation of the original data
r=m(l+1)-CDim
Wherein m represents the number of monitoring elements of the fetched data; i is related to the lag time.
Further, the specific implementation process of the step S2 is as follows:
s21, mapping the constructed optimal time-lag data matrix, and calculating to obtain mapping data by using the following formula:
wherein k=1, 2, N, t k For the value of the kth measurement data in the mapping space, p k For mapping features of data covariance matrixVector andfor the weighting factor>For the mapping relationship, K (x i X) is a core matrix after centering, lambda k Is the characteristic value thereof;
s22, screening the characteristic values by using the following formula; the formula is as follows:
λ p ≥ε,p=1,2,3,...,N
wherein epsilon is determined according to the actual situation, and the data matrix is calculated by using the calculated eigenvector pN D =N-l;λ p Feature vectors representing covariance matrices of the mapping data; p represents the final value of data screening; n represents the input data row dimension; t (T) p Representing a data matrix; n (N) D Representing the reconstructed sample data row dimension.
Further, the specific implementation process of the step S3 is as follows:
s31, utilizing a fractal theory formula to perform a fractal theory on the data matrix T obtained in the step S22 p Analysis is carried out, and corresponding association dimension CDim (T p ) Is marked as
S32, calculating a data matrix tau by using the following formula, analyzing the data matrix tau by using a fractal theory formula, calculating to obtain a corresponding correlation dimension CDim (tau), and recording as d τ The method comprises the steps of carrying out a first treatment on the surface of the Wherein, the formula is as follows:
τ=T p A
wherein A represents an orthogonal matrix composed of eigenvectors of a covariance matrix, and is obtained through singular value decomposition calculation;
s33, willAnd d τ Comparing and analyzing, namely taking the maximum value of the two values, and taking the maximum value as an integer, and taking the maximum value to be rounded upwards to obtain a principal element characteristic state parameter value gamma, so as to construct a principal element characteristic data matrix +_>
Compared with the prior art, the invention has the following advantages:
1. according to the intelligent ship system equipment dynamic characteristic parameter extraction method, the kernel function is used for carrying out mapping dimension reduction processing on the measured multi-source heterogeneous high-dimensional data, so that accurate extraction of a ship system dynamic nonlinear complex data principal element sequence is realized, a principal element characteristic matrix is constructed, analysis and calculation on redundant information in original data are reduced, and the operation calculation efficiency of a machine is improved.
2. The method for extracting the dynamic characteristic parameters of the intelligent ship system equipment provided by the invention utilizes the extracted principal component characteristic parameters to carry out corresponding analysis, can objectively, accurately and comprehensively describe the healthy running state of the system, provides more reliable basis for the judgment of the ship system state by staff, and is beneficial to promoting the development and progress of intelligent and unmanned management of ships.
Based on the reasons, the invention can be widely popularized in the fields of intelligent ships and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
As shown in fig. 1, the invention provides a method for extracting dynamic characteristic parameters of intelligent ship system equipment, which comprises the following steps:
s1, processing original data by utilizing a dynamic fractal theory, and constructing an optimal time-lag matrix;
s2, performing kernel principal component analysis on the constructed optimal time-lag matrix to obtain a mapping matrix, and solving eigenvalues and eigenvectors of a covariance matrix of the mapping matrix;
s3, analyzing and calculating the screened matrix, calculating to obtain the numerical value of the principal component characteristic parameter by using a fractal theory, and constructing a principal component characteristic parameter matrix.
In the specific implementation, as a preferred embodiment of the present invention, an optimal time lag matrix is constructed, and first, it is necessary to acquire a detected ship system and equipment by a monitor and a sensor of a shipThe state data of the backup is taken as a sample X epsilon R N×m The data in X is standardized, the data are converted into dimensionless evaluation values, all index values are in the same magnitude, and further, calculation and analysis are carried out on the reconstructed data matrix by utilizing fractal theory and dynamic theory, so that the optimal reconstruction lag time l is obtained opt The data autocorrelation and the cross correlation among different principal components are reduced, and an optimal time-lag matrix is obtained so as to analyze the whole. The specific implementation process of the step S1 is as follows:
s11, acquiring state data of a detected ship system and equipment through a ship monitor and a sensor, and taking the state data as a sample XE R N×m ;
S12, carrying out standardized processing on the data in the sample X, converting each column of monitoring element data into dimensionless evaluation values, wherein all index values are in the same magnitude, and calculating the selected state data by using the following formula:
wherein x represents standardized data; x is x i Data representing each column;mean value of each column of data; s represents the variance of each column of data; n represents the dimension of each column of input data row;
s13, assuming that the initial value of the hysteresis time l is 0, calculating the correlation dimension CDim when l=0 by using a fractal theory formula, wherein the calculation formula of the correlation dimension is as follows:
wherein N represents the number of measurements; delta ij Euclidean distance of the row and the row state vector in the data matrix is represented; distance parameter epsilon and delta ij In relation, H represents a step function, satisfyingCD (epsilon) and epsilon follow CD (epsilon) -epsilon as epsilon values become smaller CDim The relation, taking logarithm to both sides at the same time, obtains the association dimension as follows:
s14, carrying the calculated correlation dimension CDim into the following formula to calculate and obtain a circulation function r n Is a value of (2);
s15, sequentially selecting different values of hysteresis time l, and repeatedly executing the steps S13-S14 until r is obtained n Stopping calculation when the temperature is less than or equal to 0, and selecting the most suitable hysteresis time l (CDim is generally selected to tend to be constant and r n Less than or equal to 0.3, if not, r is taken n Lag time l) at 0 or less, and constructing an augmentation matrix with minimized autocorrelation and cross-correlation of the original data
r=m(l+1)-CDim
Wherein m represents the number of monitoring elements of the fetched data; i is related to the lag time. In specific implementation, as a preferred embodiment of the present invention, the specific implementation procedure of the step S2 is as follows:
s21, mapping the constructed optimal time-lag data matrix, and calculating to obtain mapping data by using the following formula:
wherein k=1, 2, N, t k For the value of the kth measurement data in the mapping space, p k To map data covariance momentEigenvector of array andfor the weighting factor>For the mapping relationship, K (x i X) is a core matrix after centering, lambda k Is the characteristic value thereof;
s22, screening the characteristic values by using the following formula; the formula is as follows:
λ p ≥ε,p=1,2,3,...,N
wherein epsilon is determined according to the actual situation, and the data matrix is calculated by using the calculated eigenvector pN D =N-l;λ p Feature vectors representing covariance matrices of the mapping data; p represents the final value of data screening; n represents the input data row dimension; t (T) p Representing a data matrix; n (N) D Representing the reconstructed sample data row dimension.
In specific implementation, as a preferred embodiment of the present invention, the specific implementation procedure of the step S3 is as follows:
s31, utilizing a fractal theory formula to perform a fractal theory on the data matrix T obtained in the step S22 p Analysis is carried out, and corresponding association dimension CDim (T p ) Is marked as
S32, calculating a data matrix tau by using the following formula, analyzing the data matrix tau by using a fractal theory formula, calculating to obtain a corresponding correlation dimension CDim (tau), and recording as d τ The method comprises the steps of carrying out a first treatment on the surface of the Wherein, the formula is as follows:
τ=T p A
wherein A represents an orthogonal matrix composed of eigenvectors of a covariance matrix, and is obtained through singular value decomposition calculation;
s33, willAnd d τ Comparing and analyzing, namely taking the maximum value of the two values, and taking the maximum value as an integer, and taking the maximum value to be rounded upwards to obtain a principal element characteristic state parameter value gamma, so as to construct a principal element characteristic data matrix +_>
