CN113919549A - Ship slip rate prediction system - Google Patents
Ship slip rate prediction system Download PDFInfo
- Publication number
- CN113919549A CN113919549A CN202111014629.8A CN202111014629A CN113919549A CN 113919549 A CN113919549 A CN 113919549A CN 202111014629 A CN202111014629 A CN 202111014629A CN 113919549 A CN113919549 A CN 113919549A
- Authority
- CN
- China
- Prior art keywords
- data
- historical
- ship
- points
- meteorological
- 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
- 238000003780 insertion Methods 0.000 claims abstract description 69
- 230000037431 insertion Effects 0.000 claims abstract description 69
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000007637 random forest analysis Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000001502 supplementing effect Effects 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000013523 data management Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 description 23
- 238000012360 testing method Methods 0.000 description 11
- 230000006872 improvement Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000013439 planning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000013535 sea water Substances 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 230000002706 hydrostatic effect Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Abstract
The invention relates to a ship slip rate prediction system, belongs to the technical field of ships, and solves the problem that the slip rate of a course plan cannot be automatically predicted according to weather forecast data in the prior art. The system comprises: the historical data processing module is used for acquiring historical navigation section data, calculating ship heading, acquiring historical meteorological data by using a meteorological data interface, and preprocessing the historical meteorological data to obtain a historical data set; the model training module is used for extracting meteorological data characteristics and actual navigational speed deviation according to the historical data set to obtain a historical sample set, and training to obtain a trained random forest model; the prediction data processing module is used for supplementing insertion points to the original route plan, calculating the ship heading, acquiring meteorological forecast data and obtaining a prediction data set; and the loss-loss rate prediction module is used for extracting meteorological data characteristics according to the prediction data set to obtain a navigational speed deviation prediction value, and calculating the ship loss rate corresponding to the prediction data set according to the planned navigational speed. The loss rate of the automatic prediction air route plan is realized.
Description
Technical Field
The invention relates to the technical field of ships, in particular to a ship slip rate prediction system.
Background
The economic situation in the world is low at present, the international shipping market is inevitably influenced, the shipping cost is reduced, the profit is improved, the general concerned topic of the international market is formed, and the reduction of the fuel consumption of the host is a key part.
Many shipping companies face operating pressure and choose speed optimization to save fuel consumption in the hope of achieving the goal of reducing expenses. The optimization of the navigational speed is to navigate at different navigational speeds in different sea areas according to the sea state conditions of different areas. Therefore, the influence of sea state conditions on the ship speed, i.e. the relation between sea state and slip rate, is analyzed first.
Currently, only the influence of weather on the ship resistance or the ship stall value is studied, and no method or system for predicting the slip rate according to sea conditions exists, wherein the prior art calculates the ship resistance through a mathematical model of hydrostatic resistance, wind resistance and wave resistance increase, and then calculates the stall value of the ship under the same main engine power by using the main engine power, the propeller efficiency and the ship resistance. However, the actual offshore situation is complex, the scheme does not consider the influence of the flow, and needs numerical values which are difficult to measure, such as seawater density, wet surface area, seawater kinematic viscosity and the like, so that the prediction error is large; in addition, although the mainstream viscous flow CFD commercial software has the capability of simulating ship resistance, the engineering application is very complex and time-consuming, complicated model tests are needed, and the cost is high.
Disclosure of Invention
In view of the above analysis, the present invention provides a ship loss-rate prediction system, so as to solve the problem that the loss-rate of an airline plan cannot be automatically predicted according to weather forecast data.
The embodiment of the invention provides a ship slip rate prediction system, which comprises the following steps:
acquiring an original route plan, and supplementing insertion points to obtain supplemented flight segment data; calculating the heading of the ship according to the timestamp, the longitude and the latitude in the supplemented segment data;
based on the supplemented leg data, calling a meteorological data interface to obtain meteorological forecast data, and eliminating abnormal values of the meteorological forecast data and the leg data corresponding to the abnormal values to obtain processed meteorological forecast data and final leg data;
and extracting meteorological data characteristics based on the processed meteorological forecast data and the ship bow direction, transmitting the meteorological data characteristics into a trained random forest model, predicting the navigational speed deviation of the final flight segment data, and calculating the loss rate of the final flight segment data according to the planned navigational speed in the final flight segment data.
Based on the further improvement of the system, the historical navigation section data are obtained, and the ship heading is calculated based on the historical navigation section data, and the method comprises the following steps:
acquiring to-be-processed flight segment data from the flight segment data table according to at least one transmitted time range, wherein the to-be-processed flight segment data comprises: number of turning point, time stamp, longitude, latitude, rotation speed, navigation speed;
judging whether any value of a timestamp, longitude and latitude of each turning point in the leg data to be processed is missing or abnormal, and if so, deleting the historical leg data corresponding to the turning point;
taking the rest to-be-processed flight segment data as historical flight segment data;
in the historical navigation section data, for the historical navigation section data lacking the ship heading, the historical navigation section data at the adjacent time are respectively taken out to be used as two points to be calculated, and the ship heading is calculated according to the longitude and the latitude of the two points to be calculated.
Based on the further improvement of the system, the ship heading is calculated according to the longitude and the latitude of two points to be calculated, and the method comprises the following steps:
dividing the latitude difference between two points to be calculated into a plurality of small segments according to preset dividing precision;
sequentially calculating the distance of each small section on the mercator chart;
summarizing and summing the distances on the mercaton chart of each segment, and recording as p;
dividing the longitude difference between two points to be calculated by a preset dividing precision and recording as q;
calculating an absolute included angle alpha between two points to be calculated, which is arctan (p/q), according to p and q based on an arctan function;
and converting alpha into an included angle with the due north direction to obtain the heading theta of the ship which is 90-alpha.
Based on further improvement of the system, historical meteorological data are obtained by using a meteorological data interface, and are obtained according to timestamps, longitudes and latitudes in historical flight data; the historical meteorological data includes: wind speed, flow velocity and wave height.
Based on the further improvement of the system, the process of obtaining the historical data set after preprocessing the historical navigation section data, the ship heading and the historical meteorological data comprises the following steps:
removing unstable historical flight segment data according to the rotating speed in the historical flight segment data;
removing abnormal values in the historical meteorological data, wherein the abnormal values comprise null values and values larger than 360 degrees;
removing historical flight segment data corresponding to the abnormal values;
and associating the remaining historical navigation section data, ship heading and historical meteorological data according to the same timestamp, longitude and latitude to serve as a historical data set.
Based on the further improvement of the system, the unstable historical segment data comprises:
the rotating speed is less than or equal to 0;
the difference between the maximum rotating speed and the minimum rotating speed exceeds 2 revolutions from the current moment to the previous 15 minutes;
the difference between the rotating speed at the current moment and the rotating speed before 20 minutes exceeds 2 revolutions, and the difference between the average rotating speed from the last 20 minutes to the last 10 minutes and the average rotating speed from the last 10 minutes to the current moment exceeds 2 revolutions;
and if the rotating speed at any moment in the historical flight segment data meets any condition, rejecting the flight segment data at the moment.
Based on a further improvement of the above system, the original route plan includes: turn point number, longitude, latitude, speed, distance to the next turn point, distance to the destination, time scheduled to reach the current turn point;
the step of supplementing insertion points to the original route plan to obtain supplemented route segment data comprises the following steps:
sequentially identifying whether the distance between every two adjacent turning points is greater than the shortest distance, if so, sequentially supplementing 1 or more insertion points according to the shortest distance, setting insertion point numbers, and calculating the longitude and latitude of 1 or more insertion points according to the longitude and latitude of every two adjacent turning points;
based on the spherical trigonometry cosine theorem, calculating the distance between every two adjacent points between the turning point and the insertion point according to the longitude and latitude of the turning point and the insertion point, and taking the distance as the distance to the next turning point; calculating the distance from each insertion point to the destination according to the distance from the turning point to the destination;
and sequentially calculating the time of reaching each insertion point based on the time of reaching the current turning point, the planned navigational speed and the distance between each two adjacent points in the original route plan.
Based on the further improvement of the system, the shortest distance is obtained according to the product of the planned navigational speed of the initial turning point in two adjacent turning points and 1 hour, the longitude and latitude of 1 or more insertion points are calculated, the insertion points are added between the two adjacent turning points by taking the shortest distance as an interval until the distance between any two adjacent points is less than the shortest distance, the insertion points are not added, and the calculation formula of the longitude lot and the latitude lat of each insertion point is as follows:
wherein, lw1Is the latitude, lj, of the initial turning point of two adjacent turning points1Longitude, lw, of the initial turning point2Is the latitude, lj, of the target turning point of two adjacent turning points2The longitude of the target turning point is shown, d is the distance between an insertion point and an initial turning point, wherein the distance between the first insertion point and the initial turning point is the shortest distance, the distance between the second insertion point and the initial turning point is 2 times the shortest distance, and the like; distonext is the distance between two adjacent turning points.
Based on the further improvement of the system, the meteorological data feature extraction method comprises the following steps:
acquiring historical meteorological data in a historical data set or meteorological forecast data in a forecast data set;
the wind speed and the flow speed in the historical meteorological data or the meteorological forecast data are respectively vertically and horizontally decomposed along the corresponding ship heading direction to obtain the wind speed and the flow speed which are vertical to the ship heading direction and the wind speed and the flow speed which are parallel to the ship heading direction, wherein the calculated quantity of the wind speed and the flow speed which are vertical to the ship heading direction is an absolute value;
and then acquiring the wave height in the historical meteorological data or meteorological forecast data, and taking the wave height, the wind speed and the flow speed which are vertical to the heading direction of the ship, and the wind speed and the flow speed which are parallel to the heading direction of the ship as meteorological data characteristics.
Based on the further improvement of above-mentioned system, still include:
the navigation section data management module is used for periodically acquiring navigation section data in navigation by using the data acquisition interface, storing the navigation section data in a navigation section data table, and cleaning, inquiring and counting the data in the navigation section data table;
and the loss-loss rate analysis module is used for selecting actual flight segment data corresponding to the prediction data set from the flight segment data table, calculating the actual loss rate, comparing the actual loss rate with the predicted loss rate, and displaying a comparison result through a visual chart.
Compared with the prior art, the invention can realize at least one of the following beneficial effects:
1. historical meteorological data and meteorological forecast data are acquired in time by establishing a meteorological data interface; the method has the advantages that wind and flow in meteorological data are decomposed along the bow direction, gushes in the meteorological data are abandoned, redundant features are eliminated, the correlation between the meteorological features and the speed deviation is increased, the effectiveness of data features is improved, and the accuracy of model prediction is improved;
2. the method comprises the steps of managing the data of the flight segment in a unified mode, dynamically calculating the heading of a ship according to the longitude and latitude of two adjacent turning points in the data of the flight segment, replacing the heading with the heading under the condition that a flight path plan has no heading, increasing the applicability of a prediction method, automatically establishing the association of the data of the flight segment, the heading of the ship and meteorological data through a timestamp, the longitude and the latitude, and facilitating data analysis and data feature extraction;
3. the ship slip rate is modeled by adopting an integrated algorithm-random forest, so that the method is simple and easy to use, computing resources are saved, model parameters are convenient to adjust and the model training speed is improved by automatically training a system, identifying and displaying training results; the loss-slip rate is predicted by training meteorological data and the speed deviation, and the method has important guiding significance for planning ship routes and making a rotating speed regulation strategy, so that energy efficiency management is promoted, and the effects of energy conservation and emission reduction are improved;
4. the obtained original route plan identifies the turning points with overlong adjacent distances, interpolation is supplemented, the coordinate of the insertion point is calculated by adopting the principle of similar triangles, the distance between two points on the spherical surface is calculated based on the cosine theorem of spherical trigonometry, the interpolated route section data is perfected, and the prediction precision is improved;
5. the interaction among the function modules is realized through the system, the manual operation is reduced, the data is automatically acquired and analyzed, and the system is flexible and easy to use.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
Fig. 1 is a functional block diagram of a ship slip rate prediction system in embodiment 1 of the present invention;
FIG. 2 is a flowchart of a method for obtaining a historical data set according to embodiment 1 of the present invention;
FIG. 3 is an exemplary diagram of a tree with a depth of 3 during random forest model training in embodiment 1 of the present invention;
FIG. 4 is a schematic diagram illustrating the calculation of a large arc length between any two points on the earth in example 1 of the present invention;
fig. 5 is a fitting graph of a predicted value and a true value of the loss rate in embodiment 2 of the present invention;
FIG. 6 is a graph of predicted results of planned loss on airlines in accordance with embodiment 2 of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
In the case of the example 1, the following examples are given,
the invention discloses a ship slip rate prediction system, which comprises the following modules as shown in fig. 1:
the historical data processing module is used for acquiring historical flight data, calculating ship heading based on the historical flight data, acquiring historical meteorological data by using a meteorological data interface, and preprocessing the historical flight data, the ship heading and the historical meteorological data to obtain a historical data set;
the model training module is used for extracting meteorological data characteristics and actual navigational speed deviation according to the historical data set to obtain a historical sample set, and training the random forest model based on the historical sample set to obtain a trained random forest model;
the prediction data processing module is used for supplementing insertion points to the original route plan to obtain supplemented route segment data; calculating ship heading based on the supplemented segment data, acquiring weather forecast data by using a weather data interface, and preprocessing the supplemented segment data, the ship heading and the weather forecast data to obtain a prediction data set;
and the loss-loss rate prediction module is used for extracting meteorological data characteristics according to the prediction data set, calling the trained random forest model to obtain a navigational speed deviation prediction value, and calculating the ship loss rate corresponding to the prediction data set according to the planned navigational speed in the prediction data set.
When the method is implemented, the data in the system module is supported through the data table to obtain and analyze, wherein the data table comprises a flight segment data table used for storing all flight segment data; the historical data table is used for storing the preprocessed historical data and selecting the preprocessed historical data during model training; the prediction data table is used for storing prediction data supplemented and preprocessed according to an original route plan and selecting the prediction data when the loss of slip is predicted; the prediction result table is used for storing the prediction result so as to facilitate data analysis; a weather data table for storing weather data provided by stormGeo in europe and wni, japan.
Calling execution of a background processing method through interface operation of a functional module to acquire data among modules for interaction, wherein a historical data set of a historical data processing module is selected when a model training module executes model training, a prediction data set of the prediction data processing module and a trained model in a model training model are selected in a loss-loss prediction module to acquire a navigational speed deviation prediction value, and then the navigational speed deviation prediction value is converted into a loss-loss rate; and when the historical data set and the prediction data set are preprocessed, the meteorological data is acquired by uniformly utilizing a meteorological data interface.
Compared with the prior art, the method has the advantages that the loss-slip rate is predicted by training meteorological data and the deviation of the navigational speed, the influence of sea conditions and the loss-slip rate is analyzed, and the method has important guiding significance for planning ship routes and making a rotating speed regulation strategy; the system realizes the acquisition, processing, training, prediction and analysis of data, reduces manual operation, and improves the accuracy and the prediction efficiency of prediction results.
Each of the functional modules is explained in detail below.
In the historical data processing module, from the historical segment data to the preprocessed historical data set, as shown in fig. 2, the method includes the following steps:
s11: and screening historical flight segment data from the flight segment data table.
Specifically, the to-be-processed leg data is acquired from a leg data table according to at least one incoming time range, and the to-be-processed leg data comprises: number of turning point, time stamp, longitude, latitude, rotation speed, navigation speed;
judging whether any value of a timestamp, longitude and latitude of each turning point in the flight segment data to be processed is missing or abnormal, and if so, deleting the historical flight segment data corresponding to the turning point;
and taking the rest to-be-processed flight segment data as historical flight segment data.
S12: and calculating the heading of the ship according to the time stamp, the longitude and the latitude in the historical navigation segment data.
It should be noted that, in the ship navigation data collected regularly, the actual ship heading may sometimes be collected, and if the actual ship heading is selected as the historical voyage data, the ship heading does not need to be calculated, so that the efficiency of preprocessing is improved.
In the historical navigation section data, for the historical navigation section data lacking the ship heading, respectively taking out the historical navigation section data of the adjacent time as two points to be calculated, and calculating according to the longitude and the latitude of the two points to be calculated to obtain the ship heading.
Because the latitudes on the mercator chart are unevenly distributed, and the distance of the latitudes cannot be directly calculated by using the latitude difference, the latitude distance is obtained by dividing the latitude difference into small segments as much as possible and then summarizing and summing the small segments, so that the calculation accuracy is improved.
Setting lat1And lat2Respectively the latitude, lot of two points to be calculated1And lot2Longitude of two points to be calculated, k division precision, n division number, and (lat)2-lat1) K is; illustratively, the preset k is 0.0001. The steps of calculating the heading of the ship are as follows:
dividing the latitude difference between two points to be calculated into a plurality of small segments according to preset dividing precision;
sequentially calculating the distance of each small section on the mercator chart;
the distances on the mercaton chart of each segment are summed up and denoted as p, and the formula is as follows:
dividing the longitude difference between two points to be calculated by the preset dividing precision, and marking as q, wherein the formula is as follows:
q＝(lot2-lot1) K (formula 2)
Based on the arctangent function, calculating an absolute included angle alpha between two points to be calculated according to p and q, wherein the formula is as follows:
α ═ arctan (p/q) (equation 3)
And converting alpha into an included angle with the due north direction to obtain the heading theta of the first point between the two points to be calculated, which is 90-alpha. The calculation mode dynamically calculates the heading of the ship according to the timestamp and the longitude and latitude under the condition that the course plan has no heading, and the heading is replaced by the heading of the ship, so that the applicability of the prediction method is improved.
S13: removing unstable historical flight segment data according to the rotating speed in the historical flight segment data;
specifically, the unstable historical leg data includes:
the rotating speed is less than or equal to 0;
the difference between the maximum rotating speed and the minimum rotating speed exceeds 2 revolutions from the current moment to the previous 15 minutes;
the difference between the rotating speed at the current moment and the rotating speed before 20 minutes is more than 2 revolutions, and the difference between the average rotating speed from the last 20 minutes to the last 10 minutes and the average rotating speed from the last 10 minutes to the current moment is more than 2 revolutions.
And if the rotating speed at any moment in the historical flight segment data meets any condition, rejecting the flight segment data at the moment.
S14: and calling a meteorological data interface to obtain historical meteorological data, and eliminating abnormal values and corresponding historical flight segment data.
It should be noted that the meteorological data is derived from global meteorological data, and when the meteorological data interface is called, the timestamp in the leg data is converted according to the timestamp format required by the meteorological data interface, and for example, when the meteorological data interface is called, the timestamp in the leg data is uniformly converted into the unix format.
Calling historical meteorological data obtained by a meteorological data interface according to a timestamp, longitude and latitude in the historical flight data, converting the wind speed and the flow speed in the historical meteorological data from m/s to kn, and unifying the wind speed and the kn with the unit of the flight speed; eliminating null values and abnormal values larger than 360 in the historical meteorological data; and removing historical flight segment data corresponding to the abnormal values.
S15: and associating the remaining historical navigation section data, ship heading and processed historical meteorological data according to the same timestamp, longitude and latitude to serve as a historical data set for subsequent data feature extraction.
In the model training module, selecting one historical data set in the historical data processing module, and extracting the characteristics of the historical meteorological data based on the meteorological data and the ship heading in the historical data set; obtaining actual speed deviation based on the rotating speed and the speed in the historical data set; and taking the historical meteorological data characteristics and the speed deviation as a historical sample set, including a training set and a testing set.
Specifically, the historical meteorological data characteristics comprise wave height, wind speed and flow speed which are obtained by decomposing the wind speed and flow speed in the meteorological data along the ship heading and are perpendicular to the ship heading, and wind speed and flow speed which are parallel to the ship heading, wherein the calculated amount of the wind speed and flow speed which are perpendicular to the ship heading is an absolute value considering that the influence effect on the slip rate of the ship is the same on the left side and the right side of the wind and flow which are perpendicular to the ship heading.
In the embodiment, the surge in the meteorological data is abandoned, the redundant features are eliminated, the correlation between the meteorological features and the speed deviation is increased, the effectiveness of the data features is improved, and the accuracy of model prediction is improved.
Obtaining historical data navigational speed deviation based on the difference between the product of the rotational speed and the pitch coefficient in the historical data set and the navigational speed in the historical data set;
the calculation formula of the speed deviation Δ v is as follows:
Δ v ═ r × l-v (equation 4)
Where v is the speed, r is the speed, l is the pitch coefficient, and the pitch coefficient l is 6 × the ship propeller pitch value/185.2.
And taking the historical meteorological data characteristics and the historical data navigational speed deviation as a historical sample set, including a training set and a testing set. Illustratively, 70% of the historical data sample set is randomly selected as the training set, and 30% of the historical data sample set is selected as the testing set.
A random forest model is built in a model training module, the random forest model is trained on the basis of a training set, the navigational speed deviation is predicted according to a test set, the slip rate is calculated, the slip rate obtained according to the actual navigational speed deviation in the test set is compared, and when the average slip rate error is smaller than 2%, the training is completed.
In order to ensure the stability of the prediction result, a random forest model is adopted, is an integrated algorithm, has good stability, is not easy to over-fit, is not easy to be influenced by individual abnormal samples, and often shows amazing performance in the aspects of classification and regression.
Preferably, the number of trees is set to 500 and the maximum depth limit is 10 during training. The method can be used for ensuring the learning ability of the tree on one hand, and can be used for reducing the complexity of the model, saving the computing resources and accelerating the computing speed on the other hand.
For the purpose of illustrating the construction of trees and branching situations, the depth of the tree is set to 3 for rendering, where one tree is shown in fig. 3.
FIG. 3 is an inverted tree with root nodes above, in which x [0] represents flow parallel to the heading of the vessel and negative numbers represent counter flow; x 2 represents the wind parallel to the bow direction, and the negative number represents the upwind; x 4 represents wave height; samples in the root node represent the number of training samples, value represents the average navigational speed deviation of the training samples corresponding to the node, the lowest layer is a leaf node, the first value in each leaf node is the number of the training samples of the node, and the second value is the average navigational speed deviation of the training samples corresponding to the node.
The root node is divided according to the wave height of x 4, if the wave height is less than 4.05m, the root node is divided into a left node, otherwise, the root node is divided into a right node, and after the root node is divided into corresponding nodes, and the rest is done in sequence until the leaf nodes are reached.
Assuming that the input meteorological data is characterized by a wave height of 4 meters, a flow parallel to the heading of the ship is-2 kn, and a wind parallel to the heading of the ship is-2 kn, according to fig. 3, a sample is divided into left nodes of a second layer according to the wave height of 4.05m of a root node; the left node of the second layer is divided according to the flow velocity parallel to the ship bow direction according to minus 1.274kn, and the flow velocity of input data is-2 kn which is smaller than minus 1.274kn, so that the left node of the third layer is divided. The left node of the third layer is divided according to the wind speed parallel to the ship heading direction according to-1.779 kn, and as the input wind along the ship heading direction is-2 kn which is smaller than-1.779 kn, the left node is divided, as shown in the leftmost side of the leaf node in fig. 3, the obtained yaw rate deviation is 0.723kn, namely the output result of the tree.
Summarizing the navigational speed deviation output by each tree according to the set number, and then taking the average value to obtain the navigational speed deviation output by the random forest model; adding the navigational speed in the training set and the corresponding navigational speed deviation to obtain a theoretical navigational speed; the loss-of-slip is the ratio of the speed deviation to the theoretical speed.
And predicting the navigational speed deviation according to the historical meteorological data characteristics in the test set, calculating the loss rate, and displaying a fitting graph of the predicted value and the true value of the test set. And comparing the loss rate obtained according to the actual speed deviation in the test set, and finishing training when the error of the average loss rate is less than 2%.
Preferably, the trained random forest model can be exported to be a file, so that other systems can be conveniently loaded and used, and the reusability is improved.
The prediction data processing module is mainly used for obtaining a prediction data set based on an original route plan; the original route plan can be imported into the module in a file form according to an actual storage format, analyzed and processed, or acquired from a route planning system by using a data access interface.
It should be noted that, because the too long flight path between many turning points in the original flight path plan prevents the prediction of the loss rate on the flight path between the adjacent turning points, the module interpolates the flight path plan and supplements the interpolation points, thereby improving the prediction accuracy.
Specifically, a route plan is the predicted route information that is made when a ship is launched, and a complete original route plan usually contains: turn point number, longitude, latitude, speed of flight, distance to the next turn point, total distance to destination, time scheduled to reach the current turn point. The step of supplementing the original route plan with insertion points includes:
sequentially identifying whether the distance between every two adjacent turning points is greater than the shortest distance, if so, sequentially supplementing 1 or more insertion points according to the shortest distance, setting insertion point numbers, and calculating the longitude and latitude of 1 or more insertion points according to the longitude and latitude of every two adjacent turning points;
calculating the distance between every two adjacent points between the turning point and the insertion point according to the longitude and latitude of the turning point and the insertion point; calculating the distance from each insertion point to the destination according to the distance from the turning point to the destination;
and sequentially calculating the time of reaching each insertion point based on the time of reaching the current turning point, the planned navigational speed and the distance between each two adjacent points in the original route plan.
The steps are refined into the following small steps:
step 1: taking out a first turning point in the original route plan as a current turning point;
step 2: if the current turning point is not the last turning point, calculating the product of the planned navigational speed of the current turning point and 1 hour to obtain the shortest distance, turning to the step 3, otherwise completing the insertion point supplement, and exiting the traversal;
and step 3: if the distance between the current turning point and the next turning point is smaller than the shortest distance, the insertion point is not added, the next turning point is taken as the current turning point, the step 2 is returned, and if not, the step 4 is carried out;
and 4, step 4: if the distance between the current turning point and the next turning point is greater than the shortest distance and the current turning point and the next turning point do not cross the longitude line of 180 degrees, turning to the step 5, otherwise, turning to the step 8;
and 5: supplementing 1 or more insertion points between the current turning point and the next turning point, calculating the longitude and latitude of 1 or more insertion points, and setting the turning point number of the insertion point;
preferably, the insertion point number-1 can be uniformly set so as to be distinguished from the original turning point.
Step 6: calculating the distance between every two adjacent points and the distance between the insertion point and the destination for the current steering point, 1 or more insertion points and the next steering point;
and 7: calculating the time of reaching each insertion point in sequence based on the time of reaching the current turning point, the planned navigational speed and the distance between each two adjacent points in the original route plan; taking the next turning point as the current turning point, and returning to the step 2;
and 8: if the distance between the current turning point and the next turning point is greater than the shortest distance and the current turning point and the next turning point cross the longitude line of 180 degrees, turning to the step 9, otherwise, returning to the step 2;
and step 9: adding 360 degrees to the negative longitude of the current turning point and the next turning point;
step 10: calculating the longitude and latitude of 1 or more insertion points, the distance between each two adjacent points, the distance from the insertion point to the destination and the time for reaching each insertion point according to the steps 5-7 in sequence;
step 11: subtracting 360 degrees greater than 180 in the current turning point and the next turning point; and taking the next turning point as the current turning point and returning to the step 2.
It should be noted that, according to the mercator projection, points on the earth's surface can be mapped to a two-dimensional plane, on the two-dimensional plane, i.e., mercator chart, all the meridians are perpendicular to the equator with equal distance, and all the wefts are parallel to the equator, perpendicular to the meridians, but are not uniformly distributed. However, when the latitudes of the two inserted turning points are not greatly different, the latitudes between the two turning points can be considered to be uniformly distributed, and the longitude and the latitude of the inserted point are calculated by using the similar triangle principle in the Euclidean geometry.
In the step 5, with the shortest distance as an interval, an insertion point is added between the current turning point and the next turning point until the distance between any two adjacent points is less than the shortest distance, and the insertion point is not added, wherein the calculation formulas of the longitude lot and the latitude lat of each insertion point are as follows:
wherein, lw1As the latitude of the current turning point, lj1Longitude, lw, of the current steering point2Latitude of the next turning point, lj2The longitude of the next turning point is shown, d is the distance between the insertion point and the current turning point, wherein the distance between the first insertion point and the current turning point is the shortest distance, the distance between the second insertion point and the current turning point is 2 times the shortest distance, and the like; distonext is the distance between the current turning point and the next turning point.
The longitude and latitude in equations 5 and 6 are angular values.
In the step 6, the earth is approximated to be a sphere, a distance formula between two points on the earth is calculated by utilizing the spherical trigonometric cosine law, and the distance between every two adjacent points in the route plan is calculated.
As shown in FIG. 4, let us say that any two points P, Q on the earth, and the longitude and latitude of P is (lat)1,lot1) And Q has a longitude and latitude of (lat)2,lot2) N (S) is north pole or south pole, and the connecting lines between the three points are all great arcs, so that the three great arcs form a spherical triangle consisting of the sidesThe formula for calculating the large arc length of PQ obtained by the cosine formula is as follows:
cosPQ ═ cosPN × cosQN + sinPN × sinQN × cos PQN (equation 7)
Let side length PN be
Side length QN of
Angle PNQ is | lot1-lot2Substituting | into equation 7 yields the following equation:
cosPQ＝sin(lat1)sin(lat2)+cos(lat1)cos(lat2)cos(lot1-lot2)
(formula 8)
According to the formula 8, the calculation formula for obtaining the distance dist between two points on the spherical surface is as follows:
dist＝arccos(sin(lat1)sin(lat2)+cos(lat1)cos(lat2)cos(lot1- lot2) ). times 3440.27 (formula 9)
Therefore, according to the formula 9, the longitude and latitude of each adjacent two points of the incoming turning point and the insertion point are obtained, and the distance between each adjacent two points is obtained.
The longitude and latitude in equations 8 and 9 are arc values, and the longitude and latitude in the flight plan are default angle values, and the angle values need to be converted into arc values when calculating the spherical distance.
And obtaining the distance between the adjacent insertion points and the destination according to the distance between the turning point and the destination and the distance between the turning point and the adjacent insertion point in the air route plan, and obtaining the distance between each insertion point and the destination by analogy.
Illustratively, the distance from the first insertion point to the destination, which is adjacent to the current turning point, is the distance from the current turning point to the destination — the distance between the two points of the current turning point and the first insertion point.
Supplementing the insertion value according to the data item required by the flight line plan to obtain supplemented flight segment data; and then according to the method for calculating the ship heading in the step S12, calculating the ship heading according to the timestamp, the longitude and the latitude in the supplemented segment data.
And in the prediction data processing module, according to the timestamp, the longitude and the latitude in the supplemented leg data, calling a meteorological data interface to obtain meteorological forecast data. Considering that a flight may take one or two months, if the incoming timestamp exceeds the current 9 days, the current time is added to the preset time interval to obtain a new timestamp, and weather data is acquired according to the new timestamp. Preferably, the preset time interval is set to 9, that is, the weather forecast data of the 9 th day is uniformly selected for the weather forecast data exceeding the current 9 days.
Converting the wind speed and the flow speed in the acquired meteorological forecast data from m/s to kn, eliminating null values and abnormal values larger than 360 in the meteorological forecast data, eliminating corresponding flight segment data from the supplemented flight segment data, and associating the rest flight segment data, the ship heading and the processed meteorological forecast data according to the same timestamp, longitude and latitude to be used as a prediction data set.
In the loss-loss rate prediction module, according to a method for extracting historical meteorological data characteristics, extracting meteorological data characteristics from meteorological forecast data in a prediction data set: the wind speed and the flow speed which are vertical to the bow direction of the ship, the wind speed and the flow speed which are parallel to the bow direction of the ship and the wave height.
Selecting a random forest model trained by a model training module, or importing a trained model file, transmitting meteorological data characteristics into the random forest model, obtaining a navigational speed deviation predicted value, and calculating the ship slip rate corresponding to a prediction data set according to the planned navigational speed in the prediction data set, wherein the specific steps comprise:
acquiring a predicted value mean of the navigational speed deviation, wherein the predicted value mean of the navigational speed deviation is an average value of the aggregated navigational speed deviations output by each tree in the random forest model;
calculating a theoretical speed _ ideal as speed + mean according to a planned speed and a predicted value mean of the deviation of the speed in the predicted data set;
and calculating the ship slip rate slip corresponding to the prediction data set as mean/speed _ ideal.
Preferably, when the ship sails, in order to avoid inaccurate weather forecast data caused by too long interval time, new weather forecast data can be acquired periodically, and new weather data features are extracted, so that new prediction data are obtained.
Preferably, this embodiment further includes:
the navigation section data management module is used for periodically acquiring navigation section data in navigation by using the data acquisition interface, storing the navigation section data in a navigation section data table, and cleaning, inquiring and counting the data in the navigation section data table;
illustratively, the data acquisition interface is called every 5 minutes to obtain real-time data when the ship sails and the real-time data are stored in the flight segment data table, the flight segment data management module provides an interface query function, and the total consumed time, the total turning point number, the total distance and the specific details of the flight segments meeting the conditions are displayed through the time range and the region range.
And the loss-loss rate analysis module is used for selecting actual flight segment data corresponding to the prediction data set from the flight segment data table, calculating the actual loss rate, comparing the actual loss rate with the predicted loss rate, and displaying a comparison result through a visual chart.
Illustratively, the comparison result is displayed through a line graph and a map and navigation line graph, so that the prediction error can be conveniently analyzed, the model training parameters can be adjusted, and a more accurate model can be obtained.
Compared with the prior art, the ship slip rate prediction system provided by the embodiment uniformly manages the flight segment data, establishes the meteorological data interface, realizes interaction among functional modules through the system, reduces manual operation, automatically acquires and analyzes data, and is flexible and easy to use; under the condition that the course is planned to have no course, dynamically calculating the heading of the ship according to the timestamp and the longitude and latitude, and replacing the course with the heading of the ship, so that the applicability of the prediction method is improved; the method has the advantages that wind and flow in meteorological data are decomposed along the bow direction, gushes in the meteorological data are abandoned, redundant features are eliminated, the correlation between the meteorological features and the speed deviation is increased, the effectiveness of data features is improved, and the accuracy of model prediction is improved; the obtained original route plan identifies the turning points with overlong adjacent distances, interpolation is supplemented, the coordinate of the insertion point is calculated by adopting the principle of similar triangles, the distance between two points on the spherical surface is calculated based on the cosine theorem of spherical trigonometry, and the prediction precision is improved; based on historical navigation data and meteorological data, an integrated algorithm-random forest is adopted to model the ship slip rate, the slip rate condition on the ship route plan is predicted, the method is simple and easy to use, the accuracy is high, and the method has important guiding significance for planning the ship route and making a rotating speed regulation strategy, so that the energy efficiency management is promoted, and the effects of energy conservation and emission reduction are improved.
In the case of the example 2, the following examples are given,
this example in the system of example 1, the actual operating data of a VLCC ship (Very Large river craft, Very Large Crude oil Carrier) was selected from the leg data table for testing and verification.
Selecting 2020.9.9-2020.10.7, 2020.11.21-2020.12.8 flight segment data, extracting time stamps, longitudes, latitudes, rotating speeds and navigational speeds, calculating heading and navigational speed deviation of a ship, preprocessing the deviation, acquiring meteorological data corresponding to the flight segments from a meteorological data interface, removing abnormal data, obtaining 10527 effective data points in total, and forming a history sample set.
Based on the historical sample set, 70% of data is randomly selected as a training set, and 30% of data is selected as a testing set and used for training a random forest model.
The speed deviation is converted into the slip rate through training, and the average absolute error of the slip rate is 1.85 percent, and the median absolute error is 1.34 percent. And selecting 100 data points to draw a fitting graph of the predicted value and the true value of the loss-of-slip ratio, as shown in fig. 5.
The ship is imported for verification from an airline plan of 2020-11-21 to 2020-12-30. Firstly, interpolation is carried out on the turning points, the number of the turning points is supplemented to 975 from the original 65, a meteorological data interface is called to obtain meteorological data, abnormal values and corresponding flight segment data of the abnormal values are removed, and 947 effective turning points are obtained. Calculating the heading data of the ship, extracting meteorological data characteristics, selecting a trained random forest model, and predicting the loss rate of the ship on the air route plan, wherein the result is shown in figure 6, wherein the ordinate represents the loss rate, and the abscissa represents the steering point. The predicted average loss rate is 6.7%, while the average loss rate after the ship actually sails the airline plan is 7.9%, and the error of the loss rate is only 1.2%. And in the loss-loss rate analysis module, the comparison result is displayed through a map and navigation chart, the route is a planned navigation route of the ship, the depth of the color represents the loss-loss rate, the darker the color represents the greater the loss-loss rate, and the lighter the color represents the smaller the loss-loss rate.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (10)
1. A system for predicting a slip rate of a ship, comprising:
the historical data processing module is used for acquiring historical flight data, calculating ship heading based on the historical flight data, acquiring historical meteorological data by using a meteorological data interface, and preprocessing the historical flight data, the ship heading and the historical meteorological data to obtain a historical data set;
the model training module is used for extracting meteorological data characteristics and actual navigational speed deviation according to the historical data set to obtain a historical sample set, and training the random forest model based on the historical sample set to obtain a trained random forest model;
the prediction data processing module is used for supplementing insertion points to the original route plan to obtain supplemented route segment data; calculating ship heading based on the supplemented segment data, acquiring weather forecast data by using a weather data interface, and preprocessing the supplemented segment data, the ship heading and the weather forecast data to obtain a prediction data set;
and the loss-loss rate prediction module is used for extracting meteorological data characteristics according to the prediction data set, calling the trained random forest model to obtain a navigational speed deviation prediction value, and calculating the ship loss rate corresponding to the prediction data set according to the planned navigational speed in the prediction data set.
2. The system for predicting ship slip rate according to claim 1, wherein the step of obtaining historical leg data and calculating ship heading based on the historical leg data comprises the steps of:
acquiring to-be-processed flight segment data from a flight segment data table according to at least one transmitted time range, wherein the to-be-processed flight segment data comprises: number of turning point, time stamp, longitude, latitude, rotation speed, navigation speed;
judging whether any value of a timestamp, longitude and latitude of each turning point in the leg data to be processed is missing or abnormal, and if so, deleting the historical leg data corresponding to the turning point; taking the rest to-be-processed flight segment data as historical flight segment data;
in the historical navigation section data, for the historical navigation section data lacking the ship heading, respectively taking out the historical navigation section data of the adjacent time as two points to be calculated, and calculating according to the longitude and the latitude of the two points to be calculated to obtain the ship heading.
3. The system for predicting ship slip rate according to claim 2, wherein calculating ship heading according to longitude and latitude of the two points to be calculated comprises:
dividing the latitude difference between two points to be calculated into a plurality of small segments according to preset dividing precision;
sequentially calculating the distance of each small section on the mercator chart;
summarizing and summing the distances on the mercaton chart of each segment, and recording as p;
dividing the longitude difference between two points to be calculated by a preset dividing precision and recording as q;
calculating an absolute included angle alpha between two points to be calculated, which is arctan (p/q), according to p and q based on an arctan function;
and converting alpha into an included angle with the due north direction to obtain the heading theta of the ship which is 90-alpha.
4. The system of claim 1, wherein the historical meteorological data obtained by the meteorological data interface is obtained according to a timestamp, longitude and latitude in historical voyage data; the historical meteorological data comprises: wind speed, flow velocity and wave height.
5. The system of claim 4, wherein the pre-processing of the historical leg data, heading and weather data to obtain the historical data set comprises:
removing unstable historical flight segment data according to the rotating speed in the historical flight segment data;
removing abnormal values in the historical meteorological data, wherein the abnormal values comprise null values and values larger than 360 degrees;
removing historical flight segment data corresponding to the abnormal values;
and associating the remaining historical navigation section data, ship heading and historical meteorological data according to the same timestamp, longitude and latitude to serve as a historical data set.
6. The system of claim 5, wherein the historical segment data of the instability comprises:
the rotating speed is less than or equal to 0;
the difference between the maximum rotating speed and the minimum rotating speed exceeds 2 revolutions from the current moment to the previous 15 minutes;
the difference between the rotating speed at the current moment and the rotating speed before 20 minutes exceeds 2 revolutions, and the difference between the average rotating speed from the last 20 minutes to the last 10 minutes and the average rotating speed from the last 10 minutes to the current moment exceeds 2 revolutions;
and if the rotating speed at any moment in the historical flight segment data meets any condition, rejecting the flight segment data at the moment.
7. The ship slip rate prediction system of claim 1 wherein the original route plan comprises: turn point number, longitude, latitude, speed, distance to the next turn point, distance to the destination, time scheduled to reach the current turn point;
the step of supplementing insertion points to the original route plan to obtain supplemented route segment data comprises the following steps:
sequentially identifying whether the distance between every two adjacent turning points is greater than the shortest distance, if so, sequentially supplementing 1 or more insertion points according to the shortest distance, setting insertion point numbers, and calculating the longitude and latitude of 1 or more insertion points according to the longitude and latitude of every two adjacent turning points;
based on the spherical trigonometry cosine theorem, calculating the distance between every two adjacent points between the turning point and the insertion point according to the longitude and latitude of the turning point and the insertion point, and taking the distance as the distance to the next turning point; calculating the distance from each insertion point to the destination according to the distance from the turning point to the destination;
and sequentially calculating the time of reaching each insertion point based on the time of reaching the current turning point, the planned navigational speed and the distance between each two adjacent points in the original route plan.
8. The system of claim 7, wherein the shortest distance is obtained by multiplying the planned speed of the initial turning point of two adjacent turning points by 1 hour, and the longitude and latitude of 1 or more insertion points are calculated by adding an insertion point between two adjacent turning points at an interval of the shortest distance until the distance between any two adjacent turning points is less than the shortest distance and the insertion point is not added, and the longitude lot and latitude lat of each insertion point are calculated by:
wherein, lw1Is the latitude, lj, of the initial turning point of two adjacent turning points1Is the longitude, lw of the initial turning point2Is the latitude, lj, of the target turning point of two adjacent turning points2The longitude of the target turning point is shown, d is the distance between an insertion point and an initial turning point, wherein the distance between the first insertion point and the initial turning point is the shortest distance, the distance between the second insertion point and the initial turning point is 2 times the shortest distance, and the like; distonext is the distance between two adjacent turning points.
9. The system of claim 8, wherein the extracting meteorological data features comprises:
acquiring historical meteorological data in a historical data set or meteorological forecast data in a forecast data set;
the wind speed and the flow speed in the historical meteorological data or the meteorological forecast data are respectively vertically and horizontally decomposed along the corresponding ship heading direction to obtain the wind speed and the flow speed which are vertical to the ship heading direction and the wind speed and the flow speed which are parallel to the ship heading direction, wherein the calculated quantity of the wind speed and the flow speed which are vertical to the ship heading direction is an absolute value;
and then acquiring the wave height in the historical meteorological data or meteorological forecast data, and taking the wave height, the wind speed and the flow speed which are vertical to the heading direction of the ship, and the wind speed and the flow speed which are parallel to the heading direction of the ship as meteorological data characteristics.
10. The system for predicting ship slip rate according to any one of claims 1 to 9, further comprising:
the navigation section data management module is used for periodically acquiring navigation section data in navigation by using the data acquisition interface, storing the navigation section data in a navigation section data table, and cleaning, inquiring and counting the data in the navigation section data table;
and the loss-loss rate analysis module is used for selecting actual flight segment data corresponding to the prediction data set from the flight segment data table, calculating the actual loss rate, comparing the actual loss rate with the predicted loss rate, and displaying a comparison result through a visual chart.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111014629.8A CN113919549A (en) | 2021-08-31 | 2021-08-31 | Ship slip rate prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111014629.8A CN113919549A (en) | 2021-08-31 | 2021-08-31 | Ship slip rate prediction system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113919549A true CN113919549A (en) | 2022-01-11 |
Family
ID=79233666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111014629.8A Pending CN113919549A (en) | 2021-08-31 | 2021-08-31 | Ship slip rate prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113919549A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114444315A (en) * | 2022-01-30 | 2022-05-06 | 中远海运科技股份有限公司 | Ship station avoidance route simulation method and system |
-
2021
- 2021-08-31 CN CN202111014629.8A patent/CN113919549A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114444315A (en) * | 2022-01-30 | 2022-05-06 | 中远海运科技股份有限公司 | Ship station avoidance route simulation method and system |
| CN114444315B (en) * | 2022-01-30 | 2023-10-31 | 中远海运科技股份有限公司 | Ship platform avoidance route simulation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A Three-Dimensional Dijkstra's algorithm for multi-objective ship voyage optimization | |
| CN107292451B (en) | Ship speed optimization method and equipment | |
| Tillig et al. | Reduced environmental impact of marine transport through speed reduction and wind assisted propulsion | |
| JP4934756B1 (en) | Ship optimum route calculation system, vessel operation support system, vessel optimum route calculation method, and vessel operation support method | |
| Tsou et al. | An Ant Colony Algorithm for efficient ship routing | |
| Wu et al. | Long-voyage route planning method based on multi-scale visibility graph for autonomous ships | |
| CN113033073A (en) | Unmanned ship energy efficiency digital twinning method and system based on data driving | |
| Chen | A dynamic program for minimum cost ship routing under uncertainty | |
| Takashima et al. | 4 On the fuel saving operation for coastal merchant ships using weather routing | |
| CN109188464B (en) | Fishing boat in-port and out-of-sea time analysis method based on Beidou boat position data | |
| CN112446096A (en) | Ship host engine oil consumption dynamic estimation method based on big navigation data | |
| Sasa et al. | Speed loss analysis and rough wave avoidance algorithms for optimal ship routing simulation of 28,000-DWT bulk carrier | |
| Cristea et al. | Operational shipping intelligence through distributed cloud computing | |
| Kim et al. | Weather routing for offshore transportation using genetic algorithm | |
| CN113919549A (en) | Ship slip rate prediction system | |
| CN106372750A (en) | Sailing management method and system | |
| Perttola | Digital navigator on the seas of the Selden Map of China: Sequential least-cost path analysis using dynamic wind data | |
| CN113962473A (en) | Ship route planning method and device, electronic equipment and storage medium | |
| Mannarini et al. | VISIR-1. b: Ocean surface gravity waves and currents for energy-efficient navigation | |
| CN108052629A (en) | A kind of quick extra large land determination methods based on high accuracy DEM data | |
| CN112099506A (en) | Tracking control method and system for under-actuated unmanned ship time-varying formation | |
| Pan et al. | Development of ship weather routing system with higher accuracy using SPSS and an improved genetic algorithm | |
| CN113682443B (en) | Theoretical daily fuel oil consumption determination method of VLCC ship under instruction navigational speed | |
| CN113935514A (en) | Ship slip rate prediction method based on air route plan and meteorological forecast data | |
| Shao | Development of an intelligent tool for energy efficient and low environment impact shipping |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xi Wen Inventor after: Li Yongjie Inventor after: Wei Muheng Inventor after: Yan Yuanyuan Inventor after: Xue Chen Inventor before: Wei Muheng Inventor before: Yan Yuanyuan Inventor before: Tan Xiao Inventor before: Xue Chen Inventor before: Li Yongjie Inventor before: Xi Wen |