WO2019116933A1 - Container terminal system utilizing artificial intelligence - Google Patents

Container terminal system utilizing artificial intelligence Download PDF

Info

Publication number
WO2019116933A1
WO2019116933A1 PCT/JP2018/044250 JP2018044250W WO2019116933A1 WO 2019116933 A1 WO2019116933 A1 WO 2019116933A1 JP 2018044250 W JP2018044250 W JP 2018044250W WO 2019116933 A1 WO2019116933 A1 WO 2019116933A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
trailer
yard
crane
container
Prior art date
Application number
PCT/JP2018/044250
Other languages
French (fr)
Japanese (ja)
Inventor
身智雄 菊地
保之 西尾
修二 上原
満 川俣
昌樹 服部
智彦 美野
崇裕 小島
翔太 井上
宗生 吉江
Original Assignee
国土交通省港湾局長が代表する日本国
国立研究開発法人 海上・港湾・航空技術研究所
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 国土交通省港湾局長が代表する日本国, 国立研究開発法人 海上・港湾・航空技術研究所 filed Critical 国土交通省港湾局長が代表する日本国
Publication of WO2019116933A1 publication Critical patent/WO2019116933A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G63/00—Transferring or trans-shipping at storage areas, railway yards or harbours or in opening mining cuts; Marshalling yard installations

Definitions

  • the present invention relates to a system for operating a container terminal, and more particularly to a technology for utilizing artificial intelligence for efficient operation of the system.
  • Patent Document 1 deploys a transport carriage that reciprocates between a GC and a storage lane that stores containers, a yard crane that moves on the storage lanes, and a cart that can transport containers along the storage lane.
  • An operation method of the container terminal has been proposed.
  • a plurality of (for example, two) yard cranes are disposed in each storage lane, and two container delivery locations are provided on the storage lane side.
  • the two container delivery locations are the delivery location for the yard crane and the delivery location for the cart, and if the yard crane near the delivery location is in operation, the operation of the yard crane where the cart is away from the delivery location It takes the form of transporting a crane to a place. For this reason, it becomes possible to improve the operation efficiency of the transfer cart and the yard crane.
  • Patent Document 1 According to the method disclosed in the above-mentioned Patent Document 1, it is possible to increase the operation efficiency of the GC because the carriage does not stand by in the container yard.
  • the transport bogie, the yard crane, and the like become excessively disposed.
  • carts that move along storage lanes are also added. For this reason, although the loading and unloading time of the ship can be shortened, when viewed as the entire container yard, the operation rates of the transport carts and yard cranes are not high, leaving room for cost reduction.
  • the present invention solves the above problems and aims to improve the working efficiency, shorten the cargo handling time of the ship, and provide a container terminal system utilizing artificial intelligence that can reduce the cost of container physical distribution. To aim.
  • Information, processing related information in the premises trailer, and processing related information in the yard crane are input as input data, and the waiting time of each of the gantry crane, the premises trailer, and the yard crane is minimized using a deep learning method.
  • the operation timing is calculated as output data, and operation instruction information based on the output data is transmitted to the gantry crane, the in-yard trailer, and the yard crane.
  • the input data includes processing related information in the foreign trailer to the container terminal
  • the output data includes the arrival prediction of the foreign trailer.
  • the time and destination information of the foreign trailer may be included, and the work instruction information may be transmitted to the foreign trailer.
  • processing related information on the gantry crane in the container terminal system utilizing the artificial intelligence having the features as described above includes data on the processing capability of the operator of the gantry crane and the handling of the hatch cover on the ship, the gantry crane Current working conditions of the gantry crane, loading speed of the gantry crane, and container position of the ship, and processing related information in the in-building trailer includes position information of the in-building trailer, status information of the in-building trailer, driver information , Weather information, yard map, and container loading and unloading information, and processing related information in the yard crane includes processing capacity of the yard crane, position of the yard crane, status information of the yard crane, operation Over data information handling speed of the yard crane, ship handling plan, and yard may plan contains.
  • Such various information can be acquired at any container terminal regardless of the location of the container terminal. Therefore, it can be set as learning information of artificial intelligence specialized in efficiency improvement of a container terminal, and substrate production in analysis can be stabilized.
  • the processing related information in the foreign trailer in the container terminal system utilizing the artificial intelligence having the characteristics as described above includes the position information of the foreign trailer and the time when the foreign trailer passes through the gate, with respect to the foreign trailer. It is preferable that the allocation status of the gate, the vehicle information at the gate, and the alignment status of the foreign trailer before the gate be included.
  • the container terminal system utilizing the artificial intelligence having the above-mentioned features, it is possible to improve the working efficiency, shorten the cargo handling time of the ship, and reduce the cost of container physical distribution.
  • FIGS. 1 and 2 a container terminal system (hereinafter, simply referred to as an AI utilization system 10) using artificial intelligence according to the first embodiment will be described.
  • the AI utilization system 10 is adopted, for example, in a container terminal 12 as shown in FIG.
  • the container terminal 12 is provided with, for example, a storage place 14 for storing the container 40, and a berth on which the container ship (the main ship 16) carrying the container 40 is placed is provided on the quayside.
  • a gantry crane hereinafter referred to as a GC 18
  • a trailer hereinafter referred to as a premises trailer 20
  • a yard crane 22 for carrying out cargo handling work of the container 40 at the storage location 14.
  • AI 28 artificial intelligence in which a neural network is constructed is configured on a TOS 26 or on a computer attached to the TOS 26. On the basis of the information managed and stored, the output of instruction information for optimizing container handling is performed.
  • the input information used by the AI 28 to output instruction information is mainly processing-related information on the GC 18, processing-related information on the in-yard trailer 20, and processing-related information on the yard crane 22.
  • Specific examples of each processing information are as follows, but the information shown below is not an absolute one, and may be selected appropriately as well as the information classification may also change. .
  • the processing-related information on the GC 18 can be the processing ability of the operator of the GC 18, data on the handling of the hatch cover on the ship 16, the current working condition of the GC 18, the loading speed, the container position of the ship 16, and the like.
  • the processing capability of the operator is, for example, the working time required for loading and unloading one container 40.
  • the loading and unloading speed may be a real-time loading and unloading speed that is actually measured, not an average or maximum speed.
  • the AI 28 can take into consideration changes in the cargo handling speed due to the influence of weather conditions, physical conditions and the like.
  • the processing-related information in the on-premises trailer 20 can be position information on the on-premises trailer 20, status information, driver information, weather information, a yard map, and container in / out information.
  • the position information is acquisition of real-time position information, and it is possible to use a terminal attached to the trailer 20, a portable terminal or the like owned by a driver, and a GPS (Global Positioning System) or the like.
  • GPS Global Positioning System
  • What is necessary is just to analyze position information using a short distance wireless communication network etc., when correct
  • the status information is information as to whether the corresponding premises trailer 20 is in operation or free.
  • the weather information is information for considering the change in the moving speed of the trailer due to the weather.
  • the yard map is a map of the entire container yard including the storage place 14 and the like.
  • the container in / out information is container information including vanning registration information, in-bond approval information, CLS information and the like. Note that techniques other than GPS may be used to detect position information.
  • the processing-related information in the yard crane 22 can be the processing capacity of the yard crane 22, position, status information, operator information, cargo handling speed, ship handling plan, yard plan, and the like.
  • the processing capacity of the yard crane 22 is an operation time when loading and unloading one container 40 and the like, and the status information is a moving speed and the like.
  • the loading and unloading speed is, like the GC 18, a real-time loading and unloading speed.
  • the cargo handling plan includes those prepared in advance and those modified in real time according to the work situation.
  • the yard plan includes container placement plans for the entire container yard and container placement status in real time.
  • Such information is mainly input to and stored in the TOS 26, and used as input information of the AI 28. It is desirable that the input data transfer be performed at regular intervals in consideration of grasping the change in actual conditions, the load at the time of analysis, and the like.
  • AI analysis Based on the input information as described above obtained through the TOS 26, the AI 28 performs analysis by a deep learning method using a neural network.
  • the analysis items in the case of the present embodiment can be, for example, the following items.
  • the order of loading and unloading tasks of the GC 18 is predicted based on the loading and unloading status of the ship.
  • the order prediction of the cargo handling tasks of the yard crane 22 is performed.
  • the optimum instruction information for the on-premises trailer 20 is the arrival time (travel distance) to the GC 18 or yard crane 22 based on the order prediction of the cargo handling task (GC 18, yard crane 22) described above and the position and status of the on-premises trailer 20. , It is required for each cargo handling task so that the waiting time is minimized.
  • the arrival time can be calculated based on the position information acquired via GPS or the like, the shortest route obtained based on the yard map, and the moving speed of the trailer 20.
  • the waiting time is calculated based on the predicted arrival time, the order of the loading and unloading tasks of the GC 18 and the yard crane 22, the current work status, and the like. Then, the optimum instruction information to the premises trailer 20 is an instruction to move to the loading position where the sum of the arrival time and the waiting time is minimized.
  • the optimum instruction information for the on-premises trailer 20 determined by the AI 28 is output to the TOS 26 and, at the same time, an instruction is given to the on-site trailer 20 from the TOS 26 via the network.
  • the TOS 26 also outputs a movement instruction based on the loading position of the on-site trailer 20 and the timing to the yard crane 22.
  • the change information is output to the GC 18 as needed (for example, when the order change of the cargo handling task occurs).
  • an AI utilization system 10A according to a second embodiment will be described with reference to FIGS. 3 and 4.
  • Most of the configuration of the AI application system 10A according to the present embodiment is the same as the AI application system 10 according to the first embodiment described above. Therefore, in the part which makes the structure the same, the same code
  • the difference between the AI utilization system 10A according to the present embodiment and the AI utilization system 10 according to the first embodiment is the consideration of the presence of the foreign trailer 32 with respect to the container terminal 12.
  • the foreign trailer 32 carries the container 40 on the land transportation side via the gate 30 with the container terminal 12 as a base point. For this reason, the container handling at the storage location 14 with respect to the foreign trailer 32 is performed simultaneously with or before or after the ship handling. Therefore, when the loading and unloading work is emphasized, the loading and unloading work for the foreign trailer 32 is delayed, causing a problem such as a traffic jam inside and outside the gate 30 at the container terminal 12.
  • processing relevant information in the foreign trailer 32 is included as input data to the AI 28, and the system performs deep learning by the AI 28.
  • the processing related information in the foreign trailer 32 includes, for example, position information of the foreign trailer 32, IN / OUT time to the gate 30, assignment of the gate 30, vehicle information at the gate 30, and alignment in front of the gate 30, etc. is there.
  • the position information of the foreign trailer 32 is information for predicting the arrival time of the foreign trailer 32 to the container terminal 12, and can be derived based on GPS, existing map information, ETC information, and the like.
  • the vehicle information at the gate 30 is, for example, determination information as to whether the vehicle is actually transported or is transported by air.
  • the row status in front of the gate 30 is, for example, analysis data using acquired images by a camera (not shown) installed at the gate 30, etc., based on actual conditions such as traffic jam status in front of the gate 30 It can be used as data etc. for predicting the time when moving up to 14.
  • Such input data is input to the TOS 26 and used for analysis by the AI 28 as in the AI utilization system 10 according to the first embodiment.
  • AI analysis As described in the first embodiment, based on the input information as described above (including the information described in the first embodiment) obtained through the TOS 26, the AI 28 uses a deep learning method using a neural network. Perform analysis.
  • the analysis item in the case of the present embodiment is the prediction of the time when the foreign trailer 32 reaches the designated storage location 14.
  • the prediction is performed based on the position information described above, the IN / OUT time to the gate 30 (the gate IN time for arrival), the allocation status of the gate 30, vehicle information, the alignment status before the gate 30, etc. I can do things.
  • the analysis is similarly performed on the optimum instruction information for the indoor trailer 20 described in the first embodiment.
  • the arrival time of the foreign trailer 32 and the loading and unloading time are considered. Become.
  • the optimum instruction information for the on-premises trailer 20 determined by the AI 28 is output to the TOS 26 and, at the same time, an instruction is given to the on-site trailer 20 from the TOS 26 via the network.
  • the arrival time and loading position of the foreign trailer 32 are added to the movement instruction output from the TOS 26 to the yard crane 22.
  • work instruction information of the pass gate, the storage place 14 and the like is output to the foreign trailer 32 as appropriate. By following this instruction, the foreign trailer 32 can minimize the waiting time at the gate passage and the waiting time at the loading operation.
  • the number of personnel including the number of in-premises trailers and the in-yard trailer 20 and the yard crane 22
  • gate layout I side
  • the calculation of the ratio of the numbers on the side and the OUT side, etc., and the output are also performed.
  • the input data used by the AI 28 for analysis include worker recognition information.
  • the determination and response of the operator of the cargo handling machine such as the GC 18 and the yard crane 22, the terminal operator, the driver of the on-premises trailer 20 and the trailer 32 and the like may be included.
  • the operator recognition information may be input via a dedicated input device, a touch panel of a portable terminal or the like, a camera, voice input means, and the like.

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Provided is a container terminal system that utilizes artificial intelligence and can improve work efficiency, shorten ship cargo handling times, and reduce distribution costs over the entire container terminal. This container terminal system comprises AI 28 constituting a neural network and is characterized by: having at least processing information pertaining to a GC 18, processing information in a yard trailer 20, or processing information in a yard crane 22 input to the AI 28 as input data; using deep learning and finding, as output data, work timing whereby the wait times for the GC 18, the yard trailer 20, and the yard crane 22, respectively, are minimized; and sending work instruction information on the basis of the output data, to the GC 18, the yard trailer 20, and the yard crane 22.

Description

人工知能を活用したコンテナターミナルシステムContainer terminal system using artificial intelligence
　本発明は、コンテナターミナルを運用する際のシステムに係り、特に、当該システムの効率的な運用に人工知能を活用する技術に関する。 The present invention relates to a system for operating a container terminal, and more particularly to a technology for utilizing artificial intelligence for efficient operation of the system.
　港湾におけるコンテナ物流において、その効率化とコストダウンのために最も重視されているのが、本船の荷役時間を短縮することである。このため、コンテナターミナルでは、本船荷役を行う際、岸壁側に構内トレーラやヤードクレーンなどの配置を集中させ、ガントリークレーン（以下、ＧＣと称す）の作業を停滞させる事無くコンテナの引き渡しが成されるような作業形態が採られている。 In container transportation at ports, the most important factor for its efficiency and cost reduction is shortening the loading and unloading time of the ship. For this reason, at the container terminal, when carrying out the cargo handling, the arrangement of the in-building trailer and yard cranes is concentrated on the quayside, and the delivery of the container is completed without stagnating the work of the gantry crane (hereinafter referred to as GC). Work forms are adopted.
　また、特許文献１には、ＧＣとコンテナを蔵置する蔵置レーンの間を往復する搬送台車と、蔵置レーン上を移動するヤードクレーン、および蔵置レーンに沿ってコンテナを搬送可能なカートとを配備するコンテナターミナルの運用方法が提案されている。そして、特許文献１に開示されている方法では、各蔵置レーンに複数（例えば２台）のヤードクレーンを配備すると共に、蔵置レーン側に、コンテナの受け渡し場所を２箇所設ける構成としている。２箇所のコンテナ受け渡し場所は、ヤードクレーン用の受け渡し場所と、カート用の受け渡し場所であり、受け渡し場所近傍のヤードクレーンが稼働中である場合には、カートが受け渡し場所から離れたヤードクレーンの稼働場所までクレーンを搬送するという形態を採っている。このため、搬送台車、ヤードクレーンは、それぞれその稼働効率を向上させることが可能となる。 Further, Patent Document 1 deploys a transport carriage that reciprocates between a GC and a storage lane that stores containers, a yard crane that moves on the storage lanes, and a cart that can transport containers along the storage lane. An operation method of the container terminal has been proposed. In the method disclosed in Patent Document 1, a plurality of (for example, two) yard cranes are disposed in each storage lane, and two container delivery locations are provided on the storage lane side. The two container delivery locations are the delivery location for the yard crane and the delivery location for the cart, and if the yard crane near the delivery location is in operation, the operation of the yard crane where the cart is away from the delivery location It takes the form of transporting a crane to a place. For this reason, it becomes possible to improve the operation efficiency of the transfer cart and the yard crane.
特開２０１５－１９６５５６号公報JP, 2015-196556, A
　上記特許文献１に開示されているような方法であれば、搬送台車がコンテナヤード内で待機する事が無くなるこのため、ＧＣの稼働効率を上げる事はできる。しかしながら、上記特許文献１に開示されているような方法では、搬送台車やヤードクレーンなどが過剰配置となる可能性が高い。さらに、蔵置レーンに沿って移動するカートも追加されている。このため、本船の荷役時間は短くすることが出来るものの、コンテナヤード全体として見た場合には、搬送台車やヤードクレーンの稼働率は高くなく、コストの低減を図る余地が残されている。 According to the method disclosed in the above-mentioned Patent Document 1, it is possible to increase the operation efficiency of the GC because the carriage does not stand by in the container yard. However, in the method as disclosed in Patent Document 1 described above, there is a high possibility that the transport bogie, the yard crane, and the like become excessively disposed. In addition, carts that move along storage lanes are also added. For this reason, although the loading and unloading time of the ship can be shortened, when viewed as the entire container yard, the operation rates of the transport carts and yard cranes are not high, leaving room for cost reduction.
　そこで本発明では、上記課題を解決し、作業効率の向上を図ると共に、本船の荷役時間を短縮し、コンテナ物流のコスト低減を図ることのできる人工知能を活用したコンテナターミナルシステムを提供することを目的とする。 Therefore, the present invention solves the above problems and aims to improve the working efficiency, shorten the cargo handling time of the ship, and provide a container terminal system utilizing artificial intelligence that can reduce the cost of container physical distribution. To aim.
　上記目的を達成するための本発明に係る人工知能を活用したコンテナターミナルシステムは、コンテナターミナルの管理システムにおいて、ニューラルネットワークを構築した人工知能を備え、前記人工知能には少なくとも、ガントリークレーンに関する処理関連情報と、構内トレーラにおける処理関連情報、およびヤードクレーンにおける処理関連情報を入力データとして入力し、ディープラーニングの手法を用いて前記ガントリークレーンと前記構内トレーラ、および前記ヤードクレーンそれぞれの待ち時間が最少となる作業タイミングを出力データとして求め、前記ガントリークレーン、前記構内トレーラ、および前記ヤードクレーンに対して前記出力データに基づく作業指示情報を送信することを特徴とする。 The container terminal system utilizing artificial intelligence according to the present invention for achieving the above object comprises artificial intelligence in which a neural network is constructed in a management system of container terminals, and the artificial intelligence includes at least processing related to a gantry crane. Information, processing related information in the premises trailer, and processing related information in the yard crane are input as input data, and the waiting time of each of the gantry crane, the premises trailer, and the yard crane is minimized using a deep learning method. The operation timing is calculated as output data, and operation instruction information based on the output data is transmitted to the gantry crane, the in-yard trailer, and the yard crane.
　また、上記のような特徴を有する人工知能を活用したコンテナターミナルシステムにおいて前記入力データには、前記コンテナターミナルへの外来トレーラにおける処理関連情報を含み、前記出力データには、前記外来トレーラの到着予測時間と前記外来トレーラの行先情報が含まれ、前記作業指示情報は、前記外来トレーラにも送信されるようにすることができる。このような特徴を有する事によれば、外来トレーラに対する荷役作業も含めたコンテナターミナルにおける総合的な荷役作業の効率化を図る事が可能となる。 In addition, in the container terminal system utilizing artificial intelligence having the characteristics as described above, the input data includes processing related information in the foreign trailer to the container terminal, and the output data includes the arrival prediction of the foreign trailer. The time and destination information of the foreign trailer may be included, and the work instruction information may be transmitted to the foreign trailer. By having such a feature, it is possible to improve the efficiency of the overall cargo handling operation at the container terminal including the cargo handling operation for the foreign trailer.
　また、上記のような特徴を有する人工知能を活用したコンテナターミナルシステムにおける前記ガントリークレーンに関する処理関連情報には、前記ガントリークレーンのオペレータの処理能力や、本船におけるハッチカバーの取り扱いに関するデータ、前記ガントリークレーンの現在の作業状況、前記ガントリークレーンの荷役速度、及び前記本船のコンテナ位置が含まれ、前記構内トレーラにおける処理関連情報には、前記構内トレーラの位置情報や、前記構内トレーラのステータス情報、ドライバー情報、気象情報、ヤードマップ、およびコンテナ搬出入情報が含まれ、前記ヤードクレーンにおける処理関連情報としては、前記ヤードクレーンの処理能力や、前記ヤードクレーンの位置、前記ヤードクレーンのステータス情報、オペレータ情報、前記ヤードクレーンの荷役速度、本船荷役計画、およびヤードプランが含まれていると良い。このような各種情報は、コンテナターミナルの場所を選ばず、いずれのコンテナターミナルでも取得する事ができる。よって、コンテナターミナルの効率化に特化した人工知能の学習情報とすることができ、解析における基板作りを安定させることができる。 Further, the processing related information on the gantry crane in the container terminal system utilizing the artificial intelligence having the features as described above includes data on the processing capability of the operator of the gantry crane and the handling of the hatch cover on the ship, the gantry crane Current working conditions of the gantry crane, loading speed of the gantry crane, and container position of the ship, and processing related information in the in-building trailer includes position information of the in-building trailer, status information of the in-building trailer, driver information , Weather information, yard map, and container loading and unloading information, and processing related information in the yard crane includes processing capacity of the yard crane, position of the yard crane, status information of the yard crane, operation Over data information handling speed of the yard crane, ship handling plan, and yard may plan contains. Such various information can be acquired at any container terminal regardless of the location of the container terminal. Therefore, it can be set as learning information of artificial intelligence specialized in efficiency improvement of a container terminal, and substrate production in analysis can be stabilized.
　さらに、上記のような特徴を有する人工知能を活用したコンテナターミナルシステムにおける前記外来トレーラにおける処理関連情報には、前記外来トレーラの位置情報や、前記外来トレーラがゲートを通過する時間、前記外来トレーラに対する前記ゲートの割り当て状況、前記ゲートにいる車両情報、およびゲート前における前記外来トレーラの並び状況が含まれるようにすると良い。 Furthermore, the processing related information in the foreign trailer in the container terminal system utilizing the artificial intelligence having the characteristics as described above includes the position information of the foreign trailer and the time when the foreign trailer passes through the gate, with respect to the foreign trailer. It is preferable that the allocation status of the gate, the vehicle information at the gate, and the alignment status of the foreign trailer before the gate be included.
　上記のような特徴を有する人工知能を活用したコンテナターミナルシステムによれば、作業効率の向上を図ると共に、本船の荷役時間を短縮し、コンテナ物流のコスト低減を図ることが可能となる。 According to the container terminal system utilizing the artificial intelligence having the above-mentioned features, it is possible to improve the working efficiency, shorten the cargo handling time of the ship, and reduce the cost of container physical distribution.
第１実施形態に係る人工知能を活用したコンテナターミナルシステムを構成する要素とコンテナターミナルとの関係を示す図である。It is a figure which shows the relationship between the element which comprises the container terminal system which utilized the artificial intelligence which concerns on 1st Embodiment, and a container terminal. 第１実施形態に係る人工知能を活用したコンテナターミナルシステムの概略構成を示す図である。It is a figure which shows schematic structure of the container terminal system which utilized the artificial intelligence which concerns on 1st Embodiment. 第２実施形態に係る人工知能を活用したコンテナターミナルシステムを構成する要素とコンテナターミナルとの関係を示す図である。It is a figure which shows the relationship between the element which comprises the container terminal system which utilized the artificial intelligence which concerns on 2nd Embodiment, and a container terminal. 第２実施形態に係る人工知能を活用したコンテナターミナルシステムの概略構成を示す図である。It is a figure which shows schematic structure of the container terminal system which utilized the artificial intelligence which concerns on 2nd Embodiment.
　以下、本発明の人工知能を活用したコンテナターミナルシステムに係る実施の形態について、図面を参照して詳細に説明する。まず、図１、図２を参照して、第１実施形態に係る人工知能を活用したコンテナターミナルシステム（以下、単にＡＩ活用システム１０と称す）について説明する。 Hereinafter, an embodiment according to a container terminal system utilizing artificial intelligence of the present invention will be described in detail with reference to the drawings. First, with reference to FIGS. 1 and 2, a container terminal system (hereinafter, simply referred to as an AI utilization system 10) using artificial intelligence according to the first embodiment will be described.
［第１実施形態：ターミナル内のみでのシステム］
　本実施形態に係るＡＩ活用システム１０は、例えば図１に示すようなコンテナターミナル１２で採用される。コンテナターミナル１２には、例えばコンテナ４０を蔵置する蔵置場所１４が設けられると共に、岸壁側には、コンテナ４０を運ぶコンテナ船（本船１６）が着岸するバースが設けられている。また、着岸している本船１６には、コンテナ４０を荷役するためのガントリークレーン（以下、ＧＣ１８と称す）と、コンテナターミナル内でのコンテナ４０の移送を行うトレーラ（以下、構内トレーラ２０と称す）、および蔵置場所１４においてコンテナ４０の荷役作業を行うヤードクレーン２２とを有する。 [First embodiment: system in terminal only]
The AI utilization system 10 according to the present embodiment is adopted, for example, in a container terminal 12 as shown in FIG. The container terminal 12 is provided with, for example, a storage place 14 for storing the container 40, and a berth on which the container ship (the main ship 16) carrying the container 40 is placed is provided on the quayside. In addition, a gantry crane (hereinafter referred to as a GC 18) for loading and unloading the container 40 and a trailer (hereinafter referred to as a premises trailer 20) for transferring the container 40 in the container terminal to the docked ship 16 And a yard crane 22 for carrying out cargo handling work of the container 40 at the storage location 14.
　また、このようなコンテナターミナル１２では、管理塔２４内などに設けられたターミナルオペレーションシステム（以下、ＴＯＳ２６と称す）により、ＧＣ１８に対する作業指示、構内トレーラ２０の作業指示、ヤードクレーン２２の作業指示、およびコンテナ４０の搬出入管理等が行われている。本実施形態に係るＡＩ活用システム１０では、ＴＯＳ２６上、あるいはＴＯＳ２６に付帯されたコンピュータ上に、ニューラルネットワークを構築した人工知能（以下、artificial intelligence：ＡＩ２８と称す）が構成されており、主にＴＯＳ２６によって管理、蓄積されている情報に基づいて、コンテナ荷役の最適化を図るための指示情報の出力が成される。 Further, in such a container terminal 12, a work instruction to the GC 18, a work instruction to the premises trailer 20, a work instruction to the yard crane 22 by a terminal operation system (hereinafter referred to as TOS 26) provided in the management tower 24 or the like. And the transfer management of the container 40, etc. are performed. In the AI utilization system 10 according to the present embodiment, artificial intelligence (hereinafter referred to as artificial intelligence: AI 28) in which a neural network is constructed is configured on a TOS 26 or on a computer attached to the TOS 26. On the basis of the information managed and stored, the output of instruction information for optimizing container handling is performed.
［ＡＩ入力情報］
　ＡＩ２８が指示情報の出力のために利用する入力情報としては、主に、ＧＣ１８に関する処理関連情報や、構内トレーラ２０における処理関連情報、およびヤードクレーン２２における処理関連情報などである。各処理情報の具体例としては、次の通りであるが、以下に示す情報は、絶対的なものでは無く、適宜取捨選択が成される事があると共に、その情報区分も変動することがある。 [AI input information]
The input information used by the AI 28 to output instruction information is mainly processing-related information on the GC 18, processing-related information on the in-yard trailer 20, and processing-related information on the yard crane 22. Specific examples of each processing information are as follows, but the information shown below is not an absolute one, and may be selected appropriately as well as the information classification may also change. .
　ＧＣ１８に関する処理関連情報としては、ＧＣ１８のオペレータの処理能力や、本船１６におけるハッチカバーの取り扱いに関するデータ、ＧＣ１８の現在の作業状況、荷役速度、及び本船１６のコンテナ位置等とすることができる。ここで、オペレータの処理能力とは、例えば、１個のコンテナ４０を荷役する際に要する作業時間などである。また、荷役速度は、平均的、あるいは最高速度では無く、実測されるリアルタイムな荷役速度とすると良い。リアルタイムな荷役速度を入力情報とすることで、ＡＩ２８は、気象状況や体調等の影響による荷役速度の変化を考慮することが可能となるからである。 The processing-related information on the GC 18 can be the processing ability of the operator of the GC 18, data on the handling of the hatch cover on the ship 16, the current working condition of the GC 18, the loading speed, the container position of the ship 16, and the like. Here, the processing capability of the operator is, for example, the working time required for loading and unloading one container 40. In addition, the loading and unloading speed may be a real-time loading and unloading speed that is actually measured, not an average or maximum speed. By using the real-time cargo handling speed as input information, the AI 28 can take into consideration changes in the cargo handling speed due to the influence of weather conditions, physical conditions and the like.
　構内トレーラ２０における処理関連情報としては、構内トレーラ２０の位置情報や、ステータス情報、ドライバー情報、気象情報、ヤードマップ、およびコンテナ搬出入情報などとすることができる。位置情報は、リアルタイムな位置情報の取得であり、構内トレーラ２０に付帯された端末、あるいはドライバーが保有する携帯端末等と、ＧＰＳ（Global Positioning System）などを利用する事ができる。なお、ＧＰＳによる取得位置情報についての誤差を補正する場合には、短距離無線通信網などを利用して位置情報の解析を行うようにすれば良い。また、ステータス情報とは、該当する構内トレーラ２０が作業中であるのか、フリーであるのかといった情報である。気象情報は、天候によるトレーラの移動速度の変化を考慮するための情報である。ヤードマップは、蔵置場所１４などを含むコンテナヤード全体の地図である。また、コンテナ搬出入情報とは、バンニング登録情報や保税運送承認情報、ＣＬＳ情報などを含むコンテナ情報である。なお、位置情報の検出については、ＧＰＳ以外の技術を利用しても良い。 The processing-related information in the on-premises trailer 20 can be position information on the on-premises trailer 20, status information, driver information, weather information, a yard map, and container in / out information. The position information is acquisition of real-time position information, and it is possible to use a terminal attached to the trailer 20, a portable terminal or the like owned by a driver, and a GPS (Global Positioning System) or the like. In addition, what is necessary is just to analyze position information using a short distance wireless communication network etc., when correct | amending the difference | error about the acquisition position information by GPS. The status information is information as to whether the corresponding premises trailer 20 is in operation or free. The weather information is information for considering the change in the moving speed of the trailer due to the weather. The yard map is a map of the entire container yard including the storage place 14 and the like. Further, the container in / out information is container information including vanning registration information, in-bond approval information, CLS information and the like. Note that techniques other than GPS may be used to detect position information.
　ヤードクレーン２２における処理関連情報としては、ヤードクレーン２２の処理能力や、位置、ステータス情報、オペレータ情報、荷役速度、本船荷役計画、およびヤードプランなどとすることができる。ヤードクレーン２２の処理能力とは、１個のコンテナ４０を荷役する際の作業時間などであり、ステータス情報とは、移動速度などである。また、荷役速度は、ＧＣ１８と同様に、リアルタイムな荷役速度である。本船荷役計画は、事前に作成されたもの、および作業状況に応じてリアルタイムに修正を加えたものを含む。さらにヤードプランは、コンテナヤード全体のコンテナ配置計画、およびリアルタイムでのコンテナ配置状況などである。 The processing-related information in the yard crane 22 can be the processing capacity of the yard crane 22, position, status information, operator information, cargo handling speed, ship handling plan, yard plan, and the like. The processing capacity of the yard crane 22 is an operation time when loading and unloading one container 40 and the like, and the status information is a moving speed and the like. Further, the loading and unloading speed is, like the GC 18, a real-time loading and unloading speed. The cargo handling plan includes those prepared in advance and those modified in real time according to the work situation. Furthermore, the yard plan includes container placement plans for the entire container yard and container placement status in real time.
　このような情報は、主に、ＴＯＳ２６に入力、蓄積され、ＡＩ２８の入力情報として利用される。情報の取得は、実状の変化の把握や、解析時の負荷などを考慮し、入力データの転送が一定間隔で行われることが望ましい。 Such information is mainly input to and stored in the TOS 26, and used as input information of the AI 28. It is desirable that the input data transfer be performed at regular intervals in consideration of grasping the change in actual conditions, the load at the time of analysis, and the like.
［ＡＩ解析］
　ＴＯＳ２６を介して得られる上記のような入力情報に基づき、ＡＩ２８は、ニューラルネットワークを用いたディープラーニングの手法による解析を行う。本実施形態の場合における解析事項は、例えば次のような事項とすることができる。 [AI analysis]
Based on the input information as described above obtained through the TOS 26, the AI 28 performs analysis by a deep learning method using a neural network. The analysis items in the case of the present embodiment can be, for example, the following items.
　まず、本船荷役状況によるＧＣ１８の荷役タスクの順序予測である。次に、ヤードクレーン２２の荷役タスクの順序予測。そして、本船荷役タスクの順序予測や、ヤードクレーン２２の荷役タスクの順序予測に基づく構内トレーラ２０への最適指示情報の解析である。構内トレーラ２０への最適指示情報は、前述した荷役タスクの順序予測（ＧＣ１８、ヤードクレーン２２）と、構内トレーラ２０の位置やステータスに基づき、ＧＣ１８やヤードクレーン２２への到達時間（移動距離）と、待機時間が最少化されるように、荷役タスク毎に求められる。なお、到達時間は、ＧＰＳ等を介して取得された位置情報と、ヤードマップに基づいて求められる最短経路と、構内トレーラ２０の移動速度に基づいて算出する事ができる。また、待機時間は、予測される到達時間と、ＧＣ１８やヤードクレーン２２の荷役タスクの順序や、現在の作業状況などに基づいて算出されることとなる。そして、構内トレーラ２０への最適指示情報は、到達時間と待機時間の和が最小となる荷役位置への移動指示となる。 First, the order of loading and unloading tasks of the GC 18 is predicted based on the loading and unloading status of the ship. Next, the order prediction of the cargo handling tasks of the yard crane 22 is performed. And it is analysis of the optimal instruction | indication information to the yard trailer 20 based on order prediction of a ship handling task, and order prediction of the loading task of the yard crane 22. FIG. The optimum instruction information for the on-premises trailer 20 is the arrival time (travel distance) to the GC 18 or yard crane 22 based on the order prediction of the cargo handling task (GC 18, yard crane 22) described above and the position and status of the on-premises trailer 20. , It is required for each cargo handling task so that the waiting time is minimized. The arrival time can be calculated based on the position information acquired via GPS or the like, the shortest route obtained based on the yard map, and the moving speed of the trailer 20. In addition, the waiting time is calculated based on the predicted arrival time, the order of the loading and unloading tasks of the GC 18 and the yard crane 22, the current work status, and the like. Then, the optimum instruction information to the premises trailer 20 is an instruction to move to the loading position where the sum of the arrival time and the waiting time is minimized.
［ＡＩ出力情報］
　ＡＩ２８によって求められた構内トレーラ２０への最適指示情報は、ＴＯＳ２６へ出力されると共に、ＴＯＳ２６からネットワークを介して構内トレーラ２０へ、荷役場所（移動場所）の指示が成される。また、ＴＯＳ２６は、ヤードクレーン２２に対しても、構内トレーラ２０の荷役場所、およびタイミングに基づく移動指示が出力される。また、ＧＣ１８に対しては、必要に応じて（荷役タスクの順序変更が生じた場合など）、変更情報の出力が成される。 [AI output information]
The optimum instruction information for the on-premises trailer 20 determined by the AI 28 is output to the TOS 26 and, at the same time, an instruction is given to the on-site trailer 20 from the TOS 26 via the network. The TOS 26 also outputs a movement instruction based on the loading position of the on-site trailer 20 and the timing to the yard crane 22. In addition, the change information is output to the GC 18 as needed (for example, when the order change of the cargo handling task occurs).
［効果］
　上記のようなＡＩ活用システム１０によれば、ＧＣ１８と構内トレーラ２０、及びヤードクレーン２２における作業待機時間の最小化を図る事ができる。よって、作業効率の向上を図る事ができる。また、構内トレーラ２０に対する最適指示情報を求める事により、構内トレーラ２０の移動に無駄が無く、コンテナターミナル１２内に配備する構内トレーラ２０の数を最小化する事ができる。これにより、本船１６の荷役時間の短縮と共に、コンテナターミナル全体において物流のコスト低減を図ることが可能となる。 [effect]
According to the above-described AI application system 10, it is possible to minimize the work standby time in the GC 18 and the on-premises trailer 20 and the yard crane 22. Therefore, the working efficiency can be improved. Further, by obtaining the optimum instruction information for the indoor trailer 20, the movement of the indoor trailer 20 is not wasted, and the number of the indoor trailers 20 disposed in the container terminal 12 can be minimized. This makes it possible to reduce the cost of physical distribution in the entire container terminal as well as shortening the loading and unloading time of the ship 16.
［第２実施形態：外来トレーラを含む場合］
　次に、第２実施形態に係るＡＩ活用システム１０Ａについて、図３、図４を参照して説明する。本実施形態に係るＡＩ活用システム１０Ａの殆どの構成は、上述した第１実施形態に係るＡＩ活用システム１０と同様である。よって、その構成を同一とする箇所には、図面に同一符号を附して、詳細な説明は省略することとする。 Second Embodiment In the Case of Including an Outpatient Trailer
Next, an AI utilization system 10A according to a second embodiment will be described with reference to FIGS. 3 and 4. Most of the configuration of the AI application system 10A according to the present embodiment is the same as the AI application system 10 according to the first embodiment described above. Therefore, in the part which makes the structure the same, the same code | symbol is attached | subjected to drawing, and suppose that detailed description is abbreviate | omitted.
　本実施形態に係るＡＩ活用システム１０Ａと、第１実施形態に係るＡＩ活用システム１０との相違点は、コンテナターミナル１２に対する外来トレーラ３２の存在の考慮である。外来トレーラ３２は、コンテナターミナル１２を基点として、ゲート３０を介して陸運側におけるコンテナ４０の搬出入を行う。このため、外来トレーラ３２に対する蔵置場所１４でのコンテナ荷役は、本船荷役と同時、あるいは前後して成されることとなる。よって、本船荷役作業を重視した場合には、外来トレーラ３２に対する荷役作業が遅滞し、コンテナターミナル１２におけるゲート３０の内外での渋滞等の問題を生じさせることとなってしまう。 The difference between the AI utilization system 10A according to the present embodiment and the AI utilization system 10 according to the first embodiment is the consideration of the presence of the foreign trailer 32 with respect to the container terminal 12. The foreign trailer 32 carries the container 40 on the land transportation side via the gate 30 with the container terminal 12 as a base point. For this reason, the container handling at the storage location 14 with respect to the foreign trailer 32 is performed simultaneously with or before or after the ship handling. Therefore, when the loading and unloading work is emphasized, the loading and unloading work for the foreign trailer 32 is delayed, causing a problem such as a traffic jam inside and outside the gate 30 at the container terminal 12.
　本実施形態では、こうした外来トレーラ３２に対する荷役作業も含めたコンテナターミナル１２における総合的な荷役作業の効率化を図る事を目的としている。具体的には、ＡＩ２８に対する入力データとして、外来トレーラ３２における処理関連情報を含ませて、ＡＩ２８によるディープラーニングを実施するシステムとする。 In the present embodiment, it is an object of the present invention to improve the efficiency of the overall cargo handling operation at the container terminal 12 including the cargo handling operation for the foreign trailer 32. Specifically, processing relevant information in the foreign trailer 32 is included as input data to the AI 28, and the system performs deep learning by the AI 28.
［ＡＩ入力情報］
　外来トレーラ３２における処理関連情報とは、例えば、外来トレーラ３２の位置情報や、ゲート３０に対するＩＮ／ＯＵＴ時間、ゲート３０の割り当て状況、ゲート３０にいる車両情報、およびゲート３０前における並び状況などである。外来トレーラ３２の位置情報は、コンテナターミナル１２に対する外来トレーラ３２の来場時期を予測するための情報であり、ＧＰＳや、既存の地図情報、ＥＴＣ情報などに基づいて導く事ができる。また、ゲート３０にいる車両情報とは、その車両が実入り運送なのか、空運送なのかの判定情報などである。ゲート３０前における並び状況とは、例えばゲート３０に設置されたカメラ（不図示）などによる取得映像を利用した解析データであり、ゲート３０前における渋滞状況などの実状に基づき、来場して蔵置場所１４まで移動する際の時間を予測するためのデータ等として用いることができる。 [AI input information]
The processing related information in the foreign trailer 32 includes, for example, position information of the foreign trailer 32, IN / OUT time to the gate 30, assignment of the gate 30, vehicle information at the gate 30, and alignment in front of the gate 30, etc. is there. The position information of the foreign trailer 32 is information for predicting the arrival time of the foreign trailer 32 to the container terminal 12, and can be derived based on GPS, existing map information, ETC information, and the like. The vehicle information at the gate 30 is, for example, determination information as to whether the vehicle is actually transported or is transported by air. The row status in front of the gate 30 is, for example, analysis data using acquired images by a camera (not shown) installed at the gate 30, etc., based on actual conditions such as traffic jam status in front of the gate 30 It can be used as data etc. for predicting the time when moving up to 14.
　このような入力データは、第１実施形態に係るＡＩ活用システム１０と同様に、ＴＯＳ２６へ入力され、ＡＩ２８による解析に利用される。 Such input data is input to the TOS 26 and used for analysis by the AI 28 as in the AI utilization system 10 according to the first embodiment.
［ＡＩ解析］
　第１実施形態に記載したように、ＴＯＳ２６を介して得られる上記のような入力情報（第１実施形態に記載した情報を含む）に基づき、ＡＩ２８は、ニューラルネットワークを用いたディープラーニングの手法による解析を行う。本実施形態の場合における解析事項は、外来トレーラ３２が指定された蔵置場所１４へ到達する時刻の予測である。 [AI analysis]
As described in the first embodiment, based on the input information as described above (including the information described in the first embodiment) obtained through the TOS 26, the AI 28 uses a deep learning method using a neural network. Perform analysis. The analysis item in the case of the present embodiment is the prediction of the time when the foreign trailer 32 reaches the designated storage location 14.
　具体的には、上述した位置情報や、ゲート３０に対するＩＮ／ＯＵＴ時間（到達に関してはゲートＩＮ時間）、ゲート３０の割り当て状況、車両情報、ゲート３０前における並び状況等に基づいて、予測を行う事ができる。なお、第１実施形態において説明した構内トレーラ２０に対する最適指示情報についても同様に解析を行う。ここで、構内トレーラ２０に対する最適指示情報の解析を行う際に必要となるヤードクレーン２２の荷役タスクの順序予測を行う際には、外来トレーラ３２の到達時刻や、荷役時間が考慮されることとなる。 Specifically, the prediction is performed based on the position information described above, the IN / OUT time to the gate 30 (the gate IN time for arrival), the allocation status of the gate 30, vehicle information, the alignment status before the gate 30, etc. I can do things. The analysis is similarly performed on the optimum instruction information for the indoor trailer 20 described in the first embodiment. Here, in order to predict the order of the loading and unloading tasks of the yard crane 22 which is required when analyzing the optimum instruction information for the in-building trailer 20, the arrival time of the foreign trailer 32 and the loading and unloading time are considered. Become.
［ＡＩ出力情報］
　ＡＩ２８によって求められた構内トレーラ２０への最適指示情報は、ＴＯＳ２６へ出力されると共に、ＴＯＳ２６からネットワークを介して構内トレーラ２０へ、荷役場所（移動場所）の指示が成される。また、ＴＯＳ２６からヤードクレーン２２に対して出力される移動指示には、構内トレーラ２０の荷役場所、およびタイミングに加え、外来トレーラ３２の到達時刻と荷役場所が付加される。また、外来トレーラ３２には、適宜、通過ゲートや、蔵置場所１４等の作業指示情報が出力される。外来トレーラ３２は、この指示に従う事で、ゲート通過時の待ち時間や、荷役作業時の待ち時間を最小に抑える事が可能となる。さらに、本実施形態におけるＡＩ活用システム１０Ａでは、日単位でのコンテナターミナル１２に投入する人員（構内作業者数の他、構内トレーラ２０やヤードクレーン２２を含む）の数や、ゲートレイアウト（ＩＮ側とＯＵＴ側の数の割合等）の算出、および出力も行われる。 [AI output information]
The optimum instruction information for the on-premises trailer 20 determined by the AI 28 is output to the TOS 26 and, at the same time, an instruction is given to the on-site trailer 20 from the TOS 26 via the network. In addition to the loading position and timing of the on-premises trailer 20, the arrival time and loading position of the foreign trailer 32 are added to the movement instruction output from the TOS 26 to the yard crane 22. In addition, work instruction information of the pass gate, the storage place 14 and the like is output to the foreign trailer 32 as appropriate. By following this instruction, the foreign trailer 32 can minimize the waiting time at the gate passage and the waiting time at the loading operation. Furthermore, in the AI utilization system 10A in the present embodiment, the number of personnel (including the number of in-premises trailers and the in-yard trailer 20 and the yard crane 22) and gate layout (IN side) The calculation of the ratio of the numbers on the side and the OUT side, etc., and the output are also performed.
［効果］
　上記のようなＡＩ活用システム１０Ａによれば、ＧＣ１８と構内トレーラ２０、及びヤードクレーン２２における作業待機時間の最小化を図る事ができることに加え、外来トレーラ３２がコンテナ４０を搬出入する際の待ち時間も低減することができる。このため、コンテナターミナル１２における総合的な荷役作業の効率化を図る事が可能となる。よって、本船１６の荷役時間の短縮と共に、コンテナ物流のコスト低減を図ることが可能となる。 [effect]
According to the AI utilization system 10A as described above, in addition to being able to minimize the work standby time in the GC 18 and the on-premises trailer 20 and the yard crane 22, the waiting when the foreign trailer 32 carries the container 40 in and out Time can also be reduced. Therefore, it is possible to improve the efficiency of the overall cargo handling operation at the container terminal 12. Therefore, it becomes possible to aim at cost reduction of container physical distribution while shortening loading and unloading time of the ship 16.
［応用例］
　上記実施形態では、ＡＩ２８が解析に利用する入力データとして、作業者等の判断による影響が無い事項のみを選定要素として挙げている。しかしながら、作業者等の操作や判断、すなわちコンテナターミナル１２内に人が居る事による影響（波動的な変化）を入力データに含ませる事で、ＡＩ２８による解析が、人による影響を踏まえたものとなり、より実状に最適な結果を得る事が可能となると考えられる。 [Application example]
In the above embodiment, only the items that are not affected by the judgment of the worker or the like are listed as selection elements as input data that the AI 28 uses for analysis. However, by including the operation and judgment of the workers etc., that is, the influence (wavelike change) due to the presence of a person in the container terminal 12 in the input data, the analysis by the AI 28 will be based on the influence of the person. It is considered possible to obtain more optimal results in a more practical manner.
　このため、ＡＩ２８が解析に利用する入力データには、作業者認知情報を含むようにすると良い。具体的には、ＧＣ１８やヤードクレーン２２などの荷役機械のオペレータ、ターミナルオペレータ、構内トレーラ２０や外来トレーラ３２のドライバー等における判断や対応を含むようにすれば良い。 Therefore, it is preferable that the input data used by the AI 28 for analysis include worker recognition information. Specifically, the determination and response of the operator of the cargo handling machine such as the GC 18 and the yard crane 22, the terminal operator, the driver of the on-premises trailer 20 and the trailer 32 and the like may be included.
　作業者認知情報の入力については、専用の入力機器の他、携帯端末等におけるタッチパネルや、カメラ、音声入力手段等を介してなされるようにすれば良い。 The operator recognition information may be input via a dedicated input device, a touch panel of a portable terminal or the like, a camera, voice input means, and the like.
１０………ＡＩ活用システム、１２………コンテナターミナル、１４………蔵置場所、１６………本船、１８………ＧＣ、２０………構内トレーラ、２２………ヤードクレーン、２４………管理塔、２６………ＴＯＳ、２８………ＡＩ、３０………ゲート、３２………外来トレーラ、４０………コンテナ。 10 ...... AI utilization system, 12 ...... Container terminal, 14 ...... Storage location, 16 ...... Main ship, 18 ...... GC, 20 ...... Premise trailer, 22 ...... Yard crane, 24 ... ...... Management tower, 26 ...... ...... TOS, 28 ...... AI, 30 ...... Gate, 32 ...... Outpatient trailer, 40 ...... Container.

Claims (4)

  1. 　コンテナターミナルの管理システムにおいて、
    　ニューラルネットワークを構築した人工知能を備え、
    　前記人工知能には少なくとも、ガントリークレーンに関する処理関連情報と、構内トレーラにおける処理関連情報、およびヤードクレーンにおける処理関連情報を入力データとして入力し、
    　ディープラーニングの手法を用いて前記ガントリークレーンと前記構内トレーラ、および前記ヤードクレーンそれぞれの待ち時間が最少となる作業タイミングを出力データとして求め、
    　前記ガントリークレーン、前記構内トレーラ、および前記ヤードクレーンに対して前記出力データに基づく作業指示情報を送信することを特徴とする人工知能を活用したコンテナターミナルシステム。     In the container terminal management system,
    Equipped with artificial intelligence that built a neural network,
    In the artificial intelligence, at least processing-related information on a gantry crane, processing-related information on a yard trailer, and processing-related information on a yard crane are input as input data,
    The operation timing at which the waiting time of each of the gantry crane, the yard trailer, and the yard crane is minimized is obtained as output data using a deep learning method,
    A container terminal system utilizing artificial intelligence, comprising transmitting work instruction information based on the output data to the gantry crane, the indoor trailer, and the yard crane.
  2. 　前記入力データには、前記コンテナターミナルへの外来トレーラにおける処理関連情報を含み、
    　前記出力データには、前記外来トレーラの到着予測時間と前記外来トレーラの行先情報が含まれ、
    　前記作業指示情報は、前記外来トレーラにも送信されることを特徴とする請求項１に記載の人工知能を活用したコンテナターミナルシステム。     The input data includes processing related information in the foreign trailer to the container terminal,
    The output data includes estimated arrival time of the foreign trailer and destination information of the foreign trailer.
    The container terminal system using artificial intelligence according to claim 1, wherein the work instruction information is also transmitted to the foreign trailer.
  3. 　前記ガントリークレーンに関する処理関連情報には、前記ガントリークレーンのオペレータの処理能力や、本船におけるハッチカバーの取り扱いに関するデータ、前記ガントリークレーンの現在の作業状況、前記ガントリークレーンの荷役速度、及び前記本船のコンテナ位置が含まれ、
    　前記構内トレーラにおける処理関連情報には、前記構内トレーラの位置情報や、前記構内トレーラのステータス情報、ドライバー情報、気象情報、ヤードマップ、およびコンテナ搬出入情報が含まれ、
    　前記ヤードクレーンにおける処理関連情報としては、前記ヤードクレーンの処理能力や、前記ヤードクレーンの位置、前記ヤードクレーンのステータス情報、オペレータ情報、前記ヤードクレーンの荷役速度、本船荷役計画、およびヤードプランが含まれていることを特徴とする請求項１または２に記載の人工知能を活用したコンテナターミナルシステム。     The processing related information on the gantry crane includes the processing ability of the operator of the gantry crane, data on the handling of the hatch cover on the ship, the current working condition of the gantry crane, the loading speed of the gantry crane, and the container of the ship. Position is included,
    The processing related information in the premises trailer includes position information of the premises trailer, status information of the premises trailer, driver information, weather information, a yard map, and container in / out information.
    The processing related information in the yard crane includes the processing capacity of the yard crane, the position of the yard crane, the status information of the yard crane, the operator information, the loading speed of the yard crane, the cargo handling plan, and the yard plan. A container terminal system utilizing artificial intelligence according to claim 1 or 2, characterized in that:
  4. 　前記外来トレーラにおける処理関連情報には、前記外来トレーラの位置情報や、前記外来トレーラがゲートを通過する時間、前記外来トレーラに対する前記ゲートの割り当て状況、前記ゲートにいる車両情報、およびゲート前における前記外来トレーラの並び状況が含まれることを特徴とする請求項２を含む請求項３に記載の人工知能を活用したコンテナターミナルシステム。 The processing related information in the foreign trailer includes the position information of the foreign trailer, the time when the foreign trailer passes through the gate, the assignment of the gate to the foreign trailer, the vehicle information in the gate, and the information before the gate. The container terminal system using artificial intelligence according to claim 3, further comprising an arrangement status of the foreign trailers.
PCT/JP2018/044250 2017-12-11 2018-11-30 Container terminal system utilizing artificial intelligence WO2019116933A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017-237272 2017-12-11
JP2017237272A JP6818325B2 (en) 2017-12-11 2017-12-11 Container terminal system utilizing artificial intelligence

Publications (1)

Publication Number Publication Date
WO2019116933A1 true WO2019116933A1 (en) 2019-06-20

Family

ID=66820276

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/044250 WO2019116933A1 (en) 2017-12-11 2018-11-30 Container terminal system utilizing artificial intelligence

Country Status (2)

Country Link
JP (1) JP6818325B2 (en)
WO (1) WO2019116933A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112232108A (en) * 2020-08-27 2021-01-15 宁波大榭招商国际码头有限公司 AI-based intelligent gate system
WO2021134589A1 (en) * 2019-12-31 2021-07-08 唐山哈船科技有限公司 Port container management system and usage method therefor

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7246336B2 (en) * 2020-03-06 2023-03-27 株式会社三井Ｅ＆Ｓマシナリー Container terminal and container terminal operation method
JP7309133B2 (en) 2020-07-13 2023-07-18 株式会社三井E&S Cargo handling instruction support system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08319027A (en) * 1995-05-23 1996-12-03 Nippon Yuusen Kk Method and device of gate control in container terminal
JP2005075592A (en) * 2003-09-02 2005-03-24 Mitsubishi Heavy Ind Ltd Cargo handling method and cargo handling system for container yard
JP2008007270A (en) * 2006-06-29 2008-01-17 Mitsui Eng & Shipbuild Co Ltd Reception system of container terminal
WO2014061252A1 (en) * 2012-10-15 2014-04-24 Ｊｆｅスチール株式会社 Shipping work planning system, shipping work planning method, and shipping work method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08319027A (en) * 1995-05-23 1996-12-03 Nippon Yuusen Kk Method and device of gate control in container terminal
JP2005075592A (en) * 2003-09-02 2005-03-24 Mitsubishi Heavy Ind Ltd Cargo handling method and cargo handling system for container yard
JP2008007270A (en) * 2006-06-29 2008-01-17 Mitsui Eng & Shipbuild Co Ltd Reception system of container terminal
WO2014061252A1 (en) * 2012-10-15 2014-04-24 Ｊｆｅスチール株式会社 Shipping work planning system, shipping work planning method, and shipping work method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
MINISTRY OF LAND, INFRASTRUCTURE, TRANSPORT AND TOURISM: "The 1st social gathering of port's medium and long-term policy review", 23 August 2017 (2017-08-23), XP055617269, Retrieved from the Internet <URL:http://www.mlit.go.jp/common/001198165.pdf> *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021134589A1 (en) * 2019-12-31 2021-07-08 唐山哈船科技有限公司 Port container management system and usage method therefor
CN112232108A (en) * 2020-08-27 2021-01-15 宁波大榭招商国际码头有限公司 AI-based intelligent gate system
CN112232108B (en) * 2020-08-27 2022-06-14 宁波大榭招商国际码头有限公司 AI-based intelligent gate system

Also Published As

Publication number Publication date
JP2019104576A (en) 2019-06-27
JP6818325B2 (en) 2021-01-20

Similar Documents

Publication Publication Date Title
WO2019116933A1 (en) Container terminal system utilizing artificial intelligence
Chen et al. Yard crane and AGV scheduling in automated container terminal: A multi-robot task allocation framework
Kizilay et al. A comprehensive review of quay crane scheduling, yard operations and integrations thereof in container terminals
Gharehgozli et al. Sea container terminals: New technologies and OR models
CN105205629B (en) Steel mill&#39;s finished product storage dispensing automation control method
KR20120100601A (en) Optimization system of smart logistics network
KR102327188B1 (en) Controlling method for multiple dispatching strategies of a plurality of transportation equipments in container terminal
US20150112476A1 (en) System and method for integral planning and control of container flow operations in container terminals
CN108932563A (en) One kind interconnects formula harbour information platform Intelligent Dispatching System
JP2019104578A (en) Comprehensive container terminal system and operation method utilizing artificial intelligence
Kemme et al. Container-terminal logistics
Shepelev et al. Optimization of the operating parameters of transport and warehouse complexes
JP6818326B2 (en) Distributed placement system for cargo handling machines utilizing artificial intelligence
KR20220145104A (en) A method for scheduling works of yardcranes in container terminal using a simulation-based algorithm
CN108985510B (en) Large-scale intelligent logistics path judgment system based on artificial intelligence
Kim Models and methods for operations in port container terminals
Homayouni et al. Integrated scheduling of SP-AS/RS and handling equipment in automated container terminals
Bichou Port Operations
US20240078900A1 (en) System and method for simulating a multimodal transportation network
JP7302536B2 (en) CONTROL SYSTEM AND CONTROL METHOD FOR WAREHOUSE FACILITIES
Homayouni et al. Energy-Efficient Scheduling of Intraterminal Container Transport
JPH10254847A (en) Scheduling device
Malyshev et al. Robotic automation of inland container terminals
Zakrzewski et al. Changes in logistics processes caused by the implementation of automation in transport
FI130312B (en) Tracking a truck in a container handling area

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18889176

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18889176

Country of ref document: EP

Kind code of ref document: A1