CN106779135A - A kind of hybrid power ship bearing power Forecasting Methodology - Google Patents
A kind of hybrid power ship bearing power Forecasting Methodology Download PDFInfo
- Publication number
- CN106779135A CN106779135A CN201610994380.4A CN201610994380A CN106779135A CN 106779135 A CN106779135 A CN 106779135A CN 201610994380 A CN201610994380 A CN 201610994380A CN 106779135 A CN106779135 A CN 106779135A
- Authority
- CN
- China
- Prior art keywords
- function
- bearing power
- hybrid power
- wavelet
- forecasting methodology
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 230000005284 excitation Effects 0.000 claims abstract description 9
- 230000007935 neutral effect Effects 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 40
- 238000004364 calculation method Methods 0.000 claims description 3
- 229910017435 S2 In Inorganic materials 0.000 claims 1
- 230000008859 change Effects 0.000 abstract description 4
- 230000000737 periodic effect Effects 0.000 description 5
- 238000013459 approach Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002592 echocardiography Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000000714 time series forecasting Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine 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
- G06Q10/04—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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Game Theory and Decision Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of hybrid power ship bearing power Forecasting Methodology, it is comprised the steps of：S1, collect the n bearing power in cycle before hybrid power ship predetermined period, and the bearing power chaos time sequence to collecting is normalized, it is configured to many dimensional input vectors of multiresolution wavelet neural network prediction model and is stored in database as training sample；S2, selection wavelet function and scaling function are collectively as the excitation function in network hidden layer node；S3, multiresolution wavelet neural network prediction model is set up according to training sample and excitation function；S4, network is trained；S5, prediction output renormalization treatment obtain (n+1)th bearing power sequence in cycle to be predicted.Its advantage is：Multiresolution wavelet neutral net can increase Resolving size to improve approximation accuracy, meet the complicated working conditions change demand of hybrid power ship in practice；Required amount to initial data is small, the need for meeting on-line training real-time estimate.
Description
Technical field
The present invention relates to hybrid power ship technical field, and in particular to a kind of hybrid power ship bearing power prediction side
Method.
Background technology
With continuing to develop for Electrical Propulsion Ship and hybrid power ship, the requirement to its power system is also increasingly
It is high.Hybrid power ship bearing power short-term forecast is optimum load between the energy-optimised management of its power system and each power source
The important foundation of power distribution.Particularly there is the ship of periodic job, such as ferry, craft tug and Vaporetto, it
Bearing power between the single work period there is similar intrinsic characteristic.These intrinsic characteristics are fully understood by and grasped, is taken
Obtaining bearing power precision of prediction higher will largely influence security, stability and the economy of vessel motion.
Operating condition change in the hybrid power ship signal period of periodic job is complex, influences its load work(
The factor of rate fluctuation is numerous.Phase space reconfiguration is carried out by hybrid power ship bearing power time series, and is asked for most
Big Lyapunov indexes, determine that it is chaos time sequence.
At present, marine vessel power load forecasting method is generally support vector machine method, chaos local prediction method and nerve net
Network method etc., these are all the traditional Time Series Forecasting Methods of comparing, and they are all present, and initial data required amount is big, train speed
Degree is slowly and treatment complication system non-linear relation difficulty is big waits not enough, and most of traditional Chaotic time series forecastings are to build
Stand on the basis of phase space reconfiguration, although State Space Reconstruction is numerous, implement all comparatively laborious, efficiency low.
The content of the invention
It is an object of the invention to provide a kind of hybrid power ship bearing power Forecasting Methodology, using based on multiresolution
The chaos time sequence short term prediction method of wavelet neural network, realizes the single work of hybrid power ship to periodic job
Cyclic loading power prediction, and prediction process is simple, efficiency high, be the energy-optimised management of hybrid power ship powerline systems and
Optimum load power distribution lays the foundation between each power source.
In order to achieve the above object, the present invention is achieved through the following technical solutions：
A kind of hybrid power ship bearing power Forecasting Methodology, it is comprised the steps of：
S1, collection hybrid power ship bearing power data, obtain the n bearing power in cycle before the cycle to be predicted, and
Bearing power chaos time sequence to collecting is normalized, and is configured to multiresolution wavelet neural network prediction mould
Many dimensional input vectors of type, and be stored in database as training sample；
S2, selection wavelet function and scaling function are collectively as the excitation function in network hidden layer node；
S3, multiresolution wavelet neural network prediction model is set up according to training sample and excitation function；
S4, treat the hybrid power ship bearing power chaos time sequence in n cycle before predetermined period and be trained；
S5, prediction output renormalization treatment obtain the bearing power sequence in the cycle of cycle to be predicted, i.e., (n+1)th.
Described hybrid power ship bearing power Forecasting Methodology, wherein, in described step S2：
The wavelet function and scaling function select orthogonal basis function.
Described hybrid power ship bearing power Forecasting Methodology, wherein, in described step S3：
According to formulaI=1,2 ..., N-m sets up forecast model,
In formula, ψj,k(Xi) and φJ,k(Xi) it is respectively wavelet function and scaling function, N is number of samples, and m is input dimension, and J is any
The yardstick of setting, predicted valueIt is by the corresponding scaling functions of out to out J and subdivision different scale (2j, j=1,2 ..., J)
The neutral net of corresponding wavelet function composition.
Described hybrid power ship bearing power Forecasting Methodology, wherein, described step S4 is specifically included：
S41, network configuration is carried out, input node number, learning probability, error ε and iterations；Weight initialization, section
Point initialization and the initialization of weights learning increment；
S42, calculating network prediction output fJ(x)；
S43, calculation error E：
In formula, N is total sample number,It is predicted value, f (n) is actual value, XnIt is n-th sample value；
S44, corrective networks weights ωj；
S45, the small nodal point of increase, continue to calculate；
S46, judge whether to meet end condition of the error function absolute value less than error ε set in advance, if meeting, net
Network training terminates, and performs step S5 outputs and predicts the outcome；If it is not satisfied, return performing step S42.
The present invention has advantages below compared with prior art：Hybrid power ship based on multiresolution wavelet neutral net
Overall prediction of the oceangoing ship bearing power Forecasting Methodology to periodic sequence has precision higher, particularly in sign mutation, many points
Resolution wavelet neural network can increase Resolving size to improve approximation accuracy, meet the complicated operating mode of hybrid power ship in practice
Change demand；The method is small to the required amount of initial data, and structure design is clear, can meet the need of on-line training, real-time estimate
Will, with larger engineering application and development potentiality.
Brief description of the drawings
Fig. 1 is flow chart of the method for the present invention；
Fig. 2 is by the multiresolution wavelet neural network structure figure set up in the embodiment of the present invention；
Fig. 3 is by the forecast model structure chart set up in the embodiment of the present invention.
Specific embodiment
Below in conjunction with accompanying drawing, by describing a preferably specific embodiment in detail, the present invention is further elaborated.
In the present embodiment, hardware is adopted using the data acquisition computer provisioned in hybrid power ship, software using data
The Matlab softwares installed in collection computer, hereafter by data acquisition computer completion, step S2~S5 passes through step S1
Matlab softwares are realized.
Fig. 1 is the prediction of the hybrid power ship bearing power based on multiresolution wavelet neutral net proposed by the invention
The flow chart of method, specifically includes following steps：
S1, data acquisition and procession；Vessel motion is gathered by the data acquisition computer provisioned in hybrid power ship
The n bearing power time series in cycle before cycle to be predicted, the sampling period is T, the sampling interval is Δ t, and will be collected
Hybrid power ship bearing power chaos time sequence is normalized, and is configured to multiresolution wavelet neural network prediction
Many dimensional input vectors X (i) of model=(x (i), x (i+1) ..., x (i+m-1)), wherein m are input dimension, by forecast model
Output valve is defined as y (i)=x (i+m), and (N is to obtain ordered pair during one group of network training (X (i), y (i)) (i=1,2 ..., N-m)
Number of samples), X (i) is configured to 4 D data, it is stored in database as training sample；
Specifically, method for normalizing mentioned above uses deviation standardized method, it is mapped to each pressure value put
Between 0-1, transformational relation is as follows：
Wherein, PiIt is i-th bearing power sample, PmaxIt is the maximum of sample data, PminIt is the minimum of sample data
Value, P*It is the bearing power sequence after normalization；
S2, the suitable wavelet function of selection and scaling function are collectively as the excitation function in network hidden layer node；Fig. 2
It is the multilayer multiresolution wavelet neural network structure figure set up of the invention, wherein x1,x2,…,xmIt is input load power sequence
Row, ak,bk(k is wavelet basis number) is the flexible and translation parameters of wavelet function, ωkIt is hidden layer to the net between output layer
Network weights, by adjusting the flexible of wavelet function, translation parameters and network weight come approach time sequence, the effect of this step is
The overall profile of approach time sequence first from large scale, the size for then being fluctuated according to bearing power, in different scale
On successively add details to approach, improve precision of prediction.
Preferably, wavelet function and scaling function should select a suitable orthogonal basis.In the present embodiment, wavelet function with
Scaling function chooses Meyer small echos.Meyer small echos have good time domain and frequency domain local characteristicses, arbitrary order regularity, n
Rank can continuously lead (n is integer), and with time domain convergence rate faster.
S3, multiresolution wavelet neural network prediction model is set up according to training sample and excitation function；Fig. 3 is this reality
The forecast model structure chart set up in example is applied, wherein X (i) is the training sample of input,It is predicted value, implies layer unit
Excitation function is respectively adopted φ according to projector space differenceJAnd ψJ, connection weight is respectively between input layer and hidden layer node
2 and 2J, i.e., the refinement yardstick in multiresolution analysis keeps constant in network learning procedure.Forecast model is set up as the following formula：
In formula, ψj,k(Xi) and φJ,k(Xi) it is respectively the wavelet function and scaling function selected in step S2, J is arbitrarily to set
Fixed yardstick, in the present embodiment, out to out takes J=4；With out to out J as boundary, the following yardsticks of J are used as fine-characterization
Approximately, predicted valueIt is by the corresponding scaling functions of yardstick J and subdivision different scale (2j, j=1,2 ..., J) corresponding small echo
The neutral net of function composition.
S4, network is trained, that is, when treating before predetermined period the hybrid power ship bearing power chaos in n cycle
Between sequence be trained, this step realizes that it is specifically comprised the steps of by Matlab software programmings：
S41, network configuration is carried out first, input node number is that 2, learning probability is that 0.01, error ε is 0.001 and repeatedly
Generation number is 100；The initialization of weight initialization, node initializing and weights learning increment；
S42, calculating network prediction output fJ(x)；
S43, calculation error E,
Wherein N is total sample number,It is predicted value, f (n) is actual value, XnIt is n-th sample value；
S44, corrective networks weights ωj；
S45, the small nodal point of increase, continue to calculate；
S46, judge whether to meet end condition, i.e. error function absolute value less than error ε set in advance, if meeting,
Network training terminates, and performs step S5 outputs and predicts the outcome；If it is not satisfied, returning to S42；
S5, predict the outcome output, and prediction output renormalization treatment obtains the negative of the cycle of cycle to be predicted, i.e., (n+1)th
Carry power sequence.
The above-mentioned hybrid power ship bearing power Forecasting Methodology based on multiresolution wavelet neutral net is to periodic sequence
Overall prediction there is precision higher, particularly in sign mutation, multiresolution wavelet neutral net can increase resolution chi
Spend to improve approximation accuracy, meet the complicated working conditions change demand of hybrid power ship in practice；And this method is to initial data
Required amount it is small, structure design is clear, the need for meeting on-line training, real-time estimate, with larger engineering application and development
Potentiality.
Although present disclosure is discussed in detail by above preferred embodiment, but it should be appreciated that above-mentioned
Description is not considered as limitation of the present invention.After those skilled in the art have read the above, for of the invention
Various modifications and substitutions all will be apparent.Therefore, protection scope of the present invention should be limited to the appended claims.
Claims (4)
1. a kind of hybrid power ship bearing power Forecasting Methodology, it is characterised in that comprise the steps of：
S1, collection hybrid power ship bearing power data, obtain the n bearing power in cycle before the cycle to be predicted, and to adopting
The bearing power chaos time sequence for collecting is normalized, and is configured to multiresolution wavelet neural network prediction model
Many dimensional input vectors be stored in database as training sample；
S2, selection wavelet function and scaling function are collectively as the excitation function in network hidden layer node；
S3, multiresolution wavelet neural network prediction model is set up according to training sample and excitation function；
S4, treat the hybrid power ship bearing power chaos time sequence in n cycle before predetermined period and be trained；
S5, prediction output renormalization treatment obtain the bearing power sequence in the cycle of cycle to be predicted, i.e., (n+1)th.
2. hybrid power ship bearing power Forecasting Methodology as claimed in claim 1, it is characterised in that described step S2
In：
The wavelet function and scaling function select orthogonal basis function.
3. hybrid power ship bearing power Forecasting Methodology as claimed in claim 1, it is characterised in that described step S3
In：
According to formulaForecast model is set up, in formula,
ψj,k(Xi) and φJ,k(Xi) it is respectively wavelet function and scaling function, N is number of samples, and m is input dimension, and J is any setting
Yardstick, predicted valueIt is by the corresponding scaling functions of out to out J and subdivision different scale (2j, j=1,2 ..., J) correspondence
Wavelet function composition neutral net.
4. hybrid power ship bearing power Forecasting Methodology as claimed in claim 1, it is characterised in that described step S4 tools
Body is included：
S41, network configuration is carried out, input node number, learning probability, error ε and iterations；At the beginning of weight initialization, node
Beginningization and weights learning increment are initialized；
S42, calculating network prediction output fJ(x)；
S43, calculation error E：
In formula, N is total sample number,It is predicted value, f (n) is actual value, XnIt is n-th sample value；
S44, corrective networks weights ωj；
S45, the small nodal point of increase, continue to calculate；
S46, judge whether to meet end condition of the error function absolute value less than error ε set in advance, if meeting, training knot
Beam, performs step S5 outputs and predicts the outcome；If it is not satisfied, return performing step S42.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610994380.4A CN106779135A (en) | 2016-11-11 | 2016-11-11 | A kind of hybrid power ship bearing power Forecasting Methodology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610994380.4A CN106779135A (en) | 2016-11-11 | 2016-11-11 | A kind of hybrid power ship bearing power Forecasting Methodology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106779135A true CN106779135A (en) | 2017-05-31 |
Family
ID=58973170
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610994380.4A Pending CN106779135A (en) | 2016-11-11 | 2016-11-11 | A kind of hybrid power ship bearing power Forecasting Methodology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779135A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108622362A (en) * | 2018-01-25 | 2018-10-09 | 上海海事大学 | A kind of hybrid power ship energy management method based on switching system theory |
| CN111310920A (en) * | 2020-03-17 | 2020-06-19 | 无锡多纬智控科技有限公司 | Method for applying deep learning neural network technology to signal acquisition device |
| CN111597640A (en) * | 2020-05-22 | 2020-08-28 | 上海海事大学 | Method for predicting demand load of hybrid power ship under condition classification |
| CN114154583A (en) * | 2021-12-08 | 2022-03-08 | 深圳博沃智慧科技有限公司 | Water quality prediction method of wavelet analysis coupling LSTM neural network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102208028A (en) * | 2011-05-31 | 2011-10-05 | 北京航空航天大学 | Fault predicting and diagnosing method suitable for dynamic complex system |
| CN103729687A (en) * | 2013-12-18 | 2014-04-16 | 国网山西省电力公司晋中供电公司 | Electricity price forecasting method based on wavelet transform and neural network |
| CN105976020A (en) * | 2016-04-28 | 2016-09-28 | 华北电力大学 | Network flow prediction method considering wavelet cross-layer correlations |
-
2016
- 2016-11-11 CN CN201610994380.4A patent/CN106779135A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102208028A (en) * | 2011-05-31 | 2011-10-05 | 北京航空航天大学 | Fault predicting and diagnosing method suitable for dynamic complex system |
| CN103729687A (en) * | 2013-12-18 | 2014-04-16 | 国网山西省电力公司晋中供电公司 | Electricity price forecasting method based on wavelet transform and neural network |
| CN105976020A (en) * | 2016-04-28 | 2016-09-28 | 华北电力大学 | Network flow prediction method considering wavelet cross-layer correlations |
Non-Patent Citations (2)
| Title |
|---|
| QINGHUA ZHANG等: "Wavelet Networks", 《IEEE TRANSACTIONS ON NEURAL NETWORKS》 * |
| 吕淑萍: "小波网络建模预报方法研究及其在股市预测中的应用", 《中国博士学位论文全文数据库 社会科学Ⅰ辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108622362A (en) * | 2018-01-25 | 2018-10-09 | 上海海事大学 | A kind of hybrid power ship energy management method based on switching system theory |
| CN111310920A (en) * | 2020-03-17 | 2020-06-19 | 无锡多纬智控科技有限公司 | Method for applying deep learning neural network technology to signal acquisition device |
| CN111597640A (en) * | 2020-05-22 | 2020-08-28 | 上海海事大学 | Method for predicting demand load of hybrid power ship under condition classification |
| US11945559B2 (en) | 2020-05-22 | 2024-04-02 | Shanghai Maritime University | Method for forecasting demand load of hybrid electric ship by means of working condition |
| CN114154583A (en) * | 2021-12-08 | 2022-03-08 | 深圳博沃智慧科技有限公司 | Water quality prediction method of wavelet analysis coupling LSTM neural network |
| CN114154583B (en) * | 2021-12-08 | 2024-05-24 | 深圳博沃智慧科技有限公司 | Water quality prediction method of wavelet analysis coupled LSTM neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | A ship motion forecasting approach based on empirical mode decomposition method hybrid deep learning network and quantum butterfly optimization algorithm | |
| Madhiarasan et al. | Comparative analysis on hidden neurons estimation in multi layer perceptron neural networks for wind speed forecasting | |
| CN106779135A (en) | A kind of hybrid power ship bearing power Forecasting Methodology | |
| CN107886161A (en) | A kind of global sensitivity analysis method for improving Complex Information System efficiency | |
| CN111860982A (en) | Wind power plant short-term wind power prediction method based on VMD-FCM-GRU | |
| CN110070229A (en) | The short term prediction method of home electrical load | |
| Hu et al. | Toward a digital twin: time series prediction based on a hybrid ensemble empirical mode decomposition and BO-LSTM neural networks | |
| Mori et al. | Short-term load forecasting with chaos time series analysis | |
| CN108022014A (en) | A kind of Load Prediction In Power Systems method and system | |
| Datong et al. | Online adaptive status prediction strategy for data-driven fault prognostics of complex systems | |
| CN112185104A (en) | Traffic big data restoration method based on countermeasure autoencoder | |
| KR970008532B1 (en) | Neural metwork | |
| CN114595858A (en) | Short-term wind speed prediction method and system based on rolling time series and support vector machine | |
| CN112307963A (en) | Converter transformer running state identification method based on vibration signals | |
| Zu et al. | Short-term wind power prediction method based on wavelet packet decomposition and improved GRU | |
| Chen et al. | A novel Bayesian-optimization-based adversarial TCN for RUL prediction of bearings | |
| Shi et al. | Wasserstein distance based multi-scale adversarial domain adaptation method for remaining useful life prediction | |
| CN1996192A (en) | Industrial soft measuring instrument based on bionic intelligence and soft measuring method therefor | |
| Chen et al. | Fault diagnosis of full-hydraulic drilling rig based on RS–SVM data fusion method | |
| Tabib et al. | Hybrid deep-learning POD-based parametric reduced order model for flow around wind-turbine blade | |
| Zhu et al. | Wind power prediction based on the chaos theory and the GABP neural network | |
| CN105572472A (en) | Frequency measuring method and system of distribution type power supply environment | |
| Hu et al. | Application on crude oil output forecasting based on gray neural network | |
| Lin et al. | Approximate Dynamic Programming for Control of Wave Energy Converters With Implementation and Validation on a Point Absorber Prototype | |
| Zheng et al. | Short Term Wind Power Prediction Based on Wavelet Transform and BP Neural Network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |