CN102254184A - Method for fusing multi-physical-domain feature information - Google Patents
Method for fusing multi-physical-domain feature information Download PDFInfo
- Publication number
- CN102254184A CN102254184A CN 201110200365 CN201110200365A CN102254184A CN 102254184 A CN102254184 A CN 102254184A CN 201110200365 CN201110200365 CN 201110200365 CN 201110200365 A CN201110200365 A CN 201110200365A CN 102254184 A CN102254184 A CN 102254184A
- Authority
- CN
- China
- Prior art keywords
- broad sense
- probability
- interval
- characteristic information
- hidden markov
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a method for fusing multi-physical-domain feature information, and the method comprises the following steps of: (1) obtaining required apriori information in an engineering event through a measuring tool, removing redundant information and obtaining an optimized feature information set; (2) converting each feature information value Xi in the optimized feature information into an interval form; (3) solving a broad sense Hidden Markov initial model; (4) obtaining an optimal model according to the obtained broad sense Hidden Markov initial model alpha; and (5) solving the optimum broad sense Hidden Markov model of each single-physical-domain, after synthesizing combined broad sense interval, checking the propability distribution according to a coupling relationship among various single-physical-domain optimum model parameters, and finishing and obtaining the fusion of the multi-physical-domain feature information. The method can be used for establishing coupling relationship among the multi-physical-domain parameters in different engineering and effectively solving the fusion problem of the multi-physical-domain feature information.
Description
Technical field
The present invention relates to field of information processing, particularly a kind of method of many physical domain feature fusion.
Background technology
Many physical domain feature fusion is to handle most important components at engineering information, is to utilize technology such as computing machine that decision-making and estimation task are analyzed, comprehensively finished to all observation information automatically.Many physical domain feature fusion runs into two class problems through regular meeting, and the one, the characteristic information uncertain problem that causes owing to the scarcity of the imperfection of the inexactness of survey instrument, information and randomness and priori; The 2nd, how many physical domain (as vibration, temperature, noise and the cutting force etc.) characteristic information during engineering information is handled merges problem.
The characteristic information uncertainty is inevitable in engineering modeling and the many physical domain observation process, wants to find the characteristic parameter of one group of energy accurate description engineering state and performance, sets up the identification and the forecast model of this stack features parameter, is a very difficult job.Although many researchists have spent the plenty of time and carried out constantly effort, effect is little.To the research method of uncertain problem, described by the accurate probability of observational variable mostly in the past, and only considered the randomness of observation, and ignored the imperfection of observation information and the scarcity of priori, this obviously can lower result's degree of belief.In recent years, people attempt going to address this problem with the out of true probability, and begin to be applied to the engineering field, as sensing data fusion, Reliability Estimation, reliability optimal design, and uncertain design proposal etc., the lower bound strictness of its out of true interval probability semantically can't form closure less than the upper bound in interval, reasoning and demonstration are complicated, calculate to be difficult to handle.
Many physical domain feature fusion also is the typical problem during engineering information is handled, present research method more is at determining amount, research at random information and imperfect information is less, wherein, relatively typical method mainly contains two classes: a class is the multiple dimensioned gaussian variable model that Choi M.J etc. proposes, Monte Carlo (Monte Carlo) simulation that Chamoin L etc. propose, method of weighted mean, Kalman filtering method, many Bayes' assessments and D-S evidential reasoning method, this several method all is a probability distribution of having supposed that earlier certain is special, make the scarcity of the randomness of observation and priori obscure and be in the same place, thereby limited its application; An other class research is based on Hidden Markov Model (HMM) and related expanding model thereof, wherein, use Hidden Markov Model (HMM) and will solve 3 basic problems: evaluation problem, decoding problem and training problem, specific implementation adopts forward backward algorithm, Viterbi algorithm and Baum-Welch algorithm to finish, and sees " the A tutorial on Hidden Markov Models and selected applications in speech recognition " of Lawre R.Rabiner for details.Hidden Markov Model (HMM) is described information implicit in the engineering by the observation that is easy to the observation vector sequence, and the coupled relation between implicit information is handled many physical domain information fusion problem in observation vector sequence by different physical quantities and the engineering, calculating is difficult to handle, and Hidden Markov Model (HMM) can not solve the uncertain problem that the scarcity of the imperfection of information and priori is brought.
