CN112149909A - Ship oil consumption prediction method and device, computer equipment and storage medium - Google Patents
Ship oil consumption prediction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112149909A CN112149909A CN202011041015.4A CN202011041015A CN112149909A CN 112149909 A CN112149909 A CN 112149909A CN 202011041015 A CN202011041015 A CN 202011041015A CN 112149909 A CN112149909 A CN 112149909A
- Authority
- CN
- China
- Prior art keywords
- oil consumption
- characteristic parameters
- characteristic parameter
- original
- regression 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 38
- 238000007637 random forest analysis Methods 0.000 claims abstract description 38
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 239000000446 fuel Substances 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 12
- 238000012549 training Methods 0.000 description 11
- 238000003066 decision tree Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Biology (AREA)
- Business, Economics & Management (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Algebra (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a ship oil consumption prediction method, a ship oil consumption prediction device, computer equipment and a storage medium. The method for predicting the oil consumption of the ship comprises the steps of obtaining characteristic parameters of the oil consumption of the ship; extracting each oil consumption characteristic parameter by adopting a random forest algorithm to obtain a preset number of original characteristic parameters; preprocessing each original characteristic parameter to obtain a target characteristic parameter; establishing an LASSO regression model according to each target characteristic parameter; and acquiring the current characteristic parameters, and processing the current characteristic parameters by adopting an LASSO regression model to obtain the predicted value of the oil consumption. The number of characteristic parameters required by establishing the model is reduced through the random forest algorithm, a data set with more characteristics can be processed, and before the random forest algorithm is used for extracting the characteristics, data corresponding to the characteristic parameters do not need to be processed in a standardized mode. The interpretability of the model and the accuracy of the prediction can be further improved by the LASSO regression model.
Description
Technical Field
The application relates to the technical field of ships, in particular to a ship oil consumption prediction method, a ship oil consumption prediction device, computer equipment and a storage medium.
Background
In the international shipping market, how to reduce shipping cost and increase profit is a topic that is generally concerned by the international shipping market, and the reduction of host fuel consumption is a key part of the international shipping market. Meanwhile, as the level of people's lives increases with the development of productivity, more and more countries are beginning to pay attention to environmental issues, requiring shipping ships to have lower emissions. These have all prompted shipping companies to pursue lower host fuel consumption.
In the implementation process, the inventor finds that at least the following problems exist in the conventional technology: the current fuel consumption prediction method has the problems of poor interpretability and the like.
Disclosure of Invention
In view of the above, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for predicting fuel consumption of a ship, which can improve interpretability of the fuel consumption prediction method.
In order to achieve the above object, in one aspect, an embodiment of the present invention provides a method for predicting ship oil consumption, including:
acquiring characteristic parameters of oil consumption of a ship;
extracting each oil consumption characteristic parameter by adopting a random forest algorithm to obtain a preset number of original characteristic parameters;
preprocessing each original characteristic parameter to obtain a target characteristic parameter;
establishing an LASSO regression model according to each target characteristic parameter;
and acquiring the current characteristic parameters, and processing the current characteristic parameters by adopting an LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the step of extracting each oil consumption characteristic parameter by using a random forest algorithm to obtain a preset number of original characteristic parameters comprises:
processing each oil consumption characteristic parameter by adopting a random forest algorithm to obtain an importance value of the characteristic;
and extracting the characteristic parameters of the oil consumption according to the importance value to obtain the original characteristic parameters of a preset number.
In one embodiment, the step of extracting each feature parameter according to the importance value to obtain a preset number of original feature parameters includes:
extracting the first K characteristic parameters with the highest importance values; wherein K is a natural number;
and taking the first K characteristic parameters with the highest importance values as the original characteristic parameters with preset quantity.
In one embodiment, the method further comprises the following steps:
obtaining the consistency of the LASSO regression models corresponding to the ships;
under the condition that the consistency is smaller than a preset value, outputting each LASSO regression model;
the method comprises the following steps of obtaining current characteristic parameters, processing the current characteristic parameters by adopting an LASSO regression model, and obtaining a predicted value of oil consumption:
and acquiring an LASSO regression model corresponding to the current characteristic parameters, and processing the current characteristic parameters by adopting the corresponding LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the method further comprises the following steps:
under the condition that the consistency is greater than the preset value, outputting a unified LASSO regression model according to the consistency;
the method comprises the following steps of obtaining current characteristic parameters, processing the current characteristic parameters by adopting an LASSO regression model, and obtaining a predicted value of oil consumption:
and acquiring the current characteristic parameters, and processing the current characteristic parameters by adopting a unified LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the step of preprocessing each original feature parameter to obtain a target feature parameter includes:
and carrying out standardization processing on each original characteristic parameter to obtain a target characteristic parameter.
In one embodiment, in the step of normalizing each original feature parameter to obtain the target feature parameter, the target feature parameter is obtained based on the following formula:
wherein, XnormIs a target characteristic parameter; x is an original characteristic parameter; mu is the mean value of the original characteristic parameters; σ is the standard deviation of the original feature parameters.
On one hand, the embodiment of the invention also provides a ship oil consumption prediction device, which comprises:
the acquisition module is used for acquiring each oil consumption characteristic parameter of the ship;
the characteristic extraction module is used for extracting each oil consumption characteristic parameter by adopting a random forest algorithm to obtain a preset number of original characteristic parameters;
the preprocessing module is used for preprocessing each original characteristic parameter to obtain a target characteristic parameter;
the model construction module is used for establishing an LASSO regression model according to the target characteristic parameters;
and the oil consumption prediction module is used for acquiring the current characteristic parameters and processing the current characteristic parameters by adopting an LASSO regression model to obtain the predicted oil consumption value.
In one aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.
In another aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above method.
One of the above technical solutions has the following advantages and beneficial effects:
according to the ship oil consumption prediction method, the number of the characteristic parameters required by model building is reduced through the random forest algorithm, a data set with more characteristics can be processed, and before the random forest algorithm is used for characteristic extraction, data corresponding to the characteristic parameters do not need to be processed in a standardized mode. And the LASSO regression model can carry out variable screening and complexity adjustment while fitting the generalized linear model. The interpretability of the model and the accuracy of the prediction can be further improved by the LASSO regression model.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is a first schematic flow chart of a method for predicting fuel consumption of a ship in one embodiment;
FIG. 2 is a flowchart illustrating steps of obtaining a predetermined number of original feature parameters according to an embodiment;
FIG. 3 is a flowchart illustrating steps of obtaining a predetermined number of original feature parameters according to one embodiment;
FIG. 4 is a second schematic flow chart of a method for predicting fuel consumption of a ship in one embodiment;
FIG. 5 is a block diagram of a fuel consumption prediction apparatus of a ship according to an embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment;
FIG. 7 is a comparison graph of predicted values and actual values of No. 1 ship;
FIG. 8 is a comparison graph of predicted values and true values of No. 2 vessel.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, a method for predicting oil consumption of a ship is provided, which includes the steps of:
s110, acquiring characteristic parameters of oil consumption of the ship;
the characteristic parameters of the oil consumption are characteristic parameters affecting the oil consumption, and can include a series of characteristic parameters affecting the oil consumption, such as host power, ship speed, draught, host rotating speed, wind direction, wind speed, water flow speed and the like.
Specifically, each oil consumption characteristic parameter of the ship can be obtained by any technical means in the field. In one specific example, each fuel consumption characteristic parameter in the operation of the ship can be obtained through sample collection. In another specific example, the data set including the characteristic parameters may also be directly obtained, so as to obtain the characteristic parameters of oil consumption of the ship.
S120, extracting each oil consumption characteristic parameter by adopting a random forest algorithm to obtain a preset number of original characteristic parameters;
the random forest is a common method in machine learning, a forest is established in a random mode, a lot of decision trees are arranged in the forest, and each decision tree of the random forest is not related. Wherein the decision tree is a tree structure (which may be a binary tree or a non-binary tree), each non-leaf node represents a test on a characteristic attribute, each branch represents an output of the characteristic attribute over a range of values, and each leaf node stores a category. The process of using the decision tree to make a decision is to start from the root node, test the corresponding characteristic attributes in the items to be classified, select an output branch according to the value of the characteristic attributes until the leaf node is reached, and take the category stored by the leaf node as a decision result. After the forest is obtained, when a new input sample enters, each decision tree in the forest judges the belonged category of the sample (for a classification algorithm), and the category selected most is the final classification result. In addition, the random forest can also carry out unsupervised learning clustering and abnormal point detection.
Specifically, the importance of each fuel consumption characteristic parameter can be evaluated by using a random forest algorithm, and in this embodiment, part of the characteristic parameters can be removed according to the importance of each fuel consumption characteristic parameter, so that a preset number of original characteristic parameters can be obtained. In one specific example, the preset number is 5. It should be noted that, in a practical situation, the fuel consumption characteristic parameter generally includes hundreds of characteristic parameters. In the application, the preset number of characteristic parameters are selected according to characteristics of a plurality of oil consumption characteristic parameters through a random forest algorithm, so that the complexity of a subsequent model construction is reduced. For example: in a series of characteristic parameters which can influence the oil consumption, such as the power of a host, the ship speed, the draft, the rotating speed of the host, the wind speed, the wind direction, the wind speed, the water flow speed and the like, 5 characteristic parameters, namely the power of the host, the ship speed, the draft and the rotating speed of the host, are selected through a random forest algorithm.
