CN116805184A - Ship passing time prediction method and system - Google Patents
Ship passing time prediction method and system Download PDFInfo
- Publication number
- CN116805184A CN116805184A CN202311055578.2A CN202311055578A CN116805184A CN 116805184 A CN116805184 A CN 116805184A CN 202311055578 A CN202311055578 A CN 202311055578A CN 116805184 A CN116805184 A CN 116805184A
- Authority
- CN
- China
- Prior art keywords
- ship
- time
- vector
- section
- lock
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 239000013598 vector Substances 0.000 claims abstract description 119
- 230000008569 process Effects 0.000 claims abstract description 16
- 238000004140 cleaning Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000011144 upstream manufacturing Methods 0.000 claims description 7
- 230000000737 periodic effect Effects 0.000 claims description 5
- 230000001174 ascending effect Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/30—Flood prevention; Flood or storm water management, e.g. using flood barriers
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a ship passing time prediction method and a ship passing time prediction system, wherein the method comprises the following steps: acquiring ship positioning data and then cleaning to obtain ship candidate information; determining a track point of the ship according to the ship candidate information, and determining a lock section near the track point by using a GEOHOSH algorithm; determining a target track point vector according to the track points, and determining a section endpoint vector according to the section endpoints; judging whether the target track point vector and the section end point vector are intersected or not according to a vector cross multiplication theorem, and if so, determining that the ship passes through the section of the lock; obtaining uplink and downlink information of the ship according to the position relation between the target track point and the section endpoint vector; and acquiring the historical uplink and downlink time of the ship from the ship record table, and predicting the future gate passing time of the ship according to the historical uplink and downlink time and the uplink and downlink information. The ship gate-crossing time prediction method can predict the ship gate-crossing time and provides support for effectively reducing the residence time of the ship in the gate-crossing process and reducing the transportation cost.
Description
Technical Field
The application relates to the technical field of ship scheduling, in particular to a ship passing time prediction method and a ship passing time prediction system.
Background
The ship passing process comprises three steps of declaration, security inspection and passing, so that the time for delivering goods is guaranteed, the detention time of the ship in the passing process is reduced, the transportation cost is reduced, and the ship passing time is predicted to be important. At present, the ship passing time is predicted by mainly using a method based on rules and experience, such as a model based on expert knowledge and experience, and by considering various factors in the passing process, such as weather conditions, ship types and the like, the method has relatively high subjectivity and low accuracy.
Disclosure of Invention
In view of the above, the present application aims to overcome the defects in the prior art, and provide a ship passing time prediction method and system.
The application provides the following technical scheme:
in a first aspect, the present application provides a ship passing time prediction method, including:
acquiring ship positioning data, converting the ship positioning data into binary stream to obtain ship analysis information, and cleaning the ship analysis information to obtain ship candidate information;
determining a track point of the ship according to the ship candidate information, and determining a lock section near the track point by using a GEOHOSH algorithm;
selecting two adjacent target track points from the track points, determining a target track point vector according to the target track points, selecting two section endpoints from the ship lock section, and determining a section endpoint vector according to the section endpoints;
judging whether the target track point vector and the section end point vector are intersected or not according to a vector cross multiplication theorem, and if so, determining that the ship passes through the ship lock section;
obtaining uplink and downlink information of the ship according to the position relation between the target track point and the section endpoint vector;
and acquiring historical uplink and downlink time of the ship from a ship record table, determining average gate passing time of the ship according to the historical uplink and downlink time and the uplink and downlink information, and predicting future gate passing time of the ship by utilizing a propset algorithm according to the average gate passing time.
In one embodiment, the obtaining the ship positioning data, converting the ship positioning data into a binary stream, and obtaining the ship analysis information includes:
extracting original ship positioning data from a ship positioning system, and extracting encapsulated ship positioning data message information;
converting the message information from an ASCII code string form to a binary stream form, and intercepting the binary stream according to the ship positioning data message information conversion standard to obtain binary data;
and the binary data are corresponding to corresponding information segments according to the segments to form the ship analysis information.
