CN113822513B - Port congestion monitoring method based on anchor ground and berth automatic identification algorithm - Google Patents

Port congestion monitoring method based on anchor ground and berth automatic identification algorithm Download PDF

Info

Publication number
CN113822513B
CN113822513B CN202011429529.7A CN202011429529A CN113822513B CN 113822513 B CN113822513 B CN 113822513B CN 202011429529 A CN202011429529 A CN 202011429529A CN 113822513 B CN113822513 B CN 113822513B
Authority
CN
China
Prior art keywords
ship
port
determining
berthing
area
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
CN202011429529.7A
Other languages
Chinese (zh)
Other versions
CN113822513A (en
Inventor
侯尧
白茜文
杨冬
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.)
Tsinghua University
Shenzhen Research Institute HKPU
Original Assignee
Tsinghua University
Shenzhen Research Institute HKPU
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 Tsinghua University, Shenzhen Research Institute HKPU filed Critical Tsinghua University
Priority to CN202011429529.7A priority Critical patent/CN113822513B/en
Publication of CN113822513A publication Critical patent/CN113822513A/en
Application granted granted Critical
Publication of CN113822513B publication Critical patent/CN113822513B/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
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2477—Temporal data queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Fuzzy Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Remote Sensing (AREA)
  • Software Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a port congestion monitoring method based on an anchor ground and berth automatic identification algorithm, which comprises the following steps of: acquiring a dynamic position report record of a ship, and determining a berthing record of the ship at a port according to the dynamic position report record of the ship; determining a berthing area and an anchorage area of the port according to the docking record of the ship at the port; and determining the congestion index of the port according to the berthing record of the ship at the port and the berthing area and the anchorage area of the port. Obtaining a docking record of the ship at a port according to the dynamic position report record of the ship; therefore, the harbor is efficiently and accurately identified in the berthing area and the anchor area, and the congestion index of the harbor is obtained, so that the actual congestion condition of the harbor is accurately measured through the congestion index.

