CN106779137A - A kind of method that ship oil consumption is predicted according to sea situation and operating condition - Google Patents

A kind of method that ship oil consumption is predicted according to sea situation and operating condition Download PDF

Info

Publication number
CN106779137A
CN106779137A CN201611001429.8A CN201611001429A CN106779137A CN 106779137 A CN106779137 A CN 106779137A CN 201611001429 A CN201611001429 A CN 201611001429A CN 106779137 A CN106779137 A CN 106779137A
Authority
CN
China
Prior art keywords
oil consumption
data
ship
lasso
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.)
Pending
Application number
CN201611001429.8A
Other languages
Chinese (zh)
Inventor
王胜正
冀宝仙
申心泉
姜春宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Maritime University
Original Assignee
Shanghai Maritime University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Maritime University filed Critical Shanghai Maritime University
Priority to CN201611001429.8A priority Critical patent/CN106779137A/en
Publication of CN106779137A publication Critical patent/CN106779137A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40Business processes related to the transportation industry

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a kind of method for predicting ship oil consumption according to sea situation and operating condition, the method of the prediction ship oil consumption obtains sample data set by data screening, data integration and normalized first, then set up Multiple Linear Regression Forecasting Models of Chinese, based on sample data set, one cost function is defined using minimum of contraction and selection opertor (LASSO algorithms), and return (LARS) algorithm to carry out variable and shrink to be selected with parameter with reference to cross validation and minimum angular convolution, last Osborne Conjugate Search Algorithms solve LASSO and estimate, are calculated ship oil consumption.A kind of method that ship oil consumption is predicted according to sea situation and operating condition proposed by the present invention, the functional relation that can be set up between marine fuel oil consumption and each influence factor, solve the Problems of Multiple Synteny during oil consumption is calculated, ship oil consumption computational accuracy is improved, is had great importance to maritime traffic transport energy-saving and emission-reduction.

Description

A kind of method that ship oil consumption is predicted according to sea situation and operating condition
Technical field
The invention belongs to ship shipping field, and in particular to a kind of side that ship oil consumption is predicted according to sea situation and operating condition Method.
Background technology
Fuel consumption during ship's navigation is subject to meteorological sea conditions, ship navigation state and operating condition etc. many The influence of uncertain factor is planted, and oil consumption prediction is manipulated to ship speed, course etc. and has important directive significance.Accurate oil Consumption calculating can preferably instruct crewman to manipulate ship's navigation, it is ensured that want in seeking time with low oil consumption, low emission, efficient at sailing date The manipulation schemes navigation of benefit.However, the high correlation between the uncertainty and some factors of influence factor causes oil consumption Cannot accurately determine with the functional relation between each influence factor, also cannot oil consumption of the Ship ' between the voyage schedule exactly.
Statistical machine learning is the distribution based on a large amount of historical datas, and model hypothesis are set up with reference to statistical theory, is passed through Algorithm for design process estimates parameter from data and model, and constantly study is deposited so as to improved model performance between Automatic-searching data Rule, be calculated a functional relation approximate to natural model, and unknown data is entered using gained functional relation Row prediction, the generalization ability of test model simultaneously verifies a kind of research method of model hypothesis
Regression analysis is one of method for commonly using in data mining, and it reflects the characteristic of data attribute value, and by letter The relation of number form formula expression data mapping, so that the dependence between finding property value.Regression analysis are widely used In the prediction and the research of dependency relation to data sequence.
LASSO algorithms are that one kind can realize that index set is simplified in machine learning algorithm, and can be processed with multiple common The Biased estimator method of linear behavio(u)r data.The algorithm in loss function by introducing L1Penalty, in regression coefficient Under absolute value sum is less than a constraints for constant, minimize residual sum of squares (RSS), so that the recurrence system of some indexs Number is exactly equal to zero, that is to say, that LASSO algorithms have the sparse characteristic of variable, can eliminate redundancy feature, and pinpointing the problems needs The variable and only to need, obtains the model for having stronger interpretability to result while realizing that index set is simplified.
LARS algorithms are used to determine which variable is selected into model and provides the parameter Estimation of relevant variable.The algorithm is not Certain variable is directly added into each step forward stepwire regression, but is first found out and that change of dependent variable degree of correlation highest Amount, the direction then along least squares error is adjusted to the coefficient of variable, is in course of adjustment, the variable and residual error Coefficient correlation can be gradually reduced until new variable occur to be more than the now variable with the correlation of residual error related with residual error Property, then it is adjusted along the direction of least squares error again, repeat the process, until all variables are selected into certainly In variables collection, required parameter Estimation is finally given.
The content of the invention
The invention provides a kind of method for predicting ship oil consumption according to sea situation and operating condition, ship's navigation is can solve the problem that During oil consumption computational problem, consider the factors such as the influence meteorology of ship's navigation, sea situation, operational configuration and maneuvering performance, By building statistical model and carrying out parameter learning and model training to model with reference to machine learning algorithm, final training obtains one Individual oil consumption forecast model is used to solve quick, the Accurate Prediction of ship oil consumption under the influence of many factors.
A kind of method for predicting ship oil consumption according to sea situation and operating condition that the present invention is provided, primary object is to be based on The ship oil consumption forecast model framework of LASSO algorithms.
Ship oil consumption forecast model framework based on LASSO algorithms is based on ship history aeronautical data and weather sea situation number According to initially setting up Linear Regression Forecasting Model and propose it is assumed that then defining a cost function using LASSO algorithms, and turn It is changed to solution L1The convex quadratic programming problem of the lower square error minimization of loss of constraint, with reference to LARS Algorithm for Solving LASSO problems Sparse solution, realize coefficients model and variables choice, finally training obtaining ship oil consumption forecast model.
In order to realize the above object the invention mainly includes steps:
Step (1) raw data acquisition.Mainly using different equipment and approach collection weather sea state data, ship's navigation Status data and Ship Controling data.
Step (2) data prediction.Initial data for collection in (1) carries out data screening, to data de-noising, cuts With the treatment such as synchronous, then the integrated data from multiple data sources remove redundancy simultaneously, and finally integrated data are united One normalized, obtains model training data set.
Step (3) sets up oil consumption forecast model.According to the characteristic distributions of training dataset and empirical hypothesis in step (2) Meet linear relationship between input feature vector variable and corresponding prediction output variable, set up Multiple Linear Regression Forecasting Models of Chinese.
Step (4) parameter learning and model training.It is fixed using LASSO algorithms based on the training data obtained in step (2) An adopted cost function, and be converted to solution L1The convex quadratic programming problem of the lower square error minimization of loss of constraint, most terminates Close cross validation to learn model parameter with LARS algorithms, and LASSO is solved using Osborne Conjugate Search Algorithms and estimate.Most In the oil consumption forecast model that will be set up in LASSO estimates substitution step (3) afterwards, the oil consumption forecast model after being trained.
Step (5) model application.By what is obtained in unknown meteorological sea state data and Ship Controling data input step (5) In oil consumption forecast model, final oil consumption can be exported and predicted the outcome.
It is of the invention compared with existing artificial neural network (BP-ANN), support vector regression (SVR) forecast model, have Following characteristics:
1. the present invention can realize that variable is sparse, solve Problems of Multiple Synteny and over-fitting the problems such as.
The present invention mainly defines a cost function using LASSO algorithm combinations least square method, based on training data, With reference to cross validation and LARS Algorithm for Solving sparse solutions, realize that parameter is shunk and selected, so as to realize being solved while variables choice Determine Problems of Multiple Synteny.Additionally, LASSO algorithms introduce L in object function1Regularization term, by regularization coefficient Proportion between balance regularization term and square error term, prevent to some extent the situation of model over-fitting.
2. the present invention has stronger generalization ability and result interpretability.
The present invention has considered the possible factor of various influence ship oil consumption predictions, can in unknown test data set Obtain accurate oil consumption to predict the outcome, and preferably the oil consumption that causes of predicted impact factor mutation can be mutated, with compared with Strong generalization ability and the interpretability to predicting the outcome..
Brief description of the drawings
Fig. 1 is a kind of method composition frame chart that ship oil consumption is predicted according to sea situation and operating condition in the present invention;
Fig. 2 predicts the outcome comparison diagram for LASSO, BP-ANN and SVR forecast model;
Fig. 3 is the cumulative point comparison diagram that LASSO, BP-ANN and SVR forecast model predict the outcome;
Fig. 4 is the mean absolute error value that LASSO, BP-ANN and SVR forecast model predict the outcome.
Specific embodiment
The a kind of of present invention offer is provided in detail below in conjunction with the accompanying drawings ship oil consumption is predicted according to sea situation and operating condition Method.Fig. 1 is a kind of method composition frame chart that ship oil consumption is predicted according to sea situation and operating condition.
Such as Fig. 1, the structure of model of the present invention is mainly including five steps:Step (1) raw data acquisition.It is main to use not Same equipment and approach collection weather sea state data, ship navigation state data and Ship Controling data;Step (2) data are located in advance Reason.Initial data for collection in (1) carries out data screening, to data de-noising, cuts and the treatment such as synchronous, then it is integrated come Redundancy is removed simultaneously from the data of multiple data sources, unified normalized finally is carried out to integrated data, obtain model Training dataset;Step (3) sets up oil consumption forecast model.According to the characteristic distributions and experience of training dataset in step (2) Assuming that meeting linear relationship between input feature vector variable and corresponding prediction output variable, Multiple Linear Regression Forecasting Models of Chinese is set up; Step (4) parameter learning and model training.Based on the training data obtained in step (2), in a generation, is defined using LASSO algorithms Valency function, and be converted to solution L1The convex quadratic programming problem of the lower square error minimization of loss of constraint, it is final to be tested with reference to intersection Card learns with LARS algorithms to model parameter, and solves LASSO estimations using Osborne Conjugate Search Algorithms.Finally by LASSO Estimate is substituted into the oil consumption forecast model set up in step (3), the oil consumption forecast model after being trained;Step (5) model Using.In the oil consumption forecast model that will be obtained in unknown meteorological sea state data and Ship Controling data input step (4), can be with The final oil consumption of output predicts the outcome.
Step one:Raw data acquisition
Initial data mainly includes meteorological sea state data, ship's navigation historical data and Ship Controling data.Meteorological data Essentially from the Weather Forecast Information of weather bureau's issue, sea state data some sensors are measured indirectly, ship's navigation historical data Pass through high speed, the acquisition of high-precision sensing device assembly aboard ship of log noon report and installation with data are manipulated, finally will Data are sent to database server and are stored and analyzed.In order to carry out ship oil consumption prediction, it is necessary to the signal of collection includes Oil consumption, fuel density, fuel oil temperature, Angle of Trim, Angle of Heel, the side of a ship high, pitch, rudder angle, true course, yaw angle, drinking water, wind angle, Wind speed, speed through water, ground speed, longitude, latitude, wherein oil consumption as output respond, its dependent variable as model input Variable.
Step 2:Data prediction
Data prediction is the premise for ensureing high-quality model prediction result.In the magnanimity initial data for gathering in practice A large amount of imperfect, inconsistent, repetitions, high-dimensional and Noise data are generally there are, machine learning algorithm has been had a strong impact on Execution efficiency and model complexity.Data screening, data set are passed through to the initial data gathered in step one in the present invention Sample data set is obtained into normalized.
Step 3:Set up oil consumption forecast model
Because ship oil consumption is that have the coefficient result of many factors, it is assumed that meet line between oil consumption and each influence factor Sexual intercourse, therefore forecast model is set up using multiple linear regression, oil consumption forecast model may be used to following formula subrepresentation:
yiTxi+∈i(1)
In formula, xiRepresent i-th sample, yiIt is the corresponding response variable of i-th sample, i.e. oil consumption.∈iIt is to obey normal state The random error of distribution, β=(β12,…,βp)TIt is regression coefficient variable, wherein βjRepresent j-th regression coefficient.
Step 4:Parameter learning and model training
Due to there may be high correlation between the factor for influenceing oil consumption, such as wind speed and wave are high, air pressure and wind it is strong Degree, goods weight and drinking water etc. are separate between each input variable in step 4 in order to ensure, LASSO is used in the present invention Algorithm enters line parameter and shrinks and variables choice.LASSO algorithms may be expressed as solving L as follows1The loss of constraint lower square error is most Small problem:
In formula, N represents sample size, and p represents the input variable number that each sample is included, xijRepresent i-th sample pair J-th input variable answered, βjThe corresponding regression coefficient of j-th input variable is represented, t represents decision regularization set in advance The free parameter of degree, t >=0.
(2) formula is expressed as matrix form:
s.t.||βj||1≤t (3)
BecauseSo,
Formula (3) can be re-written as:
s.t.||βj||1≤t (5)
Method of Lagrange multipliers is expressed as:
In formula, λ >=0 is regulation parameter, weighs squared and L1The proportion of regularization term.Using intersection in the present invention Proof method is combined with LARS algorithms, calculating parameter regularization path, while the parameter lambda in the formula of solution (6), all friendships of λ correspondences Pitch the corresponding λ value of that mean square error of minimum in the average value of the result.Then solved using Osborne Conjugate Search Algorithms LASSO estimates.Oil consumption forecast model is tried to achieve during LASSO estimates finally are substituted into formula (1).
Step 5:Model application
In training the oil consumption forecast model for obtaining in meteorological sea conditions and Ship Controling condition data input step four, The fuel consumption for obtaining ship under the meteorological sea conditions and operating condition can be predicted.By predict fuel consumption values according to Cubic function relation between oil consumption and the speed of a ship or plane extrapolates the speed of following ship's navigation, so as to instruct crewman ensureing navigation peace On the premise of complete, within regulation sailing date, navigated by water with the manipulation schemes of low oil consumption, low emission, high benefit.
Such as Fig. 2 for LASSO, BP-ANN and SVR forecast model predict the outcome comparison diagram.Shown in figure unknown by 20 groups In three kinds of oil consumption forecast models of meteorological sea state data and Ship Controling data input, the final oil consumption of output predicts the outcome and truly Fuel consumption values.It can be seen that under identical navigation condition, prediction of the LASSO forecast models to oil consumption is more accurate, to boat The change of row environment is more sensitive, and it is more stable to predict the outcome.
If Fig. 3 is the cumulative point comparison diagram that LASSO, BP-ANN and SVR forecast model predict the outcome.Mean absolute error (MAE) refer to predicted value and actual value difference means absolute value result.Cumulative point is defined as:
Wherein, M is the size of unknown data collection, ME < δData set of the absolute error that expression predicts the outcome less than δ ton days Size.As can be seen from the figure predict the outcome BP-ANN models and the SVR moulds compared with the error between actual value of LASSO models Type is small, and precision of prediction is higher.
If Fig. 4 is the mean absolute error value comparative result that LASSO, BP-ANN and SVR forecast model predict the outcome, the knot Fruit is obtained on the basis of 5000 test sets.There it can be seen that the mean absolute error for predicting the outcome of LASSO models is most Small, the excursion of mean absolute error is also minimum.
Those skilled in the art can carry out various remodeling and change to the present invention.Therefore, present invention covers falling into Various remodeling and change in the range of appending claims and its equivalent.

Claims (1)

1. a kind of method that ship oil consumption is predicted according to sea situation and operating condition, it is characterised in that it is described according to sea situation with manipulate The method of conditional forecasting ship oil consumption includes following five steps:
Raw data acquisition step:The Weather Forecast Information from weather bureau's issue is collected as meteorological data;By sensor Sea state data is measured indirectly;Ship's navigation historical data is obtained by log noon report;By installing biography aboard ship Sensor component obtains Ship Controling data;Data above is finally sent to database server storage;
Data prediction step:Data screening is carried out for the initial data gathered in raw data acquisition step, data are gone Make an uproar, cut and synchronization process, then the integrated data from multiple data sources remove redundancy simultaneously, and finally integrated data are entered The unified normalized of row, obtains model training data set;
Oil consumption forecast model establishment step:According to the characteristic distributions of training dataset and empirical hypothesis in data prediction step Meet linear relationship between input feature vector variable and corresponding prediction output variable, set up Multiple Linear Regression Forecasting Models of Chinese;
Parameter learning and model training step:It is fixed using LASSO algorithms based on the training data obtained in data prediction step An adopted cost function, and be converted to solution L1The convex quadratic programming problem of the lower square error minimization of loss of constraint, most terminates Close cross validation to learn model parameter with LARS algorithms, and LASSO is solved using Osborne Conjugate Search Algorithms and estimate;Most In LASSO estimates substitution oil consumption forecast model establishment step is set up oil consumption forecast model afterwards, the oil consumption after being trained Forecast model;
Model applying step:Unknown meteorological sea state data and Ship Controling data input oil consumption forecast model establishment step are obtained To oil consumption forecast model in, export final oil consumption and predict the outcome.
CN201611001429.8A 2016-11-14 2016-11-14 A kind of method that ship oil consumption is predicted according to sea situation and operating condition Pending CN106779137A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611001429.8A CN106779137A (en) 2016-11-14 2016-11-14 A kind of method that ship oil consumption is predicted according to sea situation and operating condition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611001429.8A CN106779137A (en) 2016-11-14 2016-11-14 A kind of method that ship oil consumption is predicted according to sea situation and operating condition

Publications (1)

Publication Number Publication Date
CN106779137A true CN106779137A (en) 2017-05-31

Family

ID=58968058

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611001429.8A Pending CN106779137A (en) 2016-11-14 2016-11-14 A kind of method that ship oil consumption is predicted according to sea situation and operating condition

Country Status (1)

Country Link
CN (1) CN106779137A (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107292451A (en) * 2017-07-18 2017-10-24 上海海阳气象导航技术有限公司 A kind of ship speed optimization method and equipment
CN107545785A (en) * 2017-07-21 2018-01-05 华南理工大学 A kind of river channel running method based on big data
CN107944648A (en) * 2018-01-08 2018-04-20 中国船舶工业系统工程研究院 A kind of accurate Forecasting Methodology of large ship speed of a ship or plane rate of fuel consumption
CN108564237A (en) * 2017-12-13 2018-09-21 中国银联股份有限公司 A kind of Capacity Evaluation Model method for building up, capacity evaluating method and device
CN109710879A (en) * 2017-08-17 2019-05-03 中国水利水电科学研究院 A kind of optimized treatment method and device of forecast system of controlling flood
CN109743019A (en) * 2018-12-21 2019-05-10 中国计量大学 The system and method for hot spot temperature prediction and hot spot positioning based on meteorologic factor
CN110046735A (en) * 2018-12-10 2019-07-23 南京航空航天大学 Aircraft based on flying quality analysis is left the theatre fuel consumption appraisal procedure
CN110826790A (en) * 2019-10-31 2020-02-21 天津大学 Intelligent prediction method for construction productivity of cutter suction dredger
CN110849411A (en) * 2018-08-21 2020-02-28 上海博泰悦臻网络技术服务有限公司 Internet of vehicles server, vehicle and vehicle condition evaluation method based on driving oil consumption data
CN111476484A (en) * 2020-04-07 2020-07-31 上海船舶研究设计院(中国船舶工业集团公司第六0四研究院) Ship fuel consumption reason analysis method and device
CN112149909A (en) * 2020-09-28 2020-12-29 神华中海航运有限公司 Ship oil consumption prediction method and device, computer equipment and storage medium
CN112836893A (en) * 2021-02-26 2021-05-25 上海海事大学 Method for predicting ship oil consumption under severe sea conditions based on sea condition and ship navigation conditions
CN112925201A (en) * 2021-01-20 2021-06-08 北京大学 Model prediction control-based fuel control method for ship propulsion system
CN112977754A (en) * 2021-04-07 2021-06-18 梧州欣欣科技发展有限公司 Oil consumption analysis method suitable for running of inland ship
US20220194533A1 (en) * 2019-02-07 2022-06-23 Shell Oil Company Method and system for reducing vessel fuel consumption
CN114780644A (en) * 2022-06-17 2022-07-22 鹏城实验室 Ship navigation data processing method, device, equipment and storage medium
CN115456451A (en) * 2022-09-28 2022-12-09 中远海运科技股份有限公司 Ship oil consumption estimation method and system based on AIS
CN115660137A (en) * 2022-09-07 2023-01-31 中远海运科技股份有限公司 Method for accurately estimating wind wave navigation energy consumption of ship

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110208377A1 (en) * 2007-08-14 2011-08-25 Propeller Control Aps Efficiency optimizing propeller speed control for ships
CN104463381A (en) * 2015-01-04 2015-03-25 福州大学 Building energy consumption predication method based on KPCA and WLSSVM

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110208377A1 (en) * 2007-08-14 2011-08-25 Propeller Control Aps Efficiency optimizing propeller speed control for ships
CN104463381A (en) * 2015-01-04 2015-03-25 福州大学 Building energy consumption predication method based on KPCA and WLSSVM

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
叶睿 等: "基于人工神经网络的船舶油耗模型", 《船舶工程》 *
周雁舟 等: "基于LASSO-LARS的软件复杂性度量属性特征选择研究", 《计算机科学》 *

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107292451B (en) * 2017-07-18 2020-11-03 上海海阳气象导航技术有限公司 Ship speed optimization method and equipment
CN107292451A (en) * 2017-07-18 2017-10-24 上海海阳气象导航技术有限公司 A kind of ship speed optimization method and equipment
CN107545785A (en) * 2017-07-21 2018-01-05 华南理工大学 A kind of river channel running method based on big data
CN109710879A (en) * 2017-08-17 2019-05-03 中国水利水电科学研究院 A kind of optimized treatment method and device of forecast system of controlling flood
CN108564237A (en) * 2017-12-13 2018-09-21 中国银联股份有限公司 A kind of Capacity Evaluation Model method for building up, capacity evaluating method and device
CN107944648A (en) * 2018-01-08 2018-04-20 中国船舶工业系统工程研究院 A kind of accurate Forecasting Methodology of large ship speed of a ship or plane rate of fuel consumption
CN107944648B (en) * 2018-01-08 2021-06-18 中国船舶工业系统工程研究院 Large ship speed and oil consumption rate prediction method
CN110849411A (en) * 2018-08-21 2020-02-28 上海博泰悦臻网络技术服务有限公司 Internet of vehicles server, vehicle and vehicle condition evaluation method based on driving oil consumption data
CN110046735B (en) * 2018-12-10 2021-02-26 南京航空航天大学 Aircraft departure fuel oil consumption evaluation method based on flight data analysis
CN110046735A (en) * 2018-12-10 2019-07-23 南京航空航天大学 Aircraft based on flying quality analysis is left the theatre fuel consumption appraisal procedure
CN109743019B (en) * 2018-12-21 2023-09-19 中国计量大学 System and method for hot spot temperature prediction and hot spot positioning based on meteorological factors
CN109743019A (en) * 2018-12-21 2019-05-10 中国计量大学 The system and method for hot spot temperature prediction and hot spot positioning based on meteorologic factor
US20220194533A1 (en) * 2019-02-07 2022-06-23 Shell Oil Company Method and system for reducing vessel fuel consumption
CN110826790A (en) * 2019-10-31 2020-02-21 天津大学 Intelligent prediction method for construction productivity of cutter suction dredger
CN111476484A (en) * 2020-04-07 2020-07-31 上海船舶研究设计院(中国船舶工业集团公司第六0四研究院) Ship fuel consumption reason analysis method and device
CN111476484B (en) * 2020-04-07 2024-03-12 上海船舶研究设计院(中国船舶工业集团公司第六0四研究院) Ship fuel consumption high cause analysis method and device
CN112149909A (en) * 2020-09-28 2020-12-29 神华中海航运有限公司 Ship oil consumption prediction method and device, computer equipment and storage medium
CN112925201A (en) * 2021-01-20 2021-06-08 北京大学 Model prediction control-based fuel control method for ship propulsion system
CN112925201B (en) * 2021-01-20 2022-01-28 北京大学 Model prediction control-based fuel control method for ship propulsion system
CN112836893A (en) * 2021-02-26 2021-05-25 上海海事大学 Method for predicting ship oil consumption under severe sea conditions based on sea condition and ship navigation conditions
CN112836893B (en) * 2021-02-26 2024-05-14 上海海事大学 Method for predicting ship oil consumption under severe sea conditions based on sea condition and ship navigation condition
CN112977754A (en) * 2021-04-07 2021-06-18 梧州欣欣科技发展有限公司 Oil consumption analysis method suitable for running of inland ship
CN114780644A (en) * 2022-06-17 2022-07-22 鹏城实验室 Ship navigation data processing method, device, equipment and storage medium
CN114780644B (en) * 2022-06-17 2022-09-13 鹏城实验室 Ship navigation data processing method, device, equipment and storage medium
CN115660137A (en) * 2022-09-07 2023-01-31 中远海运科技股份有限公司 Method for accurately estimating wind wave navigation energy consumption of ship
CN115660137B (en) * 2022-09-07 2023-08-11 中远海运科技股份有限公司 Accurate estimation method for wind wave navigation energy consumption of ship
CN115456451A (en) * 2022-09-28 2022-12-09 中远海运科技股份有限公司 Ship oil consumption estimation method and system based on AIS
CN115456451B (en) * 2022-09-28 2023-10-31 中远海运科技股份有限公司 AIS-based ship oil consumption estimation method and system

Similar Documents

Publication Publication Date Title
CN106779137A (en) A kind of method that ship oil consumption is predicted according to sea situation and operating condition
Fan et al. A novel model to predict significant wave height based on long short-term memory network
CN107944648B (en) Large ship speed and oil consumption rate prediction method
CN109214107A (en) A kind of ship's navigation behavior on-line prediction method
CN108960421B (en) Improved online forecasting method for speed of unmanned surface vehicle based on BP neural network
CN109143408B (en) Dynamic region combined short-time rainfall forecasting method based on MLP
CN107092987B (en) Method for predicting autonomous landing wind speed of small and medium-sized unmanned aerial vehicles
CN114444378A (en) Short-term power prediction method for regional wind power cluster
JPWO2006120724A1 (en) Geographic information system using neural network
Zhao et al. An evaporation duct height prediction model based on a long short-term memory neural network
CN112380781B (en) Satellite observation completion method based on reanalysis data and unbalanced learning
CN111144666A (en) Ocean thermocline prediction method based on deep space-time residual error network
Castelão A machine learning approach to quality control oceanographic data
CN115081307A (en) Weather numerical mode assimilation method and device based on neural network
CN115545159A (en) Average sea surface temperature forecasting method of deep neural network
CN116021981A (en) Method, device, equipment and storage medium for predicting ice coating faults of power distribution network line
CN118312792A (en) Artificial intelligent detection method and system for ocean buoy data quality
Liang et al. A multivariate empirical orthogonal function method to construct nitrate maps in the Southern Ocean
Niu et al. Precipitation forecast based on multi-channel ConvLSTM and 3d-CNN
Menaka et al. Prediction of dominant ocean parameters for sustainable marine environment
CN117665974A (en) Sea fog and low cloud coverage two-dimensional distribution field forecasting method and system
CN116822716A (en) Typhoon prediction method, system, equipment and medium based on space-time attention
Domala et al. A Univariate and multivariate machine learning approach for prediction of significant wave height
Eleftheriou et al. Micro climate prediction utilising machine learning approaches
Trifunov et al. A data-driven approach to partitioning net ecosystem exchange using a deep state space model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170531