In one embodiment, the cleaning the ship analysis information to obtain ship candidate information includes:
cleaning incomplete information and abnormal information in the ship analysis information to obtain normal information;
and performing thinning on the normal information through a linear thinning algorithm to obtain the ship candidate information.
In one embodiment, the determining the track point of the ship according to the ship candidate information, determining the lock section near the track point by using a GEOHASH algorithm, includes:
dividing a map grid by using a GEOHASH algorithm, and inputting the ship candidate information into the map grid to obtain track points of the ship;
inputting the section information of the ship lock into the map grid to obtain the section point of the ship lock; the ship track points and the ship lock section points are in character string form;
and if the track point is the same as the lock section point, indicating that the lock section is near the ship track point.
In one embodiment, the determining whether the target track point vector and the section end point vector intersect according to a vector cross-over theorem, if so, determining that the ship passes through the lock section comprises:
defining the two adjacent target track points as Q1 and Q2, and defining the section end points as P1 and P2;
constructing a vector (Q1-P1), a vector (P1-Q1), a vector (Q1-P2), a vector (P1-Q2), a vector (Q1-Q2) and a vector (P1-P2);
judging whether the vector (Q1-P1), the vector (P1-Q1), the vector (Q1-P2), the vector (P1-Q2), the vector (Q1-Q2) and the vector (P1-P2) meet the following conditions simultaneously or not through a vector cross-multiplication theorem:
if so, it is indicative of the ship passing through the lock section.
In one embodiment, the obtaining the uplink and downlink information of the ship according to the position relationship between the target track point and the section endpoint vector includes:
if the track point Q1 is in the counterclockwise direction of the vector (P1-P2) and the track point Q2 is in the clockwise direction of the vector (P1-P2), the navigation direction of the ship is indicated to be upward;
if the locus point Q1 is in the clockwise direction of the vector (P1-P2) and the locus point Q2 is in the counterclockwise direction of the vector (P1-P2), the navigation direction of the ship is indicated as the down direction.
In one embodiment, the obtaining the historical uplink and downlink time of the ship from the ship record table, and determining the average gate passing time of the ship according to the historical uplink and downlink time and the uplink and downlink information, includes:
acquiring the time of the ship passing through the upstream section of the ship lock and the time of the ship passing through the downstream section of the ship lock from the ship record table;
calculating the difference between the time of passing through the upstream section of the ship lock and the time of passing through the downstream section of the ship lock, and taking the difference as the time of passing through the ship lock;
dividing the passing time into ship ascending time and ship descending time according to the ship navigation direction;
and calculating the uplink average gate-crossing time according to the ship uplink time, and calculating the downlink average gate-crossing time according to the ship downlink time.
In one embodiment, the predicting the future transit time of the vessel using prophet algorithm based on the average transit time comprises:
converting the average gate-crossing time into time series data, and decomposing the time series data into a plurality of combinations of non-periodic variation trend, special event influence item and error item to obtain a future average gate-crossing time prediction model of the ship:
in the method, in the process of the application,for the predicted mean time to pass of the ship, +.>For the aperiodic trend of the average transit time of the ship, +.>Period of average transit time for shipSex tendency, ->For special event influencing items ++>Is an error term.
In one embodiment, after the obtaining the future average gate passing time prediction model of the ship, the method includes:
and performing model fitting and training on the prediction model to obtain a final prediction model, and predicting the future gate crossing time of the ship through the final prediction model.
In a second aspect, the present application also provides a ship passing time prediction system, including:
the acquisition module is used for acquiring ship positioning data, converting the ship positioning data into binary stream to obtain ship analysis information, and cleaning the ship analysis information to obtain ship candidate information;
the determining module is used for determining the track point of the ship according to the ship candidate information and determining the lock section near the track point by using a GEOHASH algorithm;
the selecting module is used for selecting two adjacent target track points from the track points, determining a target track point vector according to the target track points, selecting two section endpoints from the ship lock section, and determining a section endpoint vector according to the section endpoints;
the judging module is used for judging whether the target track point vector and the section endpoint vector are intersected or not according to a vector cross-over theorem, and if so, determining that the ship passes through the lock section;
the obtaining module is used for obtaining the uplink and downlink information of the ship according to the position relation between the target track point and the section endpoint vector;
the prediction module is used for obtaining the historical uplink and downlink time of the ship from the ship record table, determining the average gate passing time of the ship according to the historical uplink and downlink time and the uplink and downlink information, and predicting the future gate passing time of the ship by utilizing a propset algorithm according to the average gate passing time.
The embodiment of the application has the following beneficial effects:
the ship passing time prediction method provided by the application can predict the ship passing time, provides support for effectively reducing the retention time of the ship in the passing process and reducing the transportation cost, and is beneficial to better basis of port managers, ship operators and shipowners in the decision process.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a flow chart of a ship passing time prediction method;
FIG. 2 is a schematic flow diagram of a method for obtaining candidate information of a ship;
FIG. 3 is a schematic view showing the positional relationship between ship track points and lock section end points;
FIG. 4 shows a ship up schematic;
fig. 5 shows a ship's downstream schematic.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
It will be understood that when an element is referred to as being "fixed to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. In contrast, when an element is referred to as being "directly on" another element, there are no intervening elements present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
In the present application, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art according to the specific circumstances.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the templates herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a ship lock time prediction method provided in this embodiment, where the ship lock time prediction method is mainly used for predicting time of a ship passing through a ship lock, and includes:
s101, acquiring ship positioning data, converting the ship positioning data into binary stream to obtain ship analysis information, and cleaning the ship analysis information to obtain ship candidate information.
The ship positioning data can be data obtained from a ship positioning system, the ship positioning system can be an AIS system, a satellite AIS is a ship positioning technology, AIS message information sent by a ship is received through a low-orbit satellite, the satellite forwards the received and decoded AIS message information to a corresponding earth station, so that a land management mechanism can master relevant dynamic information of the ship, the monitoring of the navigation ship in the open sea area is realized, the AIS positioning technology is widely used in the positioning and navigation of the ship, and the data has reliability.
Extracting original ship AIS data support from an AIS system, extracting encapsulated ship AIS message information, converting the message information from an ASCII code string form into a binary stream form, following a ship AIS message information conversion standard, intercepting the binary stream according to a certain number of bits in sequence, and corresponding each binary data segment to a corresponding information segment to form ship AIS analysis information data.
After the ship AIS analysis information data is obtained, the analysis information needs to be cleaned firstly in order to avoid that incomplete information and abnormal information influence the prediction result because of the incomplete information and the abnormal information in the analysis information.
Referring to fig. 2, step S101 further includes:
s1011, cleaning incomplete information and abnormal information in the ship analysis information to obtain normal information.
The data cleaning can clean abnormal data such as incomplete messages, flying spots and the like, and a user can select different data cleaning methods according to requirements, so that the application is not limited.
And S1012, performing thinning on the normal information through a linear thinning algorithm to obtain the ship candidate information.
The AIS point location number is reasonably thinned through a linear thinning algorithm, abnormal and redundant data are removed, analysis efficiency is improved, and the main steps of the linear thinning algorithm in the process are as follows:
1) Representing the original point location data as a sequence comprising a plurality of points;
2) Selecting an appropriate threshold for deciding which points need to be preserved and which points can be deleted;
3) Setting the first point as a starting point, and calculating the linear distance between the current point and the starting point from the second point;
4) Judging whether the distance exceeds a threshold value, if so, taking the current point as a new starting point and reserving the current point; if the point is not exceeded, ignoring the point and continuing to process the next point;
5) And iterating continuously, wherein the last reserved point is the data after the thinning, and taking the data after the thinning as the ship candidate information.
According to the method, the original ship positioning data are cleaned and thinned, so that the processed data meet the follow-up prediction requirements, and inaccurate prediction results caused by the fact that the data do not meet the requirements are avoided.
S102, determining the track point of the ship according to the ship candidate information, and determining the lock section near the track point by using a GEOHASH algorithm.
The AIS data of the ship comprises track data of all ships, wherein the track data also comprises ship track data which does not pass through a selected section, firstly, a map grid is divided by using GEOHIASH, the GEOHIASH is a space index mode, the basic principle is that the earth is understood to be a two-dimensional plane, the plane is recursively decomposed into smaller sub-blocks, and each sub-block has the same code in a certain longitude and latitude range. Geolight converts two-dimensional latitude and longitude into a character string, one character string representing a rectangular area.
After a map grid is obtained, respectively inputting the ship candidate information and the ship lock section information into the map grid to obtain ship track points representing ships and ship lock section points representing ship locks; the ship track points and the ship lock section points are in character string form;
if the trajectory point is the same as the lock section point, it means that the lock section is in the vicinity of the trajectory point.
The sections near the track points can be quickly searched by using the GEOHISH, if the character string of the track points of a certain ship is the same as the character string of the section, the ship is considered to find the sections nearby, and then whether the ship passes through the sections is judged, so that the judgment can be performed without traversing all the sections, the calculation time is saved, and the calculation efficiency is improved.
S103, selecting two adjacent target track points from the track points, determining target track point vectors according to the target track points, selecting two section endpoints from the ship lock sections, and determining section endpoint vectors according to the section endpoints.
Selecting the latitude and longitude range of the ship lock, dividing the section, and extracting the character string value of the section and the latitude and longitude of the left end point and the right end point of the section.
Calculating the character string value of the current ship AIS track point, and finding out the section with the same character string as the current ship AIS track point as the section to be judged.
Referring to fig. 3, the two adjacent target trajectory points are defined as Q1 and Q2, and the section end points are defined as P1 and P2;
construct vector (Q1-P1), vector (P1-Q1), vector (Q1-P2), vector (P1-Q2), vector (Q1-Q2) and vector (P1-P2).
And S104, judging whether the target track point vector and the section endpoint vector are intersected or not through a vector cross-over theorem, and if so, determining that the ship passes through the lock section.
Judging whether the vector (Q1-P1), the vector (P1-Q1), the vector (Q1-P2), the vector (P1-Q2), the vector (Q1-Q2) and the vector (P1-P2) meet the following conditions simultaneously or not through a vector cross-multiplication theorem:
if so, it is indicative of the ship passing through the lock section.
The principle of the vector cross theorem is as follows:
assuming that there are vector a (x 1, y 1) and vector B (x 2, y 2), the formula for the calculation of the vector product is as follows:
the modular length of the vector product is as follows: (where θ represents the angle between the two vectors (assuming a common origin) (0.ltoreq.θ.ltoreq.180°) which lies in the plane defined by the two vectors.
The operation result of the vector cross multiplication is a cross product, the cross product of two vectors is perpendicular to the two vectors, and the direction of the A multiplied by B is determined by turning the vector A to the vector B according to the right hand rule, so that the spatial position relation between the vector A and the vector B can be judged by the direction of the cross product, namely the cross product is positive and negative: if A B <0, then vector A is in the counterclockwise direction of vector B; if A B >0, then vector A is in the clockwise direction of B.
When the trajectory line segment Q1Q2 is collinear with but not coincident with the cross-section line segment P1P2, a rectangle having Q1Q2 as a diagonal line and a rectangle having P1P2 as a diagonal line are constructed and whether or not to intersect is determined, wherein the coordinates of Q1 are defined as (xq 1, yq 1), the coordinates of Q2 are defined as (xq 2, yq 2), the coordinates of P1 are defined as (xp 1, yp 1), the coordinates of P2 are defined as (xp 2, yp 2), and the determination conditions are as follows:
s105, obtaining the uplink and downlink information of the ship according to the position relation between the target track point and the section endpoint vector.
Referring to fig. 4, if the trajectory point Q1 is in the counterclockwise direction of the vector (P1-P2) and the trajectory point Q2 is in the clockwise direction of the vector (P1-P2), it means that the ship navigation direction is upward.
Referring to fig. 5, if the trajectory point Q1 is in the clockwise direction of the vector (P1-P2) and the trajectory point Q2 is in the counterclockwise direction of the vector (P1-P2), it means that the ship navigation direction is descending.