In the research in the past, what how characteristic information uncertainty and characteristic information in many physical domain feature fusion were merged usually all is independently, can not form an organic combination, causes the reliability, intelligent low of information processing.One or a class problem can only be solved, the problem that information uncertainty and many physical domain feature fusion combines can not be solved simultaneously.
Summary of the invention
The objective of the invention is to handle the deficiency of research method, a kind of many physical domain feature fusion method is provided, can solve that the characteristic information uncertain problem can solve many physical domain feature fusion problem again simultaneously in the engineering at existing engineering information.
Realize that the concrete technical scheme that purpose of the present invention adopts is as follows:
A kind of many physical domain feature fusion method specifically comprises the steps:
(1) obtains the characteristic information collection
Obtain needed prior imformation in the engineering by survey instrument, remove redundant information, obtain the characteristic information collection of optimizing;
(2) each characteristic information value Xi that step (1) characteristic information is concentrated converts interval form to
Consider in the survey instrument measuring process and other uncertainty, by theory of errors each characteristic information value Xi is converted to interval form, to increase the reliability of the characteristic information value of measuring, wherein i is the sequence number of arbitrary characteristic information.
(3) ask for broad sense Hidden Markov initial model
At first, divide engineering state according to the engineering actual conditions;
Utilize the interval characteristic information value Xi that has changed and the engineering state of division then, with asking for Hidden Markov initial model similar approach, ask for state transition probability matrix A in the broad sense Hidden Markov initial model, observation probability matrix B and ask for original state probability matrix π according to check, wherein, probability replaces with the broad sense interval probability in above-mentioned all matrixes, can obtain broad sense Hidden Markov initial model λ=(A, B, π);
Wherein, the broad sense Hidden Markov Model (HMM) is with interval replacing characteristic information value in the Hidden Markov Model (HMM), replace probability in the Hidden Markov Model (HMM) with the broad sense interval probability, and the model that organically combines with Hidden Markov.
The theoretical foundation of broad sense interval probability is the Kaucher algorithm in the broad sense interval.Upper and lower dividing value size in its interval probability is not limited greater than floor value by dividing value, and last dividing value is less than or equal to floor value and all permits, semantic sealing;
The broad sense interval probability satisfies the logical consistency constraint, has multiple possibility Ei as an incident, and the last dividing value addition and the floor value addition result of all possible interval probability all are necessary for 1, promptly
Keep logic consistent with the accurate probability of classics.
(4) according to broad sense Hidden Markov initial model λ and algorithm, obtain optimization model.
(4.1) utilize broad sense Hidden Markov initial model, and the concentrated observation sequence O of characteristic information, by the forward-backward algorithm algorithm, calculate the interval probability P (O| λ) under model λ.
(4.2) utilize broad sense Hidden Markov initial model, and the concentrated observation sequence O of characteristic information, by the viterbi algorithm, the corresponding optimum state sequence of preference pattern λ Q=q
1q
2Q
T
(4.3) utilize broad sense Hidden Markov initial model, and the concentrated observation sequence O of characteristic information, by the Baum-Welch algorithm, progressively improve the initial model parameter, till the upper and lower boundary of P (O| λ) interval probability all restrains, can obtain optimum broad sense Hidden Markov Model (HMM) parameter
(5) utilize the dual random procedure structure of Hidden Markov Model (HMM), and the broad sense bayes rule is set up the coupled relation between each single physical domain optimization model parameter, the interval posterior probability of the broad sense of synthetic associating distributes, and can obtain the result of many physical domain feature fusion.
Wherein, the interval bayes rule of broad sense has replaced probability in the classical bayes rule with the broad sense interval probability, and it is defined as follows:
In the formula; A is and incident E
iThe physical event of coupled relation is arranged, has in addition:
Daulp (A|E
j)=1-p (A
c| E
j), p (A|E
j)+p (A
c| E
j)=1;
Distribute according to the interval posterior probability of the above-mentioned associating broad sense that obtains, obtain the result of many physical domain feature fusion, can carry out objective and accurate evaluation to the state and the performance of engineering, combine with generalized transition probability matrix, the state and the performance of engineering indicated based on the trend of historical data.
