CN114066303B - AIS-based port planning adaptability analysis method and system - Google Patents

AIS-based port planning adaptability analysis method and system Download PDF

Info

Publication number
CN114066303B
CN114066303B CN202111414555.7A CN202111414555A CN114066303B CN 114066303 B CN114066303 B CN 114066303B CN 202111414555 A CN202111414555 A CN 202111414555A CN 114066303 B CN114066303 B CN 114066303B
Authority
CN
China
Prior art keywords
port
ship
data
snapshot
infrastructure
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.)
Active
Application number
CN202111414555.7A
Other languages
Chinese (zh)
Other versions
CN114066303A (en
Inventor
姚海元
齐越
方森松
王达川
杨靓
李蕊
贾鹏鹏
黄力
金哲飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Transport Planning And Research Institute Ministry Of Transport
Original Assignee
Transport Planning And Research Institute Ministry Of Transport
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Transport Planning And Research Institute Ministry Of Transport filed Critical Transport Planning And Research Institute Ministry Of Transport
Priority to CN202111414555.7A priority Critical patent/CN114066303B/en
Publication of CN114066303A publication Critical patent/CN114066303A/en
Application granted granted Critical
Publication of CN114066303B publication Critical patent/CN114066303B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/06—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Strategic Management (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Evolutionary Computation (AREA)
  • Economics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Development Economics (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a port planning adaptability analysis method and system based on AIS, comprising the following steps: step S1, carrying out dynamic snapshot sampling on historical AIS data of the port to obtain a group of ship event data representing ship port events; s2, extracting event characteristics of events in the ship harbor based on a group of ship event data, and constructing a mapping model of the number of ships and the number of harbors based on the event characteristics; and S3, calculating the long-acting occupancy of the port infrastructure based on the event characteristics, and establishing a weighting model for the long-acting occupancy and the number of the ships to obtain a port adaptability evaluation model so as to evaluate the adaptability of the future planning of the port. The invention realizes effective calculation of port infrastructure by using mass AIS data, avoids subjective consciousness of an evaluator, achieves effective evaluation of adaptability, and predicts future ship arrival flow through machine learning, thereby effectively calculating the adaptability of future planning.

Description

AIS-based port planning adaptability analysis method and system
Technical Field
The invention relates to the technical field of port planning, in particular to a port planning adaptability analysis method and system based on AIS.
Background
The port planning refers to the prediction and consummation of port layout and development scale in a certain period in the future, and is the overall and long-term positioning, arrangement and planning of the development of ports according to the objective requirements of national economy development planning and water transportation traffic industry development. The port planning comprises port layout planning and port overall planning, and the port planning is evaluated to determine that the port planning scheme has weak adaptability and achieves the purpose of evaluating the quality of the port planning scheme, so that whether the planning scheme is adopted or not is determined.
In the prior art, on the basis of calculating an evaluation index weight value by adopting an analytic hierarchy process in a 'port planning scheme technical evaluation method research' document, weight indexes of six indexes (demand performance and coordination performance) are obtained, an evaluation set is divided, an excellent, good, general, poor and poor median score is obtained, an evaluation membership matrix is obtained, index weight vectors are multiplied by the matrix to obtain membership vectors (demand performance and coordination performance), a final planning evaluation vector adaptive to a port is obtained by multiplying the weight vectors of the demand performance and coordination performance by the matrix constructed by the membership vectors, and a final evaluation score of the port planning is obtained by multiplying the weight represented by the evaluation vectors by the respective corresponding median scores.
Although the prior art can realize the port planning adaptability analysis, the prior art still has certain defects, the subjective consciousness of an evaluator is excessively depended when the planning adaptability is evaluated, and the reliability of an evaluation result is poor.
Disclosure of Invention
The invention aims to provide a port planning adaptability analysis method and system based on AIS (automatic identification system) to solve the technical problem that port adaptability evaluation excessively depends on subjective scoring means such as questionnaire survey and the like in the prior art.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
a port planning adaptability analysis method based on AIS comprises the following steps:
step S1, carrying out dynamic snapshot sampling on historical AIS data of a port to obtain a group of ship event data representing ship port events, and taking the snapshot sampling time as the time sequence attribute of the ship event data, wherein the dynamic snapshot sampling is to adopt a data snapshot mode to carry out dynamic interval sampling on the historical AIS data to improve the diversity of the ship event data, the historical AIS data is analyzed on AIS information interacted between ships and between the ships and a base station, and is represented as the historical track and the running state of the ships;
s2, extracting event characteristics of events in the ship harbor based on a group of ship event data, and constructing a mapping model of the number of ships and the number of ports based on the event characteristics to realize the estimation analysis of the number of ships at the future ports;
and step S3, calculating the long-acting occupancy of port infrastructure based on the event characteristics, and establishing a weighting model for the long-acting occupancy and the number of ships to obtain a port adaptability evaluation model so as to evaluate the adaptability of the port for future planning, wherein the long-acting occupancy is characterized by the total occupancy of the port infrastructure in a long period.
As a preferred scheme of the present invention, the dynamic snapshot sampling of the historical AIS data of the port to obtain a set of ship event data representing ship port events includes:
setting the Snapshot Interval Δ tiAnd initializing the snapshot interval Δ t1＝ΔT；
Respectively taking the acquisition time of the first data and the acquisition time of the last data of the historical AIS data as a left boundary and a right boundary of snapshot sampling, and dynamically setting snapshot sampling time in sequence from the left boundary to the right boundary, wherein the setting function expression of the snapshot sampling time is as follows:
ti+1＝ti+Δti；
in the formula, ti∈[tstart,tend]∩ti+1∈[tstart,tend]，tstart、tendRespectively characterized by the acquisition times, t, of the first and last datai+1、tiRespectively characterized as the i +1 th snapshot sampling time, delta tiCharacterized by the i +1 st snapshot sampling time and the ith snapshot sampling timeThe snapshot interval of i snapshot sampling moments, i is a metering constant, and has no substantial meaning.
As a preferred aspect of the present invention, the snapshot interval Δ tiThe calculating method comprises the following steps:
setting a degree weight representing the single degree of ship event data for each snapshot sampling moment, wherein the degree weight is measured by using Euclidean distance, and the calculation formula of the degree weight is as follows:
Figure BDA0003375414780000031
in the formula, eiCharacterised by a degree weight, X, of the acquisition instant of the ith snapshoti、Xi-1Respectively characterized as ship event data at the i-th and i-1-th snapshot acquisition time, AjThe j data component is characterized as the j data component of the ship event data, n is characterized as the total number of the data components, and j is a metering constant without substantial meaning;
constructing a snapshot interval Δ t using a trigonometric function tan based on the degree weightiTo achieve spacing of snapshots by Δ tiDynamically adjusting following degree weight change to ensure diversity of ship event data, wherein the snapshot interval is delta tiThe functional expression of (a) is:
Figure BDA0003375414780000032
in the formula, A is a constant coefficient and has no essential meaning.
As a preferable aspect of the present invention, the extracting of the event characteristics of the events in the port of the ship based on the set of ship event data includes extracting ship arrival infrastructure operation range characteristics and ship berthing event characteristics, wherein,
the extracting of the event characteristics of the arrival of the ship at the infrastructure operation range comprises the following steps:
quantifying boundary data of port infrastructure, relative position of ship space and speed judgment;
acquiring position data of a ship from ship event data, and calculating a ship set in a port at each snapshot sampling time according to a judgment principle that the ship is located in a port basic equipment range in a boundary data range, wherein the function expression of an arriving ship set in the port at each snapshot sampling time is as follows:
Figure BDA0003375414780000041
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000042
is characterized by tiSet of all arriving vessels, mmsi, within the infrastructure operating range of port y at time of dayxCharacterized by a unique identification number, continains (b) for vessel xy,px) Boundary data b characterized as harbor yyWhether or not position data p of ship x is containedxY is characterized by the distinguishing number of the port, x is characterized by the distinguishing code of the ship, Δ v is characterized by the judgment standard, txCharacterised by the time, v, at which the vessel x is within the operating range of the infrastructure of the port yxCharacterized by the speed of the vessel x over the infrastructure operating range of port y;
calculating an arrival ship set of an adjacent snapshot sampling time arriving at the port as an event characteristic of an arrival infrastructure operation range of the ship based on an arrival ship set in the port at each snapshot sampling time, wherein a function expression of the arrival ship set of the adjacent snapshot sampling time arriving at the port is as follows:
Figure BDA0003375414780000043
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000044
characterised by adjacent snapshot sampling instants ti+1、tiThe set of arriving vessels within the operational reach of the infrastructure that arrived at port y,
Figure BDA0003375414780000045
are respectively characterized by ti+1、tiThe set of all arriving vessels within the operating range of the infrastructure at port y at time.
As a preferable aspect of the present invention, the extracting of the ship docking event feature includes:
acquiring speed data of a ship from ship event data, and calculating a berthed ship set in a berthed state in a port at each snapshot sampling time according to a judgment principle that the speed data of the ship is smaller than a set threshold value and the ship arrives in the port and is in the berthed state, wherein a function expression of the berthed ship set in the port at each snapshot sampling time is as follows:
Figure BDA0003375414780000046
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000047
characterised by tiSet of all docked vessels in the docked state within the operating range of the infrastructure of the port y at the moment v0Characterized by a set threshold;
calculating a berthing ship set in a berthing state of a port at an adjacent snapshot sampling time based on a berthing ship set in the port at each snapshot sampling time, wherein a function expression of the berthing ship set in the berthing state of the port at the adjacent snapshot sampling time is as follows:
Figure BDA0003375414780000051
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000052
characterised by adjacent snapshot sampling instants ti+1、tiDuring which all the docked vessels within the operating range of the infrastructure of port y are in a docked state,
Figure BDA0003375414780000053
are respectively characterized by ti+1、tiAll berthing ships in a berthing state in the infrastructure operation range of the port y at any moment are gathered;
calculating a berthing ship set of the ending berthing state of the port at the adjacent snapshot sampling time based on the berthing ship set in the port at each snapshot sampling time, wherein the function expression of the berthing ship set of the ending berthing state of the port at the adjacent snapshot sampling time is as follows:
Figure BDA0003375414780000054
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000055
characterised by adjacent snapshot sampling instants ti+1、tiDuring which the set of ending berthed vessels of all ending berthing states within the infrastructure operating range of port y,
Figure BDA0003375414780000056
are respectively characterized by ti+1、tiAll the docked vessels within the operating range of the infrastructure of port y are brought together at that moment.
As a preferable aspect of the present invention, the constructing a mapping model of the number of ships and the port characteristics based on the event characteristics includes:
based on historical AIS data, counting the total quantity of infrastructures in the port of departure and based on a berthed ship set
Figure BDA0003375414780000057
Counting the occupancy rate of the port infrastructure in unit time, the total number of the ships in the port infrastructure operation range in unit time and the docking time of the ships at the port, wherein the occupancy rate is equal to the docking time of the ships in the port infrastructure, the left boundary sum and the docking time of the ships at the portA ratio of a right boundary time difference, the berthing time being equal to the set of berthed ships
Figure BDA0003375414780000058
Number of medium vessels times Δ ti；
Utilizing a BP neural network to construct a mapping model representing the nonlinear mapping relation between the ship number and the port characteristics for the total quantity of the infrastructure, the occupancy rate, the docking time and the ship total number, wherein the function expression of the mapping model is as follows:
Zy＝BP[zy,1,zy,2,zy,3]；
in the formula, ZyCharacterization of the total number of vessels in the operating range of the infrastructure of port y per unit of time, zy,1、zy,2、zy,3Respectively representing the occupancy rate of the basic facilities of the port y in unit time, the stop time of the ship at the port y and the total quantity of the basic facilities in the port y, and representing BP as a BP neural network;
and (3) forming a sample set for mapping model training by using the total number of the infrastructures in the port, the occupancy of the infrastructures in the port in unit time, the total number of the ships in the operation range of the infrastructures in the port in unit time and the docking time of the ships at the port, and dividing the sample set into a training set and a testing set according to the data volume of 6:4 to bring the training set into the mapping model for model training so as to obtain the nonlinear mapping relation between the number of the ships and the port characteristics.
As a preferable aspect of the present invention, the calculating of the long-term occupancy of the port infrastructure based on the event characteristics includes:
obtaining the long-acting occupancy by multiplying the total long-period duration of the long-acting occupancy by the occupancy of the infrastructure of the port y in unit time, wherein the calculation formula of the long-acting occupancy is as follows:
Lzy,1＝dy*zy,1；
in the formula, Lzy,1Characterized by the long-term occupancy of the port y infrastructure, dyCharacterized by the total duration of port y.
As a preferred aspect of the present invention, the port adaptability evaluation model has a function expression as follows:
Wy＝α*Zy+β*Lzy,1；
in the formula, WyIs characterized by the value of the fitness score of harbor y, alpha is the [0,1 ]]，β∈[0,1]，α+β＝1。
As a preferred aspect of the present invention, all data components of the ship event data need to be normalized before calculation.
As a preferred aspect of the present invention, the present invention provides an analysis system according to the AIS-based port planning adaptability analysis method, including:
the system comprises a data sampling unit, a data processing unit and a data processing unit, wherein the data sampling unit is used for carrying out dynamic snapshot sampling on historical AIS data of a port to obtain a group of ship event data representing ship port events, and taking the moment of snapshot sampling as the time sequence attribute of the ship event data;
the model establishing unit is used for extracting event characteristics of events in ship ports based on a group of ship event data, and establishing a mapping model of the number of ships and the number of ports based on the event characteristics so as to realize the estimation analysis of the number of ships at the ports in the future;
and the adaptability evaluation unit is used for calculating the long-acting occupancy rate of the port infrastructure based on the event characteristics, and establishing a weighting model for the long-acting occupancy rate and the number of the ships to obtain a port adaptability evaluation model so as to evaluate the adaptability of the future planning of the port.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the mass AIS data is utilized to realize effective calculation of port infrastructure, the subjective consciousness of evaluators is avoided, the effective evaluation of adaptability is achieved, meanwhile, the future ship arrival flow is predicted through machine learning, so that the adaptability of future planning is effectively calculated, and a dynamic snapshot sampling mode is adopted when the AIS data is sampled, so that the diversity of the data can be effectively improved, and the accuracy of adaptability prediction is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
Fig. 1 is a flowchart of a port planning adaptability analysis method provided in an embodiment of the present invention;
FIG. 2 is a schematic diagram of an extraction of features of a ship docking event provided by an embodiment of the present invention;
fig. 3 is a block diagram of an analysis system according to an embodiment of the present invention.
The reference numerals in the drawings denote the following, respectively:
1-a data sampling unit; 2-a model building unit; 3-adaptability evaluation unit.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the invention provides a port planning adaptability analysis method based on AIS, which comprises the following steps:
step S1, carrying out dynamic snapshot sampling on historical AIS data of a port to obtain a group of ship event data representing ship port events, and taking the moment of snapshot sampling as the time sequence attribute of the ship event data, wherein the dynamic snapshot sampling is to adopt a data snapshot mode to carry out dynamic interval sampling on the historical AIS data to improve the diversity of the ship event data, and the historical AIS data is analyzed on AIS information interacted between ships and between the ships and a base station and is represented as historical tracks and running states of the ships;
the historical AIS data volume of a port is huge, and ship information of each ship at each moment cannot be monitored, so that a data snapshot mode is adopted, AIS data and port infrastructure (anchor, berth and channel) are combined, one historical AIS data is sampled at intervals, a group of ship time data used for extracting events such as arrival, berthing and the like of the ship are extracted from the massive AIS data, and the ship events of the port are in a highly similar state at close time, so that if the snapshot sampling time interval is set to be a certain small fixed value, for example, sampling is carried out once every 10 minutes, the data volume of the group of sampled historical AIS data is large, the diversity is guaranteed, but more data at adjacent sampling moments are highly similar, and data redundancy is generated; if the time interval of snapshot sampling is set to a certain overlarge fixed value, for example, sampling is performed once every 90 minutes, the data volume of a group of sampled historical AIS data may be small, although data redundancy is solved, there is no high similarity of data at more adjacent sampling moments, but the data volume is too small, which may cause loss of data diversity, so how to set the time interval of snapshot sampling is an important influence factor for determining the quality of sampled data.
The embodiment provides a dynamic snapshot sampling method, which dynamically adjusts a snapshot sampling interval along with the single degree of data to avoid data redundancy while ensuring diversity, and specifically comprises the following steps:
the dynamic snapshot sampling of the historical AIS data of the port is carried out to obtain a group of ship event data representing ship events in the port, and the method comprises the following steps:
setting the Snapshot Interval Δ tiAnd initializing a snapshot interval Δ t1＝ΔT；
Respectively taking the acquisition time of the first data and the acquisition time of the last data of the historical AIS data as a left boundary and a right boundary of snapshot sampling, and dynamically setting snapshot sampling time in sequence from the left boundary to the right boundary, wherein the setting function expression of the snapshot sampling time is as follows:
ti+1＝ti+Δti；
in the formula, ti∈[tstart,tend]∩ti+1∈[tstart,tend]，tstart、tendRespectively characterised by the time of acquisition, t, of the first and last datai+1、tiRespectively characterized by the i +1 th and i th snapshot sampling time, delta tiThe method is characterized by comprising the step of representing the snapshot interval between the ith + 1-th snapshot sampling moment and the ith snapshot sampling moment, wherein i is a metering constant and has no essential meaning.
The snapshot interval Δ tiThe calculating method comprises the following steps:
setting a degree weight representing the single degree of ship event data for each snapshot sampling moment, wherein the degree weight is measured by using Euclidean distance, and the calculation formula of the degree weight is as follows:
Figure BDA0003375414780000101
in the formula, eiCharacterised by the degree weight, X, of the moment of acquisition of the ith snapshoti、Xi-1Respectively characterized as ship event data at the i-th and i-1-th snapshot acquisition time, AjThe j data component is characterized as the j data component of the ship event data, n is characterized as the total number of the data components, and j is a metering constant without substantial meaning;
the higher the degree weight is, the higher the similarity of ship event data obtained by snapshot sampling at the current moment is, that is, the current ship event data has singleness, the snapshot sampling time interval of the ship event data needs to be properly prolonged, then the sampling data volume in the time period with highly similar data is reduced, the time period with low data similarity is increased, then the snapshot sampling time interval is shortened, the sampling data volume in the time period with low data similarity is increased, so that when the snapshot sampling time interval is dynamically adjusted, the data diversity is ensured, and the data redundancy is reduced.
In order to fit the change of the data volume caused by the extension and the shortening of the sampling time interval of the snapshot, the embodiment adopts a trigonometric function tan for fitting, which is specifically as follows:
constructing a snapshot interval Δ t using a trigonometric function tan based on the degree weightiTo achieve spacing of snapshots by Δ tiDynamically adjusting following degree weight change to ensure diversity of ship event data, wherein the snapshot interval is delta tiThe functional expression of (a) is:
Figure BDA0003375414780000102
in the formula, A is a constant coefficient and has no substantial meaning.
The value range of the degree weight is in ei∈[0,1]Thus, is at
Figure BDA0003375414780000103
Time, i.e. a lower degree of weighting, ati∈(-∞,0]Then the current snapshot sampling interval follows eiThe reduction of (1) is shortened, that is, the time interval between the next snapshot sampling time and the current snapshot sampling time is shortened, resulting in that multiple sampling is performed in a time period with high diversity to obtain a larger amount of data, and the diversity of the data is ensured, as well as that in
Figure BDA0003375414780000104
Time, i.e. higher degree of weighting, atiE [0, + ∞)), then the current snapshot sampling interval follows eiThe time interval between the next snapshot sampling time and the current snapshot sampling time is prolonged, so that the single data volume is reduced by sampling less in a time period with low diversity, the redundancy of the data is reduced, and the initial time interval can be set by a user.
Step S2, extracting event characteristics of events in the ship harbor based on a group of ship event data, and constructing a mapping model of the number of ships and the number of ports based on the event characteristics to realize the estimation and analysis of the number of ships at the future ports;
the extracting event characteristics of events in the ship harbor based on the set of ship event data comprises extracting ship arrival infrastructure operation range characteristics and ship berthing event characteristics, wherein,
the extracting of the event characteristics of the arrival of the ship at the infrastructure operation range comprises the following steps:
quantifying boundary data of port infrastructure and speed errors;
acquiring position data of a ship from ship event data, and calculating a ship set in a port at each snapshot sampling time according to a judgment principle that the ship is located in a port basic equipment range in a boundary data range, wherein the function expression of an arriving ship set in the port at each snapshot sampling time is as follows:
Figure BDA0003375414780000111
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000112
is characterized by tiSet of all arriving vessels, mmsi, within the infrastructure operating range of port y at time of dayxCharacterized by a unique identification number, continains (b) for vessel xy,px) Boundary data b characterized as harbor yyWhether or not position data p of ship x is containedxY is characterised by the distinguishing number of the port, x is characterised by the distinguishing code of the vessel, Δ v is characterised by the speed error, txCharacterised by the time, v, at which the vessel x is within the operating range of the infrastructure of the port yxCharacterized by the speed of the vessel x within the infrastructure operating range of port y;
calculating an arrival ship set of an adjacent snapshot sampling time arriving at the port as an event characteristic of an arrival infrastructure operation range of the ship based on an arrival ship set in the port at each snapshot sampling time, wherein a function expression of the arrival ship set of the adjacent snapshot sampling time arriving at the port is as follows:
Figure BDA0003375414780000113
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000114
characterised by adjacent snapshot sampling instants ti+1、tiThe set of arriving vessels within the operating range of the infrastructure that arrived at port y,
Figure BDA0003375414780000121
are respectively characterized by ti+1、tiThe set of all arriving vessels within the operating range of the infrastructure of port y at time.
The extracting of the ship berthing event characteristics comprises the following steps:
by utilizing the event characteristics, the berthing ship can be rapidly extracted, the berthing time can be calculated, and the like. The AIS data records the navigational speed of the ship at each moment, a speed threshold value can be set, navigational speed information in the AIS data is sampled at intervals, the ship with the navigational speed lower than the set threshold value for a certain time within a sampling time period is screened out, and the ship is judged to be a ship with berthing and shelving events.
The ship berthing characteristics are extracted in a manner similar to the extraction of the port and berthing characteristics. Every half an hour, screening ships according with the berthing state into a data set in a database snapshot mode, acquiring the ships with the berthing events in the time interval through the addition and subtraction operation of the two data sets between the time intervals, and finally constructing the extracted ship berthing event characteristics into data records to be written into a berthing event database.
Acquiring speed data of a ship from ship event data, and calculating a berthed ship set in a berthed state in a port at each snapshot sampling time according to a judgment principle that the speed data of the ship is smaller than a set threshold value and the ship arrives in the port and is in the berthed state, wherein a function expression of the berthed ship set in the port at each snapshot sampling time is as follows:
Figure BDA0003375414780000122
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000123
characterised by tiSet of all berthing vessels at the berthing state within the infrastructure operating range of port y at the moment, v0Characterized by a set threshold;
calculating a berthing ship set in a berthing state of a port at an adjacent snapshot sampling time based on the berthing ship set in the port at each snapshot sampling time, wherein the function expression of the berthing ship set in the berthing state of the port at the adjacent snapshot sampling time is as follows:
Figure BDA0003375414780000124
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000125
characterised by adjacent snapshot sampling instants ti+1、tiDuring which all docked vessels within the operating range of the infrastructure of port y are brought together in a docked state,
Figure BDA0003375414780000131
are respectively characterized by ti+1、tiAll berthing ships in a berthing state in the infrastructure operation range of the port y at any moment are gathered;
calculating a berthing ship set of the ending berthing state of the port at the adjacent snapshot sampling time based on the berthing ship set in the port at each snapshot sampling time, wherein the function expression of the berthing ship set of the ending berthing state of the port at the adjacent snapshot sampling time is as follows:
Figure BDA0003375414780000132
in the formula (I), the compound is shown in the specification,
Figure BDA0003375414780000133
characterised by adjacent snapshot sampling instants ti+1、tiThe set of end berthing vessels during all end berthing states within the infrastructure operating range of port y,
Figure BDA0003375414780000134
are respectively characterized by ti+1、tiAll the docked vessels within the operating range of the infrastructure of port y are brought together at that moment.
As shown in FIG. 2, T is known in the y-region of a harbor1At the moment, a ship set with the speed less than 1 section is acquired from historical AIS data
Figure BDA0003375414780000135
T2Ship set with time speed less than 1 section
Figure BDA0003375414780000136
Then T1-T2Set of docked vessels entering a docked state within time
Figure BDA0003375414780000137
Set of stop-ending vessels in stop-ending state
Figure BDA0003375414780000138
The occupation ratio of a channel, an anchor land and a berth is calculated, the existing number of ships at port is mapped with the output quantity, and the number of ships at port at the port in the future is estimated and analyzed through model training and testing, so that the effect of quantity prediction in planning adaptability is achieved.
And selecting the berthing characteristic information of the proper port and the port ship number to carry out nonlinear modeling, and finding out the mapping relation between the ships and the port number so as to estimate the actual number of the ships. The BP neural network has obvious advantages on modeling of the nonlinear relation and is widely applied to the aspects of information fusion, flight path prediction, information identification and the like.
Through analysis and screening, the following characteristics are finally selected to establish a model:
total number of infrastructure (berth, anchor and channel); occupancy of port berths in unit time; the number of ships of the infrastructure in unit time is composed of the number of ships of a channel in unit time, the number of ships of an anchorage ground in unit time and the number of ships of berthing in unit time, and the specific model building steps are as follows:
the method for constructing the mapping model of the ship number and the port characteristics based on the event characteristics comprises the following steps:
counting the total number of infrastructures in the port based on historical AIS data, and collecting the infrastructures based on berthing ships
Figure BDA0003375414780000141
Counting the occupancy of the port infrastructure in unit time, the total number of ships in the port infrastructure operation range in unit time and the docking time of the ships at the port, wherein the occupancy is equal to the ratio of the docking time of the ships in the port infrastructure to the time difference between the left boundary and the right boundary, and the docking time is equal to the docking ship set
Figure BDA0003375414780000142
Number of vessels in by Δ ti；
Utilizing a BP neural network to construct a mapping model representing the nonlinear mapping relation between the ship number and the port characteristics for the total quantity of the infrastructure, the occupancy rate, the docking time and the ship total number, wherein the function expression of the mapping model is as follows:
Zy＝BP[zy,1,zy,2,zy,3]；
in the formula, ZyCharacterization of the total number of vessels in the operating range of the infrastructure of port y per unit of time, zy,1、zy,2、zy,3Are respectively characterized as being singleThe occupancy rate of the basic facilities of the port y within the bit time, the berthing time of the ship at the port y and the total number of the basic facilities in the port y, wherein BP is characterized as a BP neural network;
and (3) forming a sample set for mapping model training by using the total number of the infrastructures in the port, the occupancy of the infrastructures in the port in unit time, the total number of the ships in the operation range of the infrastructures in the port in unit time and the docking time of the ships at the port, and dividing the sample set into a training set and a testing set according to the data volume of 6:4 to bring the training set into the mapping model for model training so as to obtain the nonlinear mapping relation between the number of the ships and the port characteristics.
Calculating the occupancy of port infrastructure including a channel, an anchor place and a berth according to the year and the month, and performing index quantification on the adaptability of the existing port by establishing a weighting model; the method comprises the following steps of establishing an adaptability evaluation method for evaluating future planning through a predicted number of ships in the port and the existing port occupancy index and a weighting model, and judging planning adaptability through prediction of the ships, wherein the method comprises the following specific steps:
and S3, calculating the long-acting occupancy of the port infrastructure based on the event characteristics, and establishing a weighting model for the long-acting occupancy and the number of the ships to obtain a port adaptability evaluation model so as to evaluate the adaptability of the future planning of the port, wherein the long-acting occupancy is characterized by the total occupancy of the port infrastructure in a long period.
The calculating long term occupancy of the port infrastructure based on the event characteristics comprises:
obtaining the long-acting occupancy by multiplying the total long-period duration of the long-acting occupancy by the occupancy of the infrastructure of the port y in unit time, wherein the calculation formula of the long-acting occupancy is as follows:
Lzy,1＝dy*zy,1；
in the formula, Lzy,1Characterized by the long-term occupancy of the port y infrastructure, dyCharacterized by the total duration of port y.
The function expression of the port adaptability evaluation model is as follows:
Wy＝α*Zy+β*Lzy,1；
in the formula, WyCharacterized by the value of fitness credit for harbor y, alpha is epsilon [0,1]，β∈[0,1]，α+β＝1。
All data components of the ship event data need to be normalized before calculation.
Based on the port planning adaptability analysis method, the invention provides an analysis system, which comprises the following steps:
the system comprises a data sampling unit 1, a data processing unit and a data processing unit, wherein the data sampling unit 1 is used for carrying out dynamic snapshot sampling on historical AIS data of a port to obtain a group of ship event data representing ship port events, and taking the snapshot sampling time as the time sequence attribute of the ship event data, the dynamic snapshot sampling is to adopt a data snapshot mode to carry out dynamic interval sampling on the historical AIS data to improve the diversity of the ship event data, the historical AIS data is analyzed on AIS information interacted between ships and between the ships and a base station, and is represented as historical track and running state of the ships;
the model establishing unit 2 is used for extracting event characteristics of events in ship ports based on a group of ship event data, and establishing a mapping model of the number of ships and the number of ports based on the event characteristics so as to realize the estimation analysis of the number of ships at the ports in the future;
and the adaptability evaluation unit 3 is used for calculating the long-acting occupancy rate of the port infrastructure based on the event characteristics, and establishing a weighting model for the long-acting occupancy rate and the number of the ships to obtain a port adaptability evaluation model so as to evaluate the adaptability of the future planning of the port.
According to the invention, the mass AIS data is utilized to realize effective calculation of port infrastructure, the subjective consciousness of evaluators is avoided, the effective evaluation of adaptability is achieved, meanwhile, the future ship arrival flow is predicted through machine learning, so that the adaptability of future planning is effectively calculated, and a dynamic snapshot sampling mode is adopted when the AIS data is sampled, so that the diversity of the data can be effectively improved, and the accuracy of adaptability prediction is further improved.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.

Claims (9)

1. A port planning adaptability analysis method based on AIS is characterized by comprising the following steps:
step S1, carrying out dynamic snapshot sampling on historical AIS data of a port to obtain a group of ship event data representing events in a ship port, and taking the moment of snapshot sampling as the time sequence attribute of the ship event data, wherein the dynamic snapshot sampling is to adopt a data snapshot mode to carry out dynamic interval sampling on the historical AIS data to improve the diversity of the ship event data, the historical AIS data is analyzed on AIS information interacted between a ship and the ship and between the ship and a base station and is represented as historical track and running state of the ship, and the ship event data is represented as arrival events and stop events of the ship;
s2, extracting event characteristics of events in the ship harbor based on a group of ship event data, and constructing a mapping model of the number of ships and the number of ports based on the event characteristics to realize the estimation analysis of the number of ships at the future ports;
the extracting event features of the events within the ship port based on the set of ship event data includes extracting ship arrival infrastructure operating range features and ship berthing event features, wherein,
the extracting event characteristics of the ship arriving at the infrastructure operation range comprises the following steps:
quantifying boundary data of port infrastructure, relative position of ship space and speed judgment;
acquiring position data of the ship from the ship event data, and calculating a ship set in the port at each snapshot sampling time according to a judgment principle that the ship is located in the range of the port basic equipment in the boundary data range;
calculating an arrival ship set arriving at the port at the adjacent snapshot sampling time as an event characteristic of the ship arriving in the infrastructure operation range based on the arrival ship set arriving at the port at each snapshot sampling time;
the extracting of the ship berthing event characteristics comprises the following steps:
acquiring speed data of the ship from the ship event data, and calculating a berthed ship set in a berthed state in a port at each snapshot sampling time according to a judgment principle that the speed data of the ship is smaller than a set threshold value and the ship arrives in the port and is in the berthed state;
calculating a berthage ship set in a berthage state of a port at the adjacent snapshot sampling time based on the berthage ship set in the port at each snapshot sampling time;
calculating a ship set for stopping ending of the port at the adjacent snapshot sampling time based on the ship set for stopping in the port at each snapshot sampling time;
the construction of the mapping model of the ship number and the port characteristics based on the event characteristics comprises the following steps:
based on historical AIS data, counting the total quantity of infrastructures in the port of departure and based on a berthed ship set
Figure FDA0003687219930000021
Counting the occupancy rate of the port infrastructure in unit time, the total number of ships in the port infrastructure operation range in unit time and the docking time of the ships at the port, wherein the occupancy rate of the port infrastructure in unit time is equal to the ratio of the docking time of the ships in the infrastructure to the time difference between the left boundary and the right boundary, and the docking time is equal to the docking ship set
Figure FDA0003687219930000022
Number of medium vessels times Δ ti；
Utilizing a BP neural network to construct a mapping model representing the nonlinear mapping relation between the ship number and the port characteristics for the total number of the infrastructures, the occupancy rate of the infrastructures at the port in unit time, the docking time and the ship total number, wherein the function expression of the mapping model is as follows:
Zy＝BP[zy,1,zy,2,zy,3]；
in the formula, ZyCharacterization of the total number of vessels in the operating range of the infrastructure of port y per unit of time, zy,1、zy,2、zy,3Respectively representing the occupancy rate of the basic facilities of the port y in unit time, the stop time of the ship at the port y and the total quantity of the basic facilities in the port y, and representing BP as a BP neural network;
forming a sample set for mapping model training by the total number of the basic facilities in the port, the occupancy of the basic facilities in the port in unit time, the total number of the ships in the basic facility operation range of the port in unit time and the docking time of the ships at the port, and dividing the sample set into a training set and a testing set according to the data volume of 6:4 to bring the training set into the mapping model for model training so as to obtain the nonlinear mapping relation between the quantity of the ships and the port characteristics;
and S3, calculating the long-acting occupancy of the port infrastructure based on the event characteristics, and establishing a weighting model for the long-acting occupancy and the number of the ships to obtain a port adaptability evaluation model so as to evaluate the adaptability of the future planning of the port, wherein the long-acting occupancy is characterized by the total occupancy of the port infrastructure in a long period.
2. The AIS-based port planning adaptability analysis method of claim 1, wherein: the dynamic snapshot sampling of the historical AIS data of the port is carried out to obtain a group of ship event data representing ship port events, and the method comprises the following steps:
setting the Snapshot Interval Δ tiAnd initializing the snapshot interval Δ t1＝ΔT；
Respectively taking the acquisition time of the first data and the acquisition time of the last data of the historical AIS data as a left boundary and a right boundary of snapshot sampling, and dynamically setting snapshot sampling time in sequence from the left boundary to the right boundary, wherein the setting function expression of the snapshot sampling time is as follows:
ti+1＝ti+Δti；
in the formula, ti∈[tstart,tend]∩ti+1∈[tstart,tend]，tstart、tendRespectively characterized by the acquisition times, t, of the first and last datai+1、tiRespectively characterized by the i +1 th and i th snapshot sampling time, delta tiThe snapshot interval is characterized by the snapshot interval between the ith +1 th snapshot sampling moment and the ith snapshot sampling moment, and i is a metering constant and has no substantial meaning.
3. The AIS-based port planning adaptability analysis method of claim 2, wherein: the snapshot interval Δ tiThe calculating method comprises the following steps:
setting a degree weight representing the single degree of ship event data for each snapshot sampling moment, wherein the degree weight is measured by using Euclidean distance, and the calculation formula of the degree weight is as follows:
Figure FDA0003687219930000031
in the formula, eiCharacterised by the degree weight, X, of the moment of acquisition of the ith snapshoti、Xi-1Respectively characterized as ship event data at the i-th and i-1-th snapshot acquisition time, AjThe j is characterized as the jth data component of the ship event data, n is characterized as the total number of the data components, and j is a metering constant without substantial meaning;
constructing a snapshot interval Δ t using a trigonometric function tan based on the degree weightiTo achieve spacing of snapshots by Δ tiDynamically adjusting following degree weight change to ensure diversity of ship event data, wherein the snapshot interval is delta tiThe functional expression of (a) is:
Figure FDA0003687219930000032
in the formula, A is a constant coefficient and has no substantial meaning.
4. The AIS-based port planning adaptability analysis method of claim 3, wherein: the function expression of the arrival ship set in the port at each snapshot sampling time is as follows:
Figure FDA0003687219930000041
in the formula (I), the compound is shown in the specification,
Figure FDA0003687219930000042
is characterized by tiSet of all arriving vessels, mmsi, within the infrastructure operating range of port y at time of dayxCharacterized by a unique identification number, continains (b) of vessel xy,px) Boundary data b characterized as harbor yyWhether or not position data p of ship x is containedxY is characterized by the distinguishing number of the port, x is characterized by the distinguishing code of the ship, Δ v is characterized by the speed judging standard, txCharacterised by the time, v, at which the vessel x is within the operating range of the infrastructure of the port yxCharacterized by the speed of the vessel x within the infrastructure operating range of port y;
the function expression of the arrival ship set of the adjacent snapshot sampling time arriving at the port is as follows:
Figure FDA0003687219930000043
in the formula (I), the compound is shown in the specification,
Figure FDA0003687219930000044
characterised by adjacent snapshot sampling instants ti+1、tiThe set of arriving vessels within the operational reach of the infrastructure that arrived at port y,
Figure FDA0003687219930000045
are respectively characterized by ti+1、tiThe set of all arriving vessels within the operating range of the infrastructure of port y at time.
5. The AIS-based port planning adaptability analysis method according to claim 4, characterized in that: and the function expression of the berthing ship set in the berthing state in the port at each snapshot sampling time:
Figure FDA0003687219930000046
in the formula (I), the compound is shown in the specification,
Figure FDA0003687219930000047
characterised by tiSet of all docked vessels in the docked state within the operating range of the infrastructure of the port y at the moment v0Characterized by a set threshold;
the function expression of the berthing ship set in the berthing state at the port at the adjacent snapshot sampling time is as follows:
Figure FDA0003687219930000048
in the formula (I), the compound is shown in the specification,
Figure FDA0003687219930000049
characterised by adjacent snapshot sampling instants ti+1、tiDuring which all docked vessels within the operating range of the infrastructure of port y are brought together in a docked state,
Figure FDA0003687219930000051
are respectively characterized by ti+1、tiAll the berthing ships in the berthing state in the infrastructure operation range of the port y are gathered at any moment;
the function expression of the ship set for ending the berthing of the port at the adjacent snapshot sampling time is as follows:
Figure FDA0003687219930000052
in the formula (I), the compound is shown in the specification,
Figure FDA0003687219930000053
characterised by adjacent snapshot sampling instants ti+1、tiDuring which the set of ending berthed vessels of all ending berthing states within the infrastructure operating range of port y,
Figure FDA0003687219930000054
are respectively characterized by ti+1、tiAll the docked vessels within the operating range of the infrastructure of port y are brought together at that moment.
6. The AIS-based port planning adaptability analysis method according to claim 5, wherein the calculating of the long-term occupancy of the port infrastructure based on the event characteristics comprises:
obtaining the long-acting occupancy by multiplying the total long-period duration of the long-acting occupancy by the occupancy of the infrastructure of the port y in unit time, wherein the calculation formula of the long-acting occupancy is as follows:
Lzy,1＝dy*zy,1；
in the formula, Lzy,1Characterized by long-term occupancy of port y infrastructure, dyCharacterised by the total duration of port y, zy,1Characterized by the occupancy of the infrastructure of port y per unit time.
7. The AIS-based port planning adaptability analysis method of claim 6, wherein the functional expression of the port adaptability evaluation model is as follows:
Wy＝α*Zy+β*Lzy,1；
in the formula, WyIs characterized by the value of the fitness score of harbor y, alpha is the [0,1 ]]，β∈[0,1]，α+β＝1。
8. The AIS-based port planning adaptability analysis method according to claim 2, wherein all data components of the ship event data need to be normalized before calculation.
9. An analysis system of AIS based port planning adaptability analysis method according to any of claims 1-8, characterized by comprising:
the system comprises a data sampling unit (1) and a data processing unit, wherein the data sampling unit is used for carrying out dynamic snapshot sampling on historical AIS data of a port to obtain a group of ship event data representing ship port events, and taking the snapshot sampling time as the time sequence attribute of the ship event data, the dynamic snapshot sampling is to carry out dynamic interval sampling on the historical AIS data in a data snapshot mode to improve the diversity of the ship event data, and the historical AIS data is analyzed on AIS information interacted between ships and between the ships and a base station and is represented as the historical track and the running state of the ships;
the model building unit (2) extracts event characteristics of events in the ship harbor based on a group of ship event data, and builds a mapping model of the number of ships and the number of ports based on the event characteristics so as to realize the estimation and analysis of the number of ships at the ports in the future;
and the adaptability evaluation unit (3) is used for calculating the long-acting occupancy rate of the port infrastructure based on the event characteristics, establishing a weighting model for the long-acting occupancy rate and the number of the ships to obtain a port adaptability evaluation model so as to evaluate the adaptability of the future planning of the port, wherein the long-acting occupancy rate is characterized by the total occupancy rate of the port infrastructure in a long period.
CN202111414555.7A 2021-11-25 2021-11-25 AIS-based port planning adaptability analysis method and system Active CN114066303B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111414555.7A CN114066303B (en) 2021-11-25 2021-11-25 AIS-based port planning adaptability analysis method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111414555.7A CN114066303B (en) 2021-11-25 2021-11-25 AIS-based port planning adaptability analysis method and system

Publications (2)

Publication Number Publication Date
CN114066303A CN114066303A (en) 2022-02-18
CN114066303B true CN114066303B (en) 2022-07-19

Family

ID=80276337

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111414555.7A Active CN114066303B (en) 2021-11-25 2021-11-25 AIS-based port planning adaptability analysis method and system

Country Status (1)

Country Link
CN (1) CN114066303B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115689248B (en) * 2022-11-21 2023-06-30 交通运输部规划研究院 Port layout planning method and system based on AIS data
CN116882774A (en) * 2023-06-05 2023-10-13 交通运输部规划研究院 AIS-based fishing boat navigation and operation influence assessment method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107731011A (en) * 2017-10-27 2018-02-23 中国科学院深圳先进技术研究院 A kind of harbour is moored a boat monitoring method, system and electronic equipment
CN110175696A (en) * 2019-04-22 2019-08-27 中国水产科学研究院渔业工程研究所 A kind of fishing port ship entering and leaving port dynamic prediction method and system based on multiple regression
JP2020013261A (en) * 2018-07-17 2020-01-23 日本製鉄株式会社 Yard waiting demurrage time prediction device, method and program
CN111062114A (en) * 2019-10-24 2020-04-24 武汉理工大学 Navigation channel passing capacity simulation calculation method
JP2020111139A (en) * 2019-01-10 2020-07-27 株式会社日立製作所 Traffic state estimation system and traffic state estimation method
CN112085286A (en) * 2020-09-15 2020-12-15 周远鹏 Ship behavior prediction model establishing method and ship behavior prediction model

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110706827B (en) * 2019-09-26 2022-06-03 武汉理工大学 Method and system for extracting navigable water area water flow information based on ship AIS (automatic identification System) big data
CN111506968B (en) * 2020-04-21 2022-02-11 常熟理工学院 Ship type optimization method based on BP neural network algorithm
CN113343368A (en) * 2021-08-05 2021-09-03 交通运输部天津水运工程科学研究所 ARENA-based method for calculating influence of LNG ship entering port on channel passing capacity

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107731011A (en) * 2017-10-27 2018-02-23 中国科学院深圳先进技术研究院 A kind of harbour is moored a boat monitoring method, system and electronic equipment
JP2020013261A (en) * 2018-07-17 2020-01-23 日本製鉄株式会社 Yard waiting demurrage time prediction device, method and program
JP2020111139A (en) * 2019-01-10 2020-07-27 株式会社日立製作所 Traffic state estimation system and traffic state estimation method
CN110175696A (en) * 2019-04-22 2019-08-27 中国水产科学研究院渔业工程研究所 A kind of fishing port ship entering and leaving port dynamic prediction method and system based on multiple regression
CN111062114A (en) * 2019-10-24 2020-04-24 武汉理工大学 Navigation channel passing capacity simulation calculation method
CN112085286A (en) * 2020-09-15 2020-12-15 周远鹏 Ship behavior prediction model establishing method and ship behavior prediction model

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"基于 ＡＩＳ船舶数据的港口交通流量预测模型研究";李晋等;《交通信息与安全》;20181231;全文 *

Also Published As

Publication number Publication date
CN114066303A (en) 2022-02-18

Similar Documents

Publication Publication Date Title
CN114066303B (en) AIS-based port planning adaptability analysis method and system
CN107610464B (en) A kind of trajectory predictions method based on Gaussian Mixture time series models
CN107153874B (en) Water quality prediction method and system
Wang et al. Testing and modelling autoregressive conditional heteroskedasticity of streamflow processes
CN109472110A (en) A kind of aero-engine remaining life prediction technique based on LSTM network and ARIMA model
CN110361180B (en) Intelligent train pantograph service performance dynamic monitoring and evaluating method and system
CN113177657B (en) Rail transit passenger flow prediction method and device
CN107085943B (en) Short-term prediction method and system for road travel time
CN113240199B (en) Port ship track prediction method based on DILATE _ TLSTM
CN105740991A (en) Climate change prediction method and system for fitting various climate modes based on modified BP neural network
CN110738355A (en) urban waterlogging prediction method based on neural network
CN111680870B (en) Comprehensive evaluation method for quality of target motion trail
CN106845768A (en) Bus hourage model building method based on survival analysis parameter distribution
CN111563072A (en) AIS information-based ship real-time accurate position acquisition method
CN115050214B (en) AIS data-based ship collision risk prediction method
Elbagalati et al. Development of an enhanced decision-making tool for pavement management using a neural network pattern-recognition algorithm
CN107515842B (en) A kind of urban population density dynamic prediction method and system
CN111179592B (en) Urban traffic prediction method and system based on spatio-temporal data flow fusion analysis
CN113361690A (en) Water quality prediction model training method, water quality prediction device, water quality prediction equipment and medium
CN116608861A (en) Ship track behavior abnormality detection method, system, device and storage medium
CN115907181A (en) Urban rail transit passenger flow prediction method and system
CN106056577A (en) Hybrid cascaded SAR image change detection method based on MDS-SRM
CN109919362B (en) Medium-and-long-term runoff forecasting method considering hydraulic engineering scheduling influence
CN108459933B (en) Big data computer system fault detection method based on deep recursion network
US20230314144A1 (en) System and method for estimating drift path of marine floating body

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