In conclusion, the fractal theory and the dynamic theory provided by the invention can be used for realizing the dynamic analysis of the original data, so that the autocorrelation among the data and the cross correlation among different principal components are reduced, and the influence of the data dynamic property on an analysis result is reduced. Meanwhile, by utilizing the method provided by the invention, the precise selection of the principal element characteristic elements of the ship system equipment in different running states can be realized, the accurate judgment of the working states of the ship system and the equipment is realized, and meanwhile, the calculation time and the related cost are saved.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (1)
1. The method for extracting the dynamic characteristic parameters of the intelligent ship system equipment is characterized by comprising the following steps of:
s1, processing original data by utilizing a dynamic fractal theory, and constructing an optimal time-lag matrix; the specific implementation process of the step S1 is as follows:
s11, acquiring state data of a detected ship system and equipment through a ship monitor and a sensor, and taking the state data as a sample XE R N×m ;
S12, carrying out standardized processing on the data in the sample X, converting each column of monitoring element data into dimensionless evaluation values, wherein all index values are in the same magnitude, and calculating the selected state data by using the following formula:
wherein x represents standardized data; x is x i Data representing each column;mean value of each column of data; s represents the variance of each column of data; n represents the dimension of each column of input data row;
s13, assuming that the initial value of the hysteresis time l is 0, calculating the correlation dimension CDim when l=0 by using a fractal theory formula, wherein the calculation formula of the correlation dimension is as follows:
wherein N represents the number of measurements; delta ij Euclidean distance of the row and the row state vector in the data matrix is represented; distance parameter epsilon and delta ij In relation, H represents a step function, satisfyingCD (epsilon) and epsilon follow CD (epsilon) -epsilon as epsilon values become smaller CDim The relation, taking logarithm to both sides at the same time, obtains the association dimension as follows:
s14, carrying the calculated correlation dimension CDim into the following formula to calculate and obtain a circulation function r n Is a value of (2);
s15, sequentially selecting different numbersAnd repeatedly executing the steps S13-S14 until the obtained r is equal to the hysteresis time l of the value n Stopping calculation when the time is less than or equal to 0, selecting the most suitable delay time l, and constructing an augmentation matrix with minimized autocorrelation and cross-correlation of the original data
r=m(l+1)-CDim
Wherein m represents the number of monitoring elements of the fetched data; i is related to the lag time;
s2, performing kernel principal component analysis on the constructed optimal time-lag matrix to obtain a mapping matrix, solving eigenvalues and eigenvectors of a covariance matrix of the mapping matrix, and screening data by using the eigenvalues; the specific implementation process of the step S2 is as follows:
s21, mapping the constructed optimal time-lag data matrix, and calculating to obtain mapping data by using the following formula:
wherein k=1, 2, N, t k For the value of the kth measurement data in the mapping space, p k For mapping eigenvectors of data covariance matrix For the weighting factor>For the mapping relationship, K (x i X) is a core matrix after centering, lambda is its characteristicA value;
s22, screening the characteristic values by using the following formula; the formula is as follows:
λ p ≥ε,p=1,2,3,...,N
wherein epsilon is determined according to the actual situation, and the data matrix is calculated by using the calculated eigenvector pN D =N-l;λ p Feature vectors representing covariance matrices of the mapping data; p represents the final value of data screening; n represents the input data row dimension; t (T) p Representing a data matrix; n (N) D Representing a reconstructed sample data row dimension;
s3, analyzing and calculating the screened matrix, calculating to obtain the numerical value of principal component characteristic parameters by using a fractal theory, and constructing a principal component characteristic parameter matrix; the specific implementation process of the step S3 is as follows:
s31, utilizing a fractal theory formula to perform a fractal theory on the data matrix T obtained in the step S22 p Analysis is carried out, and corresponding association dimension CDim (T p ) Is marked as
S32, calculating a data matrix tau by using the following formula, analyzing the data matrix tau by using a fractal theory formula, calculating to obtain a corresponding correlation dimension CDim (tau), and recording as d τ The method comprises the steps of carrying out a first treatment on the surface of the Wherein, the formula is as follows:
τ=T p A
wherein A represents an orthogonal matrix composed of eigenvectors of a covariance matrix, and is obtained through singular value decomposition calculation;
s33, willAnd d τ Comparing and analyzing, taking the maximum value of the two values, and obtaining principal element characteristic state parameter value gamma by upwardly rounding the maximum value because the characteristic element number is an integer, thereby constructing principal element characteristicsData matrix->
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110976013.2A CN113688904B (en) | 2021-08-24 | 2021-08-24 | Method for extracting dynamic characteristic parameters of intelligent ship system equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110976013.2A CN113688904B (en) | 2021-08-24 | 2021-08-24 | Method for extracting dynamic characteristic parameters of intelligent ship system equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113688904A CN113688904A (en) | 2021-11-23 |
CN113688904B true CN113688904B (en) | 2023-08-22 |
Family
ID=78581965
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110976013.2A Active CN113688904B (en) | 2021-08-24 | 2021-08-24 | Method for extracting dynamic characteristic parameters of intelligent ship system equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113688904B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102930294A (en) * | 2012-10-18 | 2013-02-13 | 上海交通大学 | Chaotic characteristic parameter-based motion mode video segmentation and traffic condition identification method |
CN107330454A (en) * | 2017-06-20 | 2017-11-07 | 西安建筑科技大学 | The non-linear visualization of magnanimity higher-dimension sequence data sort feature and quantitative analysis method |
CN107608936A (en) * | 2017-09-22 | 2018-01-19 | 桂林电子科技大学 | A kind of epicyclic gearbox combined failure feature extracting method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140108324A1 (en) * | 2012-10-12 | 2014-04-17 | Nec Laboratories America, Inc. | Data analytic engine towards the self-management of complex physical systems |
-
2021
- 2021-08-24 CN CN202110976013.2A patent/CN113688904B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102930294A (en) * | 2012-10-18 | 2013-02-13 | 上海交通大学 | Chaotic characteristic parameter-based motion mode video segmentation and traffic condition identification method |
CN107330454A (en) * | 2017-06-20 | 2017-11-07 | 西安建筑科技大学 | The non-linear visualization of magnanimity higher-dimension sequence data sort feature and quantitative analysis method |
CN107608936A (en) * | 2017-09-22 | 2018-01-19 | 桂林电子科技大学 | A kind of epicyclic gearbox combined failure feature extracting method |
Non-Patent Citations (1)
Title |
---|
船舶动力设备退化基线计算及预测方法;蔡玉良;孙晓磊;张晋彪;方宇;;舰船科学技术(第07期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113688904A (en) | 2021-11-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021004154A1 (en) | Method for predicting remaining life of numerical control machine tool | |
Kiranyaz et al. | 1-D convolutional neural networks for signal processing applications | |
Wang et al. | High-dimensional process monitoring and fault isolation via variable selection | |
CN109034191B (en) | ELM-based one-dimensional telemetry data abnormal interpretation method | |
CN110672905A (en) | CNN-based self-supervision voltage sag source identification method | |
CN109376778B (en) | Fault classification diagnosis method based on characteristic variable weighting | |
CN110070102B (en) | Method for establishing sequence-to-sequence model for identifying power quality disturbance type | |
CN111680725A (en) | Gas sensor array multi-fault isolation algorithm based on reconstruction contribution | |
CN115828170B (en) | Fault detection method based on electronic control data of tunneling machine | |
CN116070527B (en) | Milling cutter residual life prediction method based on degradation model | |
CN113688904B (en) | Method for extracting dynamic characteristic parameters of intelligent ship system equipment | |
CN110455399B (en) | Method for carrying out global early warning on building structure vibration by using distributed optical fiber | |
CN117031294A (en) | Battery multi-fault detection method, device and storage medium | |
CN116736214A (en) | CVT stability evaluation method and system | |
CN116610990A (en) | Method and device for identifying hidden danger of breaker based on characteristic space differentiation | |
CN113433850B (en) | Method for repairing abnormal logic of FPGA (field programmable Gate array) | |
AU2021100973A4 (en) | Method for Predicting Winter-Spring Stock Abundance of Ommastrephes Bartramii in the Northwest Pacific Ocean Based on Grey System | |
CN110954841A (en) | Online monitoring method based on lithium battery wavelet denoising | |
CN113312587A (en) | Sensor acquisition data missing value processing method based on ARIMA prediction and regression prediction | |
Benaicha et al. | A new method for determining PCA models for system diagnosis | |
CN116226767B (en) | Automatic diagnosis method for experimental data of power system | |
CN117352094B (en) | Physical property prediction analysis method and system for raw oil | |
CN111898664B (en) | Bridge modal parameter automatic identification method based on Block-Bootstrap and multi-stage clustering | |
CN111914210B (en) | Complex chemical process state monitoring method based on correlation characteristic analysis | |
Schimmack et al. | Wavelet based fault detection and RLS parameter estimation of conductive fibers with a simultaneous estimation of time-varying disturbance |
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 | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20211123 Assignee: DALIAN LANDSEA MARITECH Co.,Ltd. Assignor: Dalian Maritime University Contract record no.: X2024210000004 Denomination of invention: A Dynamic Feature Parameter Extraction Method for Intelligent Ship System Equipment Granted publication date: 20230822 License type: Common License Record date: 20240115 |
|
EE01 | Entry into force of recordation of patent licensing contract |