CN113525655B - Ship energy-electric power control management system based on machine learning - Google Patents
Ship energy-electric power control management system based on machine learning Download PDFInfo
- Publication number
- CN113525655B CN113525655B CN202110226770.8A CN202110226770A CN113525655B CN 113525655 B CN113525655 B CN 113525655B CN 202110226770 A CN202110226770 A CN 202110226770A CN 113525655 B CN113525655 B CN 113525655B
- Authority
- CN
- China
- Prior art keywords
- ship
- management system
- power source
- power
- unit
- 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
Links
- 238000010801 machine learning Methods 0.000 title claims abstract description 65
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 117
- 238000004364 calculation method Methods 0.000 claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 238000000611 regression analysis Methods 0.000 claims abstract description 26
- 230000002787 reinforcement Effects 0.000 claims abstract description 22
- 238000004891 communication Methods 0.000 claims abstract description 21
- 238000004088 simulation Methods 0.000 claims abstract description 16
- 230000005856 abnormality Effects 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 36
- 230000002159 abnormal effect Effects 0.000 claims description 29
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 26
- 230000004044 response Effects 0.000 claims description 21
- 239000000446 fuel Substances 0.000 claims description 19
- 238000005259 measurement Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000009825 accumulation Methods 0.000 claims description 4
- 230000010485 coping Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 6
- 238000012217 deletion Methods 0.000 description 5
- 230000037430 deletion Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63H—MARINE PROPULSION OR STEERING
- B63H21/00—Use of propulsion power plant or units on vessels
- B63H21/21—Control means for engine or transmission, specially adapted for use on marine vessels
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63J—AUXILIARIES ON VESSELS
- B63J3/00—Driving of auxiliaries
- B63J3/04—Driving of auxiliaries from power plant other than propulsion power plant
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B49/00—Arrangements of nautical instruments or navigational aids
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63H—MARINE PROPULSION OR STEERING
- B63H21/00—Use of propulsion power plant or units on vessels
- B63H21/22—Use of propulsion power plant or units on vessels the propulsion power units being controlled from exterior of engine room, e.g. from navigation bridge; Arrangements of order telegraphs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q50/06—Energy or water supply
-
- 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
- G06Q50/10—Services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63H—MARINE PROPULSION OR STEERING
- B63H21/00—Use of propulsion power plant or units on vessels
- B63H21/21—Control means for engine or transmission, specially adapted for use on marine vessels
- B63H2021/216—Control means for engine or transmission, specially adapted for use on marine vessels using electric control means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63J—AUXILIARIES ON VESSELS
- B63J3/00—Driving of auxiliaries
- B63J2003/001—Driving of auxiliaries characterised by type of power supply, or power transmission, e.g. by using electric power or steam
- B63J2003/002—Driving of auxiliaries characterised by type of power supply, or power transmission, e.g. by using electric power or steam by using electric power
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
- H02J2310/40—The network being an on-board power network, i.e. within a vehicle
- H02J2310/42—The network being an on-board power network, i.e. within a vehicle for ships or vessels
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Mechanical Engineering (AREA)
- Ocean & Marine Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The machine learning-based ship energy-power control management system to which the present invention is applied is configured to provide a structure in which state information of a ship power source and a ship driving device is first acquired by a ship information acquisition-management unit provided on a ship, then transmitted to an energy management system-power management system cloud server unit over a period of time in which an internet communication network is accessible and big data is generated through database, and then optimal control of the ship power source and the ship driving device, device abnormality state detection, and coping, calculation of different power source output values based on prediction of power use are performed through a machine learning regression analysis algorithm of a land management server unit in communication with the energy management system-power management system cloud server unit, and then transmitted to a ship device control unit and thereby personalized operation for a corresponding ship through reinforcement learning final determination in a ship virtual environment simulation module.
Description
Technical Field
The present invention relates to a machine learning based ship energy-power control management system, and more particularly, to a machine learning regression analysis algorithm of a land management server unit communicating with an energy management system-power management system (EMS-PMS) performs optimal control of a ship power source and a ship driving device, device abnormal state detection and coping, a structure calculated based on different power source output values of a power use prediction by providing a cloud server unit that first collects state information of a ship power source (such as a generator, a battery, a fuel cell, etc.) and a ship driving device (such as an engine, a motor, etc.) using a ship information collection-management unit equipped on a ship, then transmits to an energy management system-power management system (EMS-PMS) cloud server unit over a period of time in which an internet communication network is accessible and generates large data through database, and then performs optimal control in terms of power management/energy management, according to self characteristics of the ship and a current state, while initially coping with a power control signal calculation algorithm of a power source calculation signal calculation algorithm by using a power control signal calculation algorithm of a power source prediction and a ship driving device abnormal state detection and coping, the machine learning based ship energy-power control management system for optimal control of a high performance/high efficiency ship can be realized by a structure that is transferred to the ship device control unit after reinforcement learning in the ship virtual environment simulation module is finally determined and thereby individually operated for the corresponding ship.
Background
The optimal control method of the ship may vary according to its design method, use equipment, passage of time, and the like. The capacity and efficiency of the ship power generation source will vary according to the design method, the range of use of the devices that affect each other will be limited according to the capacity, and the capacity of the devices will vary due to aging of the devices caused by the passage of time, so the initially set control algorithm will no longer conform to the optimal design method.
In addition, the machine learning optimal control algorithm for a ship, which has been recently applied in a large amount, can only provide a result derived from data measured at other ships than the corresponding ships, and thus may cause serious errors or adversely affect the stability of equipment during the process of being specifically applied to the corresponding ships.
In addition, data transceiving between the ship and the land-based management center can be implemented using a cloud server as a medium, and a network environment of the ship including an internet communication network may cause a problem of stability degradation due to a special environmental condition of the ship sailing on water. Therefore, in the case of performing real-time data transfer using a cloud server as an intermediary, a problem of data loss may be caused. In particular, when important information is included in the lost data, there is a problem in that the possibility of occurrence of an accident or loss of the ship increases because the emergency of the ship cannot be predicted.