The present invention compared with prior art, how information uncertainty problem and many physical domain characteristic information merge theory, method and the technology that provides new in the feature fusion in order to solve simultaneously, and following advantage is arranged:
1) broad sense interval probability method had both been considered the randomness in the uncertain incident, had considered the imperfection of observation information and the scarcity of priori again.
2) broad sense interval probability method provides a kind of effective calculation method to be used for the uncertainty of engineering quantitative information and knowledge, the interval border that need not in the classic method is estimated, and support probability inference, under observation data deficiency, priori shortage, parameter distribution condition of unknown, also can obtain result preferably.
3) the broad sense bayes rule combines with Hidden Markov Model (HMM), both can capture dependence and coupled relation between uncertain factor, has very strong extensibility and versatility again.By the broad sense bayes rule, set up the coupled relation between many physical domain parameter in the different engineerings, can effectively solve many physical domain feature feature fusion problem.
Description of drawings
Accompanying drawing 1 is the FB(flow block) of many physical domain of the present invention feature fusion method embodiment.
Accompanying drawing 2 is FB(flow block) of embodiment of the invention machine tooling process status monitoring
Embodiment
The present invention will be that example embodiment is further described by monitoring with the machine tooling process status.
Referring to accompanying drawing 2,
1) obtains many physical domain characteristic information of machine tooling
By sensor machine tooling process Dynamic Signal is tested, obtain the observational characteristic information (vibration, noise, temperature, cutting force, cutting speed, cutting depth etc.) of machine tooling, remove redundant information by methods such as neural network or wavelet analysises, make up the feature set that reflection machine tooling state or dynamic property are optimized;
Present embodiment is selected the survey instrument of sensor as measurement features information for use owing to be used for the machine tooling process.
2) with each characteristic information value X of machine tooling characteristic information value
iConvert intervalization form to
Consider the uncertainty in sensor error and the measuring process, the machine tooling characteristic information value of having optimized is converted to interval form, increase reliability by the error blending theory in the theory of errors or 3 σ rules.Machine tooling characteristic information value X
iCarry out intervalization and can adopt following method to realize, wherein i is the sequence number of arbitrary machine tooling characteristic information:
At first, according to becoming known for measurement features value of information X
iSensor errors be ε
i, try to achieve resultant error according to the error blending theory and be
Wherein: a
iBe the propagation of error coefficient, lathe machining feature value of information X is then arranged
iThe interval be [X
i-σ, X
i+ σ].
In addition,, can also ask standard deviation earlier,, the interval [X of being of lathe machining feature information data be arranged then then according to asking for 3 σ rules if the characteristic information value that the machine tooling characteristic information is concentrated is normal distribution
i-3 σ, X
i+ 3 σ].
3) ask for the broad sense Hidden Markov initial model of machine tooling
At first, divide the machine tooling state according to the machine tooling actual conditions.Utilize the interval machine tooling characteristic information value X that has changed then
iWith asking for Hidden Markov initial model similar approach, ask for state transition probability matrix A in the broad sense Hidden Markov initial model, observation probability matrix B and ask for original state probability matrix π according to check, wherein, probability replaces with the broad sense interval probability in above-mentioned all matrixes, can obtain the broad sense Hidden Markov initial model λ of machine tooling=(A, B, π);
Wherein, the broad sense Hidden Markov Model (HMM) is with interval replacing characteristic information value in the Hidden Markov Model (HMM), replace probability in the Hidden Markov Model (HMM) with the broad sense interval probability, and the model that organically combines with Hidden Markov.
The broad sense interval probability is the popularization of broad sense interval and interval probability, promptly the interval upper and lower boundary in the broad sense interval is replaced with the probability size, its theoretical foundation is the Kaucher algorithm in the broad sense interval, the interval has been converted to the probability form, upper and lower dividing value size in its interval probability, not limited greater than floor value by dividing value, last dividing value is less than or equal to floor value and all permits, semantic sealing;
The broad sense interval probability satisfies the logical consistency constraint, has multiple possibility E as the machine tooling state
i, the last dividing value addition and the floor value addition result of the interval probability of all possible states all are necessary for 1, promptly
Keep logic consistent with the accurate probability of classics.
4) according to broad sense Hidden Markov initial model λ and algorithm, obtain the optimization model of machine tooling.
(1) utilize broad sense Hidden Markov initial model, and the concentrated observation sequence O of machine tooling characteristic information, by the forward-backward algorithm algorithm, calculate the interval probability P (O| λ) under model λ.
(2) utilize broad sense Hidden Markov initial model, and the concentrated observation sequence O of machine tooling characteristic information, by the viterbi algorithm, the corresponding optimum state sequence of preference pattern λ Q=q
1q
2Q
T
(3) utilize broad sense Hidden Markov initial model, and the concentrated observation sequence O of machine tooling characteristic information, by the Baum-Welch algorithm, progressively improve the initial model parameter, till the upper and lower boundary of P (O| λ) interval probability all restrains, can obtain optimum machine tooling broad sense Hidden Markov Model (HMM) parameter
4) utilize the dual random procedure structure of Hidden Markov Model (HMM), and the broad sense bayes rule is set up the coupled relation between each single physical domain optimization model parameter of machine tooling, the interval posterior probability of synthetic bastard machine tool processing broad sense distributes, and obtains the result of many physical domain of machine tooling feature fusion.
Wherein, the interval bayes rule of broad sense has replaced probability in the classical bayes rule with the broad sense interval probability, is defined as follows:
In the formula: E
iMachine tooling process status events corresponding (i=1 ... n, i are any one occurrence sequence number), A is the physical event (vibration, noise, temperature, cutting force, cutting speed, cutting depth etc.) that coupled relation is arranged with the machine tooling process status, has in addition:
daulp(A|E
j)＝1-p(A
c|E
j)，p(A|E
j)+p(A
c|E
j)＝1。
In the formula: E
jMachine tooling process status events corresponding, j is any one occurrence sequence number,
Be E
jThe probability supplementary set, its probability and be 1, A
c| E
jBe A|E
jThe probability supplementary set, its probability and be 1, daul are that the computing of semantic sealing is met.
Distribute according to the interval posterior probability of the above-mentioned associating broad sense that obtains, obtain the result of many physical domain feature fusion, can carry out objective to the state of machine tooling and monitoring is finished in accurate evaluation.With combine based on the state transition probability matrix in the lathe broad sense Hidden Markov Model (HMM) of historical data trend, also can the state of machine tooling be indicated.
Or not 3) in, according to optimization model
Utilize the above-mentioned the 2nd) step, and the observation sequence O that concentrates of the characteristic information of observation can obtain the optimum state of single physical domain.
The foregoing description only is a preferred scheme of method of the present invention, method of the present invention is not limited to and the monitoring that is used for the machine tooling process status, Other Engineering field such as Intelligent Measurement, robot, many physical domain feature fusion such as automatic target identification are all applicable etc.
Claims (6)
1. the method for physical domain feature fusion more than a kind specifically comprises the steps:
(1) obtains the characteristic information collection of each single physical domain
Obtain needed prior imformation in the engineering incident by survey instrument, remove redundant information wherein, obtain the characteristic information collection of optimizing;
(2) each concentrated characteristic information value X of the characteristic information that step (1) is obtained
iConvert interval form to;
(3) ask for broad sense Hidden Markov initial model, detailed process is:
At first, divide engineering state according to the engineering actual conditions;
Utilize the interval characteristic information value X that has changed then
iAnd the engineering state of dividing, ask for state transition probability matrix A, observation probability matrix B and original state probability matrix π, can obtain broad sense Hidden Markov initial model λ=(A, B, π), wherein, the probability in above-mentioned each probability matrix replaces with the broad sense interval probability;
(4) according to the broad sense Hidden Markov initial model λ that obtains, obtain optimization model, be specially:
(4.1) the observation sequence O that utilizes characteristic information to concentrate by the forward-backward algorithm algorithm, calculates the interval probability P (O| λ) under described broad sense Hidden Markov initial model λ;
(4.2) the observation sequence O that utilizes characteristic information to concentrate by the viterbi algorithm, selects the optimum state sequence Q=q of described broad sense Hidden Markov initial model λ correspondence
1q
2Q
T
(4.3) utilize described observation sequence O,, adjust the parameter of described initial model λ, till the upper and lower boundary of P (O| λ) interval probability all restrains, promptly obtain optimum broad sense Hidden Markov Model (HMM) by the Baum-Welch algorithm
(5) utilize above-mentioned steps to try to achieve the broad sense Hidden Markov Model (HMM) of the optimum of each single physical domain, set up coupled relation between each single physical domain optimization model parameter according to the broad sense bayes rule again, the interval posterior probability of the broad sense of synthetic associating distributes, and promptly finishes obtaining many physical domain feature fusion.
2. method according to claim 1 is characterized in that, in the described step (2) with characteristic information value X
iThe interval form that converts to is [X
i-ε, X
i+ ε], wherein,
Be resultant error, a
iBe propagation of error coefficient, ε
iFor being used for measurement features value of information X
iThe error of survey instrument.
3. method according to claim 1 is characterized in that, characteristic information value X in the described step (2)
iThe interval form that converts to is [X
i-3 σ, X
i+ 3 σ], at this moment, the characteristic information value that characteristic information is concentrated is normal distribution, and σ is its standard deviation.
4. according to the described method of one of claim 1-3, it is characterized in that the interval bayes rule of described broad sense has replaced probability in the classical bayes rule with the broad sense interval probability, it is defined as follows:
Wherein, E
iBe i incident in the engineering, i=1 ... n, i are the incident sequence number, and n is a positive integer, and A is and incident E
iThe physical event that coupled relation is arranged,
Be that summation meets, in addition:
daulp(A|E
j)＝1-p(A
c|E
j)，
p(A|E
j)+p(A
c|E
j)＝1；
In the formula, E
jBe j incident in the engineering, j is any one occurrence sequence number,
Be E
jThe probability supplementary set, its probability and be 1, A
c| E
jBe A|E
jThe probability supplementary set, its probability and be 1, daul are that the computing of semantic sealing is met.
5. according to the described method of one of claim 1-4, it is characterized in that described engineering incident is machine tooling, Intelligent Measurement or automatic target identification.
6. according to the described method of one of claim 1-5, it is characterized in that described survey instrument is a sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110200365 CN102254184B (en) | 2011-07-18 | 2011-07-18 | Method for fusing multi-physical-domain feature information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110200365 CN102254184B (en) | 2011-07-18 | 2011-07-18 | Method for fusing multi-physical-domain feature information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102254184A true CN102254184A (en) | 2011-11-23 |
| CN102254184B CN102254184B (en) | 2013-01-02 |
Family
ID=44981436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110200365 Active CN102254184B (en) | 2011-07-18 | 2011-07-18 | Method for fusing multi-physical-domain feature information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102254184B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034170A (en) * | 2012-11-27 | 2013-04-10 | 华中科技大学 | Numerical control machine tool machining performance prediction method based on intervals |
| CN107844806A (en) * | 2017-11-20 | 2018-03-27 | 华东交通大学 | A kind of raisins color sorting process based on Modal Intervals |
| CN108009573A (en) * | 2017-11-24 | 2018-05-08 | 北京物灵智能科技有限公司 | A kind of robot emotion model generating method, mood model and exchange method |
| CN108694417A (en) * | 2018-08-16 | 2018-10-23 | 湖南工程学院 | A kind of sliding bearing-rotor system amount of unbalance recognition methods |
| CN112171376A (en) * | 2020-08-21 | 2021-01-05 | 杭州玖欣物联科技有限公司 | Machine tool workpiece real-time statistical method based on current signal segmentation |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520651A (en) * | 2009-03-03 | 2009-09-02 | 华中科技大学 | Analysis method for reliability of numerical control equipment based on hidden Markov chain |
| CN101984454A (en) * | 2010-11-19 | 2011-03-09 | 杭州电子科技大学 | Multi-source multi-characteristic information fusion method based on data drive |
-
2011
- 2011-07-18 CN CN 201110200365 patent/CN102254184B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520651A (en) * | 2009-03-03 | 2009-09-02 | 华中科技大学 | Analysis method for reliability of numerical control equipment based on hidden Markov chain |
| CN101984454A (en) * | 2010-11-19 | 2011-03-09 | 杭州电子科技大学 | Multi-source multi-characteristic information fusion method based on data drive |
Non-Patent Citations (3)
| Title |
|---|
| 《航空学报》 20050930 苗强等 基于隐马尔科夫模型的故障诊断系统研究 641-646 1-6 第26卷, 第5期 * |
| 《计算机工程》 20081231 孙美凤等 基于特征模式的马尔可夫链异常检测模型 155-156 1-6 第34卷, 第24期 * |
| 《计算机工程与应用》 20040531 王新民等 基于因子分析的隐马尔可夫模型及其训练算法 79-81 1-6 , 第15期 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034170A (en) * | 2012-11-27 | 2013-04-10 | 华中科技大学 | Numerical control machine tool machining performance prediction method based on intervals |
| CN103034170B (en) * | 2012-11-27 | 2014-10-29 | 华中科技大学 | Numerical control machine tool machining performance prediction method based on intervals |
| CN107844806A (en) * | 2017-11-20 | 2018-03-27 | 华东交通大学 | A kind of raisins color sorting process based on Modal Intervals |
| CN107844806B (en) * | 2017-11-20 | 2021-06-11 | 华东交通大学 | Raisin color sorting method based on modal interval |
| CN108009573A (en) * | 2017-11-24 | 2018-05-08 | 北京物灵智能科技有限公司 | A kind of robot emotion model generating method, mood model and exchange method |
| CN108009573B (en) * | 2017-11-24 | 2020-08-14 | 北京物灵智能科技有限公司 | Robot emotion model generation method, emotion model and interaction method |
| CN108694417A (en) * | 2018-08-16 | 2018-10-23 | 湖南工程学院 | A kind of sliding bearing-rotor system amount of unbalance recognition methods |
| CN112171376A (en) * | 2020-08-21 | 2021-01-05 | 杭州玖欣物联科技有限公司 | Machine tool workpiece real-time statistical method based on current signal segmentation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102254184B (en) | 2013-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103105820B (en) | Machining cutter abrasion state identification method of numerical control machine tool | |
| JP6832475B1 (en) | How to design blade stiffness based on random isogeometric analysis | |
| CN102254184B (en) | Method for fusing multi-physical-domain feature information | |
| CN105981025A (en) | Actually-measured marine environment data assimilation method based on sequence recursive filtering three-dimensional variation | |
| CN103065042A (en) | Multiple target comprehensive decision evaluation method based on scene | |
| CN103268525B (en) | A kind of Hydrological Time Series simulating and predicting method based on WD-RBF | |
| CN103345200A (en) | Cutting flutter identification method based on generalized interval | |
| CN103577676A (en) | Grey weighting method for sewage treatment process comprehensive evaluation | |
| Chen et al. | Combining fuzzy iteration model with dynamic programming to solve multiobjective multistage decision making problems | |
| CN101458779A (en) | Curve and surface fairing method based on inheritance arithmetic | |
| CN101893430B (en) | Processing method of abnormal measured values based on CNC gear measuring center | |
| Roux et al. | An efficient parallel global optimization strategy based on Kriging properties suitable for material parameters identification | |
| Sun et al. | In-situ prediction of machining errors of thin-walled parts: an engineering knowledge based sparse Bayesian learning approach | |
| CN104678989A (en) | State perception optimization method for improving fault diagnosability in noise environment | |
| CN108197809B (en) | Real-time scheduling method of weight sharing deep network based on dimension optimal conversion | |
| CN106501828A (en) | A kind of high accuracy pseudo range one-point positioning method weighted based on fuzzy logic | |
| CN106202694A (en) | Combination Kriging model building method based on combination forecasting method | |
| CN105631093A (en) | M-BSWA multi-target optimization based mechanical structure design method | |
| CN103425890A (en) | Landscape water quality analysis algorithm | |
| Chen et al. | An improved PSO-NM algorithm for structural damage detection | |
| CN102004661A (en) | General data-driven reliability model for software and system and parameter optimizing method | |
| CN105575113A (en) | Sensing method of traffic running states | |
| CN103186711A (en) | Software cost evaluation method based on non-orthogonal coordinate system | |
| Yongbiao et al. | Multicriteria fuzzy decision-making method based on weighted correlation coefficients under interval-valued intuitionistic fuzzy environment | |
| Yang et al. | Improved Fractional-order Accumulation Grey Model in Data Prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |