CN106779148A - A kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion - Google Patents
A kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion Download PDFInfo
- Publication number
- CN106779148A CN106779148A CN201611020632.XA CN201611020632A CN106779148A CN 106779148 A CN106779148 A CN 106779148A CN 201611020632 A CN201611020632 A CN 201611020632A CN 106779148 A CN106779148 A CN 106779148A
- Authority
- CN
- China
- Prior art keywords
- measuring station
- air measuring
- data
- target air
- model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000004927 fusion Effects 0.000 title claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 13
- 230000007935 neutral effect Effects 0.000 claims description 89
- 238000013528 artificial neural network Methods 0.000 claims description 53
- 238000004422 calculation algorithm Methods 0.000 claims description 48
- 238000012549 training Methods 0.000 claims description 46
- 238000000354 decomposition reaction Methods 0.000 claims description 35
- 210000002364 input neuron Anatomy 0.000 claims description 28
- 241001269238 Data Species 0.000 claims description 19
- 238000003062 neural network model Methods 0.000 claims description 19
- 239000002245 particle Substances 0.000 claims description 19
- 238000010276 construction Methods 0.000 claims description 14
- 210000004205 output neuron Anatomy 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 238000007689 inspection Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 210000004218 nerve net Anatomy 0.000 claims description 4
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 230000002452 interceptive effect Effects 0.000 abstract 1
- 238000005457 optimization Methods 0.000 description 30
- 210000002569 neuron Anatomy 0.000 description 18
- 238000013277 forecasting method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000035772 mutation Effects 0.000 description 4
- 210000005036 nerve Anatomy 0.000 description 4
- 239000003016 pheromone Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000000053 physical method Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 235000008694 Humulus lupulus Nutrition 0.000 description 1
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009022 nonlinear effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001052 transient effect Effects 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
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/08—Learning methods
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Medical Informatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Aerodynamic Tests, Hydrodynamic Tests, Wind Tunnels, And Water Tanks (AREA)
Abstract
The invention discloses a kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion, the method is comprised the following steps:1. 5 auxiliary air measuring stations are installed around the air measuring station position;2. original air speed data is processed with Interactive Multiple-Model Kalman filtering method;Step 3:Small echo treatment is carried out using filtered data, and prediction submodel is built to the low-frequency data after small echo treatment;Step 4:The advanced multi-step prediction value of target air measuring station and weather forecast target air measuring station wind speed value input BAYESIAN combined model that the advanced multi-step Predictive Model of extraterrestrial target air measuring station, self advanced multi-step Predictive Model of target air measuring station and the meteorological advanced multi-step Predictive Model of target air measuring station are obtained, obtain final target air measuring station predicted value;The present invention can not only be avoided that the data outage that single air measuring station hardware fault is caused, and can provide the longer emergency processing time to the high-speed railway safe driving under bad wind environment.
Description
Technical field
The invention belongs to railway forecasting wind speed field, more particularly to a kind of line of high-speed railway of multi-model multiple features fusion
Wind speed forecasting method.
Background technology
With the economic sustainable and stable development of China, railway construction in China enters high-speed development period.And with railway operation
The increase of circuit and the lifting of train speed, the security of train operation, stationarity, comfortableness are received more and more attention.
High wind is to cause one of Major Natural Disasters of train accident, and high wind weather occurs often in some Along Railways of China area, this
Huge challenge is brought to the operation of train safety and steady.In order to prevent the generation of train accident, it is necessary to set up railway gale monitoring
Early warning system, so as to railway interests forward scheduling commander, Along Railway forecasting wind speed technology be exactly the system core technology it
One.
Wind velocity signal is a kind of random, nonlinear properties, is predicted very difficult.At present, the research field of forecasting wind speed is more
Concentrate on wind-powered electricity generation field prediction, method is divided into statistical method, physical method and learning method, conventional model include neutral net,
SVMs, Kalman filtering, time series, wavelet decomposition, empirical mode decomposition etc., also some mixed models.
Wind power plant generally build the area that physical features is flat, wind direction is stable in, and wind speed difference is little in smaller range.Different from wind
Electric field, Along Railway terrain environment is complicated, diverse location point wind speed significant difference, and sufficiently strong transient state wind may trigger row
Car accident, therefore, Along Railway each position point forecasting wind speed must be accurate.Simultaneously as hardware device exist integrity problem,
Single forecast result of model is unstable, and Along Railway forecasting wind speed data are impermissible for interrupt output, so, Along Railway wind speed
The necessary stable performance of prediction, uninterruptedly can export high-precision forecast data under various unusual conditions.Therefore, in the urgent need to setting up
A kind of precision of prediction is high, stable performance, can incorporate the Along Railway wind speed forecasting method of many factors and various forecast models.
The content of the invention
It is not enough present in existing Along Railway wind speed forecasting method it is an object of the invention to overcome, there is provided a kind of multimode
The Along Railway wind speed forecasting method of type multiple features fusion.The method has merged 4 basic models, comprising space, time, gas
As multiple elements such as, physics, each model data exists and interweaves during prediction, and last built-up pattern can be adaptively adjusted 4 bases
The weights of this forecast model, prediction stability is high, it is possible to achieve advanced multi-step prediction, with engineering application value.
A kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion, comprises the following steps:
Step 1:N number of auxiliary air measuring station is at least installed around target air measuring station position, is adopted in real time using air measuring station is aided in
Collect the air speed data of target air measuring station, obtain the wind speed sample set of target air measuring station and auxiliary air measuring station;
Wherein, N is the integer more than or equal to 5;
Step 2:Auxiliary air measuring station data and target air measuring station data are filtered and 1 layer depth wavelet decomposition successively,
Extract low-frequency data part;
Step 3:The auxiliary air measuring station obtained using step 2 and the low-frequency data part of target air measuring station build space-mesh
Mark the advanced multi-step Predictive Model of air measuring station, meanwhile, using the low-frequency data part of target air measuring station build self-target air measuring station
Advanced multi-step Predictive Model;
Step 4:Using low-frequency data part and the air pressure of target air measuring station present position, the humidity and temperature of target air measuring station
Degrees of data builds meteorology-advanced multi-step Predictive Model of target air measuring station;
Step 5:Using numerical weather forecast acquisition of information target air measuring station wind speed value;
Step 6:By space-advanced multi-step Predictive Model of target air measuring station, self-the advanced multi-step prediction mould of target air measuring station
The advanced multi-step prediction value of target air measuring station and step 5 that type and the advanced multi-step Predictive Model of meteorology-target air measuring station are obtained are obtained
The target air measuring station wind speed value input BAYESIAN combined model for obtaining, obtains final target air measuring station predicted value;
The advanced multi-step prediction refers to be input under correspondence forecast model is obtained for the moment using the air speed data at current time T
The forecasting wind speed of T+1 is carved, then, correspondence forecast model is input into again using the wind speed value of subsequent time T+1, obtain T+2
The wind speed value at moment, reciprocal iteration obtains advanced multi-step prediction value.
4 forecast models are obtained with advanced multi-step prediction value using BAYESIAN combined model do not carry out simple equality and add
Power, but the forecast model output to higher precision assigns bigger proportionality coefficient, that is, allow the forecast model institute of higher precision defeated
The wind speed value for going out occupies greater proportion in weighting.
Further, the space in the step 2-advanced multi-step Predictive Model of target air measuring station and self-target survey wind
Stand advanced multi-step Predictive Model construction step it is as follows:
Step 2.1:Low-frequency data part to auxiliary air measuring station and target air measuring station carries out FEEMD decomposition, obtains each
The corresponding low frequency of air measuring station, intermediate frequency and high frequency subsequence;
Step 2.2:Each IMF components to auxiliary air measuring station and the high frequency subsequence of target air measuring station are based on respectively
The training of the LVQ neutral nets of PSO, builds auxiliary air measuring station and respective self high frequency of target air measuring station is based on the LVQ god of PSO
Through network model, the advanced multi-step prediction value of self high frequency of auxiliary air measuring station and target air measuring station is obtained;
Each IMF components to auxiliary air measuring station and the intermediate frequency subsequence of target air measuring station set up the limit based on CBA respectively
Learning machine is trained, and builds auxiliary air measuring station and respective self intermediate frequency of target air measuring station is based on the extreme learning machine mould of CBA
Type, obtains the advanced multi-step prediction value of self intermediate frequency of auxiliary air measuring station and target air measuring station;
Each IMF components to aiding in the low frequency subsequence of air measuring station and target air measuring station are set up RARIMA and are instructed respectively
Practice, build auxiliary air measuring station and respective self the low frequency RARIMA model of target air measuring station, obtain auxiliary air measuring station and mesh
Mark the advanced multi-step prediction value of self low frequency of air measuring station;
Step 2.3:The high frequency of target air measuring station is based on the limit that the LVQ neural network models of PSO, intermediate frequency are based on CBA
Learning machine model and low frequency RARIMA model combinations, formed self-the advanced multi-step Predictive Model of target air measuring station;
Step 2.4:To aid in low frequency, intermediate frequency and the high frequency subsequence data of air measuring station as input, target air measuring station
Low frequency, intermediate frequency and high frequency subsequence data build the BP neural network mould that each frequency range subsequence is based on Adaboost as output
Type, is based on using aiding in the corresponding advanced multi-step prediction value of each frequency range subsequence of air measuring station to be input into each frequency range subsequence
The BP neural network model of Adaboost, obtains the advanced multi-step prediction value of target air measuring station each frequency range of correspondence, with each frequency range
The BP neural network model that sequence is based on Adaboost forms space-advanced multi-step Predictive Model of target air measuring station;
The BP neural network model that each frequency range subsequence is based on Adaboost refers to, using Adaboost algorithm to many
The mean absolute error of the predicted value that individual BP neural network is exported according to each BP neural network carries out not decile weighted sum, each
BP neural network is input into neuron and 13 layer network structure of output neuron using multiple, for the input data trained
In, at the every group of acquisition time of data previous moment super than previous group input data, the acquisition time of output data is than last
One group of input data super previous moment.
In the mixed model, the BP neural network model of Adaboost includes 10 BP neural networks as weak study
Device, the BP neural network with the mean absolute relative error of forecasting wind speed more than 5% is considered as the object for needing to strengthen study, BP god
300 steps are taken through the greatest iteration step number of network.The prediction of 10 BP neural networks by Adaboost algorithm to being included is defeated
Going out has carried out not decile weighted sum, i.e. Adaboost algorithm in an iterative process, and the prediction according to each BP neural network is defeated
The mean absolute relative error for going out, adjusts the BP neural network in next iteration meter in whole neural network inverse systems in real time
Shared weight ratio.The better single BP neural network of performance will be endowed weights higher.
Adaboost-BP Neural network mixed models are divided into training study and prediction calculates two aspects.Learn in training
Stage, what each BP neural network will be input into being screened aids in low frequency, intermediate frequency and the high frequency subsequence of air measuring station administrative
Whole IMF components, each BP neural network is output as low frequency, intermediate frequency and the administrative whole of high frequency subsequence of target air measuring station
IMF components, each BP neural network will complete the training study of itself, then by Adaboost algorithm to whole BP nerves
The weight ratio of network is adjusted, and to the last obtains the optimal weighting ratio value of this 10 BP neural networks.In the present invention
In, in each BP neural network itself neuron connection weight and hidden layer threshold value be randomly assigned.
Single BP neural network is input into neuron and 13 layer network structure of output neuron using multiple, i.e.,:It is single
Individual BP neural network needs that synchronously network is learnt and trained with multigroup input air speed data and 1 group of output wind speed data;
After 10 BP neural networks of Adaboost algorithm optimization all complete training, as long as the multiple input to each BP neural network
Neuron port is input into the air speed data of multigroup equal length, and each BP neural network just can automatically export 1 group and input wind speed etc.
The prediction of wind speed sequence of length, then carries out not decile using BP neural network weight ratio value determined by Adaboost algorithm
Weighted sum, obtains the final prediction of wind speed sequence of Adaboost-BP Neural network mixed models.
After Adaboost-BP Neural network mixed models complete global learning trains, it is possible to wait using new defeated
Enter the forecasting wind speed output data that air speed data obtains equal length.Namely the BP neural network input that each is trained is obtained
After each frequency layer for obtaining uses the advanced multi-step prediction value of auxiliary air measuring station that various combination forecast model is obtained, the BP nerve nets
Network can just predict the advanced multi-step prediction value of target air measuring station.When the advanced multistep for completing all 10 BP neural networks is pre-
It is final to obtain target air measuring station after measured value output, it is possible to which the weight ratio provided with Adaboost algorithm is sued for peace
Advanced multistep wind speed value.
The BP neural network model of Adaboost includes 10 BP neural networks as weak learner, with forecasting wind speed
BP neural network of the mean absolute relative error more than 5% is considered as the object for needing to strengthen study, and the maximum of BP neural network changes
Number of riding instead of walk takes 300 steps.
Further, the specific construction step of LVQ neural network model of self high frequency based on PSO is as follows:
(1) particle populations of the connection weight of LVQ models are randomly generated using PSO, each particle represents one group of LVQ model
Initial connection weight;
(2) setting value as the training direction of PSO algorithms is reached to realize minimum windspeed mean absolute relative error, is completed
The training learning process of PSO algorithms so that the particle in particle populations is constantly brought near optimal particle, exports optimal
The initial connection weight of LVQ neutral nets;
(3) the obtained initial connection weight of LVQ neutral nets will be trained to LVQ god by PSO in above two steps
It is configured through network, input and output data using each IMF components of the high frequency subsequence at wind station as neutral net, is completed
Study and training of the LVQ neutral nets itself to wind speed, form the PSO- of self high frequency subsequence air speed data high-precision forecast
LVQ mixed models;
In for the input data of training, when every group of acquisition time of data is super than previous group input data previous
Carve, the acquisition time of output data is than last group of input data super previous moment.
Utilize the LVQ neutral nets that set up PSO optimizes complete to each IMF wind speed component in wind speed high frequency subsequence
Calculated into advanced multi-step prediction, to obtain the respective IMF components advanced multi-step prediction value of corresponding wind speed.
The LVQ neutral nets set up are input into neuron and 1 structure of output neuron using 3, i.e.,:LVQ god
Need that synchronously network is learnt and trained with 3 groups of input air speed datas and 1 group of output wind speed data through network;When PSO is excellent
After the LVQ neutral nets of change complete training, as long as being input into 3 corresponding wind to 3 input neuron ports of LVQ neutral nets
Fast data, LVQ neutral nets just can automatically export 1 wind speed value.
The initial population quantity generated using PSO sets iterations when taking 50, PSO optimum choice LVQ neutral nets
Take 200 times, particle speed of service maximum is 0.5, the minimum value of the particle speed of service is 0.01;The iteration of LVQ neutral nets
Target mean absolute relative error takes 5%;LVQ neutral nets obtain PSO assign the initial connection weight of optimal network after from
The maximum study iterative steps of body take 100 steps.
The essence that the LVQ neutral nets that each IMF components of high frequency subsequence set up PSO optimizations respectively are trained is to utilize
PSO selects the initial connection weight of LVQ neutral nets so that the LVQ neutral nets of optimization can preferably follow the trail of the sub- sequence of high frequency
The extreme mutation rule of each administrative IMF component air speed data of row, realizes the prediction of high-precision intermediate frequency subsequence.
Further, the construction step of extreme learning machine model of self intermediate frequency based on CBA is as follows:
(1) bat algorithm is initialized;
The location parameter of every bat represents one group of output weights and hidden layer node threshold value of extreme learning machine, every bat
The initial loudness and pulse rate of bat take 0.5, and bat number 50, iterations is 100, and the flight step-length of every bat takes
Value scope is [0.001,0.05];
(2) the output wind speed mean absolute relative error with extreme learning machine reaches setting value as the fitness of bat algorithm
Guidance function, the loudness and pulse rate of every bat of real-time update so that bat fly to extreme learning machine input weights and
The corresponding optimal solution of hidden layer node threshold value;
In preceding 50 iteration, the flight step-length of bat takes maximum, since the 51st iteration, the flight step-length of bat
Take minimum value;
(3) the input weights and the corresponding optimal solution of hidden layer node threshold value of the extreme learning machine of (2) acquisition are utilized, by wind
Input and output data of each IMF components of the intermediate frequency subsequence for standing as extreme learning machine, carry out extreme learning machine model instruction
Practice, obtain the extreme learning machine model based on CBA;
In for the input data of training, when every group of acquisition time of data is super than previous group input data previous
Carve, the acquisition time of output data is than last group of input data super previous moment.
Utilize the extreme learning machine that set up CBA optimizes complete to each IMF wind speed component in wind speed intermediate frequency subsequence
Calculated into advanced multi-step prediction, to obtain the respective IMF components advanced multi-step prediction value of corresponding wind speed.
The extreme learning machine set up is input into neuron and 1 structure of output neuron using 3, i.e.,:The limit
Habit machine needs that synchronously network is learnt and trained with 3 groups of input air speed datas and 1 group of output wind speed data;When CBA optimizations
Extreme learning machine complete training after, as long as being input into 3 corresponding wind speed numbers to 3 of extreme learning machine input neuron ports
According to extreme learning machine just can automatically export 1 wind speed value.
The iterative target mean absolute relative error of extreme learning machine model takes 5%, in CBA optimum choice extreme learning machines
Initial input weights and hidden layer node threshold stage and extreme learning machine assignment phase, pole after CBA algorithm optimizing is obtained
The greatest iteration step number for limiting learning machine takes 200 steps.
It is profit to set up the essence that the extreme learning machine of CBA optimizations is trained respectively to each IMF components of intermediate frequency subsequence
With the initial input weights and hidden layer node threshold value of variable-step self-adaptive bat algorithm optimization extreme learning machine so that optimization
Extreme learning machine can preferably follow the trail of the mutation rule of each administrative IMF component air speed data of intermediate frequency subsequence, realize high
The prediction of the intermediate frequency subsequence of precision.
The flight step-length of bat automatically changes with the incremental of iterations, it is ensured that bat algorithm is to extreme learning machine
Ability of searching optimum on forecasting wind speed, makes to take maximum during the 50 step iteration before algorithm optimizing, it is therefore an objective to avoid calculating
Method it is too early be absorbed in locally optimal solution;With the increase (i.e. since 50 steps to 100 steps) of iterations, the flight of bat
Step-length actively reduces, and minimum value is taken, so that bat algorithm is more accurately solved in later stage Fast Convergent.
Further, the construction step of self low frequency RARIMA model is as follows:
(1) whole IMF components wind speed numbers of acquisition are decomposed to each low frequency subsequence using nonparametric pleasure boat method of inspection
According to carrying out data stationarity inspection;
Such as run into certain IMF components air speed data and be presented non-stationary, then difference meter is carried out to this section of IMF components air speed data
Calculate untill it shows stationarity;
(2) acquisition is decomposed to each low frequency subsequence to by the whole IMF components wind speed after step 1 stationary test
Data carry out sample auto-correlation and sample partial correlation is calculated, and true according to the auto-correlation and partial correlation value of respective component air speed data
Determine the optimal type and Optimal order of RARIMA models;
(3) the optimal type and Optimal order of the RARIMA models for being obtained to step 2, are solved each using maximum-likelihood method
The equation coefficient of individual IMF components air speed data correspondence RARIMA models, using each IMF components of the low frequency subsequence at wind station as
The input data of RARIMA models, forms self low frequency RARIMA model.
During the prediction of advanced multistep, constantly using the equation of newest predicted value real-time update RARIMA models
Coefficient.
RARIMA model equations are actually an auto-correlation expression formula, that is, describe current air speed value and history wind
The relation of speed value.Such as, RARIMA models are all set up to the whole IMF components inside low frequency subsequence, it is also to use each IMF
Component data fits the RARIMA models of different parameters.As described in following instance, certain IMF component has 500 data, just
Set up a RARIMA model.So being exactly to certain section it is believed that RARIMA models do not have so-called input and output data
IMF component datas set up an auto-correlation expression formula, so but need prediction when, just be input into the historical juncture data, obtain
The data at current time, by that analogy, until untill moment corresponding wind speed value is wanted in acquisition.
The reason for each IMF component to low frequency subsequence sets up RARIMA models be:Relative to medium, high frequency subsequence institute
Each IMF component after decomposition, each administrative IMF component of low frequency subsequence is more steady.By being used before this patent
Unscented kalman filtering method and 1 layer of wavelet method denoising after, the air speed data of low frequency subsequence does not include wind speed number of hops
According to.Now realize that process of fitting treatment is wise using the RARIMA models in statistical mathematics field, can accomplish fitting precision and
Export taking into account for real-time.
In the step content, the calculation procedure of the excellent wheel method of inspection of nonparametric, Difference Calculation and RARIMA models belongs to
Existing algorithm in statistical mathematics.
Further, the construction step of the meteorology-advanced multi-step Predictive Model of target air measuring station is as follows:
(1) population of the connection weight of Elman Model of Neural Network is randomly generated using ACO;
(2) setting value as the training direction of ACO algorithms is reached to realize minimum windspeed mean absolute relative error, is carried out
The training learning process of ACO algorithms so that the ant in initialization ant population is by iteration constantly near optimal solution, output
The optimal initial connection weight of Elman neutral nets and hidden layer threshold value;
(3) the initial connection weight and threshold value for above-mentioned steps being obtained by ACO training are carried out to Elman neutral nets
Set, the second layer low frequency component data of air pressure, temperature, humidity and target air measuring station are carried out as Elman neutral nets
Input and output data to study and the training of wind speed, form meteorology-advanced multi-step Predictive Model of target air measuring station;
In for the input data of training, when every group of acquisition time of data is super than previous group input data previous
Carve, the acquisition time of output data is than last group of input data super previous moment.
The Elman neutral nets that set up ACO optimizes are utilized to the of air pressure, temperature, humidity and target air measuring station
Two layers of low frequency wind speed component data this 4 kinds of objects complete advanced multi-step predictions and calculate, corresponding advanced many to obtain various objects
Step predicted value.
The Elman neutral nets set up are input into neuron and 1 structure of output neuron using 4, i.e.,:Elman
Neutral net needs that synchronously network is learnt and trained with the data and 1 group of output wind speed data of 4 groups of above-mentioned 4 kinds of objects;
After the Elman neutral nets of ACO optimizations complete training, as long as to 4 input neuron port difference of Elman neutral nets
4 data of above-mentioned 4 kinds of objects of input, Elman neutral nets just can automatically export 1 wind speed value.
Initial population ant quantity takes 100, and the ant pheromones significance level factor takes 0.5, the important journey of ant heuristic function
The degree factor takes 1, and ant pheromones volatilization factor takes 0.1.Iterations during ACO optimum choice Elman neutral nets takes 50 times.
The iterative target mean absolute relative error of Elman neutral nets takes 5%.Elman neutral nets are obtaining the optimal of ACO impartings
The maximum study iterative steps of itself take 100 steps after the initial connection weight of network.
Further, the filtering process described in step 2 uses Unscented kalman filtering method.
Further, the auxiliary air measuring station for structure model in step 3 refers to m for selecting in accordance with the following methods
Auxiliary air measuring station:
First, to being entered using adaptive noise completely integrated empirical modal by the filtered wind speed sample set of step 2
Row is decomposed;
Secondly, treatment is filtered to the data after decomposition;
Then, filtered data signal reconstruction will be carried out again, will obtain the wind speed reconstruct data of each air measuring station;
The wind speed reconstruct data of each auxiliary air measuring station are carried out into correlation test with the wind speed reconstruct data of target air measuring station,
Sorted from high to low by the degree of correlation, selected and m groups auxiliary air measuring station before target air measuring station wind speed reconstruct Data mutuality degree ranking
Wind speed reconstructs data and corresponding m auxiliary air measuring station;
Wherein, m is integer, and span is [3,60%N].
Beneficial effect
Compared with prior art, the present invention has advantages below:
1. the multiple elements such as space, time, meteorology, physics have been incorporated, auxiliary air measuring station data, target air measuring station has been make use of
Various data such as data, history meteorological data, numerical weather forecast data, it is ensured that the diversity of data.
2. statistical method, physical method, learning method are organically combined, improve forecasting reliability.
There is data interlacing in 3.4 basic models, reduce amount of calculation during prediction;4 kinds of models are by standard
BAYESIAN combined model is weighted fusion, is adaptively adjusted weights, improves the stability of prediction.Ensure in any one
In the case of the embedded forecast model timeliness in inherence, the wind speed forecasting method based on multi-model multiple features strategy proposed by the invention
Remain able to export the advanced multi-step prediction value of final wind speed exactly, for the Railway Traffic Dispatching Control under harsher wind conditions.
In the 1st kind of model for being proposed, by Unscented kalman filtering method and wavelet method to target air measuring station and auxiliary
The original air speed data of whole of air measuring station has carried out filtering and noise reduction treatment so that below for correlation calculations and the wind speed of prediction
Data maintain pure property and rule potentiality to greatest extent.Additionally, using FEEMD algorithms to the wind speed number after filtering and noise reduction
According to multilayer decomposition has been carried out, more air speed data samples are generated for the modeling in later stage.Air speed data after decomposition according to
The difference of their jump frequency has been divided into low frequency, intermediate frequency and the gear of high frequency three, and by different combination forecastings to this three
Class predicted respectively, has taken into account the precision and real-time of final forecast model.For example, being built to the IMF components of low frequency subsequence
Simple RARIMA models are found, the extreme learning machine mould set up after the CBA optimizations of medium accuracy to the IMF components of intermediate frequency subsequence
Type, the IMF to high frequency subsequence decomposes the LVQ neural network prediction models for then establishing high-precision PSO optimizations.Only with regard to this
For the hybrid prediction model of different frequency, technical staff is just difficult to what is obtained to three classes without innovation.And this patent is not
To being directly realized by final prediction with this three classes hybrid prediction model, but their predicted value is input to again newly-built
Adaboost-BP hybrid neural networks forecast models in, dexterously auxiliary air measuring station and target air measuring station contact one
Rise, realize high-precision forecasting wind speed.
2nd kind of model does not set up the spatial prediction model of auxiliary air measuring station and target air measuring station, but precision of prediction is put
Target air measuring station itself has been arrived, it is final directly to realize prediction output by the forecast model group of built IMF components.
3rd kind of model dexterously introduces air pressure, three objects of humidity and temperature so that build the robustness of forecast model
Can get a promotion.
The foundation of the 4th kind of model has incorporated the technology of the numerical weather forecast that Modern High-Speed Along Railway is generally used.
Brief description of the drawings
Fig. 1 is the principle flow chart of the method for the invention;
Fig. 2 is the BP neural network training figure of the Adaboost optimizations of model 1 in the present invention;
Fig. 3 is the advanced multi-step Predictive Model figure of target air measuring station of model 1 in the present invention;
Fig. 4 is the advanced multi-step Predictive Model figure of target air measuring station of model 2 in the present invention;
Fig. 5 is 1 layer of wavelet decomposition figure of target air measuring station A in the present invention;
Fig. 6 is 2 layers of wavelet decomposition figure of target air measuring station of model 3 in the present invention;
Fig. 7 is the railway forecasting wind speed result schematic diagram obtained using Forecasting Methodology proposed by the invention;
Fig. 8 is the railway forecasting wind speed result schematic diagram obtained using traditional single ELMAN neural network models;
Fig. 9 is the railway forecasting wind speed result schematic diagram obtained using traditional single ARIMA models.
Specific embodiment
Below in conjunction with drawings and Examples, the present invention is described further:
As shown in figure 1, a kind of forecasting wind speed of high speed railway line side of multi-model multiple features fusion, comprises the following steps:
Step 1:N number of auxiliary air measuring station is at least installed around target air measuring station position, is adopted in real time using air measuring station is aided in
Collect the air speed data of target air measuring station, obtain the wind speed sample set of target air measuring station and auxiliary air measuring station;
Wherein, N is the integer more than or equal to 5;
Step 2:Auxiliary air measuring station data and target air measuring station data are filtered and 1 layer depth wavelet decomposition successively,
Extract low-frequency data part;
Step 3:Using low-frequency data build space-advanced multi-step Predictive Model of target air measuring station, self-target air measuring station
Advanced multi-step Predictive Model and meteorology-advanced multi-step Predictive Model of target air measuring station;
Step 4:By space-advanced multi-step Predictive Model of target air measuring station, self-the advanced multi-step prediction mould of target air measuring station
The advanced multi-step prediction value of target air measuring station and weather forecast that type and the advanced multi-step Predictive Model of meteorology-target air measuring station are obtained
Target air measuring station wind speed value is input into BAYESIAN combined model, obtains final target air measuring station predicted value;
Wherein, the step of space-target air measuring station advanced multi-step Predictive Model prediction of wind speed value is as follows:
1st, it is that prediction is realized to the railway future wind speed of certain target air measuring station position, 5 is installed around the air measuring station position
Individual auxiliary air measuring station.Obtain the original air speed data of same session target air measuring station and 5 auxiliary air measuring stations, every group of air speed data
Comprising 600 data, first 500 in 600 data are used to model, the 501st~600 data are used to verify.
Target air measuring station is designated as A, 5 auxiliary air measuring stations are designated as B, C, D, E, F respectively, before each air measuring station 500 it is original
Air speed data is expressed as follows:
The original air speed data of target air measuring station A:{a1,a2,a3...,a499,a500}
The original air speed data of auxiliary air measuring station B:{b1,b2,b3...,b499,b500}
The original air speed data of auxiliary air measuring station C:{c1,c2,c3...,c499,c500}
The original air speed data of auxiliary air measuring station D:{d1,d2,d3...,d499,d500}
The original air speed data of auxiliary air measuring station E:{e1,e2,e3...,e499,e500}
The original air speed data of auxiliary air measuring station F:{f1,f2,f3...,f499,f500}
2nd, with Unscented kalman filtering method to air measuring station A, the original air speed data of B, C, D, E, F is filtered treatment, goes
Except potential error in air speed data, following filtered air speed datas are obtained:
The filtered air speed datas of target air measuring station A:{a′1,a′2,a′3...,a′499,a′500}
The auxiliary air measuring station filtered air speed datas of B:{b′1,b′2,b′3...,b′499,b′500}
The auxiliary air measuring station filtered air speed datas of C:{c′1,c′2,c′3...,c′499,c′500}
The auxiliary air measuring station filtered air speed datas of D:{d′1,d′2,d′3...,d′499,d′500}
The auxiliary air measuring station filtered air speed datas of E:{e′1,e′2,e′3...,e′499,e′500}
The auxiliary air measuring station filtered air speed datas of F:{f′1,f′2,f′3...,f′499,f′500}
3rd, high frequency Jump is removed with the tower algorithms of Mallat of 1 layer of wavelet decomposition respectively to filtered each data,
Take low-frequency data:
Low-frequency data after target air measuring station A wavelet decompositions:{a″1,a″2,a″3...,a″499,a″500}
Low-frequency data after auxiliary air measuring station B wavelet decompositions:{b″1,b″2,b″3...,b″499,b″500}
Low-frequency data after auxiliary air measuring station C wavelet decompositions:{c″1,c″2,c″3...,c″499,c″500}
Low-frequency data after auxiliary air measuring station D wavelet decompositions:{d″1,d″2,d″3...,d″499,d″500}
Low-frequency data after auxiliary air measuring station E wavelet decompositions:{e″1,e″2,e″3...,e″499,e″500}
Low-frequency data after auxiliary air measuring station F wavelet decompositions:{f″1,f″2,f″3...,f″499,f″500}
4th, each auxiliary air measuring station low-frequency data is shown with target air measuring station low-frequency data respectively by Frechet distances
The inspection of work property, will aid in 5 groups of data of air measuring station to carry out conspicuousness sequence by group, select conspicuousness maximum and suitable preceding 3
Group data and its corresponding 3 auxiliary air measuring station.This 3 auxiliary air measuring stations such as selected are respectively auxiliary air measuring station B, auxiliary and survey
Wind station C, auxiliary air measuring station D.
5th, the low-frequency data to target air measuring station and B, C, D for selecting auxiliary air measuring station carries out FEEMD decomposition respectively, obtains
Following components:
Target air measuring station A:AIMF1,AIMF2,...AIMFn,AR
Auxiliary air measuring station B:BIMF1,BIMF2,...BIMFn,BR
Auxiliary air measuring station C:CIMF1,CIMF2,...CIMFn,CR
Auxiliary air measuring station D:DIMF1,DIMF2,...DIMFn,DR
6th, each IMF components after being decomposed to 3 auxiliary air measuring stations are divided into low frequency, intermediate frequency, the Seed Sequences of high frequency 3 by frequency,
RARIMA is set up respectively to each IMF components of low frequency subsequence to be trained, each IMF components to intermediate frequency subsequence are set up respectively
The extreme learning machine of CBA optimizations is trained, and each IMF components of high frequency subsequence set up the LVQ neutral nets of PSO optimizations respectively
It is trained, the advanced multi-step prediction value of each IMF components is obtained eventually through iteration.
The specific construction step that high frequency is based on the LVQ neural network models of PSO is as follows:
The initial population quantity generated using PSO sets iterations when taking 50, PSO optimum choice LVQ neutral nets
Take 200 times, particle speed of service maximum is 0.5, the minimum value of the particle speed of service is 0.01;The iteration of LVQ neutral nets
Target mean absolute relative error takes 5%;LVQ neutral nets obtain PSO assign the initial connection weight of optimal network after from
The maximum study iterative steps of body take 100 steps.
(1) particle populations of the connection weight of LVQ models are randomly generated using PSO, each particle represents one group of LVQ model
Initial connection weight;
(2) setting value as the training direction of PSO algorithms is reached to realize minimum windspeed mean absolute relative error, is completed
The training learning process of PSO algorithms so that the particle in particle populations is constantly brought near optimal particle, exports optimal
The initial connection weight of LVQ neutral nets;
(3) the obtained initial connection weight of LVQ neutral nets will be trained to LVQ god by PSO in above two steps
It is configured through network, each IMF components of high frequency subsequence of air measuring station and target air measuring station will be aided in as neutral net
Input data, completes study and training of the LVQ neutral nets itself to wind speed, forms self high frequency subsequence air speed data high-precision
Spend the PSO-LVQ mixed models of prediction.
The essence that the LVQ neutral nets that each IMF components of high frequency subsequence set up PSO optimizations respectively are trained is to utilize
PSO selects the initial connection weight of LVQ neutral nets so that the LVQ neutral nets of optimization can preferably follow the trail of the sub- sequence of high frequency
The extreme mutation rule of each administrative IMF component air speed data of row, realizes the prediction of high-precision intermediate frequency subsequence.
For example, there are 2 groups of intermediate frequency IMF wind speed component (if being referred to as IMF1 and IMF2) wind speed high frequency subsequence the inside,
Their air speed data length is 500.IMF1 components have 500 wind speed sample datas, then by the 1-497 wind speed sample
The input air speed data of neuron is input into as the 1st of LVQ neutral nets, using the 2-498 air speed data as LVQ nerves
The 2nd of the network input air speed data of input neuron, using the 3-499 air speed data as the 3rd of LVQ neutral nets
The input air speed data of neuron is input into, using the 4-500 air speed data as unique output neuron of LVQ neutral nets
, then synchronously be loaded into these air speed data groups on LVQ neural network models, according to described PSO by output wind speed data
The step of algorithm optimization LVQ neutral nets, completes whole study and training.
After PSO-LVQ Neural network mixed models complete to learn, the 1st input neuron to LVQ neutral nets is defeated
Enter the 498th air speed data of IMF1 components, to the 2nd the 499th of input neuron input IMF1 components the of LVQ neutral nets
Individual air speed data, the 3rd input neuron to LVQ neutral nets is input into the 500th air speed data of IMF1 components, then
LVQ neutral nets will automatically export 1 air speed value, the value be IMF1 components the 501st wind speed value (that is,
Above-mentioned steps are realized and obtain advanced 1 step predicted value using 1-500 existing decomposition wind speed sample of IMF1 components, i.e.,
501st wind speed value).
By that analogy, multi-Step Iterations calculating is carried out, to the 1st input neuron input IMF1 component of LVQ neutral nets
The 499th air speed data, the 500th wind speed number of IMF1 components is input into the 2nd of LVQ neutral nets input neuron
According to the 3rd input neuron input to LVQ neutral nets predicts the 501st wind speed for having obtained by above advanced 1 step
Predicted value, then LVQ neutral nets will automatically export 1 air speed value again, then the value is the 502nd wind of IMF1 components
(namely above-mentioned steps predict institute to fast predicted value using 1-500 existing wind speed sample of IMF1 components by advanced 2 step
The 502nd wind speed value for obtaining).Like this, the LVQ neutral nets after PSO algorithm optimizations can be completed to IMF1 components
The advanced multistep forecasting wind speed of required any step number is calculated.Other decomposed components (such as IMF2 components) in high frequency wind speed subsequence
The step of advanced multistep wind speed value obtained by PSO-LVQ Neural network mixed models and above-mentioned IMF1 components
Step is the same.
The construction step that intermediate frequency is based on the extreme learning machine model of CBA is as follows:
The iterative target mean absolute relative error of extreme learning machine model takes 5%, in CBA optimum choice extreme learning machines
Initial input weights and hidden layer node threshold stage and extreme learning machine assignment phase, pole after CBA algorithm optimizing is obtained
The greatest iteration step number for limiting learning machine takes 200 steps.
(1) bat algorithm is initialized;
The location parameter of every bat represents one group of output weights and hidden layer node threshold value of extreme learning machine, every bat
The initial loudness and pulse rate of bat take 0.5, and bat number 50, iterations is 100, and the flight step-length of every bat takes
Value scope is [0.001,0.05];
(2) the output wind speed mean absolute relative error with extreme learning machine reaches setting value as the fitness of bat algorithm
Guidance function, the loudness and pulse rate of every bat of real-time update so that bat fly to extreme learning machine input weights and
The corresponding optimal solution of hidden layer node threshold value;
In preceding 50 iteration, the flight step-length of bat takes maximum, since the 51st iteration, the flight step-length of bat
Take minimum value;
(3) the input weights and the corresponding optimal solution of hidden layer node threshold value of the extreme learning machine of (2) acquisition are utilized, by wind
Input and output data of each IMF components of the intermediate frequency subsequence for standing as extreme learning machine, carry out extreme learning machine model instruction
Practice, obtain the extreme learning machine model based on CBA;
In for the input data of training, when every group of acquisition time of data is super than previous group input data previous
Carve, the acquisition time of output data is than last group of input data super previous moment.