Description

Port congestion monitoring method based on anchor ground and berth automatic identification algorithm
Technical Field
The invention relates to the technical field of port traffic, in particular to a port congestion monitoring method based on an anchor ground and berth automatic identification algorithm.
Background
With the continuous development of container trade, the port congestion condition is increasingly intensified. Port congestion results in extended ship berth times, which can cause significant losses to multiple stakeholders in shipping supply chains such as shipping companies, shippers and ports. For the airliner, port congestion causes difficulty in delivering goods by schedule for the airliner, and service performance of the airliner is affected. For the cargo owner, port congestion may bring additional logistics cost, affecting time, resources and route planning of the subsequent land transportation links. For a port, port congestion can reduce port competitiveness and appeal to customers. Based on this, the port congestion has become a topic of great attention in the shipping industry in recent years, and the level of the port congestion also becomes an important index for measuring the performance of the port.
The existing research on port congestion mainly focuses on the following fields: the method comprises the steps of planning a ship route and a dispatch considering port congestion, recovering a ship dispatch considering port congestion, pricing the port congestion and solving a shipping network flow problem considering port congestion. In these studies, the congestion level of a port is often set to a certain value or obeyed a certain probability distribution as an exogenous parameter, and based on this, a discussion of relevant scheduling and management problems is developed.
However, these discussions and studies are only of practical significance if the setting of congestion levels is practical. Current measurements and research on actual port congestion levels are also very limited. According to the method, three indexes for measuring the port congestion conditions are provided by researching and utilizing the data of an Automatic Identification System (AIS) of a ship and considering space complexity, space density and time criticality, and the congestion conditions of three ports, namely Harifasx, Chinese hong Kong and Singapore, are investigated on the basis of the method. However, this method fails to effectively distinguish between berths and anchor sites, may not accurately measure actual congestion conditions, and relies on the chart to manually demarcate port areas to limit the expansion of its applications.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a port congestion monitoring method based on an anchor ground and berth automatic identification algorithm aiming at solving the problem that the actual congestion condition and the universal applicability of a port cannot be accurately measured in the prior art.
The technical scheme adopted by the invention for solving the technical problem is as follows:
a port congestion monitoring method based on an anchor ground and berth automatic identification algorithm comprises the following steps:
acquiring a dynamic position report record of a ship, and determining a stop record of the ship at a port according to the dynamic position report record of the ship;
determining a berthing area and an anchorage area of the port according to the docking record of the ship at the port;
and determining the congestion index of the port according to the berthing record of the ship at the port and the berthing area and the anchorage area of the port.
The port congestion monitoring method based on the anchor ground and berth automatic identification algorithm comprises the following steps of: the method comprises the steps of collecting position coordinates of a ship, collecting the navigational speed of the ship and collecting a timestamp of the ship;
determining a port stop record of the ship at the port according to the dynamic position report record of the ship, comprising:
determining an observation position coordinate set of the ship according to the position coordinate set of the ship and the navigational speed set of the ship; the navigation speed corresponding to the observation position coordinates in the observation position coordinate set of the ship is less than a preset speed;
clustering the observation position coordinate set of the ship to obtain a cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship;
and determining a docking record of the ship at the port according to the timestamp set of the ship, the observation position coordinate set of the ship and the cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship.
The port congestion monitoring method based on the anchor ground and berth automatic identification algorithm is characterized in that the port congestion monitoring method based on the anchor ground and berth automatic identification algorithm comprises the following steps of: the method comprises the following steps of collecting the number of times of arrival and the number of times of berthing of a ship at a port and collecting the average position coordinates of each time of arrival and berthing of the ship;
determining a docking record of the ship at the port according to the timestamp set of the ship, the observation position coordinate set of the ship and the cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship, wherein the determining comprises:
determining the number of times of the ship entering the port according to the timestamp set of the ship; when two adjacent timestamps in the timestamp set of the ship are greater than a preset time difference, the port entry times of the ship in the two adjacent timestamps are different;
determining the number of times of the ship berthing at the port according to the timestamp set of the ship and the cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship; when two adjacent timestamps in the timestamp set of the ship are smaller than or equal to a preset time difference, and the cluster clusters to which the observation position coordinates respectively corresponding to the two adjacent timestamps belong are the same, the ship stops at a port;
determining a set of the times of entry and the times of berthing of the ship in the port according to the times of entry and the times of berthing of the ship in the port;
and determining a set of average position coordinates of each time the ship is docked.
The port congestion monitoring method based on the anchor ground and berth automatic identification algorithm is characterized in that the preset time difference is 12 hours.
The harbor congestion monitoring method based on the anchor ground and berth automatic identification algorithm is characterized in that the berthing area and the anchor ground area of the harbor are determined according to the berthing record of the ship at the harbor, and the method comprises the following steps:
clustering all average position coordinates in the set of average position coordinates of each time the ship enters a port and stops to obtain noise points and non-noise points;
determining a berthing area and an anchor area of the port according to the noise points and the non-noise points; wherein the noise point is located within the anchor region and the non-noise point is located within the berthing region.
The port congestion monitoring method based on the anchor ground and berth automatic identification algorithm is characterized in that a density-based clustering method is adopted for clustering.
The port congestion monitoring method based on the anchor ground and berth automatic identification algorithm comprises the following steps of: latency and/or latency;
the determining the congestion index of the port according to the stop record of the ship at the port and the berthing area and the anchorage area of the port comprises the following steps:
determining the number of the ports of the port waiting in the anchoring area and the number of the ports of the port according to the docking records of the ship in the port and the berthing area and the anchoring area of the port;
determining the delay rate according to the number of the ports of the port waiting in the anchor area and the number of the ports of the port; and/or
And determining the waiting time of the ship in the anchorage area when the ship enters the port according to the berthing record of the ship in the port and the berthing area and the anchorage area of the port.
The port congestion monitoring method based on the anchor ground and berth automatic identification algorithm is characterized in that the waiting time is average waiting time; the average waiting time is the average of the waiting times in the anchorage area when all ships enter the port.
A computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods for monitoring port congestion based on an anchor and berth automatic identification algorithm when executing the computer program.
A computer readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of any one of the above-mentioned methods for monitoring port congestion based on an anchor and berth automatic identification algorithm.
Has the advantages that: the berthing record of the ship at the port is obtained according to the dynamic position report record of the ship; therefore, the harbor is efficiently and accurately identified in the berthing area and the anchor area, and the congestion index of the harbor is obtained, so that the actual congestion condition of the harbor is accurately measured through the congestion index.
Drawings
FIG. 1 is a diagram of the identification of the anchoring area and the berth of Ningbo-Zhoushan harbor obtained by the method of the present invention.
FIG. 2 is an identification diagram of anchor areas and berths of high-bridge harbor areas outside Shanghai harbor obtained by the method of the present invention.
FIG. 3 is a diagram showing the identification of the anchor area and the berth of the Shanghai Yangshan harbor area obtained by the method of the present invention.
FIG. 4 is a diagram of delay rate transition of three ports, 12 months in 2018 to 8 months in 2020, obtained by the method in the present invention.
FIG. 5 is a graph of the average latency transition of three ports, 12 months in 2018 to 2020 and 8 months in the invention.
FIG. 6 is a functional block diagram of a computing device in accordance with the present invention.
FIG. 7 is a flowchart of a port congestion monitoring method based on an anchor and berth automatic identification algorithm in the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1 to 7, the present invention provides some embodiments of a port congestion monitoring method based on an anchor and berth automatic identification algorithm.
As shown in fig. 7, the method for monitoring port congestion based on the anchor ground and berth automatic identification algorithm of the present invention includes the following steps:
and S100, acquiring a dynamic position report record of the ship, and determining a stop record of the ship at a port according to the dynamic position report record of the ship.
Specifically, when identifying the berth area and the anchor area of the port, the identification is completed by a density-based clustering (DBSCAN) method. The invention is based on a density clustering method and comprises two steps: a first-layer DBSCAN clustering algorithm and a second-layer DBSCAN clustering algorithm. Firstly, determining the stop record of the ship at the port according to the dynamic position report record of the ship by adopting a first-layer DBSCAN clustering algorithm.
Specifically, the dynamic position reporting record of the vessel comprises: a set of position coordinates of the vessel, a set of speed of the vessel, and a set of timestamps of the vessel. The recording of the ship berthing at the port comprises the following steps: the method comprises the steps of collecting the number of times of arrival and the number of times of berthing of the ship at a port and collecting the average position coordinates of each time of arrival and berthing of the ship.
And taking a position coordinate set of the ship, a speed set of the ship and a timestamp set of the ship as input items of the first-layer DBSCAN clustering algorithm, wherein the set of the number of times of the ship entering a port and the number of times of the ship berthing and the set of the average position coordinate of the ship berthing each time are output items of the first-layer DBSCAN clustering algorithm.
Specifically, step S100 includes:
step S110, determining an observation position coordinate set of the ship according to the position coordinate set of the ship and the navigational speed set of the ship; and the navigational speed corresponding to the observation position coordinate in the observation position coordinate set of the ship is less than the preset speed.
And step S120, clustering the observation position coordinate set of the ship to obtain a cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship.
And S130, determining a docking record of the ship at the port according to the timestamp set of the ship, the observation position coordinate set of the ship and the cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship.
Specifically, the total number of data entries reported by the ship AIS is n, and the number of data entries in a parking state in the reported data is k. Set of position coordinates of a vesselIs A ═ a1,a2,......,anThe speed of the ship is set as S ═ S1,s2,......,snThe time stamp set of the ship is T ═ T1,t2,......,tnSelecting observation position coordinates with the navigational speed less than a preset speed from the set A, and generating an observation position coordinate set B ═ B of the ship consisting of the observation position coordinates1,b2,......,bk}. The preset speed is 1 knot.
Of course, after the observation position coordinate set B of the ship is obtained, the abnormal ship may be excluded, and specifically, when the number of elements (observation position coordinates of the ship) in the observation position coordinate set B of the ship is smaller than a first preset threshold or larger than a second preset threshold, it may be determined that the ship has abnormal berthing, a record of the ship may be deleted from the AIS database, and the ship is no longer subjected to subsequent estimation. The first preset threshold is 100, and the second preset threshold is 100000.
And recording the number of the data items identified as the abnormal report as k ', and recording the number of the data items in the parking state in the data reported by the ship after the abnormal report is removed as k-k'. Clustering an observation position coordinate set B of the ship to obtain a cluster to which the observation position coordinate belongs in the observation position coordinate set B of the ship, wherein the cluster to which the observation position coordinate belongs in the observation position coordinate set B of the ship is L ═ L1,l2,......,lk-k’Observed position coordinates identified as noise can be removed in the clustering process.
Specifically, step S130 includes:
s131, determining the port entry times of the ship at a port according to the timestamp set of the ship; when two adjacent timestamps in the timestamp set of the ship are larger than a preset time difference, the number of times of the ship entering the port in the two adjacent timestamps is different.
Step S132, determining the number of times of berthing of the ship at a port according to the timestamp set of the ship and the cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship; and when the cluster clusters to which the observation position coordinates corresponding to the two adjacent timestamps respectively belong are the same, the ship stops at the port.
Step S133, determining a set of the number of times of the ship entering the port and the number of times of the ship berthing according to the number of times of the ship entering the port and the number of times of the ship berthing at the port.
And S134, determining a set of average position coordinates of each time the ship enters a port and stops.
In the first layer of DBSCAN clustering, based on the reported speed and position information of each ship, a berthing record of each ship in the sea area near the port is obtained. And judging the relevance of the berths on the time dimension through the time information reported by each ship, and classifying a plurality of berths entering the port at the same time into one class.
Specifically, when the time stamp set T of the ship is { T ═ T1,t2,......,tnWhen two adjacent timestamps in the set T are greater than a preset time difference, namely the difference T between the ith-1 timestamp and the ith timestamp in the set Ti-ti-1A time difference of ≧ a predetermined time difference indicates two entries of the ship at the two timestamps, e.g., departure after cargo is carried at monday entry and then return to port on friday, then the time interval between two entries is large and can be determined as two entries rather than a wait during one entry. Therefore, the number of times the ship enters the port can be obtained according to the time stamp set T of the ship, and the time stamp of the ship belongs to the port can be determined. Specifically, the preset time difference is 12 hours. Of course, other times may also be employed.
The time difference between two adjacent time stamps in the time stamp set T of the ship is less than or equal to the preset time difference, namely Ti-ti-1If the time difference is less than or equal to the preset time difference, the ship is imported at the same time on the two timestamps, so that multiple berths at the same time at the port can be classified into one class through the time interval between the two adjacent timestamps in the timestamp set T of the ship; the cluster to which the observation position coordinates respectively corresponding to two adjacent timestamps belong is the same, namelyli＝li-1This indicates that the vessel is stopped at the observation position coordinates.
If the cluster clusters to which the observation position coordinates respectively corresponding to two adjacent timestamps belong are different, i.e. |i≠li-1Then it indicates that the state of the ship entering port is changed, i.e. the ship is at ti-1To tiThe bay is moved from a position in the sea area near the port to another position, for example ending the waiting at the anchorage and starting the loading and unloading by moving from the anchorage to the berth.
Determining a set of the number of times of the ship entering the port and the number of times of the ship berthing at the port according to the number of times of the ship entering the port and the number of times of the ship berthing at the port, wherein the set of the number of times of the ship entering the port and the number of times of the ship berthing at the port is C ═ { C ═ C1,c2,......,ck-k’To record the number of stops each observation in set B belongs to the ship at the number of times the port was entered.
After the number of times of entering the port is determined, a set of average position coordinates of the ship entering the port and berthing each time can be determined according to an observation position coordinate set of the ship. The total number of times of berthing of the ship in the sea area near the port in the observation time period is counted as m, and the set of average position coordinates of each time of berthing of the ship is D ═ D1,d2,......,dmTo record the average position coordinates of each berth for each arrival of the ship.
And S200, determining a berthing area and an anchor area of the port according to the docking record of the ship at the port.
Specifically, in the second layer of DBSCAN clustering, berthing in a berthing area and berthing in an anchor area are respectively identified based on berthing records of each ship in a sea area near the port, and then the berthing area and the anchor area are delineated. And taking the set of the average position coordinates of each time the ship enters a port and stops as an input item of the second-layer DBSCAN clustering algorithm, and then collecting the berthing area and the anchor area of the port as an output item of the second-layer DBSCAN clustering algorithm. The set of berthing area and anchor area of the port is E ═ E { (E)1, e2,......,emIndicates that the corresponding berth in the set D is at the anchorage groundIs a set of berths.
Specifically, step S200 specifically includes:
and S210, clustering the average position coordinates in the set of the average position coordinates of each time the ship enters a port and stops to obtain noise points and non-noise points.
Step S220, determining a berthing area and an anchor area of the port according to the noise points and the non-noise points; wherein the noise point is located within the anchor region and the non-noise point is located within the berthing region.
Specifically, in the DBSCAN clustering process, according to the average position coordinate in the set D of the average position coordinates of each port entering and docking of the ship, the average distance dist from all elements in the set D to the centroid of the set D is determined, according to the number m of the elements contained in the set D, a first parameter MinPts of the DBSCAN clustering is determined, according to the average distance dist, a second parameter Eps of the DBSCAN clustering is determined, and the first parameter MinPts and the second parameter Eps are used as parameters of the DBSCAN clustering to cluster the elements in the set D.
Specifically, in the iterative process, the parameters Eps and MinPts are both set according to the following equation relationship: eps ═ 0.5 × dist; MinPts is 0.08 × m. Before entering the iteration, the initial value of the average distance dist is set as the average distance from all elements in the set D to the centroid of the set D, the initial value of the number m is set as the number of elements included in the set D, and the initial distance dist0Is set to 0. And then enters an iterative process. At the beginning of each iteration, dist and dist are first paired0And judging the condition according to the difference value. When dist-dist0>At 0.3km, clustering points in the set D by taking the second parameter Eps and the first parameter MinPts as parameters of DBSCAN clustering, and taking the average distance dist as an initial distance, namely dist0Dist; taking the average distance from each non-noise point in the set D to the centroid of the cluster to which the non-noise point belongs as an average distance dist, namely, dist is the average distance from each non-noise point in the set D to the centroid of the cluster to which the non-noise point belongs; determining a second parameter Eps according to the average distance dist, namely, Eps is 0.5 dist; determining the number m' of points identified as noise in the set D and stacking the last timeAnd taking the difference value of the number m obtained by the generation and the number m' of the points identified as the noise in the iteration as the number m obtained by the iteration, determining a first parameter MinPts, completing the iteration and entering the next iteration. After several iterations, dist and dist0Will be continuously reduced when dist-dist0And when the number of the positions is less than or equal to 0.3km, considering that iteration is converged, accurately identifying a berthing area and an anchor area of the port, and ending the iteration process. diIs recognized as noise, then diIn the anchorage zone; diIs identified as non-noise, then diAnd (4) in a berthing area, so that a berthing area and an anchor area set E of the port are obtained.
And S300, determining the congestion index of the port according to the stop record of the ship at the port and the berthing area and the anchorage area of the port.
Analyzing the entry pattern of each ship at each entry of the port in combination with a set C marking each ship at each entry of the port, a set E indicating whether each ship is anchored or berthed at each entry of the port: if the first berthing of the entry is in the berth, the entry is considered to be not directly berthed after waiting at the anchoring ground; if the first berth of the entry is at the anchoring ground and the second berth is at the berth, the entry is considered to wait at the anchoring ground (namely the first berth); if the first berth of the entry is at the anchor site and the second berth is also at the anchor site, the entry is considered abnormal and removed from the data set.
Specifically, the congestion indicator includes: delay rate and/or latency.
Specifically, step S300 includes:
step S310, determining the number of the ports of the port waiting in the anchor area and the number of the ports of the port according to the docking records of the ship in the port and the berthing area and the anchor area of the port.
Step S320, determining the delay rate according to the number of the ports of the port waiting in the anchor area and the number of the ports of the port.
And S330, determining the waiting time of the ship in the anchor area when the ship enters the port according to the docking record of the ship in the port and the berthing area and the anchor area of the port.
Specifically, the delay rate is the ratio of the number of harbors that pass through the harbor waiting at the anchor site to the total number of harbors; and calculating the waiting time at the anchoring place of each ship at each time of entering according to the timestamp set T of the ship and the entrance mode obtained by the central analysis. If the entry does not wait at the anchor site, the waiting time at the anchor site is recorded as 0.
Specifically, the waiting time is an average waiting time; the average waiting time is the average of the waiting times in the anchorage area when all ships enter the port. The average waiting time for all the ports of the port is calculated through the stop records of all the ships in the port and the berthing area and the anchoring area of the port.
The method of the invention has the following effects:
firstly, the method realizes the accurate identification of the anchor area and the berth area of the global port. For example, fig. 1 to 3 in the drawing section illustrate the identification of a Ningbo-Zhoushan harbor, a high bridge harbor outside the Shanghai harbor and a Shanghai-hong harbor area, respectively, using the method according to the invention, wherein the black dots represent the berthing of the ship in the berth area and the light gray dots represent the berthing of the ship in the anchor area. It can be seen that the method of the present invention clearly distinguishes the two regions. Furthermore, the recognition result is compared with reality, the recognition area is highly consistent with the area division of the actual port, and accurate recognition is achieved.
Secondly, the method realizes effective monitoring of the global port congestion level. Fig. 4 and 5 illustrate the evaluation of global port congestion levels by the method of the present invention, using the example of nibo-navian port in asia, cervid port in europe, and new york-new jersey port in america. Through the evaluation, not only can huge differences of the congestion levels among different ports be seen, but also dynamic changes of the congestion levels of the same port along with time can be seen. For example, after 2020, the congestion level of Ningbo obviously decreases with the decrease of ship traffic at the port, and the congestion level rises again with the restoration of work and economic resuscitation at the port; the congestion level of the ports in Europe and America at the same period is hardly influenced. The characteristics presented in the indexes are consistent with the reality, and the accuracy of the technology on the port congestion measurement is further verified.
Finally, the method has important application significance for all interest relevant parties in shipping industries such as shift companies, cargo owners, ports and the like. For a banjo company, knowing the exact congestion levels at different ports can provide a reference for short and long term routing. In short term, based on the current congestion condition of each port, the ship speed can be adjusted, or a port with serious congestion is skipped to transport goods to other adjacent ports, or the sequence of arriving at different ports is adjusted according to the congestion level of different ports. In the long run, the airliner can take the congestion levels of different ports into consideration during the design of the transportation line, so as to effectively improve the transportation efficiency. For the cargo owner, the congestion levels at different ports may be quantitatively incorporated into their port selection decisions. The owner can make a more informed port selection based on the level of congestion at the port, trading off efficiency over time versus convenience over distance. For harbors, since time efficiency is an important factor in harbor competitiveness, harbor authorities can monitor their own harbors and other harbors for congestion levels and compare their own performance on this index with other harbors in the world. For a port with a continuously serious congestion, effective measures may need to be taken to improve the congestion and thus improve the competitiveness of the port, such as improving and expanding the port infrastructure.
Based on the port congestion monitoring method based on the anchor ground and berth automatic identification algorithm, the invention also provides a preferred embodiment of computer equipment, which comprises the following steps:
as shown in fig. 6, a computer device according to an embodiment of the present invention includes a memory 20 and a processor 10, where the memory 20 stores a computer program, and the processor 10 implements the following steps when executing the computer program:
acquiring a dynamic position report record of a ship, and determining a stop record of the ship at a port according to the dynamic position report record of the ship;
determining a berthing area and an anchorage area of the port according to the docking record of the ship at the port;
and determining the congestion index of the port according to the stop record of the ship at the port and the berthing area and the anchorage area of the port.
Based on the port congestion monitoring method based on the anchorage and berth automatic identification algorithm, the invention also provides a preferred embodiment of computer equipment, which comprises the following steps:
a computer-readable storage medium of an embodiment of the present invention has a computer program stored thereon, which when executed by a processor implements the steps of:
acquiring a dynamic position report record of a ship, and determining a stop record of the ship at a port according to the dynamic position report record of the ship;
determining a berthing area and an anchor area of a port according to the berthing record of the ship at the port;
and determining the congestion index of the port according to the stop record of the ship at the port and the berthing area and the anchorage area of the port.
It is to be understood that the invention is not limited to the examples described above, but that modifications and variations may be effected thereto by those of ordinary skill in the art in light of the foregoing description, and that all such modifications and variations are intended to be within the scope of the invention as defined by the appended claims.

Claims (7)

1. A port congestion monitoring method based on an anchor ground and berth automatic identification algorithm is characterized by comprising the following steps:
acquiring a dynamic position report record of a ship, and determining a stop record of the ship at a port according to the dynamic position report record of the ship;
determining a berthing area and an anchorage area of the port according to the docking record of the ship at the port;
determining a congestion index of a port according to a berthing record of the ship at the port and a berthing area and an anchor area of the port;
the dynamic position reporting record for the vessel includes: the method comprises the steps of collecting position coordinates of a ship, collecting the navigational speed of the ship and collecting a timestamp of the ship;
determining the docking record of the ship at the port according to the dynamic position report record of the ship, comprising:
determining an observation position coordinate set of the ship according to the position coordinate set of the ship and the navigational speed set of the ship; the navigation speed corresponding to the observation position coordinates in the observation position coordinate set of the ship is less than a preset speed;
clustering the observation position coordinate set of the ship to obtain a cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship;
determining a docking record of the ship at a port according to the timestamp set of the ship, the observation position coordinate set of the ship and a cluster to which an observation position coordinate belongs in the observation position coordinate set of the ship;
the recording of the ship berthing at the port comprises the following steps: the method comprises the following steps of collecting the number of times of arrival and the number of times of berthing of a ship at a port and collecting the average position coordinates of each time of arrival and berthing of the ship;
determining a docking record of the ship at the port according to the timestamp set of the ship, the observation position coordinate set of the ship and the cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship, wherein the determining comprises:
determining the number of times of the ship entering the port according to the timestamp set of the ship; when two adjacent timestamps in the timestamp set of the ship are greater than a preset time difference, the port entry times of the ship in the two adjacent timestamps are different;
determining the number of times of the ship berthing at the port according to the timestamp set of the ship and the cluster to which the observation position coordinate belongs in the observation position coordinate set of the ship; when two adjacent timestamps in the timestamp set of the ship are smaller than or equal to a preset time difference, and the cluster clusters to which the observation position coordinates respectively corresponding to the two adjacent timestamps belong are the same, the ship stops at a port;
determining a set of the number of times of the ship entering the port and the number of times of the ship berthing according to the number of times of the ship entering the port and the number of times of the ship berthing at the port;
determining a set of average position coordinates of each time the ship enters a port and stops;
the determining the berthing area and the anchorage area of the port according to the docking record of the ship at the port comprises the following steps:
clustering all average position coordinates in the set of average position coordinates of each time the ship enters a port and stops to obtain noise points and non-noise points;
determining a berthing area and an anchor area of the port according to the noise points and the non-noise points; wherein the noise point is located within the anchor region and the non-noise point is located within the berthing region;
the clustering of each average position coordinate in the set of average position coordinates of each time the ship enters a port and stops to obtain noise points and non-noise points comprises the following steps:
in the DBSCAN clustering process, according to the average position coordinate in the set D of the average position coordinate of each port entering and docking of the ship, determining the average distance dist from all elements in the set D to the centroid of the set D, according to the number m of the elements contained in the set D, determining a first parameter MinPts of the DBSCAN clustering, according to the average distance dist, determining a second parameter Eps of the DBSCAN clustering, and clustering the elements in the set D by taking the first parameter MinPts and the second parameter Eps as the parameters of the DBSCAN clustering;
in the iterative process, the parameters Eps and MinPts are both set according to the following equation: eps ═ 0.5 × dist; MinPts is 0.08 × m; before entering iteration, the initial value of the average distance dist is set as the average distance from all elements in the set D to the centroid of the set D, the initial value of the number m is set as the number of the elements contained in the set D, and the initial distance dist0Is set to 0; then entering an iterative process; at the beginning of each iteration, first pair dist and dist0Carrying out condition judgment on the difference value; when dist-dist0>At 0.3km, clustering points in the set D by taking a second parameter Eps and a first parameter MinPts as parameters of DBSCAN clustering, and taking an average distance dist as an initial distance, namely dist0Dist; taking the average distance from each non-noise point in the set D to the centroid of the cluster to which the non-noise point belongs as an average distance dist, namely, dist is the average distance from each non-noise point in the set D to the centroid of the cluster to which the non-noise point belongs; and determining a second parameter Eps according to the average distance dist, namely, Eps is 0.5 dist; determining the number m 'of the points identified as noise in the set D, taking the difference value between the number m obtained in the last iteration and the number m' of the points identified as noise in the iteration as the number m obtained in the iteration, determining a first parameter MinPts, completing the iteration and entering the next iteration; after several iterations, dist and dist0Will be continuously reduced when dist-dist0And when the number is less than or equal to 0.3km, considering that iteration is converged, accurately identifying the berthing area and the anchor area of the port, and ending the iteration process.
2. The method for monitoring the port congestion based on the anchor and berth automatic identification algorithm as claimed in claim 1, wherein the preset time difference is 12 hours.
3. The port congestion monitoring method based on the anchor and berth automatic identification algorithm as claimed in claim 1, wherein the clustering adopts a density-based clustering method.
4. The port congestion monitoring method based on the anchor and berth automatic identification algorithm as claimed in claim 1, wherein the congestion index comprises: latency and/or latency;
the determining the congestion index of the port according to the stop record of the ship at the port and the berthing area and the anchorage area of the port comprises the following steps:
determining the number of the ports of the port waiting in the anchoring area and the number of the ports of the port according to the docking records of the ship in the port and the berthing area and the anchoring area of the port;
determining the delay rate according to the number of the ports of the port waiting in the anchor area and the number of the ports of the port; and/or
And determining the waiting time of the ship in the anchorage area when the ship enters the port according to the berthing record of the ship in the port and the berthing area and the anchorage area of the port.
5. The method for monitoring the port congestion based on the anchor and berth automatic identification algorithm as claimed in claim 4, wherein the waiting time is an average waiting time; the average waiting time is the average of the waiting times in the anchorage area when all ships enter the port.
6. Computer arrangement comprising a memory and a processor, the memory storing a computer program, characterized in that the processor when executing the computer program realizes the steps of the method for port congestion monitoring based on an anchor and berth automatic identification algorithm according to any of claims 1 to 5.
7. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the method for port congestion monitoring based on an anchor and berth automatic identification algorithm of any one of claims 1 to 5.
CN202011429529.7A 2020-12-09 2020-12-09 Port congestion monitoring method based on anchor ground and berth automatic identification algorithm Active CN113822513B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011429529.7A CN113822513B (en) 2020-12-09 2020-12-09 Port congestion monitoring method based on anchor ground and berth automatic identification algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011429529.7A CN113822513B (en) 2020-12-09 2020-12-09 Port congestion monitoring method based on anchor ground and berth automatic identification algorithm

Publications (2)

Publication Number Publication Date
CN113822513A CN113822513A (en) 2021-12-21
CN113822513B true CN113822513B (en) 2022-06-24

Family

ID=78924845

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011429529.7A Active CN113822513B (en) 2020-12-09 2020-12-09 Port congestion monitoring method based on anchor ground and berth automatic identification algorithm

Country Status (1)

Country Link
CN (1) CN113822513B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115481919B (en) * 2022-09-29 2023-06-27 中远海运科技股份有限公司 Port congestion condition analysis method
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
CN116797117B (en) * 2023-06-16 2024-08-27 深圳大学 Port congestion state monitoring and evaluating method, system, terminal and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105632003A (en) * 2014-11-04 2016-06-01 香港理工大学深圳研究院 Evaluation method and apparatus thereof for customs clearance port queuing time
CN107146061A (en) * 2017-05-26 2017-09-08 亿海蓝（北京）数据技术股份公司 A kind of ship Guakao event method for digging and system based on harbour multi-layer area
CN109658439A (en) * 2017-10-12 2019-04-19 中电科海洋信息技术研究院有限公司 Ship is overstocked a harbour state identification method, device, equipment and storage medium
CN109740494A (en) * 2018-12-27 2019-05-10 中国船舶重工集团公司第七研究院 A kind of harbour recognition methods based on ship track big data
CN111581314A (en) * 2020-04-26 2020-08-25 亿海蓝（北京）数据技术股份公司 Berth identification method and device based on ship track

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2520926B (en) * 2013-11-11 2017-05-10 Tradenet Commercial Networking Ltd A method and system of tracking vessels
CN110750571B (en) * 2018-07-23 2023-12-29 中电科海洋信息技术研究院有限公司 Port berth data mining method, device, equipment and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105632003A (en) * 2014-11-04 2016-06-01 香港理工大学深圳研究院 Evaluation method and apparatus thereof for customs clearance port queuing time
CN107146061A (en) * 2017-05-26 2017-09-08 亿海蓝（北京）数据技术股份公司 A kind of ship Guakao event method for digging and system based on harbour multi-layer area
CN109658439A (en) * 2017-10-12 2019-04-19 中电科海洋信息技术研究院有限公司 Ship is overstocked a harbour state identification method, device, equipment and storage medium
CN109740494A (en) * 2018-12-27 2019-05-10 中国船舶重工集团公司第七研究院 A kind of harbour recognition methods based on ship track big data
CN111581314A (en) * 2020-04-26 2020-08-25 亿海蓝（北京）数据技术股份公司 Berth identification method and device based on ship track

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
"A competitive analysis of port of Hong";Dong Yang 等;《Journal of Shipping and trade》;20200331;第1-17页 *
Mining Port Congestion Indicators from Big AIS Data;Ibrahim AbuAlhaol 等;《2018 International Joint Conference on Neural Networks》;20180713;第1-8页 *
上海外高桥港区停泊船聚类分析与异常检测;郑海林等;《地球信息科学学报》;20180524(第05期);第640-646页 *
基于AIS数据的港口船舶营运效率评估系统;徐明强;《中国航海》;20180925(第03期);第119-122页 *

Also Published As

Publication number Publication date
CN113822513A (en) 2021-12-21

Similar Documents

Publication Publication Date Title
CN113822513B (en) Port congestion monitoring method based on anchor ground and berth automatic identification algorithm
Xin et al. A simulation model for ship navigation in the “Xiazhimen” waterway based on statistical analysis of AIS data
Yang et al. Urban freight delivery stop identification with GPS data
CN114066354A (en) Intelligent air route recommendation method and system based on global ship historical track
CN112016730B (en) Port berth loading and unloading efficiency mining method, device, equipment and storage medium
Yang et al. Can we trust the AIS destination port information for bulk ships?–Implications for shipping policy and practice
Elgesem et al. A traveling salesman problem with pickups and deliveries and stochastic travel times: An application from chemical shipping
CN112785030A (en) Ship behavior recognition system, method and platform
CN113822518B (en) AIS big data driven container port loading and unloading efficiency calculation method
Boufaied A diagnostic approach for advanced tracking of commercial vehicles with time window constraints
CN116797117B (en) Port congestion state monitoring and evaluating method, system, terminal and storage medium
CN116007647A (en) Routing inspection path planning method and device, electronic equipment and storage medium
AU2018215876B2 (en) A method of predicting a traffic behaviour in a road system
Kang et al. Study of narrow waterways congestion based on automatic identification system (AIS) data: A case study of Houston Ship Channel
CA3043672A1 (en) A method of predicting a traffic behaviour in a road system
Arifin et al. Development of ship allocation models using marine logistics data and its application to bulk carrier demand forecasting and basic planning support
CN113222040B (en) Marine fixed target identification method, device, computer equipment and storage medium
CN115577868A (en) Method and device for predicting destination port of in-transit ship, readable storage medium and ship
Wang et al. Fundamental challenge and solution methods in prescriptive analytics for freight transportation
Chen et al. Monitoring and evaluation of ship operation congestion status at container ports based on AIS data
Asborno et al. Inland waterway network mapping of AIS data for freight transportation planning
CN116308000B (en) Logistics scheme evaluation method and device, electronic equipment and readable storage medium
CN117216615A (en) Method, system, medium and electronic equipment for identifying channeling behavior
Zhong et al. A novel oil port risk and efficiency performance measured by using AIS data and maritime open data: the case of Guangzhou, China
CN116664025A (en) Loading and unloading position point generation method, device and equipment

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