The anticlockwise and clockwise directions of the ship track points on the section can be judged through the vector cross-over theorem. The specific judgment conditions are as follows:
1) The ship descending needs to meet one of the following conditions:
2) The ship uplink needs to meet one of the following conditions:
s106, acquiring historical uplink and downlink time of the ship from a ship record table, determining average gate-crossing time of the ship according to the historical uplink and downlink time and the uplink and downlink information, and predicting future gate-crossing time of the ship by utilizing a prophet algorithm according to the average gate-crossing time.
And obtaining the time of the ship passing through the upstream section of the lock and the time of the ship passing through the downstream section of the lock from the ship record table. The difference between the time of passing through the section upstream of the ship lock and the time of passing through the section downstream of the ship lock is calculated and taken as the time of passing through the ship lock.
And dividing the passing time into ship ascending time and ship descending time according to the ship navigation direction.
Referring to fig. 4 and 5, it can be seen that the ship is illustrated as descending if it first passes through the upstream section of the lock, and that the ship is illustrated as ascending if it first passes through the downstream section of the lock. And then calculating the uplink average gate-crossing time according to the ship uplink time, and calculating the downlink average gate-crossing time according to the ship downlink time.
Converting the average gate-crossing time into time series data, and decomposing the time series data into a plurality of combinations of non-periodic variation trend, special event influence item and error item to obtain a future average gate-crossing time prediction model of the ship:
in the method, in the process of the application,for the predicted mean time to pass of the ship, +.>For the aperiodic trend of the average transit time of the ship, +.>Is a periodic trend of average crossing time of ship, +.>For special event influencing items ++>Is an error term.
In the method, in the process of the application,mean cycle rate of increase of mean time to crossing of a ship over time t +.>For the number of times before a specific time the average transit time of the ship is changed, < >>For the time increment rate change, +.>For the offset +.>=-s×/>Is related to the selection of mutation points caused by special time.
In the method, in the process of the application,for the length of the statistical period>、/>For Fourier coefficients, ++>The order of the fourier series is self-adjusting for prophet.
In the method, in the process of the application,for the collection of special events (like holiday effects) of ship crossing +.>Date for a single special event, +.>Factor influencing the model for the corresponding event, +.>Is the time contained in the window period.
After obtaining a prediction model, performing model fitting and training on the prediction model to obtain a final prediction model, and predicting the future lock passing time of the ship through the final prediction model, wherein the ship in the application refers to all ships passing through a lock, and does not refer to a certain fixed ship.
The training process comprises the following steps: and (3) inputting the historical gate crossing time of the ship into a prediction model, enabling an output result of the model to be the future gate crossing time of the ship, continuously adjusting parameters of the prediction model until the output result is the future gate crossing time if the output result is not the future gate crossing time, and taking the prediction model at the moment as a final prediction model.
To verify the accuracy of the final predictive model, historical gate crossing times over a plurality of time periods may be collected, for example: and collecting ship passing time of 1 month and 2 months, inputting the passing time of 1 month into a final prediction model, verifying whether the similarity between the output result and the average passing time of the ship of 2 months reaches a preset similarity threshold value, and if the similarity threshold value is reached, indicating that the final prediction model can normally predict future passing time.
According to the method and the device, information in historical ship operation data can be fully utilized, and prediction accuracy is improved. The data resource and the value of the large water transportation data are fully utilized, the prediction model can automatically learn and discover rules from the large-scale ship operation data, so that the prediction capability is improved, and more accurate and comprehensive gate passing time prediction is provided.
In addition, machine learning and ship operation data are combined, ship passing time prediction is achieved, support is provided for how to reduce the retention time of the ship in the passing process, and port management efficiency is improved.
