CN116362296A - Ship energy efficiency information collection management system and energy consumption state analysis method based on same - Google Patents
Ship energy efficiency information collection management system and energy consumption state analysis method based on same Download PDFInfo
- Publication number
- CN116362296A CN116362296A CN202211342569.7A CN202211342569A CN116362296A CN 116362296 A CN116362296 A CN 116362296A CN 202211342569 A CN202211342569 A CN 202211342569A CN 116362296 A CN116362296 A CN 116362296A
- Authority
- CN
- China
- Prior art keywords
- data
- ship
- main controller
- phase
- power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 21
- 238000004458 analytical method Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000012544 monitoring process Methods 0.000 claims abstract description 24
- 230000005540 biological transmission Effects 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000004891 communication Methods 0.000 claims abstract description 4
- 230000009466 transformation Effects 0.000 claims description 20
- 238000010586 diagram Methods 0.000 claims description 15
- 238000011176 pooling Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 13
- 238000005070 sampling Methods 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 12
- 210000002569 neuron Anatomy 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 11
- 239000000446 fuel Substances 0.000 claims description 10
- 230000003068 static effect Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- LIWAQLJGPBVORC-UHFFFAOYSA-N ethylmethylamine Chemical compound CCNC LIWAQLJGPBVORC-UHFFFAOYSA-N 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 210000004027 cell Anatomy 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000013505 freshwater Substances 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000004804 winding Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 21
- 238000005457 optimization Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000002747 voluntary effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a ship energy efficiency information collection management system, which comprises a WEB server, a data transmission unit, an S-Link controller, a frequency converter system main controller, a monitoring alarm system main controller, a communication system main controller and a data acquisition card, wherein the monitoring alarm system main controller is connected with the monitoring alarm system main controller; the data transmission unit is used for exchanging data information with the S-Link controller, and the S-Link controller is used for exchanging data information with the frequency converter system main controller, the monitoring alarm system main controller, the lead-through system main controller and the data acquisition card respectively; the S-Link controller sends the operation data of the ship to the WEB server through the data transmission unit, and the WEB server processes the data and displays the data to a user; the invention also discloses an energy consumption state analysis method based on the method.
Description
Technical Field
The invention relates to a ship management system, in particular to a ship energy efficiency information collection management system and an energy consumption state analysis method based on the same.
Background
With the development of shipping science and technology, sustainable development and environment-friendly concepts are increasingly paid attention to in the ship operation process, and International Maritime Organization (IMO) respectively makes related files such as "regulations for energy conservation and emission reduction and energy efficiency management (SEEMP)", "guidelines for voluntary use of ship Energy Efficiency Operation Index (EEOI)", and "guidelines for verification of ship Energy Efficiency Design Index (EEDI)", so as to monitor the emission of greenhouse gases such as carbon dioxide by the maritime enterprises. Meanwhile, in the "intelligent ship specification" formulated in 2015 by China class society and formally effective in 2016 and 3, specific functional requirements of intelligent energy efficiency management specification are specially provided for energy efficiency management. The energy efficiency of the ship is managed according to guidelines and specifications, and the method is also an effective measure and way for improving the operation energy efficiency of the ship and reducing the energy consumption.
Under the large environment of intelligent manufacturing, the traditional ship power monitoring system cannot meet the requirements of intelligent ships under new situation, a large amount of historical data are processed and analyzed on the basis of data monitoring, main energy consumption equipment and energy efficiency indexes of the ships can be evaluated in real time, warning and reminding are carried out on overrun indexes, and optimized and improved auxiliary decision-making suggestions are given according to comprehensive evaluation results of ship energy consumption or energy efficiency, so that a ship energy efficiency management system in a real sense is formed.
The main problems of the current ship power monitoring system are as follows: (1) Only the indexes related to the power system in the ship cabin are monitored, the process of analyzing the data is omitted, and a large amount of data is wasted.
(2) The energy consumption and the energy efficiency of the ship are not optimized and improved, and the energy saving and emission reduction effects are not achieved.
(3) Certain auxiliary decisions are not provided for ship enterprises and ship management staff, and the ship enterprise energy efficiency management staff is not guided.
(4) In the operation process of the ship, a large amount of data related to energy consumption and energy efficiency are accumulated, and the data are not collected for system science analysis, so that resource loss is caused.
(5) Because the management department or the management system of the ship enterprise cannot obtain the real-time condition of the energy efficiency of the ship in time, scientific management plans and measures cannot be made, and the improvement of the energy efficiency of the ship is greatly influenced.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the ship energy efficiency information collecting and managing system is visual to monitor and manage conveniently.
In order to solve the technical problems, the invention adopts the following technical scheme: the ship energy efficiency information collection management system comprises a WEB server, a data transmission unit, an S-Link controller, a frequency converter system main controller, a monitoring alarm system main controller, a lead-through system main controller and a data acquisition card; the data transmission unit is used for exchanging data information with the S-Link controller, and the S-Link controller is used for exchanging data information with the frequency converter system main controller, the monitoring alarm system main controller, the lead-through system main controller and the data acquisition card respectively; the S-Link controller sends the operation data of the ship to the WEB server through the data transmission unit, and the WEB server processes the data and displays the data to a user.
The frequency converter system main controller collects corresponding three-phase stator currents obtained by different current sensors for measuring the generator and the motor, collects corresponding three-phase stator voltages obtained by different voltage sensors for measuring the generator and the motor, collects winding temperature and bearing temperature of the motor measured by the temperature sensor, and collects rotating speed of the motor obtained by the photoelectric encoder, wherein the sampling frequency is 100 Hz-5 kHz.
Transforming three-phase stator current into ClarkeThe current under the alpha-beta two-phase static coordinate system is converted into the current I of the d-q two-phase rotating coordinate system through Park conversion sq ，I sd Three-phase stator voltage conversion to V sd 、V sq Wherein V is sd 、V sq The components of the stator voltage space vector in d-q two-phase rotation coordinate system d axis and q axis are respectively; and calculating the active power P of the motor by the following formula (1), and calculating the reactive power Q of the motor by the formula (2):
P=1.5*（V sd *I sd +V sq *I sq ） （1）
Q=1.5*（V sq *I sd -V sd *I sq ） （2）
the main controller of the frequency converter system obtains the voltage V of the battery pack through a direct-current voltage sensor b Acquiring a current group I of a battery through a current sensor b Calculating the power P of the battery by the formula (3) b ：
P b =V b *I b （3）
The main controller of the frequency converter system acquires the voltage and the temperature of all the battery cells in the battery system.
After the signals are obtained, the main controller of the frequency converter system reduces the sampling frequency through a low-pass filtering algorithm, and then transmits the signals to the S-Link controller through OPC/UA.
The monitoring and alarming system collects data of the turbine equipment of the main controller, the alternating current power distribution and various sensors on the engine room, and transmits the data to the S-Link controller, so that the S-Link controller alarms when the running state values of the power system, the alternating current power distribution system, the engine room piping, auxiliary equipment, oil and fresh water exceed preset thresholds, and accordingly staff are reminded.
The navigation system main controller acquires navigational speed and navigational path data acquired by the log, acquires wind speed and wind direction data acquired by the anemoscope, acquires comprehensive information of a ship by an electronic chart, acquires ship position information and ground speed acquired by a GPS, acquires ship bottom water depth acquired by a depth finder, acquires ship trim and trim data acquired by an inclinometer, acquires heading information acquired by a compass, and transmits the information to the S-Link controller.
The data acquisition card acquires fuel flow data on the fuel flow meter and transmits the fuel flow data to the S-Link controller.
As a preferable scheme, the main control of the variable frequency system also obtains three-phase voltages of the daily power supply system and the shore power system through a direct-current voltage sensor, and obtains three-phase currents of the daily power supply system and the shore power system through a current sensor.
The three-phase current of the daily power supply system is converted into the current under an alpha-beta two-phase static coordinate system through Clarke transformation, and then is converted into the current I of a d-q two-phase rotating coordinate system through Park transformation sq ′，I sd ' three-phase voltage of daily power supply system is converted into V sd ′、V sq ', V therein sd ′、V sq ' is the component of the voltage space vector on the d-axis and the q-axis of the d-q two-phase rotating coordinate system respectively; and calculating the active power P 'of the motor by the following formula (4), and calculating the reactive power Q' of the motor by the formula (5):
P′=1.5*（V sd ′*I sd ′+V sq ′*I sq ′） （4）
Q′=1.5*（V sq ′*I sd ′-V sd ′*I sq ′） （5）
the three-phase current of the shore power system is converted into the current under an alpha-beta two-phase static coordinate system through Clarke transformation, and then is converted into the current I of a d-q two-phase rotating coordinate system through Park transformation sq "，I sd ", three-phase voltage of shore power system is converted into V sd "、V sq ", wherein V sd "、V sq "the components of the voltage space vector on the d-axis and the q-axis of the d-q two-phase rotating coordinate system respectively; and calculating the active power p″ of the motor by the following formula (6), and calculating the reactive power q″ of the motor by the formula (7):
P"=1.5*（V sd "*I sd "+V sq "*I sq "） （6）
Q"=1.5*（V sq "*I sd "-V sd "*I sq "） （7）
after the signals are obtained, the main controller of the frequency converter system reduces the sampling frequency through a low-pass filtering algorithm and transmits the sampling frequency to the S-Link controller.
As a preferable scheme, the main controller of the frequency converter system communicates with the BMS of the battery system through the CAN bus to obtain the voltages and temperatures of all the battery cells in the battery system.
As a preferable scheme, after obtaining the signal, the main controller of the frequency converter system reduces the sampling frequency to 0.1 Hz-1 Hz through a low-pass filtering algorithm and transmits the sampling frequency to the S-Link controller.
As a preferable scheme, the S-Link controller supports ModbusTCP, modbusRTU, OPCUA, MQTT, webSocket, socketIO, NMEA protocol, various signals collected by the transducer system through the sensor are transmitted to the S-Link controller through OPA/UA protocol, various signals collected by the monitoring alarm system through the sensor are transmitted to the S-Link controller through OPA/UA protocol, various signals collected by the conduction system through the sensor are transmitted to the S-Link controller through NMEA protocol, and various signals collected by the data collecting card through the sensor are transmitted to the S-Link controller through PCI/e bus.
Another technical problem to be solved by the invention is: the ship energy efficiency information collecting and managing system is visual to monitor and manage conveniently.
In order to solve the technical problems, the invention adopts the following technical scheme: an energy consumption state analysis method based on a ship energy efficiency information collection management system comprises the following steps of predicting a endurance mileage;
when the endurance mileage is predicted, the propulsion power, the daily consumption power, the ship speed and the wind power are subjected to wavelet transformation to construct a time-frequency diagram, and then the time-frequency diagram is spliced to be used as the input of a deep learning network for predicting the endurance mileage.
The deep learning network comprises an input layer, a first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer, a third convolution layer, a full connection layer and an output layer; the convolution kernel is determined by adopting a random initialization weight method, and the size of the input characteristic and the number of network parameters are reduced by using a maximum pooling method.
The first convolution layer feature map has a size of 28×28, a convolution kernel has a size of 5×5, a step size of 1, and a number of convolution kernels of 6, and an activation function RELU is used.
The first pooling layer feature map size is 14×14, the convolution kernel size is 2×2, and the step size is 2.
The second convolution layer feature map has a size of 10×10, convolution kernel has a size of 5×5, step size is 1, the number of convolution kernels is 6, and an activation function RELU is used.
The second pooling layer feature map size is 5×6, the convolution kernel size is 2×2, and the step size is 2.
The third convolution layer feature map has a size of 1×1, convolution kernel has a size of 5×5, step size is 1, the number of convolution kernels is 60, and an activation function RELU is used.
The full link layer feature map size is 1 x 60.
The output layer feature map size is 1×1, and an activation function Softmax is used.
As a preferable scheme, the importance degree of the load on the ship to the safe operation of the ship is divided into an important load, a primary non-important load and a secondary non-important load; the important load comprises a conduction system and a steering engine system; the primary unimportant load includes a cabin fan; the secondary unimportant loads include recreational facilities, kitchen facilities; and according to the difference value between the predicted endurance mileage and the actually required range, sequentially ensuring an important load, a primary non-important load and a secondary non-important load.
As a preferred solution, the method further comprises the step of estimating the instant driving energy consumption state, specifically: taking propulsion power, rotation speed, a change rate of propulsion power and a change rate of rotation speed as inputs, taking 6 sailing states of berthing, port maneuvering, low-speed sailing, economic sailing, full-speed sailing and maneuvering sailing as outputs, establishing a neural network model, and training the neural network model through historical data; the neural network model comprises an input layer, a hidden layer 1, a hidden layer 2 and an output layer, wherein the number of neurons of the input layer is 6, the number of neurons of the hidden layer 1 is 8, the number of neurons of the hidden layer 2 is 10, the number of neurons of the output layer is 6, all the layers are connected, the initial weight is generated in a random mode, and the discarding rate is 0.5 in the training process.
The beneficial effects of the invention are as follows:
1) The invention fully utilizes the hardware systems of the ship frequency converter system, the monitoring alarm system and the lead-through system, reads the existing perception data of the hardware systems of the ship frequency converter system, the monitoring alarm system and the lead-through system through bus technology, and saves the hardware cost of the system compared with the traditional sensor independently arranged; meanwhile, through the configuration of the data acquisition card, additional signals can be acquired as required, and the whole system not only simplifies the structure of hardware, reduces the cost, but also ensures the comprehensiveness of data acquisition.
2) The S-Link controller supports ModbusTCP, modbusRTU, OPCUA, MQTT, webSocket, socketIO, NMEA protocol, facilitates the integration of various signals, and expands the application range of the system;
3) The invention not only carries out remote monitoring on the running state of the ship, but also models and analyzes the running state data based on deep learning, thereby predicting the running state of the ship and providing optimization suggestions.
4) Based on propulsion power, daily consumption power, ship speed and wind power, the ship endurance mileage is predicted based on deep learning, and compared with the traditional prediction of the endurance mileage based on a single index, the method has the advantage that the result is more accurate.
5) The propulsion power, daily consumption power, ship speed and wind power are subjected to wavelet transformation to construct a time-frequency diagram, the time-frequency diagram is used as input of a predicted range deep learning network, in the process of predicting the range, historical data and current conditions are considered, and compared with a traditional range prediction system based on the current conditions, the result is more accurate.
6) The method comprises the steps of taking propulsion power, rotating speed, change rate of power and rotating speed as input, taking 6 sailing states of berthing, port maneuvering, low-speed sailing, economic sailing, full-speed sailing and maneuvering sailing as output, establishing a neural network model, and training the neural network model through historical data. The dropping rate is introduced into the model network, so that the gradient disappearance phenomenon is effectively avoided in the training process; thereby obtaining reliable output results for visual display and being capable of roughly evaluating the driving energy consumption state of the ship according to the reliable output results, and providing basis for decision-making by a decision-maker according to the change of navigation conditions.
Drawings
Fig. 1 is a hardware configuration diagram of a ship energy efficiency information collection management system.
Fig. 2 is a functional block diagram of a ship energy efficiency information collection management system.
Fig. 3 is a schematic diagram of a deep learning network structure for range prediction.
FIG. 4 is a schematic diagram of a deep learning network for navigational state prediction.
Detailed Description
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
As shown in FIG. 1, the ship energy efficiency information collection management system comprises a WEB server, a data transmission unit, an S-Link controller, a frequency converter system main controller, a monitoring alarm system main controller, a communication system main controller and a data acquisition card; the system comprises a WEB server, a data transmission unit, an S-Link controller, a frequency converter system, a monitoring alarm system, a data acquisition card, a PCI/e bus and a PCI/e bus, wherein the WEB server and the data transmission unit are used for exchanging data information, the data transmission unit is used for exchanging data information with the S-Link controller, the S-Link controller supports ModbusTCP, modbusRTU, OPCUA, MQTT, webSocket, socketIO, NMEA protocol, various signals acquired by the frequency converter system through a sensor are transmitted to the S-Link controller through an OPA/UA protocol, various signals acquired by the monitoring alarm system through the sensor are transmitted to the S-Link controller through the OPA/UA protocol, various signals acquired by the sensor by the data acquisition card are transmitted to the S-Link controller through the NMEA protocol. The S-Link controller sends the operation data of the ship to the WEB server through the data transmission unit, the WEB server processes the data and displays the data to a user in a webpage form, and the user can browse a customized webpage interface by using any equipment to know the ship state.
The frequency converter system main controller collects corresponding three-phase stator currents obtained by different current sensors for measuring the generator and the motor, collects corresponding three-phase stator voltages obtained by different voltage sensors for measuring the generator and the motor, collects winding temperature and bearing temperature of the motor measured by the temperature sensor, and collects rotating speed of the motor obtained by the photoelectric encoder, wherein the sampling frequency is 100 Hz-5 kHz.
The three-phase stator current is converted into current under an alpha-beta two-phase static coordinate system through Clarke transformation, and then is converted into current I of a d-q two-phase rotating coordinate system through Park transformation sq ，I sd Three-phase stator voltage conversion to V sd 、V sq Wherein V is sd 、V sq The components of the stator voltage space vector in d-q two-phase rotation coordinate system d axis and q axis are respectively; and calculating the active power P of the motor by the following formula (1), and calculating the reactive power Q of the motor by the formula (2):
P=1.5*（V sd *I sd +V sq *I sq ） （1）
Q=1.5*（V sq *I sd -V sd *I sq ） （2）
the main controller of the frequency converter system obtains the voltage V of the battery pack through a direct-current voltage sensor b Acquiring a current group I of a battery through a current sensor b Calculating the power P of the battery by the formula (3) b ：
P b =V b *I b （3）
The main controller of the frequency converter system acquires the voltage and the temperature of all the battery cells in the battery system.
The main control of the variable frequency system also obtains three-phase voltages of the daily power supply system and the shore power system through a direct-current voltage sensor, and obtains three-phase currents of the daily power supply system and the shore power system through a current sensor.
The three-phase current of the daily power supply system is converted into the current under an alpha-beta two-phase static coordinate system through Clarke transformation, and then is converted into the current I of a d-q two-phase rotating coordinate system through Park transformation sq ′，I sd ' three-phase voltage of daily power supply system is converted into V sd ′、V sq ', V therein sd ′、V sq ' is the component of the voltage space vector on the d-axis and the q-axis of the d-q two-phase rotating coordinate system respectively; and calculating the active power P 'of the motor by the following formula (4), and calculating the reactive power Q' of the motor by the formula (5):
P′=1.5*（V sd ′*I sd ′+V sq ′*I sq ′） （4）
Q′=1.5*（V sq ′*I sd ′-V sd ′*I sq ′） （5）
the three-phase current of the shore power system is converted into the current under an alpha-beta two-phase static coordinate system through Clarke transformation, and then is converted into the current I of a d-q two-phase rotating coordinate system through Park transformation sq "，I sd ", three-phase voltage of shore power system is converted into V sd "、V sq ", wherein V sd "、V sq "the components of the voltage space vector on the d-axis and the q-axis of the d-q two-phase rotating coordinate system respectively; and calculating the active power p″ of the motor by the following formula (6), and calculating the reactive power q″ of the motor by the formula (7):
P"=1.5*（V sd "*I sd "+V sq "*I sq "） （6）
Q"=1.5*（V sq "*I sd "-V sd "*I sq "） （7）
and the main controller of the frequency converter system is communicated with the BMS of the battery system through the CAN bus to acquire the voltage and the temperature of all battery cells in the battery system.
After the frequency converter system main controller obtains signals, the sampling frequency is reduced to 0.1 Hz-1 Hz through a low-pass filtering algorithm, and the signals are transmitted to the S-Link controller.
The monitoring and alarming system collects data of the turbine equipment of the main controller, the alternating current power distribution and various sensors on the engine room, and transmits the data to the S-Link controller, so that the S-Link controller alarms when the running state values of the power system, the alternating current power distribution system, the engine room piping, auxiliary equipment, oil and fresh water exceed preset thresholds, and accordingly staff are reminded.
The navigation system main controller acquires navigational speed and navigational path data acquired by the log, acquires wind speed and wind direction data acquired by the anemoscope, acquires comprehensive information of a ship by an electronic chart, acquires ship position information and ground speed acquired by a GPS, acquires ship bottom water depth acquired by a depth finder, acquires ship trim and trim data acquired by an inclinometer, acquires heading information acquired by a compass, and transmits the information to the S-Link controller.
The data acquisition card acquires fuel flow data on the fuel flow meter and transmits the fuel flow data to the S-Link controller.
As shown in fig. 2, the ship energy efficiency information collection management system can realize: dynamic display of equipment operation data, remote monitoring of equipment operation state, core data calculation and energy efficiency analysis, historical data storage, operation report generation, application scene analysis, optimization suggestion and the like.
The dynamic display of equipment operation data is combined with the depth of the DC networking electric propulsion system, and the operation overview of all power stations on the DC networking system is displayed on a driving platform, so that detailed operation information of each generator set, each battery set, each propulsion system, each daily power supply system, each shore power system, and information of key equipment such as communication navigation equipment, a log and the like are displayed.
Remote monitoring of the running state of the equipment, and realizing cross-region and cross-platform display of the running data of the equipment based on the Internet; remote data backtracking, remote fault analysis, data modeling, statistical analysis, ship management optimization and the like. The user logs in through any device on the WEB browser by using an account number, and checks the latest state, running data and the like of the ship in real time.
The system can store collected data in the ship operation time in a historical database, the database adopts MySQL, crews and shore-based management personnel can check all equipment operation data in any period of time, and meanwhile, the operation report of the ship in a period of time can be automatically generated according to the historical data, so that advice is provided for the ship operation; the operation report comprises data of passenger carrying unit transportation power consumption, whole ship unit transportation power consumption, propulsion unit distance energy consumption, whole ship unit distance energy consumption, average power consumption per day for whole ship hour and average power consumption per day for propulsion hour.
The method comprises the steps of applying scene analysis and optimization suggestions, and carrying out deep analysis on the running state of the ship according to historical power data so as to solve the attention points of different clients, wherein the attention points comprise fuel saving condition analysis, diesel unit control mode optimization, battery pack use state analysis, cruising mileage, running suggestions and the like.
As shown in FIG. 3, the energy consumption state analysis method based on the ship energy efficiency information collection management system comprises the following steps of endurance mileage prediction.
When the endurance mileage is predicted, the propulsion power, the daily consumption power, the ship speed and the wind power are subjected to wavelet transformation to construct a time-frequency diagram, and then the time-frequency diagram is spliced to be used as the input of a deep learning network for predicting the endurance mileage.
The deep learning network comprises an input layer, a first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer, a third convolution layer, a full connection layer and an output layer; the convolution kernel is determined by adopting a random initialization weight method, and the size of the input characteristic and the number of network parameters are reduced by using a maximum pooling method.
The first convolution layer feature map has a size of 28×28, a convolution kernel has a size of 5×5, a step size of 1, and a number of convolution kernels of 6, and an activation function RELU is used.
The first pooling layer feature map size is 14×14, the convolution kernel size is 2×2, and the step size is 2.
The second convolution layer feature map has a size of 10×10, convolution kernel has a size of 5×5, step size is 1, the number of convolution kernels is 6, and an activation function RELU is used.
The second pooling layer feature map size is 5×6, the convolution kernel size is 2×2, and the step size is 2.
The third convolution layer feature map has a size of 1×1, convolution kernel has a size of 5×5, step size is 1, the number of convolution kernels is 60, and an activation function RELU is used.
The full link layer feature map size is 1 x 60.
The output layer feature map size is 1×1, and an activation function Softmax is used.
The method comprises the steps of dividing the importance degree of the load on the ship on the safe operation of the ship into an important load, a primary non-important load and a secondary non-important load; the important load comprises a conduction system and a steering engine system; the primary unimportant load includes a cabin fan; the secondary unimportant loads include recreational facilities, kitchen facilities; according to the difference value between the predicted endurance mileage and the actually needed range, the important load, the primary non-important load and the secondary non-important load are ensured in sequence:
for example, it is possible to take: when the predicted endurance mileage is more than 2 times of the range actually required, the important load, the primary non-important load and the secondary non-important load are kept in an operating state;
when the predicted endurance mileage is greater than 1.5 times of the range actually required and is less than 2 times of the range actually required, keeping the important load and the first-level non-important load in an operating state, and closing the second-level non-important load;
and when the predicted endurance mileage is smaller than 1.5 times of the range actually required, keeping the important load in an operating state, and closing the first-stage non-important load and the second-stage non-important load.
As shown in fig. 4, the energy consumption state analysis method further includes an instant energy consumption state evaluation, specifically: taking propulsion power, rotation speed, a change rate of propulsion power and a change rate of rotation speed as inputs, taking 6 sailing states of berthing, port maneuvering, low-speed sailing, economic sailing, full-speed sailing and maneuvering sailing as outputs, and building a neural network model so as to train the neural network model through historical data; the neural network model comprises an input layer, a hidden layer 1, a hidden layer 2 and an output layer, wherein the number of neurons of the input layer is 6, the number of neurons of the hidden layer 1 is 8, the number of neurons of the hidden layer 2 is 10, the number of neurons of the output layer is 6, all the layers are connected, the initial weight is generated in a random mode, and the discarding rate is 0.5 in the training process.
The above-described embodiments are merely illustrative of the principles and functions of the present invention, and some of the practical examples, not intended to limit the invention; it should be noted that modifications and improvements can be made by those skilled in the art without departing from the inventive concept, and these are all within the scope of the present invention.
Claims (8)
1. The utility model provides a boats and ships efficiency information gathers management system which characterized in that: the system comprises a WEB server, a data transmission unit, an S-Link controller, a frequency converter system main controller, a monitoring alarm system main controller, a communication system main controller and a data acquisition card; the data transmission unit is used for exchanging data information with the S-Link controller, and the S-Link controller is used for exchanging data information with the frequency converter system main controller, the monitoring alarm system main controller, the lead-through system main controller and the data acquisition card respectively; the S-Link controller sends the operation data of the ship to the WEB server through the data transmission unit, and the WEB server processes the data and displays the data to a user;
the frequency converter system main controller collects corresponding three-phase stator currents obtained by different current sensors for measuring the generator and the motor, collects corresponding three-phase stator voltages obtained by different voltage sensors for measuring the generator and the motor, collects winding temperature and bearing temperature of the motor measured by a temperature sensor, and collects rotating speed of the motor obtained by a photoelectric encoder, wherein the sampling frequency is 100 Hz-5 kHz;
the three-phase stator current is converted into current under an alpha-beta two-phase static coordinate system through Clarke transformation, and then is converted into current I of a d-q two-phase rotating coordinate system through Park transformation sq ，I sd Three-phase stator voltage conversion to V sd 、V sq Wherein V is sd 、V sq The components of the stator voltage space vector in d-q two-phase rotation coordinate system d axis and q axis are respectively; and calculating the active power P of the motor by the following formula (1), and calculating the reactive power Q of the motor by the formula (2):
P=1.5*（V sd *I sd +V sq *I sq ） （1）
Q=1.5*（V sq *I sd -V sd *I sq ） （2）
the main controller of the frequency converter system obtains the voltage V of the battery pack through a direct-current voltage sensor b Acquiring a current group I of a battery through a current sensor b Calculating the power P of the battery by the formula (3) b ：
P b =V b *I b （3）
The method comprises the steps that a main controller of a frequency converter system obtains voltages and temperatures of all battery cells in a battery system;
after the frequency converter system main controller obtains the signals, the sampling frequency is reduced through a low-pass filtering algorithm, and then the signals are transmitted to the S-Link controller through OPC/UA;
the monitoring and alarming system collects data of the turbine equipment of the main controller, the alternating current power distribution and various sensors on the engine room, and transmits the data to the S-Link controller, so that the S-Link controller alarms when the running state values of the power system, the alternating current power distribution system, the engine room piping, auxiliary equipment, oil and fresh water exceed preset thresholds, and accordingly staff are reminded;
the navigation system main controller acquires navigational speed and navigational path data acquired by the log, acquires wind speed and wind direction data acquired by the anemoscope, acquires comprehensive information of a ship by an electronic chart, acquires ship position information and ground speed acquired by a GPS (global positioning system), acquires ship bottom water depth acquired by a depth finder, acquires ship trim and trim data acquired by an inclinometer, acquires heading information acquired by a compass, and transmits the information to the S-Link controller;
the data acquisition card acquires fuel flow data on the fuel flow meter and transmits the fuel flow data to the S-Link controller.
2. The ship energy efficiency information collection management system of claim 1, wherein: the main control of the variable frequency system also obtains three-phase voltages of the daily power supply system and the shore power system through a direct-current voltage sensor, and obtains three-phase currents of the daily power supply system and the shore power system through a current sensor;
the three-phase current of the daily power supply system is converted into the current under an alpha-beta two-phase static coordinate system through Clarke transformation, and then is converted into the current I of a d-q two-phase rotating coordinate system through Park transformation sq ′，I sd ' three-phase voltage of daily power supply system is converted into V sd ′、V sq ', V therein sd ′、V sq ' is the component of the voltage space vector on the d-axis and the q-axis of the d-q two-phase rotating coordinate system respectively; and calculating the active power P 'of the motor by the following formula (4), and calculating the reactive power Q' of the motor by the formula (5):
P′=1.5*（V sd ′*I sd ′+V sq ′*I sq ′） （4）
Q′=1.5*（V sq ′*I sd ′-V sd ′*I sq ′） （5）
the three-phase current of the shore power system is converted into the current under an alpha-beta two-phase static coordinate system through Clarke transformation, and then is converted into the current I of a d-q two-phase rotating coordinate system through Park transformation sq "，I sd ", three-phase voltage of shore power system is converted into V sd "、V sq ", wherein V sd "、V sq "the components of the voltage space vector on the d-axis and the q-axis of the d-q two-phase rotating coordinate system respectively; and calculating the active power p″ of the motor by the following formula (6), and calculating the reactive power q″ of the motor by the formula (7):
P"=1.5*（V sd "*I sd "+V sq "*I sq "） （6）
Q"=1.5*（V sq "*I sd "-V sd "*I sq "） （7）
after the signals are obtained, the main controller of the frequency converter system reduces the sampling frequency through a low-pass filtering algorithm and transmits the sampling frequency to the S-Link controller.
3. The ship energy efficiency information collection management system of claim 1, wherein: and the main controller of the frequency converter system is communicated with the BMS of the battery system through the CAN bus to acquire the voltage and the temperature of all battery cells in the battery system.
4. A ship energy efficiency information collection management system according to any one of claims 1-3, wherein: after the main controller of the frequency converter system obtains signals, the sampling frequency is reduced to 0.1 Hz-1 Hz through a low-pass filtering algorithm, and the signals are transmitted to the S-Link controller.
5. The ship energy efficiency information collection management system of claim 4, wherein: the S-Link controller supports ModbusTCP, modbusRTU, OPCUA, MQTT, webSocket, socketIO, NMEA protocol, various signals collected by the transducer system through the sensor are transmitted to the S-Link controller through OPA/UA protocol, various signals collected by the monitoring alarm system through the sensor are transmitted to the S-Link controller through OPA/UA protocol, various signals collected by the conduction system through the sensor are transmitted to the S-Link controller through NMEA protocol, and various signals collected by the data collecting card through the sensor are transmitted to the S-Link controller through PCI/e bus.
6. An energy consumption state analysis method based on the ship energy efficiency information collection management system of any one of claims 1-5, comprising a range prediction;
when the endurance mileage is predicted, the propulsion power, the daily consumption power, the ship navigational speed and the wind power size data are subjected to wavelet transformation to construct a time-frequency diagram, and then the time-frequency diagram is spliced to be used as the input of a deep learning network for predicting the endurance mileage;
the deep learning network comprises an input layer, a first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer, a third convolution layer, a full connection layer and an output layer; determining a convolution kernel by adopting a random initialization weight method, and reducing the size of input characteristics and the number of network parameters by using a maximum pooling method;
the feature map of the first convolution layer is 28 multiplied by 28, the convolution kernel is 5 multiplied by 5, the step length is 1, the number of the convolution kernels is 6, and an activation function RELU is adopted;
the size of the first pooling layer feature map is 14 multiplied by 14, the size of the convolution kernel is 2 multiplied by 2, and the step length is 2;
the feature map of the second convolution layer is 10 multiplied by 10, the convolution kernel is 5 multiplied by 5, the step length is 1, the number of the convolution kernels is 6, and an activation function RELU is adopted;
the characteristic diagram of the second pooling layer is 5 multiplied by 6, the convolution kernel is 2 multiplied by 2, and the step length is 2;
the characteristic diagram of the third convolution layer is 1 multiplied by 1, the convolution kernel is 5 multiplied by 5, the step length is 1, the number of the convolution kernels is 60, and an activation function RELU is adopted;
the size of the full connection layer characteristic diagram is 1 multiplied by 60;
the output layer feature map size is 1×1, and an activation function Softmax is used.
7. The energy consumption state analysis method of the ship energy efficiency information collection management system according to claim 6, wherein: the method comprises the steps of dividing the importance degree of the load on the ship on the safe operation of the ship into an important load, a primary non-important load and a secondary non-important load; the important load comprises a conduction system and a steering engine system; the primary unimportant load includes a cabin fan; the secondary unimportant loads include recreational facilities, kitchen facilities; and according to the difference value between the predicted endurance mileage and the actually required range, sequentially ensuring an important load, a primary non-important load and a secondary non-important load.
8. The energy consumption state analysis method of the ship energy efficiency information collection management system according to claim 6 or 7, wherein: the method also comprises the step of estimating the instant driving energy consumption state, specifically: taking propulsion power, rotation speed, a change rate of propulsion power and a change rate of rotation speed as inputs, taking 6 sailing states of berthing, port maneuvering, low-speed sailing, economic sailing, full-speed sailing and maneuvering sailing as outputs, establishing a neural network model, and training the neural network model through historical data; the neural network model comprises an input layer, a hidden layer 1, a hidden layer 2 and an output layer, wherein the number of neurons of the input layer is 6, the number of neurons of the hidden layer 1 is 8, the number of neurons of the hidden layer 2 is 10, the number of neurons of the output layer is 6, all the layers are connected, the initial weight is generated in a random mode, and the discarding rate is 0.5 in the training process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211342569.7A CN116362296B (en) | 2022-10-31 | 2022-10-31 | Ship energy efficiency information collection management system and energy consumption state analysis method based on same |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211342569.7A CN116362296B (en) | 2022-10-31 | 2022-10-31 | Ship energy efficiency information collection management system and energy consumption state analysis method based on same |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116362296A true CN116362296A (en) | 2023-06-30 |
| CN116362296B CN116362296B (en) | 2024-03-01 |
Family
ID=86940471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211342569.7A Active CN116362296B (en) | 2022-10-31 | 2022-10-31 | Ship energy efficiency information collection management system and energy consumption state analysis method based on same |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116362296B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150149135A1 (en) * | 2012-06-01 | 2015-05-28 | Abb Technology Ag | Method and system for predicting the performance of a ship |
| CN107274085A (en) * | 2017-06-08 | 2017-10-20 | 武汉理工大学 | A kind of optimum management method of the energy storage device of double electric type ships |
| CN107563576A (en) * | 2017-10-14 | 2018-01-09 | 连云港杰瑞深软科技有限公司 | A kind of ship intelligence energy efficiency management system |
| KR101914770B1 (en) * | 2017-07-20 | 2018-11-02 | 에이블맥스(주) | Predicting System Of Energy Efficiency For Ships And Predicting Method In Using Same |
| KR20190073050A (en) * | 2017-12-18 | 2019-06-26 | 대우조선해양 주식회사 | Hybrid Generation System and Method for a Ship |
| CN110737986A (en) * | 2019-10-15 | 2020-01-31 | 大连海事大学 | unmanned ship energy efficiency intelligent optimization simulation system and method |
| CN111301655A (en) * | 2020-03-18 | 2020-06-19 | 无锡赛思亿电气科技有限公司 | Ship electric propulsion and control system and monitoring control and safety evaluation method thereof |
| US20200240787A1 (en) * | 2019-01-29 | 2020-07-30 | Alpha Ori Technologies Pte. Ltd | System and method for voyage consumption optimization |
| WO2020161055A1 (en) * | 2019-02-07 | 2020-08-13 | Shell Internationale Research Maatschappij B.V. | Method and system for reducing vessel fuel consumption |
| CN111907680A (en) * | 2020-09-07 | 2020-11-10 | 锡瑞迪船用动力系统(上海)有限公司 | Energy efficiency control system and method for hybrid power ship |
| CN112435505A (en) * | 2020-11-11 | 2021-03-02 | 南通中远海运川崎船舶工程有限公司 | Autonomous navigation system based on optimal navigation speed and navigation method thereof |
| KR20210120325A (en) * | 2020-03-26 | 2021-10-07 | 삼성중공업 주식회사 | System and method for integrated energy monitoring of vessel |
| WO2022021062A1 (en) * | 2020-07-28 | 2022-02-03 | 华为技术有限公司 | Remaining range prediction method and battery remote service system |
| CN115195971A (en) * | 2022-07-15 | 2022-10-18 | 中国船舶重工集团公司第七一一研究所 | Ship energy efficiency management system, method and storage medium |
-
2022
- 2022-10-31 CN CN202211342569.7A patent/CN116362296B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150149135A1 (en) * | 2012-06-01 | 2015-05-28 | Abb Technology Ag | Method and system for predicting the performance of a ship |
| CN107274085A (en) * | 2017-06-08 | 2017-10-20 | 武汉理工大学 | A kind of optimum management method of the energy storage device of double electric type ships |
| KR101914770B1 (en) * | 2017-07-20 | 2018-11-02 | 에이블맥스(주) | Predicting System Of Energy Efficiency For Ships And Predicting Method In Using Same |
| CN107563576A (en) * | 2017-10-14 | 2018-01-09 | 连云港杰瑞深软科技有限公司 | A kind of ship intelligence energy efficiency management system |
| KR20190073050A (en) * | 2017-12-18 | 2019-06-26 | 대우조선해양 주식회사 | Hybrid Generation System and Method for a Ship |
| US20200240787A1 (en) * | 2019-01-29 | 2020-07-30 | Alpha Ori Technologies Pte. Ltd | System and method for voyage consumption optimization |
| WO2020161055A1 (en) * | 2019-02-07 | 2020-08-13 | Shell Internationale Research Maatschappij B.V. | Method and system for reducing vessel fuel consumption |
| CN110737986A (en) * | 2019-10-15 | 2020-01-31 | 大连海事大学 | unmanned ship energy efficiency intelligent optimization simulation system and method |
| CN111301655A (en) * | 2020-03-18 | 2020-06-19 | 无锡赛思亿电气科技有限公司 | Ship electric propulsion and control system and monitoring control and safety evaluation method thereof |
| KR20210120325A (en) * | 2020-03-26 | 2021-10-07 | 삼성중공업 주식회사 | System and method for integrated energy monitoring of vessel |
| WO2022021062A1 (en) * | 2020-07-28 | 2022-02-03 | 华为技术有限公司 | Remaining range prediction method and battery remote service system |
| CN111907680A (en) * | 2020-09-07 | 2020-11-10 | 锡瑞迪船用动力系统(上海)有限公司 | Energy efficiency control system and method for hybrid power ship |
| CN112435505A (en) * | 2020-11-11 | 2021-03-02 | 南通中远海运川崎船舶工程有限公司 | Autonomous navigation system based on optimal navigation speed and navigation method thereof |
| CN115195971A (en) * | 2022-07-15 | 2022-10-18 | 中国船舶重工集团公司第七一一研究所 | Ship energy efficiency management system, method and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 武治江等: "船用直流组网系统的特点和实际案例分析", 2018船舶智能能效技术国际高峰论坛 论文集, 31 December 2018 (2018-12-31), pages 65 - 71 * |
| 郑洪燕;王跃;朱军;: "船舶智能能效管理系统设计", 水运管理, no. 11, 20 November 2018 (2018-11-20), pages 33 - 36 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116362296B (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107563576B (en) | Intelligent energy efficiency management system for ship | |
| CN110109445B (en) | Ship engine room auxiliary machine monitoring system and monitoring method | |
| JP5420723B2 (en) | Ship optimum route calculation system, vessel operation support system, vessel optimum route calculation method, and vessel operation support method | |
| CN112381406A (en) | Ship energy efficiency management big data system and method based on ship-shore cooperation | |
| CN109238735B (en) | The malfunction monitoring diagnostic system of the electronic AGV of port cargo | |
| CN104090595A (en) | Ship navigational speed optimizing device and method based on main engine energy efficiency and navigation environment | |
| CN115013261B (en) | State monitoring method and system for offshore wind farm | |
| CN110516972A (en) | A kind of ship sails and operation on the sea comprehensive forecasting assessment system | |
| CN103466041A (en) | Real-time optimizing energy-saving ship speed intelligent-analysis system | |
| CN106878430A (en) | Ship craft integrated management system and its communication means and rescue skills based on cloud framework | |
| CN115017684A (en) | Intelligent energy efficiency management system for ship | |
| CN108008718A (en) | Study on intelligent based on model | |
| CN112083355A (en) | Ship cabin equipment health management and fault prediction system and method | |
| Bassam et al. | Experimental testing and simulations of an autonomous, self-propulsion and self-measuring tanker ship model | |
| CN107437147A (en) | Reduce the vehicle travel risk dynamic assessment method and its system of freight logistics scene | |
| Xu et al. | Review of condition monitoring and fault diagnosis for marine power systems | |
| CN112784473A (en) | Ship fuel saving system and method for intelligently analyzing navigation information and optimizing energy | |
| CN116362296B (en) | Ship energy efficiency information collection management system and energy consumption state analysis method based on same | |
| Zeng et al. | A novel big data collection system for ship energy efficiency monitoring and analysis based on BeiDou system | |
| CN113428318B (en) | Ship power equipment monitoring method, device, equipment and storage medium | |
| CN103605908A (en) | Wind speed sequence forecasting method based on Kalman filtering | |
| CN104035388A (en) | Yacht state remote monitoring system and method | |
| CN116788471A (en) | Intelligent engine room management system and method for electric ship and computer storage medium | |
| CN115511121A (en) | Digital twin system for ocean nuclear power platform | |
| CN110543961B (en) | Ocean operation platform and ship overall energy efficiency management method |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Plot 83-D, Development Zone, Xinwu District, Wuxi City, Jiangsu Province, 214000 Applicant after: China Shipbuilding Saisiyi (Wuxi) Electrical Technology Co.,Ltd. Address before: Plot 83-D, Development Zone, Xinwu District, Wuxi City, Jiangsu Province, 214000 Applicant before: WUXI SILENT ELECTRIC SYSTEM (SES) TECHNOLOGY Co.,Ltd. Country or region before: China |