Prior art literature
Patent literature
(patent document 1) Korean patent laid-open publication No. 10-2019-0105149 "Artificial intelligence-based ship control system and method of operating the same"
(patent document 2) korean registered patent publication registration No. 10-2003406, "detection of different regions of a ship based on cloud service and network system"
Patent content
In order to solve the problems in the prior art as described above, an object of the present invention is to provide a completely new type of machine learning-based ship energy-power control management system that performs optimal control of a ship power source and a ship driving device, detection of abnormal states of the device, and calculation of different power source output values based on prediction of power usage, by using a ship information acquisition-management unit, then transmitting to an energy management system-power management system (EMS-PMS) cloud server unit over a period of time in which the ship can access an internet communication network, generating big data by database, and then performing optimal control in terms of power management/energy management with higher reliability and stability according to the characteristics of the ship itself and the current state, and then performing optimal control in terms of power management/energy management by a machine learning regression analysis algorithm of a land management server unit communicating with the energy management system-power management system (EMS-PMS).
Further, the present invention has an object to provide a machine learning-based ship energy-power control management system in which a ship driving device control signal and a ship power source control signal generated by a machine learning regression analysis algorithm are initially calculated in the form of an input value calculation function algorithm for optimal control, a device abnormal state detection-response control signal generation algorithm, and a different power source output value calculation algorithm based on power use prediction, and then transferred to a ship device control unit after final determination by reinforcement learning in a ship virtual environment simulation module, thereby performing individual operations for a corresponding ship, thereby realizing a completely new form of optimal control of a ship with high performance/high efficiency.
Further, the present invention is directed to a ship energy-power control system based on machine learning, which can be constructed in a completely new form of an optimal control algorithm according to a current situation by generating a ship state time series accumulation information aggregate by means of an energy management system-power management system (EMS-PMS) cloud server unit that intermittently and sequentially receives unit measurement time interval ship state time series accumulation information generated in a ship information acquisition-management unit over time, and then generating a ship driving device control signal and a ship power source control signal by a land management server unit in a set unit analysis time interval period and intermittently transmitting the signals to a ship device control unit of a ship through the energy management system-power management system (EMS-PMS) cloud server unit.
Meanwhile, an object of the present invention is to provide a machine learning-based ship energy-power control management system of a completely new form capable of adaptively controlling a ship driving device that is operated in organic association with each other under dynamic water environmental conditions by means of a configuration of an input value calculation function algorithm for optimal control, a control signal generation algorithm for device abnormal state detection-response, and a different power source output value calculation algorithm based on power use prediction, which are finally determined by reinforcement learning in a ship virtual environment simulation module.
In order to achieve the above object, the present invention provides a machine learning-based ship energy-power control management system comprising: the power source sensing unit 100 detects power source state information by being constituted by a plurality of sensors installed in the ship power source 10 belonging to the Power Management System (PMS) 1 of the ship; a driving device sensing unit 200 that detects driving device state information by being composed of a plurality of sensors installed in a ship driving device 20 belonging to an Energy Management System (EMS) 2 of a ship; a ship information acquisition-management unit 300 for generating unit measurement time period ship state time series accumulation information by receiving the power source state information and the driving device state information from the power source sensing unit 100 and the driving device sensing unit 200 and accumulating the power source state information and the driving device state information in time series within a set unit measurement time period; a ship information transmission unit 400 for checking whether or not the ship can be connected to the internet communication network, and receiving the ship state time series accumulated information of the unit measurement time period from the ship information acquisition and management unit 300 over a time period in which the ship can access the internet communication network, and performing wireless transmission to the outside; a ship device control unit 500 that wirelessly receives a ship power source control signal and a ship drive device control signal from the outside in conjunction with the energy management system 2 and the power management system 1, and controls the ship power source 10 and the ship drive device 20 based on the ship power source control signal and the ship drive device control signal; an energy management system-power management system (EMS-PMS) cloud server unit 600 configured by a server connected to an internet communication network, for receiving unit measurement time zone ship state time series accumulated information by connecting to the ship information transmission unit 400 in a time zone in which a ship can access the internet communication network, for generating a ship state time series accumulated information aggregate by sequentially connecting the unit measurement time zone ship state time series accumulated information intermittently and sequentially transmitted over time, and for transmitting to the ship device control unit 500 in a time zone in which the ship can access the internet communication network after receiving a ship driving device control signal and a ship power source control signal from the outside; and a land management server unit 700 for use by a land management center of the ship, for receiving the ship state time series accumulated information aggregate from the energy management system-power management system (EMS-PMS) cloud server unit 600, analyzing the ship state time series accumulated information aggregate to generate a ship driving device control signal for optimally controlling the energy management system 2 and a ship power source control signal for optimally controlling the power management system 1, and transmitting the generated ship driving device control signal and the generated ship power source control signal to the energy management system-power management system (EMS-PMS) cloud server unit 600.
The land control server unit 700 generates the ship driving device control signal and the ship power source control signal by means of machine learning regression analysis, which takes as input and output the output power of the ship power source 10 and the fuel consumption of the ship driving device 20 within a set unit analysis time interval, and intermittently transmits the ship driving device control signal and the ship power source control signal to the energy management system-power management system (EMS-PMS) cloud server unit 600 with the set unit analysis time interval as a period, wherein the output power of the ship power source 10 and the fuel consumption of the ship driving device 20 are information included in the ship state time series integrated information aggregate.
In the above-described machine learning-based ship energy-power control management system to which the present invention is applied, the cloud server unit 600 for the energy management system-power management system (EMS-PMS) generates big data by database-forming the ship state time-series integrated information aggregate with the lapse of time, and the land management server unit 700 performs the machine learning regression analysis by the machine learning regression analysis algorithm 710 based on the big data.
In the above-described machine learning-based ship energy-power control management system to which the present invention is applied, the land management server unit 700 performs preliminary calculation of the ship driving device control signal and the ship power source control signal generated by the big data-based machine learning regression analysis algorithm 710 in the form of an optimal control input value calculation function algorithm 711, and the optimal control input value calculation function algorithm 711 is transmitted to the ship device control unit 500 through the energy management system-power management system (EMS-PMS) cloud server unit 600.
The ship apparatus control unit 500 controls the ship power source 10 and the ship driving device 20 based on the optimal control input value calculated in real time by the optimal control input value calculation function algorithm 711 that receives power source state information and driving device state information from the sensors provided in the respective ship power sources 10 and the ship driving devices 20 mounted on the corresponding ships.
In the machine learning based ship energy-power control management system to which the present invention is applied as described above, the above-described land management server unit 700 includes: a ship virtual environment simulation module 720 for virtually simulating the ship navigation on water by setting the water environment characteristic information, the ship characteristic information, and the ship navigation characteristic information of the ship navigation; and an optimal control input value calculation function algorithm reinforcement learning module 730 for determining the optimal control input value calculation function algorithm 711 by machine learning reinforcement learning when the optimal control input value calculation function algorithm 711 is initially input to the ship device control unit 500 of the ship virtually sailing in the ship virtual environment simulation module 720; the finally determined input value calculation function algorithm 711 for optimal control is transmitted to the ship device control unit 500 through the cloud server unit 600 for energy management system-power management system (EMS-PMS).
In the above-described machine learning-based ship energy-power control management system to which the present invention is applied, the land management server unit 700 performs preliminary calculation of the ship driving device control signal and the ship power source control signal generated by the big-data-based machine learning regression analysis algorithm 710 in the form of a device abnormal state detection-response control signal generation algorithm 712, and the device abnormal state detection-response control signal generation algorithm 712 is transmitted to the ship device control unit 500 by the energy management system-power management system (EMS-PMS) cloud server unit 600.
The ship apparatus control unit 500 controls the ship power source 10 and the ship driving device 20 based on the device abnormal state detection-response control signal calculated in real time by the device abnormal state detection-response control signal generation algorithm 712, which receives the power source state information and the driving device state information in real time from the sensors provided in the respective ship power sources 10 and the ship driving devices 20 mounted on the corresponding ships.
In the machine learning-based ship energy-power control management system to which the present invention is applied as described above, the ship power source 10 is constituted by a combination of the generator 11, the battery 12, and the fuel cell 13.
The land management and control server unit 700 performs preliminary calculation of the ship driving device control signal and the ship power source control signal generated by the big data based machine learning regression analysis algorithm 710 in the form of the power usage prediction based different power source output value calculation algorithm 713, and the power usage prediction based different power source output value calculation algorithm 713 is transmitted to the ship device control unit 500 through the energy management system-power management system (EMS-PMS) cloud server unit 600.
The ship device control unit 500 controls the ship power source 10 based on the different power source output values calculated in real time by the different power source output value calculation algorithm 713 based on the power usage prediction.
By applying the machine learning-based ship energy-power control management system of the invention, optimal control can be performed in terms of power management/energy management with higher reliability and stability according to the characteristics of the ship itself and the current state. In addition, by applying the ship energy-power control management system based on machine learning, the ship can be optimally controlled with high performance/high efficiency, an optimal control algorithm which changes according to the current situation can be constructed, and the ship driving equipment which is operated in an organic correlation mode under the dynamic water environment condition can be adaptively controlled.
Drawings
Fig. 1 is a block diagram of a basic configuration of a machine learning-based ship energy-power control management system to which an embodiment of the present invention is applied.
Fig. 2 is a graph illustrating a method of detecting an optimal operation value of a ship power source, i.e., a generator, by a machine learning regression analysis algorithm based on big data of a ship energy-power control management system to which an embodiment of the present invention is applied.
Fig. 3 is a graph illustrating a method of detecting an optimal operation value of a ship driving device, i.e., a pump, by a machine learning regression analysis algorithm based on big data of a ship energy-power control management system to which an embodiment of the present invention is applied.
Fig. 4 is a block diagram showing a configuration of a cloud server unit for an energy management system-power management system (EMS-PMS) to which an embodiment of the present invention is applied.
Fig. 5 is a firewall system illustration of a cloud server unit for an energy management system-power management system (EMS-PMS) to which an embodiment of the present invention is applied.
Fig. 6 is a schematic diagram illustrating an algorithm calculation configuration for optimal control of a land-based management server unit to which an embodiment of the present invention is applied.
Fig. 7 is a schematic diagram illustrating a configuration used for transmitting an algorithm for optimal control calculated in a machine learning-based ship energy-power control management system to a ship device control unit to which an embodiment of the present invention is applied.
Fig. 8 and 9 are explanatory diagrams of state information of a ship driving device performing optimal control and an input value calculation function algorithm for optimal control in a ship energy-power control management system based on machine learning to which an embodiment of the present invention is applied.
Fig. 10 is an explanatory diagram of a control signal generation algorithm for device abnormal state detection-response to which the present invention is applied.
Fig. 11 is a graph of power usage prediction calculated by a different power source output value calculation algorithm based on power usage prediction to which the present invention is applied.
[ symbolic description ]
1: a Power Management System (PMS);
2: an Energy Management System (EMS);
10: a marine power source;
11: a generator;
12: a battery;
13: a fuel cell;
20: a ship driving device;
21: an engine;
22: a motor;
100: a power source sensing unit;
200: a driving device sensing unit;
300: a ship information acquisition-management unit;
400: a ship information transmitting unit;
500: a ship device control unit;
600: an energy management system-cloud server unit for an energy management system (EMS-PMS);
610: an information deletion control module;
620: an information storage control module;
630: a firewall module;
700: a land-based management and control server unit;
710: machine learning regression analysis algorithm based on big data;
711: calculating a function algorithm by using the input value for optimal control;
712: an apparatus abnormal state detection-response control signal generation algorithm;
713: different power source output value calculation algorithms based on power usage predictions;
720: a ship virtual environment simulation module;
730: the optimal control is used for calculating a function algorithm reinforcement learning module by an input value;
740: the abnormal state detection-response control signal generation algorithm reinforcement learning module;
750: and a different power source output value calculation algorithm reinforcement learning module based on power use prediction.
Detailed Description
Next, an embodiment to which the present invention is applied will be described in detail with reference to fig. 1 to 11 attached. In the drawings and the detailed description, illustrations and descriptions related to the constitution and functions that can be easily understood by a practitioner in general ships, ship Power Management Systems (PMSs), ship Energy Management Systems (EMS), sensors, cloud servers, land management servers, machine learning regression analysis, big data, and the like will be simplified or omitted. In particular, in the drawings and the detailed description, description and illustration of specific technical configurations and functions of elements not directly related to technical features of the present invention will be omitted, and only technical configurations related to the present invention will be briefly described and illustrated.
As shown in fig. 1, the machine learning-based ship energy-power control management system according to the embodiment of the present invention includes a power source sensing unit 100, a driving apparatus sensing unit 200, a ship information acquisition-management unit 300, a ship information transmission unit 400, a ship device control unit 500, an energy management system-power management system (EMS-PMS) cloud server unit 600, and an onshore management server unit 700, and is effectively applicable to an autonomous navigation electric propulsion ship that travels in an autonomous navigation manner by providing the fuel cell 13, but is not applicable to an autonomous navigation electric propulsion ship only, but is applicable to a plurality of types and scales of ships.
The power source sensing unit 100 is constituted by a plurality of sensors installed in the ship power source 10 belonging to the Power Management System (PMS) 1 of the ship, for detecting power source state information. The marine power source 10 may include, for example, the generator 11, the battery 12, and the fuel cell 13, and the power source sensing unit 100 may detect, as power source state information, an instantaneous fuel consumption amount and an instantaneous output power of the generator 11, an output power and an output voltage of the battery 12 based on a charging rate (C-rate), an output power and an output power density of the fuel cell 13, a temperature and a pressure of different constituent elements of the generator 11, and a fuel oil leakage amount, in correspondence thereto.
The ship power source control signal for realizing the optimal control of the ship power source 10 is calculated based on the power source state information described above, wherein the generator 11 calculates the power source control signal based on the output power with respect to the fuel consumption amount in the manner shown in fig. 2, the battery 12 calculates the power source control signal based on the output power based on the charging rate (C-rate), and the fuel cell 13 calculates the power source control signal based on the output power and the output power density.
The driving apparatus sensing unit 200 is composed of a plurality of sensors installed in the ship driving apparatus 20 belonging to the Energy Management System (EMS) 2 of the ship for detecting driving apparatus state information. The marine drive means 20 may comprise, among other things, an engine 21 and a motor 22, wherein the motor 22 is adapted to, for example, a pump and a fan. Correspondingly thereto, the driving device sensing unit 200 may detect the rotational speed per minute (RPM) of the engine 21 and the cooling water temperature, the rotational speed per minute (RPM) of the motor 22, and the power consumption amount as driving device state information. The optimum operation value of the pump using the motor 22 is calculated based on the detected driving apparatus state information as described above in the manner shown in fig. 3.
The ship information collection-management unit 300 is configured to receive the power source state information and the driving device state information from the power source sensing unit 100 and the driving device sensing unit 200, and generate unit measurement time period ship state time series accumulated information by accumulating and storing the power source state information and the driving device state information in time series within a set unit measurement time period.
The ship information transmission unit 400 is configured to check whether the ship can be connected to the internet communication network in a set time unit, and then receive the ship state time series accumulated information of the unit measurement time zone from the above-described ship information acquisition-management unit 300 over a time period in which the ship can access the internet communication network and transmit it to the outside wirelessly.
The ship device control unit 500 is connected to the energy management system 2 and the power management system 1, and wirelessly receives a ship power source control signal and a ship driving device control signal from the energy management system-power management system (EMS-PMS) cloud server unit 600. Further, the ship device control unit 500 performs optimal control or adaptive control of the ship power source 10 and the ship driving apparatus 20 according to the ship power source control signal and the ship driving apparatus control signal. The ship power source control signal and the ship driving device control signal wirelessly received from the energy management system-power management system (EMS-PMS) cloud server unit 600 may be in the form of an optimal control input value calculation function algorithm 711, a device abnormal state detection-response control signal generation algorithm 712, and a different power source output value calculation algorithm 713 based on the prediction of power usage, and the ship device control unit 500 may calculate specific values or instructions of the ship power source control signal and the ship driving device control signal by inputting the power source state information and the driving device state information currently measured in real time to the optimal control input value calculation function algorithm 711, the device abnormal state detection-response control signal generation algorithm 712, and the different power source output value calculation algorithm 713 based on the prediction of power usage.
The energy management system-power management system (EMS-PMS) cloud server unit 600 is constituted by a server connected to an internet communication network, and can receive unit measurement time zone ship state time series accumulated information by connecting to the ship information transmission unit 400 over a time zone in which the ship can access the internet communication network. The energy management system-power management system (EMS-PMS) cloud server unit 600 generates a ship state time series integrated information aggregate by sequentially connecting ship state time series integrated information for unit measurement time intervals that are intermittently and sequentially transmitted over time. Further, the energy management system-power management system (EMS-PMS) cloud server unit 600, after receiving the ship driving device control signal and the ship power source control signal from the land management server unit 700, transfers it to the ship device control unit 500 of the ship over a period of time in which the ship can access the internet communication network.
In particular, the cloud server unit 600 for an energy management system-power management system (EMS-PMS) to which the present invention is applied can generate big data by database-forming a ship state time series accumulated information aggregate with the passage of time.
In addition, as shown in fig. 4, the cloud server unit 600 for an energy management system-power management system (EMS-PMS) to which the embodiment of the present invention is applied includes an information deletion control module 610, an information storage control module 620, and a firewall module 630.
The information deletion control module 610 is a control module for deleting corresponding information according to an information deletion instruction signal of an administrator account login person of the land management and control server unit 700, and the information storage control module 620 is a control module for maintaining a permanent storage state of information not corresponding to the information deletion instruction signal of the administrator account login person. The firewall module 630 prevents illegal access by maintaining an operational state all the time, and may be implemented using a firewall system as shown in fig. 5.
The land management and control server unit 700 is used by a land management and control center of a ship, and generates a ship driving device control signal for optimally controlling the energy management system 2 and a ship power source control signal for optimally controlling the power management system 1 by analyzing a ship state time series integrated information aggregate after receiving the ship state time series integrated information aggregate from the cloud server unit 600 for an energy management system-power management system (EMS-PMS). The ship driving device control signal and the ship power source control signal generated in the manner described above are transmitted to the energy management system-power management system (EMS-PMS) cloud server unit 600.
In particular, the land management and control server unit 700 to which the embodiment of the present invention is applied generates a ship driving device control signal and a ship power source control signal by machine learning regression analysis that takes as input and output the output power of the ship power source 10 and the fuel consumption amount of the ship driving device 20 within a set unit analysis time interval, respectively, and intermittently transmits the ship driving device control signal and the ship power source control signal to the energy management system-power management system (EMS-PMS) cloud server unit 600 with the set unit analysis time interval as a period. The output power of the ship power source 10 and the fuel consumption of the ship driving device 20 are information included in the ship state time-series integrated information aggregate.
In addition, the terrestrial management server unit 700 to which the embodiment of the present invention is applied will perform a machine learning regression analysis by a big data based machine learning regression analysis algorithm 710 in the manner as shown in fig. 6. In particular, the land management and control server unit 700 to which the embodiment of the present invention is applied can preliminarily calculate the ship driving equipment control signal and the ship power source control signal generated by the machine learning regression analysis algorithm 710 based on big data in the form of the input value calculation function algorithm 711 for optimal control, the control signal generation algorithm 712 for equipment abnormal state detection-pair application, and the different power source output value calculation algorithm 713 based on the prediction of power usage. The optimum control input value calculation function algorithm 711 applied to the ship drive apparatus may be implemented as shown in fig. 8 and 9. Further, the apparatus abnormal state detection-response control signal generation algorithm 712 is an algorithm for diagnosing an apparatus abnormality or an apparatus failure due to an apparatus aging or the like, and may be configured as shown in fig. 10. Further, the different power source output value calculation algorithm 713 based on the power use prediction may be effectively used when the ship power source 10 is constituted by a combination of the generator 11, the battery 12, and the fuel cell 13, and the different power source (generator, battery, fuel cell) output values may be calculated after deriving the power use prediction map or the like as shown in fig. 11.
The optimal control input value calculation function algorithm 711, the plant abnormal state detection-coping control signal generation algorithm 712, and the different power source output value calculation algorithm 713 based on the power usage prediction may be transferred to the marine vessel device control unit 500 through the energy management system-power management system (EMS-PMS) cloud server unit 600.
Correspondingly thereto, the ship device control unit 500 controls the ship power source 10 and the ship driving device 20 based on the optimal control input value calculation function algorithm 711, the device abnormality state detection-coping control signal generation algorithm 712, the different power source output value calculation algorithm 713 based on the power usage prediction, the device abnormality state detection-coping control signal, and the different power source output values calculated in real time from the above-described sensors provided in the respective ship power sources 10 and the ship driving devices 20 mounted on the respective ships.
The optimal control input values include an output power operation value of the ship power source 10 at which the output power of the ship power source 10 reaches a maximum value compared with the fuel consumption of the ship drive device 20, an output power reduction rate of the ship power source 10, an operation value of the ship drive device 20 at which an appropriate operation value agreement rate of the ship drive device 20 reaches a maximum value, and the like.
In addition, as shown in fig. 6, the land control server unit 700 to which the embodiment of the present invention is applied may be additionally equipped with a ship virtual environment simulation module 720, an optimal control input value calculation function algorithm reinforcement learning module 730, an equipment abnormal state detection-response control signal generation algorithm reinforcement learning module 740, and a different power source output value calculation algorithm reinforcement learning module 750 based on power usage prediction.
The ship virtual environment simulation module 720 virtually simulates the ship navigation on water by setting the ship navigation environmental characteristic information, the ship characteristic information, and the ship navigation characteristic information.
The optimal control input value calculation function algorithm reinforcement learning module 730 is a module that corrects and finally determines the optimal control input value calculation function algorithm 711 by machine learning reinforcement learning when the optimal control input value calculation function algorithm 711 is initially input to the ship device control unit 500 of the ship virtually sailing in the ship virtual environment simulation module 720.
The plant abnormal state detection-coping control signal generation algorithm reinforcement learning module 740 is a module that corrects and finally determines the plant abnormal state detection-coping control signal generation algorithm 712 by machine learning reinforcement learning when the plant abnormal state detection-coping control signal generation algorithm 712 is initially input to the ship apparatus control unit 500 of the ship virtually sailing in the ship virtual environment simulation module 720.
The power usage prediction-based different power source output value calculation algorithm reinforcement learning module 750 is a module that corrects and finally determines the power usage prediction-based different power source output value calculation algorithm 713 through machine learning reinforcement learning when the power usage prediction-based different power source output value calculation algorithm 713 is initially input into the ship device control unit 500 of the ship virtually sailing in the ship virtual environment simulation module 720.
The optimal control input value calculation function algorithm 711, the plant abnormal state detection-response control signal generation algorithm 712, and the different power source output value calculation algorithm 713 based on the power usage prediction, which are finally determined by the method described above, may be transferred to the ship device control unit 500 through the energy management system-power management system (EMS-PMS) cloud server unit 600, as shown in fig. 7. The final determination of the optimal control input value calculation function algorithm 711, the plant abnormal state detection-response control signal generation algorithm 712, and the power usage prediction-based different power source output value calculation algorithm 713 is limited to a set unit analysis time period, and the optimal control input value calculation function algorithm 711, the plant abnormal state detection-response control signal generation algorithm 712, and the power usage prediction-based different power source output value calculation algorithm 713 may be changed in the set unit analysis time period from the different ship state time series integrated information aggregate input over time. Because the aggregate of the ship state time series accumulated information is greatly dataized with the passage of time, the ship energy-power control management system based on machine learning to which the embodiment of the present invention is applied can construct an optimal control algorithm according to the current situation variation.
The machine learning based ship energy-power control management system of the embodiment of the present invention constructed as described above collects power source state information and driving device state information of a ship using the ship information collection-management unit 300, then transmits to the cloud server unit 600 for an energy management system-power management system (EMS-PMS) over a period of time in which the ship can access the internet communication network and generates big data through database formation, and then performs optimal control of the ship power source 10 and the ship driving device 20, device abnormal state detection and coping, calculation of different power source output values based on power use prediction through a machine learning regression analysis algorithm of the land management server unit 700 communicating with the cloud server unit 600 for an energy management system-power management system (EMS-PMS), so that optimal control can be performed in terms of power management/energy management with high reliability and stability according to the own characteristics and current state of the ship.
Further, the machine learning based ship energy-power control management system to which the embodiment of the present invention is applied performs preliminary calculation of the ship driving device control signal and the ship power source control signal generated by the machine learning regression analysis algorithm in the form of the input value calculation function algorithm 711 for optimal control, the device abnormal state detection-response control signal generation algorithm 712, the different power source output value calculation algorithm 713 based on the prediction of power use, and then transfers to the ship device control unit after final determination by reinforcement learning in the ship virtual environment simulation module 720 and thereby the structure for individual operation of the corresponding ship, whereby it is possible to realize the high-performance/high-efficiency ship optimal control.
Further, the machine learning based ship energy-power control management system to which the embodiment of the present invention is applied, by means of a structure in which the ship state time series accumulated information aggregate is generated by the cloud server unit 600 for the energy management system-power management system (EMS-PMS) by intermittently receiving the unit measurement time interval ship state time series accumulated information generated in the ship information acquisition-management unit 300 in sequence over time, and then the ship driving device control signal and the ship power source control signal are generated by the on-land management server unit 700 in a set unit analysis time interval period and intermittently transferred to the ship device control unit 500 of the ship by the cloud server unit 600 for the energy management system-power management system (EMS-PMS), it is possible to construct an optimal control algorithm according to a current situation change.
Meanwhile, the machine learning based ship energy-power control management system to which the embodiment of the present invention is applied can adaptively control the ship driving devices that are organically related to each other under dynamic water environmental conditions by means of the configuration of the input value calculation function algorithm 711 for optimal control, the control signal generation algorithm 712 for device abnormal state detection-response, and the different power source output value calculation algorithm 713 based on power use prediction, which are finally determined by reinforcement learning in the ship virtual environment simulation module 720.
While the machine learning-based ship energy-power control management system to which the embodiments of the present invention are applied has been described and illustrated in the above description, the above description is merely illustrative, and it should be understood by those skilled in the art that various changes and modifications can be made without departing from the technical spirit thereof.
Claims (6)
1. A machine learning based marine vessel energy-power control management system, comprising:
a power source sensor unit (100) that detects power source state information by being configured from a plurality of sensors installed in a ship power source (10) belonging to a power management system (1) of a ship;
a drive device sensor unit (200) that detects drive device state information by being configured of a plurality of sensors installed in a ship drive device (20) that is an energy management system (2) of a ship;
a ship information acquisition/management unit (300) that generates unit measurement time zone ship state time series accumulated information by receiving power source state information and drive device state information from the power source sensing unit (100) and drive device sensing unit (200) and accumulating the power source state information and the drive device state information in a time sequence within a set unit measurement time zone;
A ship information transmission unit (400) for checking whether the ship can be connected to the internet communication network, and for receiving the ship state time series accumulated information of the unit measurement time interval from the ship information acquisition and management unit (300) over a time period when the ship can access the internet communication network, and for performing wireless transmission to the outside;
a ship device control unit (500) that wirelessly receives a ship power source control signal and a ship drive device control signal from the outside in conjunction with the energy management system (2) and the power management system (1), and controls the ship power source (10) and the ship drive device (20) based on the ship power source control signal and the ship drive device control signal;
an energy management system-power management system cloud server unit (600) configured by a server connected to an internet communication network, which receives unit measurement time zone ship state time series accumulated information by being connected to the ship information transmission unit (400) in a time zone in which a ship can access the internet communication network, which generates a ship state time series accumulated information aggregate by being sequentially connected to the unit measurement time zone ship state time series accumulated information intermittently and sequentially transmitted over time, and which, after receiving a ship drive device control signal and a ship power source control signal from the outside, transmits the ship state time series accumulated information aggregate to the ship device control unit (500) in a time zone in which the ship can access the internet communication network; the method comprises the steps of,
A land control server unit (700) for use by a land control center of a ship, for receiving a ship state time series accumulated information aggregate from the energy management system-power management system cloud server unit (600), analyzing the ship state time series accumulated information aggregate to generate a ship driving device control signal for optimally controlling the energy management system (2) and a ship power source control signal for optimally controlling the power management system (1), and transmitting the generated ship driving device control signal and the generated ship power source control signal to the energy management system-power management system cloud server unit (600);
wherein said land-based management server unit (700),
the ship driving device control signal and the ship power source control signal are generated by machine learning regression analysis, which takes as input and output the output power of the ship power source (10) and the fuel consumption of the ship driving device (20) within a set unit analysis time interval, respectively, and the ship driving device control signal and the ship power source control signal are intermittently transmitted to the energy management system-power management system cloud server unit (600) with the set unit analysis time interval as a period, wherein the output power of the ship power source (10) and the fuel consumption of the ship driving device (20) are information included in the ship state time series accumulated information aggregate.
2. The machine learning based marine energy-power control management system of claim 1, wherein:
the energy management system-power management system cloud server unit (600) generates big data by database-forming the ship state time series accumulation information aggregate with the lapse of time,
the land management server unit (700) performs the machine learning regression analysis through a big data based machine learning regression analysis algorithm (710).
3. The machine learning based marine energy-power control management system of claim 2, wherein:
the land control server unit (700) performs preliminary calculation of the ship driving device control signal and the ship power source control signal generated by the big data based machine learning regression analysis algorithm (710) in the form of an optimal control input value calculation function algorithm (711),
the optimal control input value calculation function algorithm (711) is transmitted to the ship device control unit (500) through the energy management system-power management system cloud server unit (600),
the ship device control means (500) controls the ship power source (10) and the ship driving device (20) based on the optimal control input value calculated in real time by the optimal control input value calculation function algorithm (711) that receives power source state information and driving device state information from the sensors provided in the respective ship power sources (10) and the ship driving devices (20) mounted on the respective ships.
4. A machine learning based marine energy-power control management system according to claim 3, characterized in that:
the above-mentioned land management and control server unit (700) comprises:
a ship virtual environment simulation module (720) which virtually simulates the ship navigation on water by setting the water environment characteristic information, the ship characteristic information and the ship navigation characteristic information of the ship navigation; the method comprises the steps of,
an optimal control input value calculation function algorithm reinforcement learning module (730) that, when the optimal control input value calculation function algorithm (711) is initially input to the ship device control unit (500) of the ship virtually sailing in the ship virtual environment simulation module (720), corrects and finally determines the optimal control input value calculation function algorithm (711) by machine learning reinforcement learning;
wherein the finally determined optimal control input value calculation function algorithm (711) is transmitted to the ship device control unit (500) through the energy management system-power management system cloud server unit (600).
5. A machine learning based marine energy-power control management system according to claim 3, characterized in that:
The land control server unit (700) performs preliminary calculation of the ship driving equipment control signal and the ship power source control signal generated by the big data based machine learning regression analysis algorithm (710) in the form of an equipment abnormal state detection-response control signal generation algorithm (712),
the control signal generation algorithm (712) for detecting abnormal state of equipment is transmitted to the ship device control unit (500) through the energy management system-power management system cloud server unit (600),
the ship apparatus control unit (500) controls the ship power source (10) and the ship driving device (20) based on the device abnormality state detection-response control signal calculated in real time by the device abnormality state detection-response control signal generation algorithm (712) that receives power source state information and driving device state information in real time from the sensors provided in the respective ship power sources (10) and the ship driving devices (20) mounted on the corresponding ships.
6. A machine learning based marine energy-power control management system according to claim 3, characterized in that:
the ship power source (10) is composed of a combination of a generator (11), a battery (12) and a fuel cell (13),
The land control server unit (700) performs preliminary calculation of the ship driving device control signal and the ship power source control signal generated by the big data based machine learning regression analysis algorithm (710) in the form of a different power source output value calculation algorithm (713) based on the power usage prediction,
the power usage prediction-based different power source output value calculation algorithm (713) is transferred to the ship device control unit (500) through the energy management system-power management system cloud server unit (600),
the ship device control unit (500) controls the ship power source (10) according to the different power source output values calculated in real time by the different power source output value calculation algorithm (713) based on the power usage prediction.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR10-2020-0025495 | 2020-02-28 | ||
| KR1020200025495A KR102247165B1 (en) | 2020-02-28 | 2020-02-28 | Machine learning based ship energy-power management system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113525655A CN113525655A (en) | 2021-10-22 |
| CN113525655B true CN113525655B (en) | 2023-08-25 |
Family
ID=75740433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110226770.8A Active CN113525655B (en) | 2020-02-28 | 2021-03-01 | Ship energy-electric power control management system based on machine learning |
Country Status (2)
| Country | Link |
|---|---|
| KR (1) | KR102247165B1 (en) |
| CN (1) | CN113525655B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102630120B1 (en) * | 2021-09-08 | 2024-01-29 | 울산대학교 산학협력단 | System and Method for energy management of fuel cell system using digital twin |
| KR102547092B1 (en) * | 2021-10-06 | 2023-06-23 | 제이트러스트(주) | A power management system for hybrid ship |
| KR102547093B1 (en) * | 2021-10-14 | 2023-06-23 | 제이트러스트(주) | A power equipment management apparatus for hybrid ship and power management system including the same |
| US20230211674A1 (en) * | 2021-12-30 | 2023-07-06 | Sustainable Energy Technologies, Inc. | Supercapacitor to electrochemical hybrid system with failsafe safety capability |
| CN114301095B (en) * | 2021-12-31 | 2023-11-17 | 武汉理工大学 | PPO2 energy management method based on multi-energy distributed wireless shore power system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1914087A (en) * | 2004-02-16 | 2007-02-14 | 海运控制公司 | Method and system for testing a control system of a marine vessel |
| CN101014915A (en) * | 2004-06-08 | 2007-08-08 | 海运控制公司 | Method for testing of a combined dynamic positioning and power management system |
| CN102360209A (en) * | 2011-09-22 | 2012-02-22 | 昆明理工大学 | Multi-embedded intelligent monitoring, communication and control system for hybrid electric vehicle |
| JP2012153341A (en) * | 2011-01-28 | 2012-08-16 | Mitsubishi Heavy Ind Ltd | Ship power monitoring system, ship power control system, and method of monitoring power of regular line ship |
| KR20130037508A (en) * | 2011-10-06 | 2013-04-16 | 한국해양대학교 산학협력단 | Energy management system and method for ship and ocean plant |
| KR20140092111A (en) * | 2013-01-15 | 2014-07-23 | 현대중공업 주식회사 | An Energy System of Ship |
| JP2014165950A (en) * | 2013-02-21 | 2014-09-08 | Mitsubishi Heavy Ind Ltd | Energy management system and energy management method |
| CN106697187A (en) * | 2016-12-26 | 2017-05-24 | 武汉理工大学 | Experimental platform used for simulation and diagnosis of working conditions of shipping power system and based on intelligent engine room |
| RU2016103743A (en) * | 2016-02-04 | 2017-08-10 | Федеральное государственное унитарное предприятие "Крыловский государственный научный центр" | METHOD FOR CONTROLING BRAKING AND REVERSE OF CRAFT ELECTRIC MOTORS OF A SHIP |
| CN107140169A (en) * | 2017-05-24 | 2017-09-08 | 大鹏高科（武汉）智能装备有限公司 | A kind of modular unmanned boat intelligent power control system |
| CN108116646A (en) * | 2017-12-29 | 2018-06-05 | 武汉船用电力推进装置研究所（中国船舶重工集团公司第七二研究所） | A kind of watercraft electric propulsion system |
| CN110316331A (en) * | 2018-03-28 | 2019-10-11 | 住友重机械海洋工程株式会社 | Ship information provides device, method, system, program and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2669172A1 (en) * | 2012-06-01 | 2013-12-04 | ABB Technology AG | Method and system for predicting the performance of a ship |
| KR102003406B1 (en) | 2017-11-17 | 2019-07-24 | 대우조선해양 주식회사 | Detection and network system by zone of ship based on cloud |
| KR20190105149A (en) | 2018-02-19 | 2019-09-16 | 한국전자통신연구원 | Artificial intelligence based vessel controlling system and method |
-
2020
- 2020-02-28 KR KR1020200025495A patent/KR102247165B1/en active IP Right Grant
-
2021
- 2021-03-01 CN CN202110226770.8A patent/CN113525655B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1914087A (en) * | 2004-02-16 | 2007-02-14 | 海运控制公司 | Method and system for testing a control system of a marine vessel |
| CN101014915A (en) * | 2004-06-08 | 2007-08-08 | 海运控制公司 | Method for testing of a combined dynamic positioning and power management system |
| JP2012153341A (en) * | 2011-01-28 | 2012-08-16 | Mitsubishi Heavy Ind Ltd | Ship power monitoring system, ship power control system, and method of monitoring power of regular line ship |
| CN102360209A (en) * | 2011-09-22 | 2012-02-22 | 昆明理工大学 | Multi-embedded intelligent monitoring, communication and control system for hybrid electric vehicle |
| KR20130037508A (en) * | 2011-10-06 | 2013-04-16 | 한국해양대학교 산학협력단 | Energy management system and method for ship and ocean plant |
| KR20140092111A (en) * | 2013-01-15 | 2014-07-23 | 현대중공업 주식회사 | An Energy System of Ship |
| JP2014165950A (en) * | 2013-02-21 | 2014-09-08 | Mitsubishi Heavy Ind Ltd | Energy management system and energy management method |
| RU2016103743A (en) * | 2016-02-04 | 2017-08-10 | Федеральное государственное унитарное предприятие "Крыловский государственный научный центр" | METHOD FOR CONTROLING BRAKING AND REVERSE OF CRAFT ELECTRIC MOTORS OF A SHIP |
| CN106697187A (en) * | 2016-12-26 | 2017-05-24 | 武汉理工大学 | Experimental platform used for simulation and diagnosis of working conditions of shipping power system and based on intelligent engine room |
| CN107140169A (en) * | 2017-05-24 | 2017-09-08 | 大鹏高科（武汉）智能装备有限公司 | A kind of modular unmanned boat intelligent power control system |
| CN108116646A (en) * | 2017-12-29 | 2018-06-05 | 武汉船用电力推进装置研究所（中国船舶重工集团公司第七二研究所） | A kind of watercraft electric propulsion system |
| CN110316331A (en) * | 2018-03-28 | 2019-10-11 | 住友重机械海洋工程株式会社 | Ship information provides device, method, system, program and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| KR102247165B1 (en) | 2021-04-30 |
| CN113525655A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113525655B (en) | Ship energy-electric power control management system based on machine learning | |
| KR101703163B1 (en) | Apparatus and method for predicting vehicle mixed fault | |
| EP3108317B1 (en) | System and method of fault detection for an aircraft | |
| MXPA02004188A (en) | A process and system for developing predictive diagnostics algorithms in a machine. | |
| US10281918B2 (en) | Control system for operating a vessel | |
| CN115013261B (en) | State monitoring method and system for offshore wind farm | |
| CN113555591A (en) | Fuel cell diagnostic device and corresponding diagnostic method, vehicle and vehicle system | |
| WO2013173149A1 (en) | System for determining battery impedance | |
| KR102632527B1 (en) | System and method for fault diagnosis of fuel cell energy management system based on digital twin | |
| CN112088122B (en) | Method and system for evaluating actual sea area propulsion performance of ship and computer readable storage medium | |
| CN106894954A (en) | Wind turbine diagnostic device with various sensor tests | |
| WO2014035385A1 (en) | Method and apparatus for on-board/off-board fault detection | |
| JP2003223917A (en) | Cogeneration-plant operation support system and operation supporting method | |
| KR102438844B1 (en) | Hybrid ship | |
| CN114648212A (en) | Cloud computing-based ship equipment performance intelligent management system and method | |
| CN117131785B (en) | Health management system and method for electric aeroengine | |
| CN110070205A (en) | Trend prediction method, device, computer equipment and the storage medium of ship machine dredge pump | |
| CN111319051A (en) | Intelligent inspection robot for intelligent engine room of ship and method thereof | |
| CN110044631A (en) | Trend prediction method, device and the computer equipment of ship machine diesel engine | |
| CN113565699B (en) | Method, device and system for detecting pitch angle of wind generating set | |
| CN113050496A (en) | Embedded computing device for ship real-time monitoring system | |
| CN113052377A (en) | Embedded computing method for ship real-time monitoring system | |
| US20220200026A1 (en) | Output voltage prediction system and prediction method for fuel cell | |
| CN113757052B (en) | Method and system for detecting running state of wind driven generator | |
| KR102609725B1 (en) | Monitoring method and system of vessel parts |
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 |