Example 2
The application also provides a ship passing time prediction system, which comprises:
the acquisition module is used for acquiring ship positioning data, converting the ship positioning data into binary stream to obtain ship analysis information, and cleaning the ship analysis information to obtain ship candidate information;
the determining module is used for determining the track point of the ship according to the ship candidate information and determining the lock section near the track point by using a GEOHASH algorithm;
the selecting module is used for selecting two adjacent target track points from the track points, determining a target track point vector according to the target track points, selecting two section endpoints from the ship lock section, and determining a section endpoint vector according to the section endpoints;
the judging module is used for judging whether the target track point vector and the section endpoint vector are intersected or not according to a vector cross-over theorem, and if so, determining that the ship passes through the lock section;
the obtaining module is used for obtaining the uplink and downlink information of the ship according to the position relation between the target track point and the section endpoint vector;
the prediction module is used for obtaining the historical uplink and downlink time of the ship from the ship record table, determining the average gate passing time of the ship according to the historical uplink and downlink time and the uplink and downlink information, and predicting the future gate passing time of the ship by utilizing a propset algorithm according to the average gate passing time.
It will be appreciated that the implementation of the ship passing time prediction method in the above embodiment 1 is equally applicable to this embodiment, and thus the description thereof will not be repeated here.
Any particular values in all examples shown and described herein are to be construed as merely illustrative and not a limitation, and thus other examples of exemplary embodiments may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application.
Claims (10)
1. A ship passing time prediction method, comprising:
acquiring ship positioning data, converting the ship positioning data into binary stream to obtain ship analysis information, and cleaning the ship analysis information to obtain ship candidate information;
determining a track point of the ship according to the ship candidate information, and determining a lock section near the track point by using a GEOHOSH algorithm;
selecting two adjacent target track points from the track points, determining a target track point vector according to the target track points, selecting two section endpoints from the ship lock section, and determining a section endpoint vector according to the section endpoints;
judging whether the target track point vector and the section end point vector are intersected or not according to a vector cross multiplication theorem, and if so, determining that the ship passes through the ship lock section;
obtaining uplink and downlink information of the ship according to the position relation between the target track point and the section endpoint vector;
and acquiring historical uplink and downlink time of the ship from a ship record table, determining average gate passing time of the ship according to the historical uplink and downlink time and the uplink and downlink information, and predicting future gate passing time of the ship by utilizing a propset algorithm according to the average gate passing time.
2. The ship lock time prediction method according to claim 1, wherein the acquiring the ship positioning data, converting the ship positioning data into a binary stream, and obtaining the ship analysis information, comprises:
extracting original ship positioning data from a ship positioning system, and extracting encapsulated ship positioning data message information;
converting the message information from an ASCII code string form to a binary stream form, and intercepting the binary stream according to the ship positioning data message information conversion standard to obtain binary data;
and the binary data are corresponding to corresponding information segments according to the segments to form the ship analysis information.
3. The method for predicting ship passing time according to claim 1, wherein the step of cleaning the ship analysis information to obtain ship candidate information comprises:
cleaning incomplete information and abnormal information in the ship analysis information to obtain normal information;
and performing thinning on the normal information through a linear thinning algorithm to obtain the ship candidate information.
4. The ship lock time prediction method according to claim 1, wherein the determining the track point of the ship according to the ship candidate information, determining the lock section near the track point by using a GEOHASH algorithm, comprises:
dividing a map grid by using a GEOHASH algorithm, and inputting the ship candidate information into the map grid to obtain track points of the ship;
inputting the section information of the ship lock into the map grid to obtain the section point of the ship lock; the ship track points and the ship lock section points are in character string form;
and if the track point is the same as the lock section point, indicating that the lock section is near the ship track point.
5. The ship lock time prediction method according to claim 1, wherein the determining whether the target trajectory point vector and the section end point vector intersect according to a vector cross-over theorem, and if so, determining that the ship passes through the ship lock section, comprises:
defining the two adjacent target track points as Q1 and Q2, and defining the section end points as P1 and P2;
constructing a vector (Q1-P1), a vector (P1-Q1), a vector (Q1-P2), a vector (P1-Q2), a vector (Q1-Q2) and a vector (P1-P2);
judging whether the vector (Q1-P1), the vector (P1-Q1), the vector (Q1-P2), the vector (P1-Q2), the vector (Q1-Q2) and the vector (P1-P2) meet the following conditions simultaneously or not through a vector cross-multiplication theorem:
if so, it is indicative of the ship passing through the lock section.
6. The ship passing time prediction method according to claim 5, wherein the obtaining the uplink and downlink information of the ship according to the positional relationship between the target track point and the section endpoint vector comprises:
if the track point Q1 is in the counterclockwise direction of the vector (P1-P2) and the track point Q2 is in the clockwise direction of the vector (P1-P2), the navigation direction of the ship is indicated to be upward;
if the locus point Q1 is in the clockwise direction of the vector (P1-P2) and the locus point Q2 is in the counterclockwise direction of the vector (P1-P2), the navigation direction of the ship is indicated as the down direction.
7. The ship passing time prediction method according to claim 6, wherein the obtaining the historical uplink and downlink time of the ship from the ship record table, and determining the average passing time of the ship according to the historical uplink and downlink time and the uplink and downlink information, comprises:
acquiring the time of the ship passing through the upstream section of the ship lock and the time of the ship passing through the downstream section of the ship lock from the ship record table;
calculating the difference between the time of passing through the upstream section of the ship lock and the time of passing through the downstream section of the ship lock, and taking the difference as the time of passing through the ship lock;
dividing the passing time into ship ascending time and ship descending time according to the ship navigation direction;
and calculating the uplink average gate-crossing time according to the ship uplink time, and calculating the downlink average gate-crossing time according to the ship downlink time.
8. The ship lock time prediction method according to claim 7, wherein the predicting the future lock time of the ship using prophet algorithm according to the average lock time comprises:
converting the average gate-crossing time into time series data, and decomposing the time series data into a plurality of combinations of non-periodic variation trend, special event influence item and error item to obtain a future average gate-crossing time prediction model of the ship:
in the method, in the process of the application,for the predicted mean time to pass of the ship, +.>For the aperiodic trend of the average transit time of the ship, +.>Is a periodic trend of average crossing time of ship, +.>For special event influencing items ++>Is an error term.
9. The ship lock time prediction method according to claim 1, wherein after obtaining the future average lock time prediction model of the ship, the method comprises:
and performing model fitting and training on the prediction model to obtain a final prediction model, and predicting the future gate crossing time of the ship through the final prediction model.
10. A ship lock time prediction system, comprising:
the acquisition module is used for acquiring ship positioning data, converting the ship positioning data into binary stream to obtain ship analysis information, and cleaning the ship analysis information to obtain ship candidate information;
the determining module is used for determining the track point of the ship according to the ship candidate information and determining the lock section near the track point by using a GEOHASH algorithm;
the selecting module is used for selecting two adjacent target track points from the track points, determining a target track point vector according to the target track points, selecting two section endpoints from the ship lock section, and determining a section endpoint vector according to the section endpoints;
the judging module is used for judging whether the target track point vector and the section endpoint vector are intersected or not according to a vector cross-over theorem, and if so, determining that the ship passes through the lock section;
the obtaining module is used for obtaining the uplink and downlink information of the ship according to the position relation between the target track point and the section endpoint vector;
the prediction module is used for obtaining the historical uplink and downlink time of the ship from the ship record table, determining the average gate passing time of the ship according to the historical uplink and downlink time and the uplink and downlink information, and predicting the future gate passing time of the ship by utilizing a propset algorithm according to the average gate passing time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311055578.2A CN116805184B (en) | 2023-08-22 | 2023-08-22 | Ship passing time prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311055578.2A CN116805184B (en) | 2023-08-22 | 2023-08-22 | Ship passing time prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116805184A true CN116805184A (en) | 2023-09-26 |
| CN116805184B CN116805184B (en) | 2023-11-03 |