S130, preprocessing each original characteristic parameter to obtain a target characteristic parameter;
specifically, the original characteristic parameters may be preprocessed by any means in the art, such as: and carrying out steps of standardization, polynomial conversion and the like to obtain target characteristic parameters. It should be noted that the data corresponding to each feature parameter has different dimensions and dimension units, so that each original feature parameter needs to be preprocessed before the subsequent decision model training is used, so as to obtain data applicable to model training.
S140, establishing an LASSO regression model according to the target characteristic parameters;
the LASSO algorithm (last Absolute Shrinkage and Selection Operator) is a regression analysis method for simultaneously selecting and regularizing features, and can enhance the prediction accuracy and interpretability of a statistical model. The LASSO algorithm reveals many important properties of estimators, such as: the association between the LASSO coefficient estimate and the soft threshold is such that the LASSO coefficient estimate is not necessarily unique when the covariates are collinear. The LASSO algorithm is characterized in that variable screening and complexity adjustment are carried out while a generalized linear model is fitted. For example, assume that the model has 100 coefficients, but only 10 of them are non-zero coefficients, which effectively means that "the other 90 variables are not useful for predicting the target value". The LASSO loop automatically performs a "parameter selection" in which the unselected feature variables have a weight of 0 to the whole. Based on the characteristics, the LASSO algorithm is adopted to construct the fuel consumption model, namely, the LASSO regression model is established.
And S150, acquiring the current characteristic parameters, and processing the current characteristic parameters by adopting an LASSO regression model to obtain the predicted value of the oil consumption.
Specifically, on the basis of obtaining the LASSO regression model, the current characteristic parameters are obtained, and the predicted value of the oil consumption can be obtained.
According to the ship oil consumption prediction method, the number of the characteristic parameters required by model building is reduced through the random forest algorithm, a data set with more characteristics can be processed, and before the random forest algorithm is used for characteristic extraction, data corresponding to the characteristic parameters do not need to be subjected to standardization processing. And the LASSO regression model can carry out variable screening and complexity adjustment while fitting the generalized linear model. The interpretability of the model and the accuracy of the prediction can be further improved by the LASSO regression model.
In one embodiment, as shown in fig. 2, the step of extracting each oil consumption characteristic parameter by using a random forest algorithm to obtain a preset number of original characteristic parameters includes:
s210, processing each oil consumption characteristic parameter by adopting a random forest algorithm to obtain an importance value of the characteristic;
specifically, each fuel consumption characteristic parameter can be processed by adopting a random forest algorithm related function in a sklern open source module library integrated algorithm module ensemble, and the output value is an importance value of each characteristic.
It should be noted that, 3 hyper-parameters need to be input in the process: (1) n _ estimators: it represents the number of trees built. In general, the greater the number of trees, the better the performance, and the more stable the prediction, but this also slows down the computation. In this example, the value is 100; (2) n _ jobs: the hyper-parameter represents the number of processors the engine allows to use. If the value is 1, only one processor can be used. A value of-1 indicates no limitation. Setting n _ jobs can accelerate the model calculation speed, and the value is-1 in the embodiment; (3) oob _ score, which is a random forest cross-validation method, i.e., whether to use out-of-bag samples to evaluate the model. Default is False. This document is set to True because the out-of-bag score reflects the generalization ability after a model fit.
And S220, extracting the oil consumption characteristic parameters according to the importance values to obtain a preset number of original characteristic parameters.
Specifically, each fuel consumption characteristic parameter corresponds to an importance value. In this embodiment, each fuel consumption characteristic parameter may be extracted with reference to the importance value according to actual needs. For example: and selecting the first N characteristic parameters with the highest importance values, and then eliminating the characteristic parameters which are difficult to obtain so as to obtain the original characteristic parameters with preset quantity.
In one embodiment, as shown in fig. 3, the step of extracting each feature parameter according to the importance value to obtain a preset number of original feature parameters includes:
s310, extracting the first K characteristic parameters with the highest importance values; wherein K is a natural number;
and S320, taking the first K characteristic parameters with the highest importance values as the original characteristic parameters with preset quantity.
Specifically, the value of the preset number is also K. And sorting from small to large according to the importance values, and selecting the top K characteristic parameters with the highest importance values as the characteristic parameters for constructing the LASSO regression model.
In one embodiment, as shown in fig. 4, the method further includes the steps of:
s410, obtaining the consistency of the LASSO regression models corresponding to the ships;
specifically, the LASSO regression models corresponding to the ships can be obtained by the method of the above embodiment. Furthermore, any technical means in the field can be adopted to obtain the consistency of the LASSO regression models corresponding to the ships.
S420, outputting each LASSO regression model under the condition that the consistency is smaller than a preset value;
specifically, when the consistency is smaller than the preset value, it means that the LASSO regression models corresponding to the ships cannot be used in a unified manner, and for the oil consumption prediction of the ships, the LASSO regression models corresponding to the ships need to be used for the oil consumption prediction.
The method comprises the following steps of obtaining current characteristic parameters, processing the current characteristic parameters by adopting an LASSO regression model, and obtaining a predicted value of oil consumption:
and S430, acquiring an LASSO regression model corresponding to the current characteristic parameters, and processing the current characteristic parameters by adopting the corresponding LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the method further comprises the following steps:
under the condition that the consistency is greater than the preset value, outputting a unified LASSO regression model according to the consistency;
specifically, when the consistency is greater than the preset value, the LASSO regression model corresponding to each ship may be represented by a multi-ship unified model. In one specific example, one of the LASSO regression models may be selected as the unified LASSO regression model among the respective LASSO regression models according to the consistency. In another specific example, the unified LASSO regression model may be finally composed of new variable coefficients according to taking an average value of the coefficients of the variables as the new variable coefficients.
The method comprises the following steps of obtaining current characteristic parameters, processing the current characteristic parameters by adopting an LASSO regression model, and obtaining a predicted value of oil consumption:
and acquiring the current characteristic parameters, and processing the current characteristic parameters by adopting a unified LASSO regression model to obtain the predicted value of the oil consumption.
Specifically, after the unified LASSO regression model is obtained, the unified LASSO regression model can be used to be in the current characteristic parameters, and the predicted value of the oil consumption can be obtained. For example, when the extracted characteristic parameters are the host power, the ship speed, the draft and the host rotation speed, the current host power, the current ship speed, the current draft and the current host rotation speed are obtained, and the unified LASSO regression model is adopted to process the current host power, the current ship speed, the current draft and the current host rotation speed, so that the predicted value of the oil consumption can be obtained.
In one embodiment, the step of preprocessing each original feature parameter to obtain a target feature parameter includes:
and carrying out standardization processing on each original characteristic parameter to obtain a target characteristic parameter.
Specifically, in the characteristic parameters of the ship, each variable has different dimensions and dimension units, so that the raw data also needs to be standardized before a subsequent decision model (i.e., a LASSO regression model) is trained and used.
In one embodiment, in the step of normalizing each original feature parameter to obtain the target feature parameter, the target feature parameter is obtained based on the following formula:
wherein, XnormIs a target characteristic parameter; x is an original characteristic parameter; mu is the mean value of the original characteristic parameters; σ is the standard deviation of the original feature parameters.
It should be understood that although the various steps in the flow charts of fig. 1-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided a ship fuel consumption prediction apparatus, including:
the acquisition module is used for acquiring each oil consumption characteristic parameter of the ship;
the characteristic extraction module is used for extracting each oil consumption characteristic parameter by adopting a random forest algorithm to obtain a preset number of original characteristic parameters;
the preprocessing module is used for preprocessing each original characteristic parameter to obtain a target characteristic parameter;
the model construction module is used for establishing an LASSO regression model according to the target characteristic parameters;
and the oil consumption prediction module is used for acquiring the current characteristic parameters and processing the current characteristic parameters by adopting an LASSO regression model to obtain the predicted oil consumption value.
In one embodiment, the feature extraction module comprises:
the importance value acquisition module is used for processing each oil consumption characteristic parameter by adopting a random forest algorithm to obtain the importance value of the characteristic;
and the original characteristic parameter acquisition module is used for extracting each oil consumption characteristic parameter according to the importance value to obtain a preset number of original characteristic parameters.
In one embodiment, the raw feature parameter obtaining module includes:
the extraction module is used for extracting the first K characteristic parameters with the highest importance values; wherein K is a natural number;
and the confirming module is used for taking the first K characteristic parameters with the highest importance values as the original characteristic parameters with preset quantity.
In one embodiment, the fuel consumption prediction device further includes:
the consistency obtaining module is used for obtaining the consistency of the LASSO regression models corresponding to the ships;
the first comparison module is used for outputting each LASSO regression model under the condition that the consistency is smaller than a preset value;
the oil consumption prediction module is further used for obtaining an LASSO regression model corresponding to the current characteristic parameters, and processing the current characteristic parameters by adopting the corresponding LASSO regression model to obtain the predicted oil consumption value.
In one embodiment, the fuel consumption prediction device further includes:
the second comparison module is used for outputting a unified LASSO regression model according to the consistency under the condition that the consistency is greater than the preset value;
the oil consumption prediction module is also used for obtaining the current characteristic parameters and processing the current characteristic parameters by adopting a unified LASSO regression model to obtain the predicted oil consumption value.
For specific limitations of the fuel consumption prediction device, reference may be made to the above limitations of the fuel consumption prediction method, which are not described herein again. All or part of each module in the oil consumption prediction device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a fuel consumption prediction method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In order to further explain the technical scheme of the application, the ship oil consumption prediction method provided by the application and the processing process of the random forest algorithm provided by the application are verified by specifically combining a specific example as follows:
specifically, feature selection is performed according to different data of two ships, and the steps are as follows:
(1) the number of training cases (samples) is represented by N, and the number of features is represented by M.
(2) Inputting a characteristic number m for determining a decision result of a node on a decision tree; where M should be much smaller than M.
(3) Sampling N times from N training cases (samples) in a mode of sampling with a return sample to form a training set, and using the cases (samples) which are not sampled as a prediction to evaluate the error of the cases (samples).
(4) For each node, m features are randomly selected, and the decision for each node on the decision tree is determined based on these features. Based on the m features, the optimal splitting mode is calculated.
(5) Each tree grows completely without pruning, which may be employed after a normal tree classifier is built.
The method is realized by adopting a function related to a random forest algorithm in [9] of an integrated algorithm module ensemble of a sklern open source module library [8], and 3 hyper-parameters are required to be input in the process: (1) n _ estimators: it represents the number of trees built. In general, the larger the number of trees, the better the performance, and the more stable the prediction, but this also slows down the computation. Based on experience, selecting hundreds of trees in practice is a better choice, so the analysis process takes 100 values; (2) n _ jobs: the hyper-parameter represents the number of processors the engine allows to use. If the value is 1, only one processor can be used. A value of-1 indicates no limitation. Setting n _ jobs can accelerate the model calculation speed, and the analysis process is set to be-1; (3) oob _ score, which is a random forest cross-validation method, i.e., whether to use out-of-bag samples to evaluate the model. Default is False. This document is set to True because the out-of-bag score reflects the generalization ability after a model fit.
Further, the real ship verification of the ship fuel consumption prediction method provided by the application is as follows:
1.1 test data set information
And (3) performing feature extraction by using a random forest, and finally selecting 5 features with high rank of relevance to fuel consumption, wherein a table 1.1 shows feature extraction results of two ships.
TABLE 3.1 feature extraction results
Based on the above feature selection results, we extracted the test data set as shown in table 1.2.
TABLE 1.2 test data
The data of the test set also needs to be standardized, and it should be noted that when the test set is standardized, the data is consistent with the conversion standard of the training data set, for example, the standardization process of the ship test set No. 1 should be converted according to the mean and variance of each variable of the ship training set No. 1, and the standardization of the speed variable of the ship test set No. 1 is shown in formula (2):
μtrainis the mean, σ, of the training set variable ship speed StrainIs the variance of the variable speed S in the training set.
1.2 model accuracy measurement
The model of the ship No. 1 obtained by training the LASSO regression model is shown in formula (3), and the model of the ship No. 2 is shown in formula (4).
Eff1＝-0.164S+0.067P-0.022D+0.022S2-0.009P×S+0.008D×S+0.004W+
0.005P2 (3)
Eff2＝0.105P-0.127S+0.051R+0.026D+0.017S2+0.020R×D-0.018P×D-0.020P×S (4)
In order to verify the accuracy of the training model, R is adopted2The accuracy of the model prediction value is measured. The coefficient of determination (coeffient of determination) is an important statistic that reflects the goodness of fit of the model, as the ratio of the sum of regression squares to the sum of total squares. R2The value is between 0 and 1, and is unitless, and the magnitude reflects the relative degree of regression contribution, i.e., the percentage of the total variation of the dependent variable Y that the regression relationship can interpret. R2Is the most commonly used index for evaluating the quality degree of the regression model, R2The larger (close to 1) is, the better the fitted regression equation is.
On the other hand, the accuracy of the linear model is measured by calculating MSE (mean Square error) [11 ]. The statistical parameter is the mean value of the square sum of the error of the corresponding points of the predicted data and the original data, and the calculation formula is shown as the formula (5):
wherein y isiIs the real data that is to be presented,
is the fitted data, where n is the number of samples.
Table 1.3 shows the results of the model tests.
TABLE 1.3 results of model testing
R2 value MSE value of ship model
No. 1 ship no-load model 0.936865.9665
No. 2 ship no-load model 0.912773.6313
As shown in fig. 7 and 8, the real values of the target parameters in the test set are visually compared with the predicted values of the models, and since the test set has more data, only 200 target parameters in the test set and the corresponding predicted values of the models are randomly selected for display in the visualization process, so that the observation is facilitated.
Fig. 7 and fig. 8 represent the test results of two ship models, respectively, the blue dotted line represents the model predicted value, and the green solid line represents the true value of the target parameter. The comparison results of the predicted values and the actual values shown in FIGS. 7 and 8 and R shown in Table 1.3 were observed2And the MSE value, it can be seen that the model can better fit the fuel consumption in the sea through the five screened features.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring characteristic parameters of oil consumption of a ship;
extracting each oil consumption characteristic parameter by adopting a random forest algorithm to obtain a preset number of original characteristic parameters;
preprocessing each original characteristic parameter to obtain a target characteristic parameter;
establishing an LASSO regression model according to each target characteristic parameter;
and acquiring the current characteristic parameters, and processing the current characteristic parameters by adopting an LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the following steps are further implemented when the processor performs the step of extracting each fuel consumption characteristic parameter by using a random forest algorithm to obtain a preset number of original characteristic parameters:
processing each oil consumption characteristic parameter by adopting a random forest algorithm to obtain an importance value of the characteristic;
and extracting the characteristic parameters of the oil consumption according to the importance value to obtain the original characteristic parameters of a preset number.
In one embodiment, the processor performs the step of extracting each feature parameter according to the importance value to obtain a preset number of original feature parameters, and further performs the following steps:
extracting the first K characteristic parameters with the highest importance values; wherein K is a natural number;
and taking the first K characteristic parameters with the highest importance values as the original characteristic parameters with preset quantity.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
obtaining the consistency of the LASSO regression models corresponding to the ships;
under the condition that the consistency is smaller than a preset value, outputting each LASSO regression model;
and acquiring an LASSO regression model corresponding to the current characteristic parameters, and processing the current characteristic parameters by adopting the corresponding LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
under the condition that the consistency is greater than the preset value, outputting a unified LASSO regression model according to the consistency;
and acquiring the current characteristic parameters, and processing the current characteristic parameters by adopting a unified LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the processor performs the step of preprocessing each original feature parameter to obtain the target feature parameter, and further performs the following steps:
and carrying out standardization processing on each original characteristic parameter to obtain a target characteristic parameter.
In one embodiment, in the step of normalizing each original feature parameter by the processor to obtain the target feature parameter, the target feature parameter is obtained based on the following formula:
wherein, XnormIs a target characteristic parameter; xIs an original characteristic parameter; mu is the mean value of the original characteristic parameters; σ is the standard deviation of the original feature parameters.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring characteristic parameters of oil consumption of a ship;
extracting each oil consumption characteristic parameter by adopting a random forest algorithm to obtain a preset number of original characteristic parameters;
preprocessing each original characteristic parameter to obtain a target characteristic parameter;
establishing an LASSO regression model according to each target characteristic parameter;
and acquiring the current characteristic parameters, and processing the current characteristic parameters by adopting an LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the step of extracting each fuel consumption characteristic parameter by using a random forest algorithm to obtain a preset number of original characteristic parameters is executed by the processor to further implement the following steps:
processing each oil consumption characteristic parameter by adopting a random forest algorithm to obtain an importance value of the characteristic;
and extracting the characteristic parameters of the oil consumption according to the importance value to obtain the original characteristic parameters of a preset number.
In one embodiment, the step of extracting each feature parameter according to the importance value to obtain a preset number of original feature parameters further implements the following steps when executed by the processor:
extracting the first K characteristic parameters with the highest importance values; wherein K is a natural number;
and taking the first K characteristic parameters with the highest importance values as the original characteristic parameters with preset quantity.
In one embodiment, the computer program when executed by the processor further performs the steps of:
obtaining the consistency of the LASSO regression models corresponding to the ships;
under the condition that the consistency is smaller than a preset value, outputting each LASSO regression model;
and acquiring an LASSO regression model corresponding to the current characteristic parameters, and processing the current characteristic parameters by adopting the corresponding LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the computer program when executed by the processor further performs the steps of:
under the condition that the consistency is greater than the preset value, outputting a unified LASSO regression model according to the consistency;
and acquiring the current characteristic parameters, and processing the current characteristic parameters by adopting a unified LASSO regression model to obtain the predicted value of the oil consumption.
In one embodiment, the step of preprocessing each original feature parameter to obtain the target feature parameter further implements the following steps when executed by the processor:
and carrying out standardization processing on each original characteristic parameter to obtain a target characteristic parameter.
In one embodiment, the normalization processing is performed on each original feature parameter to obtain a target feature parameter, and when being executed by the processor, the following steps are further implemented:
wherein, XnormIs a target characteristic parameter; x is an original characteristic parameter; mu is the mean value of the original characteristic parameters; σ is the standard deviation of the original feature parameters.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus DRAM (RDRAM), and interface DRAM (DRDRAM).
In the description herein, references to the description of "some embodiments," "other embodiments," "desired embodiments," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, a schematic description of the above terminology may not necessarily refer to the same embodiment or example.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A ship oil consumption prediction method is characterized by comprising the following steps:
acquiring characteristic parameters of oil consumption of a ship;
extracting each oil consumption characteristic parameter by adopting a random forest algorithm to obtain a preset number of original characteristic parameters;
preprocessing each original characteristic parameter to obtain a target characteristic parameter;
establishing an LASSO regression model according to each target characteristic parameter;
and acquiring current characteristic parameters, and processing the current characteristic parameters by adopting the LASSO regression model to obtain a predicted value of the oil consumption.
2. The method for predicting the oil consumption of the ship according to claim 1, wherein the step of extracting each oil consumption characteristic parameter by using a random forest algorithm to obtain a preset number of original characteristic parameters comprises the following steps:
processing each fuel consumption characteristic parameter by adopting a random forest algorithm to obtain an importance value of the characteristic;
and extracting the oil consumption characteristic parameters according to the importance values to obtain a preset number of original characteristic parameters.
3. The method for predicting the oil consumption of the ship according to claim 2, wherein the step of extracting each characteristic parameter according to the importance value to obtain a preset number of original characteristic parameters comprises:
extracting the first K characteristic parameters with the highest importance values; wherein K is a natural number;
and taking the first K characteristic parameters with the highest importance values as the original characteristic parameters with preset quantity.
4. The method for predicting oil consumption of a ship according to claim 1, further comprising the steps of:
obtaining the consistency of the LASSO regression models corresponding to the ships;
under the condition that the consistency is smaller than a preset value, outputting each LASSO regression model;
the method comprises the following steps of obtaining current characteristic parameters, processing the current characteristic parameters by adopting the LASSO regression model, and obtaining a predicted value of oil consumption:
and acquiring an LASSO regression model corresponding to the current characteristic parameters, and processing the current characteristic parameters by adopting the corresponding LASSO regression model to obtain the predicted value of the oil consumption.
5. The method for predicting oil consumption of a ship according to claim 4, further comprising the steps of:
under the condition that the consistency is greater than a preset value, outputting a unified LASSO regression model according to the consistency;
the method comprises the following steps of obtaining current characteristic parameters, processing the current characteristic parameters by adopting the LASSO regression model, and obtaining a predicted value of oil consumption:
and acquiring current characteristic parameters, and processing the current characteristic parameters by adopting the unified LASSO regression model to obtain a predicted value of the oil consumption.
6. The method for predicting oil consumption of a ship according to claim 1, wherein the step of preprocessing each original characteristic parameter to obtain a target characteristic parameter comprises:
and carrying out standardization processing on each original characteristic parameter to obtain the target characteristic parameter.
7. The method for predicting oil consumption of a ship according to claim 1, wherein in the step of normalizing each original characteristic parameter to obtain the target characteristic parameter, the target characteristic parameter is obtained based on the following formula:
wherein, XnormIs a target characteristic parameter; x is an original characteristic parameter; mu is the mean value of the original characteristic parameters; σ is the standard deviation of the original feature parameters.
8. A ship fuel consumption prediction device is characterized by comprising:
the acquisition module is used for acquiring each oil consumption characteristic parameter of the ship;
the characteristic extraction module is used for extracting each oil consumption characteristic parameter by adopting a random forest algorithm to obtain a preset number of original characteristic parameters;
the preprocessing module is used for preprocessing each original characteristic parameter to obtain a target characteristic parameter;
the model construction module is used for establishing an LASSO regression model according to each target characteristic parameter;
and the oil consumption prediction module is used for acquiring the current characteristic parameters and processing the current characteristic parameters by adopting the LASSO regression model to obtain the predicted oil consumption value.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041015.4A CN112149909A (en) | 2020-09-28 | 2020-09-28 | Ship oil consumption prediction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011041015.4A CN112149909A (en) | 2020-09-28 | 2020-09-28 | Ship oil consumption prediction method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112149909A true CN112149909A (en) | 2020-12-29 |
Family
ID=73894930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011041015.4A Pending CN112149909A (en) | 2020-09-28 | 2020-09-28 | Ship oil consumption prediction method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112149909A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN113673815A (en) * | 2021-07-08 | 2021-11-19 | 三一智矿科技有限公司 | Mine car scheduling method and device based on vehicle data processing |
| CN113682443A (en) * | 2021-09-17 | 2021-11-23 | 中远海运科技(北京)有限公司 | Theoretical daily fuel oil consumption determination method of VLCC ship under instruction navigational speed |
| 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 |
| TWI792418B (en) * | 2021-07-14 | 2023-02-11 | 國立成功大學 | Method for predicting fuel consumption of ship |
| WO2024121137A1 (en) * | 2022-12-06 | 2024-06-13 | Cetasol Ab | A virtual fuel consumption sensor system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004145727A (en) * | 2002-10-25 | 2004-05-20 | Mazda Motor Corp | Automobile energy consumption prediction system, automobile energy consumption prediction server, automobile energy consumption prediction method and automobile energy consumption prediction program |
| US8738421B1 (en) * | 2013-01-09 | 2014-05-27 | Vehbi Koc Foundation Koc University | Driver moderator method for retail sales prediction |
| CN106779137A (en) * | 2016-11-14 | 2017-05-31 | 上海海事大学 | A kind of method that ship oil consumption is predicted according to sea situation and operating condition |
| 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 |
| CN109615232A (en) * | 2018-12-12 | 2019-04-12 | 税友软件集团股份有限公司 | A kind of method, system and the relevant apparatus of credit score prediction |
| CN110298611A (en) * | 2019-05-16 | 2019-10-01 | 重庆瑞尔科技发展有限公司 | Regulate and control method and system based on the cargo shipping efficiency of random forest and deep learning |
| CN110775065A (en) * | 2019-11-11 | 2020-02-11 | 吉林大学 | Hybrid electric vehicle battery life prediction method based on working condition recognition |
| CN110909907A (en) * | 2018-09-18 | 2020-03-24 | 西安四维图新信息技术有限公司 | Method and device for predicting fuel consumption of truck and storage medium |
-
2020
- 2020-09-28 CN CN202011041015.4A patent/CN112149909A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004145727A (en) * | 2002-10-25 | 2004-05-20 | Mazda Motor Corp | Automobile energy consumption prediction system, automobile energy consumption prediction server, automobile energy consumption prediction method and automobile energy consumption prediction program |
| US8738421B1 (en) * | 2013-01-09 | 2014-05-27 | Vehbi Koc Foundation Koc University | Driver moderator method for retail sales prediction |
| CN106779137A (en) * | 2016-11-14 | 2017-05-31 | 上海海事大学 | A kind of method that ship oil consumption is predicted according to sea situation and operating condition |
| 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 |
| CN110909907A (en) * | 2018-09-18 | 2020-03-24 | 西安四维图新信息技术有限公司 | Method and device for predicting fuel consumption of truck and storage medium |
| CN109615232A (en) * | 2018-12-12 | 2019-04-12 | 税友软件集团股份有限公司 | A kind of method, system and the relevant apparatus of credit score prediction |
| CN110298611A (en) * | 2019-05-16 | 2019-10-01 | 重庆瑞尔科技发展有限公司 | Regulate and control method and system based on the cargo shipping efficiency of random forest and deep learning |
| CN110775065A (en) * | 2019-11-11 | 2020-02-11 | 吉林大学 | Hybrid electric vehicle battery life prediction method based on working condition recognition |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN113673815A (en) * | 2021-07-08 | 2021-11-19 | 三一智矿科技有限公司 | Mine car scheduling method and device based on vehicle data processing |
| TWI792418B (en) * | 2021-07-14 | 2023-02-11 | 國立成功大學 | Method for predicting fuel consumption of ship |
| CN113682443A (en) * | 2021-09-17 | 2021-11-23 | 中远海运科技(北京)有限公司 | Theoretical daily fuel oil consumption determination method of VLCC ship under instruction navigational speed |
| CN113682443B (en) * | 2021-09-17 | 2022-05-31 | 中远海运科技(北京)有限公司 | Theoretical daily fuel oil consumption determination method of VLCC ship under instruction navigational speed |
| 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 |
| WO2024121137A1 (en) * | 2022-12-06 | 2024-06-13 | Cetasol Ab | A virtual fuel consumption sensor system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112149909A (en) | Ship oil consumption prediction method and device, computer equipment and storage medium | |
| CN111210024B (en) | Model training method, device, computer equipment and storage medium | |
| CN109408389B (en) | Code defect detection method and device based on deep learning | |
| CN111240975B (en) | Artificial intelligence system risk detection method, device, computer equipment and medium | |
| CN105677791B (en) | For analyzing the method and system of the operation data of wind power generating set | |
| CN112527604A (en) | Deep learning-based operation and maintenance detection method and system, electronic equipment and medium | |
| CN111401472B (en) | Infrared target classification method and device based on deep convolutional neural network | |
| CN114048468A (en) | Intrusion detection method, intrusion detection model training method, device and medium | |
| CN115936262B (en) | Yield prediction method, system and medium based on big data environment interference | |
| CN115656673A (en) | Transformer data processing device and equipment storage medium | |
| US20230161653A1 (en) | Method of managing system health | |
| CN115456107A (en) | Time series abnormity detection system and method | |
| CN117235565A (en) | Transformer fault diagnosis model construction method and device | |
| CN115269247A (en) | Flash memory bad block prediction method, system, medium and device based on deep forest | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN118333235A (en) | Behavior fraud risk prediction method and device and electronic equipment | |
| CN114169460A (en) | Sample screening method, sample screening device, computer equipment and storage medium | |
| CN113935413A (en) | Distribution network wave recording file waveform identification method based on convolutional neural network | |
| CN113836806A (en) | PHM model construction method, system, storage medium and electronic equipment | |
| CN111753907B (en) | Method, device, equipment and storage medium for processing electric quantity data | |
| CN113822336A (en) | Cloud hard disk fault prediction method, device and system and readable storage medium | |
| CN111754103A (en) | Enterprise risk image method, device, computer equipment and readable storage medium | |
| CN110865939B (en) | Application program quality monitoring method, device, computer equipment and storage medium | |
| CN113722230A (en) | Integrated assessment method and device for vulnerability mining capability of fuzzy test tool | |
| EP4372593A1 (en) | Method and system for anonymizsing data |
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 |