For example, there are 2 groups of intermediate frequency IMF wind speed component (if being referred to as IMF1 and IMF2) wind speed intermediate frequency subsequence the inside,
Their air speed data length is 500.IMF1 components have 500 wind speed sample datas, then by the 1-497 wind speed sample
The input air speed data of neuron is input into as the 1st of extreme learning machine, is learnt the 2-498 air speed data as the limit
The 2nd of the machine input air speed data of input neuron, it is defeated using the 3-499 air speed data as the 3rd of extreme learning machine
Enter the input air speed data of neuron, using the 4-500 air speed data as the defeated of unique output neuron of extreme learning machine
Go out air speed data, then synchronously these air speed data groups are loaded on extreme learning machine model, according to described CBA algorithms
The step of optimization extreme learning machine model, completes whole study and training.
After CBA- extreme learning machines mixed model completes to learn, the 1st input neuron input to extreme learning machine
498th air speed data of IMF1 components, to the 2nd the 499th of input neuron input IMF1 components of extreme learning machine
Air speed data, the 3rd input neuron to extreme learning machine is input into the 500th air speed data of IMF1 components, then the limit
Learning machine will automatically export 1 air speed value, and the value is the 501st wind speed value of IMF1 components (that is, above-mentioned step
Rapid realizing obtains advanced 1 step predicted value, i.e., the 501st using 1-500 existing decomposition wind speed sample of IMF1 components
Individual wind speed value).
By that analogy, multi-Step Iterations calculating is carried out, the 1st input neuron to extreme learning machine is input into IMF1 components
499th air speed data, the 2nd input neuron to extreme learning machine is input into the 500th air speed data of IMF1 components, right
The 3rd input neuron input of extreme learning machine predicts the 501st forecasting wind speed for having obtained by above advanced 1 step
Value, then extreme learning machine will automatically export 1 air speed value again, then the 502nd wind speed that the value is IMF1 components is pre-
(namely above-mentioned steps are obtained measured value using 1-500 existing wind speed sample of IMF1 components by the prediction of advanced 2 step
The 502nd wind speed value).Like this, the extreme learning machine after CBA algorithm optimizations is appointed needed for being completed to IMF1 components
The advanced multistep forecasting wind speed of step number of anticipating is calculated.Other decomposed components (such as IMF2 components) in intermediate frequency wind speed subsequence pass through
The step of the step of advanced multistep wind speed value that CBA- extreme learning machine mixed models are obtained, is with above-mentioned IMF1 components
Equally.
It is profit to set up the essence that the extreme learning machine of CBA optimizations is trained respectively to each IMF components of intermediate frequency subsequence
With the initial input weights and hidden layer node threshold value of variable-step self-adaptive bat algorithm optimization extreme learning machine so that optimization
Extreme learning machine can preferably follow the trail of the mutation rule of each administrative IMF component air speed data of intermediate frequency subsequence, realize high
The prediction of the intermediate frequency subsequence of precision.
The flight step-length of bat automatically changes with the incremental of iterations, it is ensured that bat algorithm is to extreme learning machine
Ability of searching optimum on forecasting wind speed, makes to take maximum during the 50 step iteration before algorithm optimizing, it is therefore an objective to avoid calculating
Method it is too early be absorbed in locally optimal solution;With the increase (i.e. since 50 steps to 100 steps) of iterations, the flight of bat
Step-length actively reduces, and minimum value is taken, so that bat algorithm is more accurately solved in later stage Fast Convergent.
The construction step of low frequency RARIMA models is as follows:
(1) whole IMF components wind speed numbers of acquisition are decomposed to each low frequency subsequence using nonparametric pleasure boat method of inspection
According to carrying out data stationarity inspection;
Such as run into certain IMF components air speed data and be presented non-stationary, then difference meter is carried out to this section of IMF components air speed data
Calculate untill it shows stationarity;
(2) acquisition is decomposed to each low frequency subsequence to by the whole IMF components wind speed after step 1 stationary test
Data carry out sample auto-correlation and sample partial correlation is calculated, and true according to the auto-correlation and partial correlation value of respective component air speed data
Determine the optimal type and Optimal order of RARIMA models;
(3) the optimal type and Optimal order of the RARIMA models for being obtained to step 2, are solved each using maximum-likelihood method
The equation coefficient of individual IMF components air speed data correspondence RARIMA models, forms self low frequency RARIMA model;
During the prediction of advanced multistep, constantly using the equation of newest predicted value real-time update RARIMA models
Coefficient.
7th, as shown in Fig. 2 being modeled respectively to high frequency series, middle frequency sequence, low frequency sequence, each sequence is aided in B, C, D
Each IMF components of air measuring station are input, are output with each IMF components of target air measuring station, using Adaboost optimizations
BP neural network is trained.
8th, as shown in figure 3, B, C, D the auxiliary advanced multi-step prediction value of air measuring station obtained to prediction bring what is trained into
The BP neural network of Adaboost optimizations, then signal reconstruction is carried out, finally give the advanced multistep forecasting wind speed of target air measuring station
Value.
The BP neural network model of Adaboost includes 10 BP neural networks as weak learner, with forecasting wind speed
BP neural network of the mean absolute relative error more than 5% is considered as the object for needing to strengthen study, and the maximum of BP neural network changes
Number of riding instead of walk takes 300 steps.
Such as, the auxiliary air measuring station by filtering out has 3, by after FEEMD decomposition, they amount to and possess 20 groups of IMF
Component, each component has 500 air speed datas, at the same this 20 group component to be divided into low frequency, intermediate frequency different with three groups of high frequency
Subsequence in.In order to be input into this totally 20 groups of IMF component, each BP neural network needs exist for 20 input neuron numbers.
In other words, the input data of each BP neural network through the auxiliary air measuring station being screened out possessed it is whole
IMF components.
Target air measuring station after FEEMD decomposition by possessing 5 groups of IMF components, then they will be used as each BP neural network
Output data, learning training is carried out to each BP neural network.Because to different wind speed sample datas, FEEMD is decomposed and produced
Raw IMF component numbers are different, so the input neuron and output neuron number of BP neural network are also dynamic
, it is respectively depending on the auxiliary air measuring station that filters out and target air measuring station finally possesses several IMF components numbers.But to same group
For identical wind speed sample data, no matter they are from auxiliary air measuring station or from target air measuring station, by FEEMD points
IMF component numbers produced after solution are fixed, that is to say, that the input neuron of corresponding 10 BP neural networks and defeated
It is also fixed to go out neuron number.
In Adaboost-BP Neural network mixed models, the structure of each BP neural network is input neuron and defeated
Go out what neuron number was just as, but for the air speed data sample different to Along Railway, the BP nerves set up every time
Network is again different.
Self-the advanced multi-step Predictive Model of target air measuring station carries out comprising the following steps that for forecasting wind speed:
1st, target air measuring station use with the 1st forecast model identical initial data, by the original wind speed number of target air measuring station
Processed according to Unscented kalman filtering method, potential error in removal air speed data.
The original air speed data of target air measuring station A:{a1,a2,a3...,a499,a500}
The filtered air speed datas of target air measuring station A:{a1′,a′2,a3′...,a′499,a5′00}
2nd, high frequency Jump is removed with the tower algorithms of Mallat of 1 layer of wavelet decomposition to filtered data, takes low frequency
Data:
Low-frequency data after target air measuring station A wavelet decompositions:{a″1,a″2,a″3...,a″499,a″500}
3rd, the low-frequency data to target air measuring station carries out FEEMD decomposition, obtains following components:
Target air measuring station A:AIMF1,AIMF2,...AIMFn,AR
4th, as shown in figure 4, each IMF components after to decomposition are divided into low frequency, intermediate frequency, the Seed Sequences of high frequency 3 by frequency, to low
Each IMF components of frequency subsequence are set up RARIMA and are trained respectively, and each IMF components to intermediate frequency subsequence set up CBA respectively
The extreme learning machine of optimization is trained, and the LVQ neutral nets that each IMF components of high frequency subsequence set up PSO optimizations respectively are entered
Row training, the advanced multi-step prediction value of each IMF components is obtained eventually through iteration.
5th, to each component weighted calculation, reconstruction signal obtains the advanced multistep wind speed value of target air measuring station.
Meteorology-advanced multi-step Predictive Model of target air measuring station carries out comprising the following steps that for forecasting wind speed:
1st, target air measuring station use with the 1st forecast model identical initial data, by the original wind speed number of target air measuring station
Processed according to Unscented kalman filtering method, potential error in removal air speed data.
The original air speed data of target air measuring station A:{a1,a2,a3...,a499,a500}
The filtered air speed datas of target air measuring station A:{a′1,a′2,a′3...,a′499,a′500}
2nd, as shown in figure 5, removing high frequency jump spy with the tower algorithms of Mallat of 1 layer of wavelet decomposition to filtered data
Levy, take low-frequency data A1:
Low-frequency data A after target air measuring station A wavelet decompositions1:{a″1,a″2,a″3...,a″499,a″500}
3rd, as shown in fig. 6, to low-frequency data A1Reusing the tower algorithms of Mallat carries out the wavelet decomposition of 2 layer depths, takes
2nd layer of low frequency component A111:
Low-frequency data A after target air measuring station A wavelet decompositions111:{a″′1,a″′2,a″′3...,a″′499,a″′500}
4th, the Elman of ACO optimizations is set up to historical barometric, humidity, temperature and wavelet decomposition is obtained twice low frequency component
Neutral net is trained, and obtains jump ahead prediction.
Initial population ant quantity takes 100, and the ant pheromones significance level factor takes 0.5, the important journey of ant heuristic function
The degree factor takes 1, and ant pheromones volatilization factor takes 0.1.Iterations during ACO optimum choice Elman neutral nets takes 50 times.
The iterative target mean absolute relative error of Elman neutral nets takes 5%.Elman neutral nets are obtaining the optimal of ACO impartings
The maximum study iterative steps of itself take 100 steps after the initial connection weight of network.
(1) population of the connection weight of Elman Model of Neural Network is randomly generated using ACO;
(2) setting value as the training direction of ACO algorithms is reached to realize minimum windspeed mean absolute relative error, is carried out
The training learning process of ACO algorithms so that the ant in initialization ant population is by iteration constantly near optimal solution, output
The optimal initial connection weight of Elman neutral nets and hidden layer threshold value;
(3) the initial connection weight and threshold value for above-mentioned steps being obtained by ACO training are carried out to Elman neutral nets
Set, the second layer low frequency component data of air pressure, temperature, humidity and target air measuring station are carried out as Elman neutral nets
Input and output data to study and the training of wind speed, form meteorology-advanced multi-step Predictive Model of target air measuring station;
In for the input data of training, when every group of acquisition time of data is super than previous group input data previous
Carve, the acquisition time of output data is than last group of input data super previous moment.
The Elman neutral nets that set up ACO optimizes are utilized to the of air pressure, temperature, humidity and target air measuring station
Two layers of low frequency wind speed component data this 4 kinds of objects complete advanced multi-step predictions and calculate, corresponding advanced many to obtain various objects
Step predicted value.
The Elman neutral nets set up are input into neuron and 1 structure of output neuron using 4, i.e.,:Elman
Neutral net needs that synchronously network is learnt and trained with the data and 1 group of output wind speed data of 4 groups of above-mentioned 4 kinds of objects;
After the Elman neutral nets of ACO optimizations complete training, as long as to 4 input neuron port difference of Elman neutral nets
4 data of above-mentioned 4 kinds of objects of input, Elman neutral nets just can automatically export 1 wind speed value.
Such as, certain moment use state air pressure, temperature, humidity and target air measuring station this 4 kinds of second layer low frequency wind speed it is right
The sample data of elephant, their data length is 500.Using the 1-499 sample of air pressure as the of Elman neutral nets
1 input data of input neuron, is input into the 1-499 sample of temperature data as the 2nd of Elman neutral nets
The input data of neuron, neuron is input into using the 1-499 sample of humidity data as the 3rd of Elman neutral nets
Input data, using the 1-499 sample of the second layer low frequency wind speed of target air measuring station as the 4th of Elman neutral nets
The input data of individual input neuron, using the 2-500 sample of the second layer low frequency wind speed of target air measuring station as Elman god
Through the output data of unique 1 output neuron of network, these data groups are synchronously then loaded into Elman nerve nets
On network, whole study and training are completed the step of according to described ACO algorithm optimization Elman neural network models.
After ACO-Elman Neural network mixed models complete to learn, to the 1st input nerve of Elman neutral nets
500th sample data of first input air pressure object, the 2nd to Elman neutral nets is input into neuron input temp object
The 500th sample data, the 500th sample number of humidity object is input into the 3rd of Elman neutral nets input neuron
According to the 4th the 500th of the second layer low frequency wind speed object of input neuron input target air measuring station the of Elman neutral nets
Individual sample data, then Elman neutral nets will automatically export 1 air speed value, the second layer that the value is target air measuring station is low
501st wind speed value of frequency wind speed object is (that is, above-mentioned steps realize the using above-mentioned 4 kinds different objects
1-500 sample data obtains the advanced 1 step predicted value of target air measuring station wind speed object, i.e., the 501st wind speed value).
By that analogy, multi-Step Iterations calculating is carried out, continues the 1st, the 2nd and the 3rd input to Elman neutral nets
Neuron difference input air pressure, the newest measured data of temperature and humidity, i.e. their corresponding 501st measured data, then
The 501st wind speed value that the 4th input neuron input to Elman neutral nets is obtained using above-mentioned steps simultaneously,
So Elman neutral nets will automatically export 1 air speed value, the of the second layer low frequency wind speed object of target air measuring station again
502 wind speed values are (that is, above-mentioned steps realize the 1- using air pressure, the different objects of this 3 kinds of temperature and humidity
500 sample datas and their corresponding newest 501st measured value, obtain advanced the 2 of target air measuring station wind speed object
The step wind speed value of predicted value, i.e., the 502nd).Like this, the Elman neutral nets after ACO algorithm optimizations can be surveyed to target
The advanced multistep forecasting wind speed that wind station wind speed object completes required any step number is calculated.
It is noted that in the calculating process of the advanced multi-Step Iterations of above-mentioned Elman neutral nets, only wind speed
The step of object has constantly carried out incremental input, other 3 meteorological objects (i.e. air pressure, temperature and humidity) are all to employ him
Measured value.So the present invention not only effectively utilizes the rule of wind speed itself, and efficiently utilizes other 3 meteorologies
The data potential contribution of object, therefore obtain the success to target air measuring station wind speed object high-precision forecast.
5th, it is the corresponding moment air pressure of numerical weather forecast, humidity, the predicted value of temperature and jump ahead predicted value band is superb
Through network, final iteration obtains the advanced multi-step prediction value of target air measuring station.
4th forecast model is comprised the following steps:
1st, the wind speed value of target air measuring station is obtained by numerical weather forecast.
With BAYESIAN combined model predicting the outcome come 4 fundamental forecasting models of summary.
Wherein, when t+1 moment forecasting wind speeds are calculated, the weights of 4 fundamental forecasting models change in BAYESIAN combined model
Start for the past t.This example takes t=500.
Realize that the result of forecasting wind speed is as shown in Figure 7 using Forecasting Methodology proposed by the invention.Using existing ELMAN god
Realize that the result of forecasting wind speed is as shown in Figure 8 through network model.Using the result of existing ARIMA model realizations forecasting wind speed as schemed
Shown in 9.Precision index calculating is carried out to predicting the outcome shown in Fig. 7-Fig. 9 using formula (1-3), 1 and table 2 is the results are shown in Table.
Mean absolute error:
Mean absolute relative error:
Root-mean-square error:
In above-mentioned formula, n is the air speed data number for model testing, and it is 100 that n is taken in this example.X (i) is actual measurement
Air speed data,It is prediction of wind speed data.
Table 1:Using the precision of prediction of Forecasting Methodology proposed by the invention
Mean absolute error | 0.2940m/s |
Mean absolute relative error | 1.51% |
Root-mean-square error | 0.2821m/s |
Table 2:Using the precision of prediction of existing ELMAN neural network models
Mean absolute error | 1.6961m/s |
Mean absolute relative error | 7.99% |
Root-mean-square error | 2.2125m/s |
Table 3:Using the precision of prediction of existing ARIMA models
Mean absolute error | 1.7237m/s |
Mean absolute relative error | 8.54% |
Root-mean-square error | 1.8426m/s |
From Fig. 7, Fig. 8 and Fig. 9, and with reference to Tables 1 and 2 from the point of view of, method of the present invention, from mean absolute error, flat
From the point of view of equal absolute relative error and root-mean-square error, hence it is evident that better than prior art, show that the method for the invention has preferable
Application effect.
Claims (8)
1. a kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion, it is characterised in that comprise the following steps:
Step 1:N number of auxiliary air measuring station is at least installed around target air measuring station position, using aiding in air measuring station Real-time Collection mesh
The air speed data of air measuring station is marked, the wind speed sample set of target air measuring station and auxiliary air measuring station is obtained;
Wherein, N is the integer more than or equal to 5;
Step 2:Auxiliary air measuring station data and target air measuring station data are filtered and 1 layer depth wavelet decomposition successively, are extracted
Low-frequency data part;
Step 3:The auxiliary air measuring station obtained using step 2 and the low-frequency data part of target air measuring station are built space-target and surveyed
The advanced multi-step Predictive Model in wind station, meanwhile, using the low-frequency data part of target air measuring station build self-target air measuring station is advanced
Multi-step Predictive Model;
Step 4:Using low-frequency data part and the air pressure of target air measuring station present position, the humidity and temperature number of target air measuring station
According to structure meteorology-advanced multi-step Predictive Model of target air measuring station;
Step 5:Using numerical weather forecast acquisition of information target air measuring station wind speed value;
Step 6:By space-advanced multi-step Predictive Model of target air measuring station, self-the advanced multi-step Predictive Model of target air measuring station with
And the advanced multi-step prediction value of target air measuring station that obtains of the advanced multi-step Predictive Model of meteorology-target air measuring station and step 5 are obtained
Target air measuring station wind speed value is input into BAYESIAN combined model, obtains final target air measuring station predicted value;
The advanced multi-step prediction refers to obtain subsequent time T+ using the air speed data input correspondence forecast model at current time T
1 forecasting wind speed, then, correspondence forecast model is input into using the wind speed value of subsequent time T+1 again, obtains the T+2 moment
Wind speed value, reciprocal iteration obtains advanced multi-step prediction value.
2. method according to claim 1, it is characterised in that the space-advanced multistep of target air measuring station in the step 2
Forecast model and self-construction step of the advanced multi-step Predictive Model of target air measuring station is as follows:
Step 2.1:Low-frequency data part to auxiliary air measuring station and target air measuring station carries out FEEMD decomposition, obtains each and surveys wind
Stand corresponding low frequency, intermediate frequency and high frequency subsequence;
Step 2.2:Each IMF components to auxiliary air measuring station and the high frequency subsequence of target air measuring station are carried out based on PSO respectively
The training of LVQ neutral nets, builds auxiliary air measuring station and respective self high frequency of target air measuring station is based on the LVQ nerve nets of PSO
Network model, obtains the advanced multi-step prediction value of self high frequency of auxiliary air measuring station and target air measuring station;
Each IMF components to auxiliary air measuring station and the intermediate frequency subsequence of target air measuring station set up the limit study based on CBA respectively
Machine is trained, and builds auxiliary air measuring station and respective self intermediate frequency of target air measuring station is based on the extreme learning machine model of CBA, obtains
Take the advanced multi-step prediction value of self intermediate frequency of auxiliary air measuring station and target air measuring station;
Each IMF components to aiding in the low frequency subsequence of air measuring station and target air measuring station are set up RARIMA and are trained respectively, structure
Auxiliary air measuring station and respective self the low frequency RARIMA model of target air measuring station are built, auxiliary air measuring station and target air measuring station is obtained
The advanced multi-step prediction value of self low frequency;
Step 2.3:The high frequency of target air measuring station is based on the limit study that the LVQ neural network models of PSO, intermediate frequency are based on CBA
Machine model and low frequency RARIMA model combinations, formed self-the advanced multi-step Predictive Model of target air measuring station;
Step 2.4:To aid in low frequency, intermediate frequency and the high frequency subsequence data of air measuring station as input, the low frequency of target air measuring station,
Intermediate frequency and high frequency subsequence data build the BP neural network model that each frequency range subsequence is based on Adaboost as output, profit
Each frequency range subsequence is input into the corresponding advanced multi-step prediction value of each frequency range subsequence of auxiliary air measuring station be based on Adaboost's
BP neural network model, obtains the advanced multi-step prediction value of target air measuring station each frequency range of correspondence, is based on each frequency range subsequence
The BP neural network model of Adaboost forms space-advanced multi-step Predictive Model of target air measuring station;
The BP neural network model that each frequency range subsequence is based on Adaboost refers to, using Adaboost algorithm to multiple BP
The mean absolute error of the predicted value that neutral net is exported according to each BP neural network carries out not decile weighted sum, each BP god
Through network using multiple input neuron and 13 layer network structure of output neuron, in the input data trained,
At the every group of acquisition time of data previous moment super than previous group input data, the acquisition time of output data is than last group
The input data super previous moment.
3. method according to claim 2, it is characterised in that self high frequency is based on the LVQ neural network models of PSO
Specific construction step it is as follows:
(1) randomly generate the particle populations of the connection weight of LVQ models using PSO, each particle represent one group of LVQ model just
Beginning connection weight;
(2) setting value as the training direction of PSO algorithms is reached to realize minimum windspeed mean absolute relative error, completes PSO
The training learning process of algorithm so that the particle in particle populations is constantly brought near optimal particle, exports optimal LVQ god
Through the initial connection weight of network;
(3) the obtained initial connection weight of LVQ neutral nets will be trained to LVQ nerve nets by PSO in above two steps
Network is configured, input and output data using each IMF components of the high frequency subsequence at wind station as neutral net, completes LVQ
Study and training of the neutral net itself to wind speed, form the PSO-LVQ of self high frequency subsequence air speed data high-precision forecast
Mixed model;
It is the every group of acquisition time of data previous moment super than previous group input data, defeated in for the input data of training
Go out the acquisition time of data than last group of input data super previous moment.
4. method according to claim 2, it is characterised in that self intermediate frequency is based on the extreme learning machine model of CBA
Construction step it is as follows:
(1) bat algorithm is initialized;
The location parameter of every bat represents one group of output weights and hidden layer node threshold value of extreme learning machine, every bat
Initial loudness and pulse rate take 0.5, and bat number 50, iterations is 100, every flight step-length value model of bat
Enclose is [0.001,0.05];
(2) setting value is reached with the output wind speed mean absolute relative error of extreme learning machine to be guided as the fitness of bat algorithm
Function, the loudness and pulse rate of every bat of real-time update so that bat is flown to the input weights of extreme learning machine and implies
The corresponding optimal solution of node layer threshold value;
In preceding 50 iteration, the flight step-length of bat takes maximum, and since the 51st iteration, the flight step-length of bat takes most
Small value;
(3) the input weights and the corresponding optimal solution of hidden layer node threshold value of the extreme learning machine of (2) acquisition are utilized, by wind station
Input and output data of each IMF components of intermediate frequency subsequence as extreme learning machine, carry out extreme learning machine model training, obtain
To the extreme learning machine model based on CBA;
It is the every group of acquisition time of data previous moment super than previous group input data, defeated in for the input data of training
Go out the acquisition time of data than last group of input data super previous moment.
5. method according to claim 2, it is characterised in that the construction step of self low frequency RARIMA model is such as
Under:
(1) whole IMF components air speed datas that acquisition is decomposed to each low frequency subsequence using nonparametric pleasure boat method of inspection enter
Row data stationary test;
Such as run into certain IMF components air speed data and be presented non-stationary, then Difference Calculation is carried out to this section of IMF components air speed data straight
To it shows stationarity;
(2) acquisition is decomposed to each low frequency subsequence to by the whole IMF components air speed datas after step 1 stationary test
Carry out sample auto-correlation and sample partial correlation is calculated, and auto-correlation and partial correlation the value determination according to respective component air speed data
The optimal type and Optimal order of RARIMA models;
(3) the optimal type and Optimal order of the RARIMA models for being obtained to step 2, each is solved using maximum-likelihood method
The equation coefficient of IMF components air speed data correspondence RARIMA models, using each IMF components of the low frequency subsequence at wind station as
The input data of RARIMA models, forms self low frequency RARIMA model.
6. the method according to claim any one of 1-5, it is characterised in that the meteorology-advanced multistep of target air measuring station
The construction step of forecast model is as follows:
(1) population of the connection weight of Elman Model of Neural Network is randomly generated using ACO;
(2) setting value as the training direction of ACO algorithms is reached to realize minimum windspeed mean absolute relative error, carries out ACO
The training learning process of algorithm so that, by iteration constantly near optimal solution, output is most for the ant in initialization ant population
The excellent initial connection weight of Elman neutral nets and hidden layer threshold value;
(3) the initial connection weight and threshold value for above-mentioned steps being obtained by ACO training set to Elman neutral nets
Put, it is right that the second layer low frequency component data of air pressure, temperature, humidity and target air measuring station are carried out as Elman neutral nets
The input of study and the training of wind speed and output data, form meteorology-advanced multi-step Predictive Model of target air measuring station;
It is the every group of acquisition time of data previous moment super than previous group input data, defeated in for the input data of training
Go out the acquisition time of data than last group of input data super previous moment.
7. method according to claim 6, it is characterised in that the filtering process described in step 2 uses Unscented kalman
Filter method.
8. the method according to claim any one of 1-5, it is characterised in that described for building the auxiliary of model in step 3
It refers to the m auxiliary air measuring station selected in accordance with the following methods to help air measuring station:
First, to being divided using adaptive noise completely integrated empirical modal by the filtered wind speed sample set of step 2
Solution;
Secondly, treatment is filtered to the data after decomposition;
Then, filtered data signal reconstruction will be carried out again, will obtain the wind speed reconstruct data of each air measuring station;
The wind speed reconstruct data of each auxiliary air measuring station are carried out into correlation test with the wind speed reconstruct data of target air measuring station, by phase
Guan Du sorts from high to low, selects the wind speed that air measuring station is aided in m groups before target air measuring station wind speed reconstruct Data mutuality degree ranking
Reconstruct data and corresponding m auxiliary air measuring station;
Wherein, m is integer, and span is [3,60%N].
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611020632.XA CN106779148B (en) | 2016-11-14 | 2016-11-14 | A kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611020632.XA CN106779148B (en) | 2016-11-14 | 2016-11-14 | A kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106779148A true CN106779148A (en) | 2017-05-31 |
CN106779148B CN106779148B (en) | 2017-10-13 |
Family
ID=58969599
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611020632.XA Active CN106779148B (en) | 2016-11-14 | 2016-11-14 | A kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106779148B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108416372A (en) * | 2018-02-11 | 2018-08-17 | 同济大学 | Wind farm wind velocity acquisition methods based on multiple sensors |
CN108510737A (en) * | 2018-04-12 | 2018-09-07 | 中南大学 | A kind of the automatic driving vehicle power supply method for real-time monitoring and device of fusion wind environment |
CN108985521A (en) * | 2018-08-02 | 2018-12-11 | 广东工业大学 | Output power predicting method, device, equipment and the medium of photovoltaic generating system |
CN109034476A (en) * | 2018-07-27 | 2018-12-18 | 中南大学 | A kind of line of high-speed railway extreme wind speeds big data Forecast method |
CN109034478A (en) * | 2018-07-27 | 2018-12-18 | 中南大学 | A kind of line of high-speed railway strong wind iteration competition high-precision forecasting method |
CN109063907A (en) * | 2018-07-27 | 2018-12-21 | 中南大学 | A kind of big step-ahead prediction method of line of high-speed railway extreme wind speed intelligence traversal |
CN109297713A (en) * | 2018-08-07 | 2019-02-01 | 浙江大学 | It is a kind of based on steadily with the steam turbine hostdown diagnostic method of Non-stationary vibration signal feature selecting |
CN109297735A (en) * | 2018-09-11 | 2019-02-01 | 浙江大学 | Vibration signal method for diagnosing faults towards intelligent power plant coal |
CN109684771A (en) * | 2019-01-11 | 2019-04-26 | 西安电子科技大学 | Maneuvering target state prediction optimization method based on interactive multi-model |
CN110009037A (en) * | 2019-04-03 | 2019-07-12 | 中南大学 | A kind of engineering wind speed Forecasting Approach for Short-term and system based on physical message coupling |
CN110210646A (en) * | 2019-04-25 | 2019-09-06 | 浙江大学 | A kind of high-speed railway high wind alarm retention time dynamic adjusting method based on forecasting wind speed |
CN112149230A (en) * | 2020-09-27 | 2020-12-29 | 中南大学 | Method for predicting comfort deterioration of wind-induced train of strong wind railway |
CN113191524A (en) * | 2021-01-29 | 2021-07-30 | 河北建投新能源有限公司 | Wind speed prediction method and device, storage medium and processor |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5646343A (en) * | 1993-07-02 | 1997-07-08 | Pritchard; Declan Nigel | System and method for monitoring wind characteristics |
CN102830446A (en) * | 2012-08-13 | 2012-12-19 | 国电南京自动化股份有限公司 | Intelligent meteorological station system capable of forecasting meteorological data |
US20130078095A1 (en) * | 2010-03-12 | 2013-03-28 | Ib Svend Olesen | Wind energy power plant equipped with an optical vibration sensor |
CN103389388A (en) * | 2012-05-08 | 2013-11-13 | 华锐风电科技(集团)股份有限公司 | Method and device for predicting wind speed in wind power plant and method and system for predicting power in wind power plant |
CN103616734A (en) * | 2013-12-11 | 2014-03-05 | 山东大学 | System and method for large-range synchronous real-time meteorological data measurement and wind speed and direction prediction |
CN204330280U (en) * | 2015-01-18 | 2015-05-13 | 中南大学 | Train parting flow field on-site testing device |
-
2016
- 2016-11-14 CN CN201611020632.XA patent/CN106779148B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5646343A (en) * | 1993-07-02 | 1997-07-08 | Pritchard; Declan Nigel | System and method for monitoring wind characteristics |
US20130078095A1 (en) * | 2010-03-12 | 2013-03-28 | Ib Svend Olesen | Wind energy power plant equipped with an optical vibration sensor |
CN103389388A (en) * | 2012-05-08 | 2013-11-13 | 华锐风电科技(集团)股份有限公司 | Method and device for predicting wind speed in wind power plant and method and system for predicting power in wind power plant |
CN103389388B (en) * | 2012-05-08 | 2015-08-19 | 华锐风电科技(集团)股份有限公司 | Method for forecasting and device thereof and power forecasting method and system thereof |
CN102830446A (en) * | 2012-08-13 | 2012-12-19 | 国电南京自动化股份有限公司 | Intelligent meteorological station system capable of forecasting meteorological data |
CN103616734A (en) * | 2013-12-11 | 2014-03-05 | 山东大学 | System and method for large-range synchronous real-time meteorological data measurement and wind speed and direction prediction |
CN103616734B (en) * | 2013-12-11 | 2015-11-18 | 山东大学 | Synchronous real time meteorological data is measured and wind speed and direction prognoses system and method on a large scale |
CN204330280U (en) * | 2015-01-18 | 2015-05-13 | 中南大学 | Train parting flow field on-site testing device |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108416372A (en) * | 2018-02-11 | 2018-08-17 | 同济大学 | Wind farm wind velocity acquisition methods based on multiple sensors |
CN108416372B (en) * | 2018-02-11 | 2022-07-19 | 同济大学 | Wind power plant wind speed acquisition method based on multiple sensors |
CN108510737A (en) * | 2018-04-12 | 2018-09-07 | 中南大学 | A kind of the automatic driving vehicle power supply method for real-time monitoring and device of fusion wind environment |
CN108510737B (en) * | 2018-04-12 | 2020-04-10 | 中南大学 | Unmanned vehicle power supply real-time monitoring method and device integrating wind environment |
CN109063907B (en) * | 2018-07-27 | 2020-06-05 | 中南大学 | Intelligent traversal large-step-length prediction method for maximum wind speed along high-speed railway |
CN109063907A (en) * | 2018-07-27 | 2018-12-21 | 中南大学 | A kind of big step-ahead prediction method of line of high-speed railway extreme wind speed intelligence traversal |
CN109034478A (en) * | 2018-07-27 | 2018-12-18 | 中南大学 | A kind of line of high-speed railway strong wind iteration competition high-precision forecasting method |
CN109034476A (en) * | 2018-07-27 | 2018-12-18 | 中南大学 | A kind of line of high-speed railway extreme wind speeds big data Forecast method |
CN109034476B (en) * | 2018-07-27 | 2020-11-17 | 中南大学 | High-speed railway line extreme wind speed big data clustering prediction method |
CN109034478B (en) * | 2018-07-27 | 2021-09-24 | 中南大学 | High-precision prediction method for high-wind iterative competition along high-speed railway |
CN108985521A (en) * | 2018-08-02 | 2018-12-11 | 广东工业大学 | Output power predicting method, device, equipment and the medium of photovoltaic generating system |
CN109297713A (en) * | 2018-08-07 | 2019-02-01 | 浙江大学 | It is a kind of based on steadily with the steam turbine hostdown diagnostic method of Non-stationary vibration signal feature selecting |
CN109297735A (en) * | 2018-09-11 | 2019-02-01 | 浙江大学 | Vibration signal method for diagnosing faults towards intelligent power plant coal |
CN109684771A (en) * | 2019-01-11 | 2019-04-26 | 西安电子科技大学 | Maneuvering target state prediction optimization method based on interactive multi-model |
CN109684771B (en) * | 2019-01-11 | 2021-09-03 | 西安电子科技大学 | Maneuvering target state prediction optimization method based on interactive multi-model |
CN110009037A (en) * | 2019-04-03 | 2019-07-12 | 中南大学 | A kind of engineering wind speed Forecasting Approach for Short-term and system based on physical message coupling |
CN110009037B (en) * | 2019-04-03 | 2020-10-27 | 中南大学 | Short-term engineering wind speed prediction method and system based on physical information coupling |
CN110210646A (en) * | 2019-04-25 | 2019-09-06 | 浙江大学 | A kind of high-speed railway high wind alarm retention time dynamic adjusting method based on forecasting wind speed |
CN112149230B (en) * | 2020-09-27 | 2022-06-10 | 中南大学 | Method for predicting comfort deterioration of wind-induced train of strong wind railway |
CN112149230A (en) * | 2020-09-27 | 2020-12-29 | 中南大学 | Method for predicting comfort deterioration of wind-induced train of strong wind railway |
CN113191524A (en) * | 2021-01-29 | 2021-07-30 | 河北建投新能源有限公司 | Wind speed prediction method and device, storage medium and processor |
CN113191524B (en) * | 2021-01-29 | 2023-07-11 | 河北建投新能源有限公司 | Wind speed prediction method, device, storage medium and processor |
Also Published As
Publication number | Publication date |
---|---|
CN106779148B (en) | 2017-10-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106779148B (en) | A kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion | |
CN106779151B (en) | A kind of line of high-speed railway wind speed multi-point multi-layer coupling prediction method | |
CN106372731B (en) | A kind of high wind line of high-speed railway wind speed spatial network structure forecast method | |
CN104765916B (en) | A kind of Dynamics Performance of High Speed Trains parameter optimization method | |
CN109146162B (en) | A kind of probability wind speed forecasting method based on integrated Recognition with Recurrent Neural Network | |
CN110007652A (en) | A kind of Hydropower Unit degradation trend interval prediction method and system | |
CN106772695B (en) | A kind of Along Railway wind speed forecasting method for merging many air measuring station measured datas | |
CN106557840B (en) | A kind of high wind line of high-speed railway wind speed adaptive decomposition Forecasting Methodology | |
CN107909206A (en) | A kind of PM2.5 Forecasting Methodologies based on deep structure Recognition with Recurrent Neural Network | |
CN105243259A (en) | Extreme learning machine based rapid prediction method for fluctuating wind speed | |
CN106875033A (en) | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting | |
CN104636801A (en) | Transmission line audible noise prediction method based on BP neural network optimization | |
CN107677473A (en) | A kind of GRNN rotating machinery fault Forecasting Methodologies based on FOA optimizations | |
CN104899446A (en) | Method for simulating fluctuating wind speeds on basis of data drive | |
CN110363349A (en) | A kind of LSTM neural network hydrologic(al) prognosis method and system based on ASCS | |
CN108053052A (en) | A kind of oil truck oil and gas leakage speed intelligent monitor system | |
CN109934422A (en) | Neural network wind speed prediction method based on time series data analysis | |
CN103793887A (en) | Short-term electrical load on-line predicting method based on self-adaptation enhancing algorithm | |
CN103020743A (en) | Ultra-short-term wind speed forecasting method for wind power plant | |
CN103955135A (en) | Method for calculating locomotive optimized operation sequence based on double-layer mode curve | |
CN110070228A (en) | BP neural network wind speed prediction method for neuron branch evolution | |
CN109063388A (en) | The micro climate architecture design addressing design method of wind environment simulation | |
CN104933471A (en) | Phase space reconstruction method for use in short-term wind speed prediction method | |
CN107423811B (en) | The streamflow change attribution recognition methods combined based on BP artificial neural network and Scene Simulation | |
CN109408896A (en) | A kind of anerobic sowage processing gas production multi-element intelligent method for real-time monitoring |
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 |