Family
ID=88079684
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311055578.2A Active CN116805184B (en) | 2023-08-22 | 2023-08-22 | Ship passing time prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116805184B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110403A (en) * | 2019-04-19 | 2019-08-09 | 长江三峡通航管理局 | A kind of scheduling gear method being applicable in unidirectional continuous lockage ship |
| CN111062568A (en) * | 2019-11-12 | 2020-04-24 | 武汉理工大学 | Ship lockage scheduling method, system and storage medium |
| JP2020165709A (en) * | 2019-03-28 | 2020-10-08 | 日産自動車株式会社 | Information processing method, information processing device, and information processing system |
| CN112700052A (en) * | 2021-01-04 | 2021-04-23 | 安徽江河技术有限公司 | Ship lockage optimization scheduling method |
| CN115629548A (en) * | 2022-12-19 | 2023-01-20 | 交通运输部天津水运工程科学研究所 | Ship lock control method and system through multistage hubs based on big data deduction |
| CN116341392A (en) * | 2023-05-26 | 2023-06-27 | 交通运输部天津水运工程科学研究所 | Multi-step ship lock ship dispatching control method |
-
2023
- 2023-08-22 CN CN202311055578.2A patent/CN116805184B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020165709A (en) * | 2019-03-28 | 2020-10-08 | 日産自動車株式会社 | Information processing method, information processing device, and information processing system |
| CN110110403A (en) * | 2019-04-19 | 2019-08-09 | 长江三峡通航管理局 | A kind of scheduling gear method being applicable in unidirectional continuous lockage ship |
| CN111062568A (en) * | 2019-11-12 | 2020-04-24 | 武汉理工大学 | Ship lockage scheduling method, system and storage medium |
| CN112700052A (en) * | 2021-01-04 | 2021-04-23 | 安徽江河技术有限公司 | Ship lockage optimization scheduling method |
| CN115629548A (en) * | 2022-12-19 | 2023-01-20 | 交通运输部天津水运工程科学研究所 | Ship lock control method and system through multistage hubs based on big data deduction |
| CN116341392A (en) * | 2023-05-26 | 2023-06-27 | 交通运输部天津水运工程科学研究所 | Multi-step ship lock ship dispatching control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116805184B (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Adaptive douglas-peucker algorithm with automatic thresholding for AIS-based vessel trajectory compression | |
| Zissis et al. | A distributed spatial method for modeling maritime routes | |
| US11105958B2 (en) | Systems and methods for distributed-solar power forecasting using parameter regularization | |
| Cao et al. | PCA-based hierarchical clustering of AIS trajectories with automatic extraction of clusters | |
| CN116703004B (en) | Water system river basin intelligent patrol method and device based on pre-training model | |
| CN113128758B (en) | Maximum wave height forecasting system constructed based on offshore buoy wave observation data | |
| CN116307291B (en) | Distributed photovoltaic power generation prediction method and prediction terminal based on wavelet decomposition | |
| CN114936332A (en) | Method and device for analyzing ship traffic flow in water area of wind power plant and storage medium | |
| CN111882122A (en) | Traffic accident black point prediction method based on deep learning and space-time big data | |
| CN115330239A (en) | Method for identifying agricultural non-point source pollution risk assessment key source area based on SWMM model | |
| CN116452850A (en) | Road ponding area identification method based on data mining and deep learning | |
| Xu et al. | Improved Vessel Trajectory Prediction Model Based on Stacked‐BiGRUs | |
| CN116805184B (en) | Ship passing time prediction method and system | |
| CN113901043A (en) | Pollution source intelligent supervision and data fusion analysis method and system | |
| Abuella et al. | Spatial clustering approach for vessel path identification | |
| CN115600047B (en) | Small watershed surface average rainfall measurement and calculation method and system based on grid analysis | |
| CN117371571A (en) | Regional air quality prediction model based on multi-scale dynamic synchronous diagram mechanism | |
| CN115424276B (en) | Ship license plate number detection method based on deep learning technology | |
| CN116629448A (en) | Photovoltaic power prediction method based on combination of empirical mode decomposition and neural network | |
| Huang et al. | Edge computing-based adaptable trajectory transmission policy for vessels monitoring systems of marine fishery | |
| CN102799891A (en) | Spectral clustering method based on landmark point representation | |
| Yang et al. | Expanding existing solar irradiance monitoring network using entropy | |
| CN109190216B (en) | Automatic continent sea-entering river sequencing and encoding method based on DEM | |
| CN111310103A (en) | Densification processing method for ecological environment monitoring data | |
| Li et al. | Research on Grid-based Abnormal Behavior Identification Method of Ships |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |