CN116931448A - Intelligent ship state monitoring and control system based on digital twin - Google Patents
Intelligent ship state monitoring and control system based on digital twin Download PDFInfo
- Publication number
- CN116931448A CN116931448A CN202310831387.4A CN202310831387A CN116931448A CN 116931448 A CN116931448 A CN 116931448A CN 202310831387 A CN202310831387 A CN 202310831387A CN 116931448 A CN116931448 A CN 116931448A
- Authority
- CN
- China
- Prior art keywords
- model
- state
- ship
- information
- intelligent ship
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 38
- 238000004088 simulation Methods 0.000 claims abstract description 41
- 230000006870 function Effects 0.000 claims abstract description 21
- 238000003745 diagnosis Methods 0.000 claims abstract description 18
- 230000036541 health Effects 0.000 claims abstract description 16
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims description 60
- 238000012937 correction Methods 0.000 claims description 32
- 230000008569 process Effects 0.000 claims description 31
- 230000003993 interaction Effects 0.000 claims description 24
- 230000000007 visual effect Effects 0.000 claims description 23
- 238000004891 communication Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000012423 maintenance Methods 0.000 claims description 16
- 238000005259 measurement Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 15
- 238000007726 management method Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000011112 process operation Methods 0.000 claims description 10
- 238000005096 rolling process Methods 0.000 claims description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 230000033001 locomotion Effects 0.000 claims description 8
- 230000015556 catabolic process Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000006731 degradation reaction Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000009877 rendering Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 230000007774 longterm Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000007654 immersion Methods 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 238000007500 overflow downdraw method Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 abstract description 4
- 238000011161 development Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 239000010687 lubricating oil Substances 0.000 description 3
- 229940098006 multigen Drugs 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003139 buffering effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000002706 hydrostatic effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 239000013643 reference control Substances 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 230000003238 somatosensory effect Effects 0.000 description 1
- 239000013585 weight reducing agent Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of digital twinning, and particularly relates to an intelligent ship state monitoring and controlling system based on digital twinning. The digital twin system of the intelligent ship is constructed, and through constructing ship navigation scenes under various sea conditions and various tight conditions, the experimental test which is difficult to be carried out on the ship can be realized through the simulation experiment, so that the risk and cost of the real ship experiment are greatly reduced. The invention has the functions of state monitoring, fault diagnosis, auxiliary decision making, health management and the like, can realize the state health monitoring of all-weather shipboard equipment, can give an alarm in time when faults occur, and greatly reduces the potential safety hazard caused by the fact that the equipment faults cannot be found in time; the physical information of the real space is mapped in real time in the virtual space, so that a manager can grasp the current navigation state of the intelligent ship on a shore basis and apply control instructions to the intelligent ship.
Description
Technical Field
The invention belongs to the technical field of digital twinning, and particularly relates to an intelligent ship state monitoring and controlling system based on digital twinning.
Background
With the progress of technology, especially the rapid development of the technologies such as industrial internet, artificial intelligence, internet of things and big data, the global industry is developing towards intellectualization, informatization and networking, and ships are gradually changed from traditional electromechanical control to digitalization and intellectualization. The intelligent ship can effectively solve the problems of running safety, labor cost increase, environmental pollution and the like in the running process of the traditional ship, and symbolizes the future of ship development.
In recent years, digital twinning has been widely studied and applied as a simulation process combining multiple disciplines, multiple physical quantities and multiple dimensions. The method fully utilizes physical models, sensor updating, historical data and the like, maps physical information of a real space in a virtual space, and reflects the full life cycle process of a corresponding entity object. The value of the digital twin is reflected in real-time performance and interactivity, a manager can grasp the state of a physical object in a real space in real time through a virtual space, and can control the physical object through the operation of the virtual twin object, so that the dynamic interactive simulation of the physical object and the digital twin is realized.
Because of the complicated marine situation, different ship scenes are required to be built for carrying out the function test of the intelligent ship, and the high cost and the existing test platform cannot meet the test condition.
On the other hand, the intelligent ship digital twin system requires real-time mapping of physical information of real space in virtual space, and in order to restore the real scene to the maximum extent, the data measurement accuracy of complex offshore environment and ship self state must be improved. However, the current information sensing technology in intelligent ships mainly uses sensing equipment, a sensing network and information processing equipment to intelligently sense and acquire the state and surrounding environment information of the ship, so that the interactive acquisition of ship-shore information is realized, the acquired data volume is large, the variety of signals is various, and contradiction and conflict exist between the information, so that further improvement and perfection are required.
Disclosure of Invention
The invention aims to provide an intelligent ship state monitoring and controlling system based on digital twinning.
An intelligent ship state monitoring and control system based on digital twinning comprises a resource layer, a communication layer, a model layer, a service layer and an application layer;
the resource layer comprises computing resources, algorithm resources, a digital model library and an entity console;
the communication layer is used for realizing data acquisition, data processing, data storage and data transmission;
the model layer comprises an environment model, a mechanism model, an operation control model and a whole process operation and maintenance model; the environment model is an environment digital twin body constructed according to sea condition environment, meteorological information and sea surface targets,
the service layer is used for state monitoring, fault diagnosis, auxiliary decision making and health management; the health management is to analyze the performance degradation of each part after long-term operation according to a mechanism model established by each device of the intelligent ship, and adjust model parameters to match the degraded physical object model;
the application layer is used for realizing man-machine interaction simulation, multi-working condition simulation, immersion simulation and operation and maintenance simulation.
Further, the data processing means that all state quantities of the intelligent ship acquired by the sensor are processed through a filtering algorithm, including wild point elimination, sensor correction, noise point filtering, decoupling dimension reduction, and some state quantities which cannot be measured in practice are estimated;
the filtering algorithm adopts rolling time domain estimation and comprises the following steps:
step 1: acquiring the position, the gesture and the operation input signals of the intelligent ship;
step 2: solving the optimization function to obtain
In the method, in the process of the invention,the state quantity to be estimated at the t-N moment of the intelligent ship; />The state priori predicted value at t-N moment of the intelligent ship is obtained; n is the length of a rolling time domain window; the performance index function is:
where k=1, 2,..n+1;representing the output equation, alpha.gtoreq.0 and beta k > 0 is a weight parameter used to trade-off confidence in state prior predictions or sensor measurements, with larger a representing more reliable state prior predictions, β k Larger means more reliable measurement;
the intelligent ship state variable in the solving process needs to meet constraint:
in the method, in the process of the invention,representing the equation of state, u i Representing manipulation input signals, X representing objective facts that each state quantity needs to satisfy;
step 3: obtaining a state estimation value at the current moment by applying recursive calculation;
step 4: repeating the steps 2 to 4 when the propagation state priori predicted value reaches the next moment and the measurement signal at the next moment arrives; the state priori prediction value propagation method comprises the following steps:
further, the construction method of the environment model comprises the following steps:
the wind disturbance model is calculated by combining the wind disturbance force model and the ocean surface wind field obtained by the scatterometer; the wave interference model is calculated by combining the wave propagation model with the sea surface wave field observed by the spectrometer; the method comprises the steps of obtaining a water flow interference model through combining a hydrodynamic model calculation by using a marine surface flow field observed by a synthetic aperture radar; observing sea surface targets through radar, AIS and visual image technologies; and according to the obtained air disturbance model, wave disturbance model, water flow disturbance model and sea surface target object, calculating to obtain an environment digital twin model, and restoring the environment state of the real space in the digital space to realize the real-time mapping of the real environment in the digital space.
Further, the entity console comprises a communication device, a display device and a manipulation device; the communication equipment is used for information transmission and instruction receiving and transmitting between the intelligent ship and the shore-based digital twin body; the display device is used for three-dimensional scene display, information input window, video and chart display of the digital twin body; the control equipment is a ship cab console at the shore base end and is used for giving a control instruction to the twin model, the twin model receives the control instruction and then carries out simulation, and the control instruction is transmitted to the real ship through the communication equipment to drive the real ship to carry out synchronous movement.
Further, the operation control model is used for designing different control methods for different navigation tasks and different sea conditions of the intelligent ship by the pointer to meet the operation requirements; if the current navigation state and model parameters of the intelligent ship are completely known, calling a model prediction controller to realize navigation control of the intelligent ship and prediction of future navigation states; if the change of the marine environment in the sailing process of the intelligent ship is severe, the hydrodynamic coefficient of the intelligent ship is changed, the self-adaptive controller is called, and the adaptation to the surrounding environment is realized and controlled by on-line identification and change of the parameters of the controller; and if the model parameters are difficult to determine, calling a fuzzy controller and a neural network controller to control the intelligent ship.
Further, the whole process operation and maintenance model is constructed by adopting a model driving and data driving fusion method, which comprises the following specific steps:
firstly, constructing a digital twin initial model by adopting a model driving method based on a mechanism model of each device; and secondly, based on the initial model, different data including real-time sensor data, fault data and historical operation data are fused, and the initial model is corrected in real time, so that the model has the behavior characteristics of accurate monitoring, fault diagnosis, performance prediction and control optimization, and further a operation digital twin body is formed.
Further, the method for online correction of the twin model in the health management specifically comprises the following steps:
firstly, initializing a correction coefficient, and transmitting the correction coefficient into a model to obtain model operation data under corresponding working conditions; and correcting the parameter model in the running process of the actual physical system by collecting the correction coefficient set in the correction model, comparing errors between test data and model data, outputting the obtained correction coefficient if the set error range is met, obtaining a new group of correction coefficients through an optimization algorithm if the errors are larger than the set range, bringing the correction coefficients into the model, and repeating the process until the correction coefficient meeting the error range is obtained, thereby obtaining the model in the corrected digital twin system.
Further, the man-machine interaction simulation is based on scene reconstruction information, supports multi-means man-machine interaction, and comprises equipment selection and basic operation interaction directly in a three-dimensional scene, and instruction input interaction based on an information window and a function button; the scene reconstruction is that after the intelligent ship state information and surrounding sea state information which are measured by a sensor are filtered, the filtered information is transmitted to a digital twin system, and the current real scene information is displayed in real time by a three-dimensional display interface, and the scene reconstruction comprises the following steps:
step one: receiving dynamic shipborne information and sea state information in real time through a data transmission module of a communication layer;
step two: based on the received shipborne information and sea state information, supporting according to detailed static information of each device, including device parameters, a three-dimensional model and a layout structure, and organically superposing the static information and the dynamic information through geometric space constraint to restore real-time scene information in a dynamic scene in real time;
step three: based on the driving of the scene information reconstruction result, three-dimensional view software is developed, scene changes corresponding to different subsystems are supported, the changes of the states and parameters of each motion device are reflected in real time, real-time three-dimensional rendering is carried out, the dynamic roaming of the scenes and the visual superposition display of key parameters are supported, and the clear and complete intelligent ship state is displayed for users.
The invention has the beneficial effects that:
the digital twin system of the intelligent ship is constructed, and through constructing ship navigation scenes under various sea conditions and various tight conditions, the experimental test which is difficult to be carried out on the ship can be realized through the simulation experiment, so that the risk and cost of the real ship experiment are greatly reduced. The invention has the functions of state monitoring, fault diagnosis, auxiliary decision making, health management and the like, can realize the state health monitoring of all-weather shipboard equipment, can give an alarm in time when faults occur, and greatly reduces the potential safety hazard caused by the fact that the equipment faults cannot be found in time; the physical information of the real space is mapped in real time in the virtual space, so that a manager can grasp the current navigation state of the intelligent ship on a shore basis and apply control instructions to the intelligent ship.
Drawings
Fig. 1 is a schematic diagram of the present invention.
Fig. 2 is a flow chart of fault diagnosis in the present invention.
Fig. 3 is a flow chart of a model correction method of the present invention.
Fig. 4 is a schematic diagram of the operation of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The invention designs and completes an intelligent ship state monitoring and controlling method based on digital twinning, and fig. 1 is a diagram of an intelligent ship digital twinning system structure of the invention, and as shown in fig. 1, the intelligent ship digital twinning system designed by the invention can be seen to be mainly divided into five modules, including a resource layer, a communication layer, a model layer, a service layer and an application layer.
The resource layer comprises a computing resource, an algorithm resource, a digital model library and an entity console.
Computing resources refer to the processors, memory, and computer storage media required by the digital twin system program of the present invention when running. The memory is used to store a computer program and the computer storage medium stores computer executable instructions that, when executed by the processor, implement the various functions of the digital twin system.
The algorithm resource refers to various algorithms stored in a computer and used for realizing various preset functions of the digital twin system, such as a rolling time domain estimation algorithm used for processing signals collected by a sensor, a model prediction control algorithm used for predicting future sailing conditions of the intelligent ship, a parameter identification algorithm matched with degradation of each part of the intelligent ship due to long-term operation, and the like.
The digital model library comprises an environment model, a mechanism model, an operation control model and a whole process operation and maintenance model of the intelligent ship under different sea conditions and different operation scenes. When the sea condition of the intelligent ship is changed or the operation mode is changed, the intelligent ship digital twin system can switch different models in time to match the environment or the operation mode of the current real-space intelligent ship.
The entity console comprises various communication equipment, display equipment, manipulation equipment and the like, wherein the communication equipment is used for information transmission, instruction transceiving between a real ship and a shore-based digital twin body; the display device is used for three-dimensional scene display, information input window, video, chart display and the like of the digital twin body; the control equipment is a ship cab console at the shore base end and is used for giving a control instruction to the twin model, the twin model receives the control instruction and then carries out simulation, and the control instruction is transmitted to the real ship through the communication equipment to drive the real ship to carry out synchronous movement.
And the communication layer is used for data acquisition, data processing, data storage and data transmission.
The data acquisition is to acquire the relevant state information of the intelligent ship and necessary feedback physical quantity information in real time, realize the pretreatment and buffering of the front end of the information, realize the dynamic acquisition, buffering and pretreatment of the environmental information such as wind, wave, current and the like, and simultaneously realize the dynamic detection and identification of the sea surface targets around the operation area of the intelligent ship, wherein various result information of environmental perception is used as a reference basis for comprehensive decision. The position, heading and speed information of the intelligent ship are acquired through the GPS and the log, the attitude information of the intelligent ship is measured through an attitude sensor, the wind field of the ocean surface is observed through a scatterometer, the wave field of the ocean surface is observed through a spectrometer, the flow field of the ocean surface is observed through a synthetic aperture radar, and the like.
The data processing refers to processing all state quantities of the intelligent ship acquired by the sensor through a filtering algorithm, including wild point elimination, sensor correction, noise point filtering, decoupling dimension reduction, and estimating some state quantities which are not measurable in practice.
When the intelligent ship operates at sea, in order to apply accurate control commands to the intelligent ship, the navigation safety is ensured, the task is completed smoothly, and the state of the intelligent ship and the surrounding environment are required to be accurately acquired. Interference noise is usually generated in the measuring process of the sensor, the collected data needs to be filtered and noise reduced, and the common Gaussian noise can be processed by Kalman filtering. However, sometimes, the conventional kalman filter will fail due to sensor failure, human operation error, large nonlinear gaussian noise occurring in steady state measurement, etc., and serious consequences will be caused if the manager takes control instructions according to the large deviation measurement value. Therefore, the invention provides a brand new filtering algorithm, namely rolling time domain estimation, which mainly comprises four steps:
step one: acquiring the position, the gesture and the operation input signals of the intelligent ship through sensors;
step two: solving the following optimization function by adopting a nonlinear programming tool package:
in the method, in the process of the invention,for the state quantity to be estimated of the intelligent ship, < >>For the state prior predicted value, N is the rolling time domain window length, where the performance index function is:
in the method, in the process of the invention,representing the output equation, alpha.gtoreq.0 and beta k > 0 is a weight parameter used to weigh the confidence in state prior predictions or sensor measurements. The larger alpha represents the more reliable the state prior predicted value, beta k Larger indicates more reliable measurement values. Since the rolling horizon estimation is based on optimization, it is well suited for scenarios with state constraints and nonlinearities. In consideration of physical and practical significance, the state variables of the intelligent ship in the solving process need to satisfy the constraint:
in the method, in the process of the invention,representing the equation of state, u i Representing manipulation input signals, X representing objective facts that each state quantity needs to satisfy;
step three: solving the formula (1) to obtainSince the solution objective function is obtained by the state estimation value at the time t-N, the state estimation value at the current time needs to be obtained by applying the recursive calculation of the formula (4):
step four: and (3) propagating a state priori predicted value to the next moment, and repeating the second to fourth steps when a measurement signal of the next moment arrives, wherein the state priori predicted value propagation method comprises the following steps:
the data storage means that an intelligent ship navigation and operation state historical information database of all equipment on the ship is built, and key historical information, early warning information, abnormal fault information, processing events and other information in the intelligent ship navigation and operation process of all the equipment are completely recorded and used for tracing and maintaining the system state.
The data transmission aims to realize efficient interaction of ship-shore information, and the problems of light weight, transmission stability, information safety and the like of the information are mainly solved. Information weight reduction starts from many aspects: for the intelligent ship and the state and parameter information of all equipment on the ship, the final integrated vectorized information is transmitted, the transmission frame rate is controlled in a reasonable range, and the information quantity is ensured to be compressed to the greatest extent; the information such as control commands and mode switching downloaded by the shore is lightweight information itself. The transmission stability and the information security are ensured by the communication protocol and the encryption processing.
Model layers including environmental models, mechanism models, operational control models, and whole process operation and maintenance models.
The environment model is used for constructing an environment digital twin body according to sea condition environment, meteorological information and sea surface targets. The wind disturbance model is calculated by combining the wind disturbance force model and the ocean surface wind field obtained by the scatterometer; the wave interference model is calculated by combining the wave propagation model with the sea surface wave field observed by the spectrometer; the method comprises the steps of obtaining a water flow interference model through combining a hydrodynamic model calculation by using a marine surface flow field observed by a synthetic aperture radar; sea surface targets are observed through radar, AIS and visual image technologies. And according to the obtained air disturbance model, wave disturbance model, water flow disturbance model and sea surface target object, calculating to obtain an environment digital twin model, and restoring the environment state of the real space in the digital space to realize the real-time mapping of the real environment in the digital space.
The mechanism model is a twin model which is established with high fidelity, high precision and high operation efficiency based on the operation principle. By analyzing the operation performance of each component and the whole system of the intelligent ship, the mechanism model established by combining with the knowledge of various aspects such as hydrostatic, hydrodynamic and structure can be well consistent with the operation process of the actual system, and the operation performance of the actual system can be highly restored.
The operation control model is used for designing different control methods for different navigation tasks and different sea conditions of the intelligent ship to meet the operation requirements. If the current navigation state of the intelligent ship and the model parameters are completely known, a model prediction controller can be called to realize the navigation control of the intelligent ship and the prediction of the future navigation state; if the change of the marine environment in the sailing process of the intelligent ship is severe, the hydrodynamic coefficient of the intelligent ship is changed, the self-adaptive controller can be called, and the adaptation to the surrounding environment is realized and controlled by on-line identification and change of the parameters of the controller; and if the model parameters are difficult to determine, calling a fuzzy controller and a neural network controller to control the intelligent ship.
The construction of the whole process operation and maintenance model is used for guaranteeing the stable operation of all equipment of the intelligent ship. The whole process operation and maintenance model mainly comprises fault management and performance management. The fault management comprises the functions of detecting equipment faults, rapidly positioning, isolating fault points, repairing and the like; performance management refers to timely discovery of device performance bottlenecks, which are eliminated before user perception and failure.
The whole process operation and maintenance model is constructed by adopting a model driving and data driving fusion method. Firstly, constructing a digital twin initial model by adopting a model driving method based on a mechanism model of each device; and secondly, based on the initial model, different data are fused, such as actual sensor data, fault data, historical operation data and the like, the initial model is corrected in real time, so that the model has the behavior characteristics of accurate monitoring, fault diagnosis, performance prediction and control optimization, and further an operation dimension digital twin body is formed.
And the service layer is used for state monitoring, fault diagnosis, auxiliary decision making and health management.
The state monitoring refers to mapping the intelligent ship state information processed by the rolling time domain estimation method and the surrounding marine environment in real time through a multi-means visual interface of the digital twin system, so as to be referred by a manager. The multi-means visualization means that a plurality of means such as three-dimensional visualization scenes, parameters, curves, charts, graphs, monitoring videos and the like are designed for monitoring. The intelligent ship state information comprises position, course, navigational speed, host rotational speed, operation conditions of various devices of a cab, a cabin and a cargo warehouse, and the like; the surrounding marine environment includes other vessels, obstacles, meteorological conditions, water depth, water flow velocity and direction, and the like.
The fault diagnosis is to establish a fault diagnosis model according to fault data of each functional area in the operation process of the intelligent ship, realize fault prediction and alarm of each module of the intelligent ship according to the fault diagnosis model, and the whole fault diagnosis flow is shown in figure 2. For example, the fault diagnosis of the engine is to record and analyze the maintenance and fault data of the same batch of engines to form a fault mode, inject the fault mode into an initial model, continuously compare the fault mode with the engine measurement data in actual operation, and extract similar fault mode prediction faults. The engine performance model in the digital space and the fault data are fused to generate a fault diagnosis model to realize the prediction of engine faults, the types of engine faults are numerous, including gas paths, vibration, lubricating oil and the like, and the monitoring system can monitor main working parameters of the engine, such as rotating speed, pressure ratio, exhaust temperature, fuel flow, lubricating oil quantity, lubricating oil pressure difference and the like, and alarm the system when the threshold value is exceeded. In addition, the fault modes of the historical engines in the same batch are integrated into the model, and when the system measurement parameters exceed the threshold value, the system measurement parameters are matched with the fault modes to perform fault diagnosis.
The auxiliary decision-making is to construct an artificial intelligence based command auxiliary decision-making system, collect historical data of the intelligent ship operation process, form a knowledge base of the intelligent ship operation process for each scene and guide a manager to issue instructions.
The health management is to analyze the performance degradation of each part after long-term operation according to a mechanism model established by each device of the intelligent ship, and adjust model parameters to match the degraded physical object model. Because the marine environment is complex, the intelligent ship can often run under the environment with severe conditions, and each part of the intelligent ship can be corroded by seawater, so that equipment faults and performance degradation are inevitably caused. When the performance of the real object is degraded, the original twin model for synchronizing the state of the system generates deviation, and the model needs to be optimally managed, so that the twin model needs to be synchronized with the physical real object in real time in the running process of the system. And identifying performance degradation and fault diagnosis through a digital twin technology, and simultaneously carrying out online correction on the mirror image model to ensure that the states of the model and the real object are synchronous.
The method for online correction of the twin model is shown in fig. 3: firstly, initializing a correction coefficient, and transmitting the correction coefficient into a model to obtain model operation data under corresponding working conditions. And correcting the parameter model in the running process of the actual physical system by collecting the correction coefficient set in the correction model, comparing errors between test data and model data, outputting the obtained correction coefficient if the set error range is met, obtaining a new group of correction coefficients through an optimization algorithm if the errors are larger than the set range, bringing the correction coefficients into the model, and repeating the process until the correction coefficient meeting the error range is obtained, thereby obtaining the model in the corrected digital twin system.
And the application layer is used for human-computer interaction simulation, multi-working-condition simulation, immersion simulation and operation and maintenance simulation.
The man-machine interaction simulation is based on scene reconstruction information, supports multi-means man-machine interaction, and comprises equipment selection and basic operation interaction directly in a three-dimensional scene, and instruction input interaction based on an information window and function buttons.
The scene reconstruction is that the state information of the intelligent ship and the surrounding sea state information measured by the sensor are filtered and then transmitted to the digital twin system, and the current real scene information is displayed in real time by a three-dimensional display interface, and the scene reconstruction comprises the following steps:
step one: receiving dynamic shipborne information and sea state information in real time through a data transmission module of a communication layer;
step two: based on the received shipborne information and sea state information, supporting according to detailed static information of each device, including device parameters, a three-dimensional model and a layout structure, and organically superposing the static information and the dynamic information through geometric space constraint to restore real-time scene information in a dynamic scene in real time;
step three: based on the driving of the scene information reconstruction result, three-dimensional view software is developed, scene changes corresponding to different subsystems are supported, the changes of the states and parameters of each motion device are reflected in real time, real-time three-dimensional rendering is carried out, the dynamic roaming of the scenes and the visual superposition display of key parameters are supported, and the clear and complete intelligent ship state is displayed for users.
The development of three-dimensional view software comprises three-dimensional modeling and scene terrain modeling of an intelligent ship by using multi-gen Creator software, configuration of a simulation environment by using Vega Prime software, and development of an application program by using Visual Studio software based on an MFC framework.
The Multigen Creator software performs three-dimensional modeling and scene terrain modeling of the intelligent ship, and in order to increase the authenticity of the visual effect of the three-dimensional model, the material technology, the light source technology and the texture technology provided by the Multigen Creator are required to be used. In order to improve the rendering speed and fluency of the three-dimensional model in the visual simulation system, the created three-dimensional model needs to be optimized, including adjusting the hierarchical structure of the model database, deleting redundant polygons, and deleting polygons invisible in the view points.
The Vega Prime software is used for configuring simulation environments, including marine environment setting, common special effect setting, multi-channel display setting and the like. In order to make the simulation environment more vivid, the invention renders the ocean in the simulation environment in real time according to the sea state information measured by the current real ship, and simulates special effects such as ground wave generated by the interaction of the three-dimensional model of the intelligent ship and the virtual ocean. In order to comprehensively observe the state of the current intelligent ship, the invention is provided with a plurality of visual angles and a plurality of channels for observing the current navigation state of the intelligent ship and the information of equipment on the ship.
The Visual Studio software develops an application program based on the MFC framework, and scene rendering, model driving and man-machine interaction are completed. Scene rendering is the core of a simulation system and mainly comprises five links of initialization, definition, configuration, frame circulation and closing. The model driving comprises simulation operation and model position and posture updating, wherein the simulation operation is based on a current intelligent ship physical model, state information and control input, and the state information of the intelligent ship at the next moment is calculated through a specified algorithm; the model position and posture updating means that the state of the intelligent ship is updated based on the result of the simulation operation. The man-machine interaction means that various visual interfaces such as a three-dimensional visual scene, parameters, curves, charts, graphs, monitoring videos and the like can be seen in real time through the visual simulation software, the operation instructions of the virtual ship in the visual simulation software can be mapped to the intelligent ship in the real world in real time, the same operation instructions are controlled to be executed, and the state monitoring of the intelligent ship in the real world is realized through the three-dimensional visual scene.
The multi-working condition simulation is to construct simulation deduction virtual scenes under various sea condition environments and various working modes. The ocean environments of ten different levels of sea conditions of 0-9 levels are respectively constructed in the visual simulation software, various complex scene areas are simulated, and simulation tests can be carried out on different scene areas aiming at different operation tasks of the intelligent ship. Because the marine situation is complicated, the test of each function of intelligent ship needs to build different boats and ships scenes, and high cost and current test platform can't satisfy this test condition. The multi-working condition simulation virtual experimental field built by the invention greatly reduces the cost of the intelligent ship performance test real ship experiment, and the virtual simulation is carried out before the water under each function is verified, thereby facilitating the initial problem investigation and performance optimization.
The immersive simulation is to introduce a three-dimensional virtual reality engine technology, a multichannel video output technology, a virtual person driving technology, a Kinect somatosensory interaction and roaming technology into an intelligent ship digital twin simulation system, and construct an immersive intelligent ship virtual reality for operation management staff in visual, auditory and interaction modes. The immersive simulation can fully exert the perception and cognition capability of the person on the contacted things, acquire various spatial information and logic information contained in the virtual environment in an omnibearing manner, and help inspire the thinking of an operation manager.
The operation and maintenance simulation is to simulate and deduce the health state of the intelligent ship according to the whole process operation and maintenance model established by the equipment of the intelligent ship. First, the health status of each device of the intelligent ship is obtained. And secondly, simulating the loss of each device caused by the intelligent ship under various working conditions. Finally, the performance bottlenecks that may occur for each device are predicted and optimization suggestions are given.
As shown in fig. 4, the intelligent ship state monitoring and controlling method based on digital twin operates according to the following principle:
and (3) carrying out state monitoring and control on the intelligent ship based on a digital twin technology. First, to enable status monitoring, current smart boat status information and ambient information needs to be acquired, which requires relevant measurements by various sensors. The data measured by the sensor are coupled with various states, and sometimes the measured data have larger deviation due to equipment failure. The processed information is transmitted into a core data management and decision module of the intelligent ship, and the module is responsible for storing, distributing, processing, issuing instructions and the like of the information. The filtered information can be displayed through a comprehensive visual interface on the ship, and the information is transmitted through a ship-shore information exchange module. Meanwhile, according to the current operation task of the intelligent ship, a reference control input is provided under the support of a knowledge base and a model base, and finally a control instruction is issued by a manager. And the shore-based digital twin system receives the intelligent ship state information, the surrounding sea state information and the control instruction information, and calls the three-dimensional scene model library to carry out real-time three-dimensional scene dynamic reconstruction in the intelligent ship navigation process. The shore-based digital twin system not only can realize multi-view three-dimensional scene display, but also provides various visual interaction means such as parameters, curves, charts, graphs, monitoring videos, information input windows and the like. The shore manager can know the current navigation state of the intelligent ship, the equipment information of the ship, the marine environment around the ship and the like in detail through the visual interface, so that the state of the intelligent ship can be remotely monitored. And secondly, a shore manager can apply a control instruction through a man-machine interaction interface, the motion state of the virtual ship after receiving the control instruction can be displayed through a three-dimensional visual simulation interface, and the control instruction is transmitted to an actual ship through a ship shore information interaction module to control the actual ship to perform synchronous motion. In addition, the functions of inquiring historical states of equipment on a ship, analyzing health conditions, checking and updating a system database and the like can be realized through the shore-based comprehensive maintenance module.
Compared with the prior art, the invention has the beneficial effects that: the invention constructs the digital twin system of the intelligent ship, realizes the real-time mapping of physical information of the real space in the virtual space, so that a manager can master the current navigation state of the intelligent ship on a shore basis and apply control instructions to the intelligent ship; according to the invention, the ship navigation scene under various sea conditions and various compaction conditions is constructed, and the experimental test which is difficult to be carried out on the ship can be realized through the simulation experiment, so that the risk and cost of the real ship experiment are greatly reduced; the intelligent ship digital twin system constructed by the invention has the functions of state monitoring, fault diagnosis, auxiliary decision making, health management and the like, can realize the state health monitoring of all-weather ship equipment, can give an alarm in time when a fault occurs, and greatly reduces the potential safety hazard caused by the fact that the equipment fault cannot be found in time; the invention discloses a rolling time domain estimation method which can finish the functions of correcting sensor acquired data, decoupling dimension reduction, wild point elimination and the like, and improves the monitoring precision of the state of an intelligent ship and a complex offshore environment; the invention also designs different advanced control methods aiming at different navigation tasks of the intelligent ship, which are used for guiding the intelligent ship to complete complex offshore operation tasks.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. An intelligent ship state monitoring and control system based on digital twinning is characterized in that: the system comprises a resource layer, a communication layer, a model layer, a service layer and an application layer;
the resource layer comprises computing resources, algorithm resources, a digital model library and an entity console;
the communication layer is used for realizing data acquisition, data processing, data storage and data transmission;
the model layer comprises an environment model, a mechanism model, an operation control model and a whole process operation and maintenance model; the environment model is an environment digital twin body constructed according to sea condition environment, meteorological information and sea surface targets,
the service layer is used for state monitoring, fault diagnosis, auxiliary decision making and health management; the health management is to analyze the performance degradation of each part after long-term operation according to a mechanism model established by each device of the intelligent ship, and adjust model parameters to match the degraded physical object model;
the application layer is used for realizing man-machine interaction simulation, multi-working condition simulation, immersion simulation and operation and maintenance simulation.
2. A digital twinning-based intelligent vessel condition monitoring and control system according to claim 1, wherein: the data processing is to process all state quantities of the intelligent ship acquired by the sensor through a filtering algorithm, including wild point elimination, sensor correction, noise point filtering, decoupling dimension reduction, and estimating some state quantities which are not measurable in practice;
the filtering algorithm adopts rolling time domain estimation and comprises the following steps:
step 1: acquiring the position, the gesture and the operation input signals of the intelligent ship;
step 2: solving the optimization function to obtain
In the method, in the process of the invention,the state quantity to be estimated at the t-N moment of the intelligent ship; />The state priori predicted value at t-N moment of the intelligent ship is obtained; n is the length of a rolling time domain window; the performance index function is:
where k=1, 2,..n+1;representing the output equation, alpha.gtoreq.0 and beta k > 0 is a weight parameter used to trade-off confidence in state prior predictions or sensor measurements, with larger a representing more reliable state prior predictions, β k Larger means more reliable measurement;
the intelligent ship state variable in the solving process needs to meet constraint:
in the method, in the process of the invention,representing the equation of state, u i Representing manipulation input signals, X representing objective facts that each state quantity needs to satisfy;
step 3: obtaining a state estimation value at the current moment by applying recursive calculation;
step 4: repeating the steps 2 to 4 when the propagation state priori predicted value reaches the next moment and the measurement signal at the next moment arrives; the state priori prediction value propagation method comprises the following steps:
3. a digital twinning-based intelligent vessel condition monitoring and control system according to claim 1, wherein: the construction method of the environment model comprises the following steps:
the wind disturbance model is calculated by combining the wind disturbance force model and the ocean surface wind field obtained by the scatterometer; the wave interference model is calculated by combining the wave propagation model with the sea surface wave field observed by the spectrometer; the method comprises the steps of obtaining a water flow interference model through combining a hydrodynamic model calculation by using a marine surface flow field observed by a synthetic aperture radar; observing sea surface targets through radar, AIS and visual image technologies; and according to the obtained air disturbance model, wave disturbance model, water flow disturbance model and sea surface target object, calculating to obtain an environment digital twin model, and restoring the environment state of the real space in the digital space to realize the real-time mapping of the real environment in the digital space.
4. A digital twinning-based intelligent vessel condition monitoring and control system according to claim 1, wherein: the entity console comprises a communication device, a display device and a manipulation device; the communication equipment is used for information transmission and instruction receiving and transmitting between the intelligent ship and the shore-based digital twin body; the display device is used for three-dimensional scene display, information input window, video and chart display of the digital twin body; the control equipment is a ship cab console at the shore base end and is used for giving a control instruction to the twin model, the twin model receives the control instruction and then carries out simulation, and the control instruction is transmitted to the real ship through the communication equipment to drive the real ship to carry out synchronous movement.
5. A digital twinning-based intelligent vessel condition monitoring and control system according to claim 1, wherein: the operation control model is used for designing different control methods for different navigation tasks and different sea conditions of the intelligent ship by the pointer to meet the operation requirements; if the current navigation state and model parameters of the intelligent ship are completely known, calling a model prediction controller to realize navigation control of the intelligent ship and prediction of future navigation states; if the change of the marine environment in the sailing process of the intelligent ship is severe, the hydrodynamic coefficient of the intelligent ship is changed, the self-adaptive controller is called, and the adaptation to the surrounding environment is realized and controlled by on-line identification and change of the parameters of the controller; and if the model parameters are difficult to determine, calling a fuzzy controller and a neural network controller to control the intelligent ship.
6. A digital twinning-based intelligent vessel condition monitoring and control system according to claim 1, wherein: the whole process operation and maintenance model is constructed by adopting a model driving and data driving fusion method, which comprises the following steps:
firstly, constructing a digital twin initial model by adopting a model driving method based on a mechanism model of each device; and secondly, based on the initial model, different data including real-time sensor data, fault data and historical operation data are fused, and the initial model is corrected in real time, so that the model has the behavior characteristics of accurate monitoring, fault diagnosis, performance prediction and control optimization, and further a operation digital twin body is formed.
7. A digital twinning-based intelligent vessel condition monitoring and control system according to claim 1, wherein: the method for carrying out online correction on the twin model in the health management specifically comprises the following steps:
firstly, initializing a correction coefficient, and transmitting the correction coefficient into a model to obtain model operation data under corresponding working conditions; and correcting the parameter model in the running process of the actual physical system by collecting the correction coefficient set in the correction model, comparing errors between test data and model data, outputting the obtained correction coefficient if the set error range is met, obtaining a new group of correction coefficients through an optimization algorithm if the errors are larger than the set range, bringing the correction coefficients into the model, and repeating the process until the correction coefficient meeting the error range is obtained, thereby obtaining the model in the corrected digital twin system.
8. A digital twinning-based intelligent vessel condition monitoring and control system according to claim 1, wherein: the man-machine interaction simulation is based on scene reconstruction information, supports multi-means man-machine interaction, and comprises equipment selection and basic operation interaction directly in a three-dimensional scene, and instruction input interaction based on an information window and a function button; the scene reconstruction is that after the intelligent ship state information and surrounding sea state information which are measured by a sensor are filtered, the filtered information is transmitted to a digital twin system, and the current real scene information is displayed in real time by a three-dimensional display interface, and the scene reconstruction comprises the following steps:
step one: receiving dynamic shipborne information and sea state information in real time through a data transmission module of a communication layer;
step two: based on the received shipborne information and sea state information, supporting according to detailed static information of each device, including device parameters, a three-dimensional model and a layout structure, and organically superposing the static information and the dynamic information through geometric space constraint to restore real-time scene information in a dynamic scene in real time;
step three: based on the driving of the scene information reconstruction result, three-dimensional view software is developed, scene changes corresponding to different subsystems are supported, the changes of the states and parameters of each motion device are reflected in real time, real-time three-dimensional rendering is carried out, the dynamic roaming of the scenes and the visual superposition display of key parameters are supported, and the clear and complete intelligent ship state is displayed for users.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310831387.4A CN116931448A (en) | 2023-07-07 | 2023-07-07 | Intelligent ship state monitoring and control system based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310831387.4A CN116931448A (en) | 2023-07-07 | 2023-07-07 | Intelligent ship state monitoring and control system based on digital twin |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116931448A true CN116931448A (en) | 2023-10-24 |
Family
ID=88374889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310831387.4A Pending CN116931448A (en) | 2023-07-07 | 2023-07-07 | Intelligent ship state monitoring and control system based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116931448A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118171395A (en) * | 2024-05-13 | 2024-06-11 | 浙江大学海南研究院 | Digital twin system for unmanned sailing boat performance analysis |
-
2023
- 2023-07-07 CN CN202310831387.4A patent/CN116931448A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118171395A (en) * | 2024-05-13 | 2024-06-11 | 浙江大学海南研究院 | Digital twin system for unmanned sailing boat performance analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110221546B (en) | Virtual-real integrated ship intelligent control system test platform | |
| US11774485B2 (en) | Fault diagnosis method and apparatus for submarine cable, and device | |
| CN109766878A (en) | A kind of method and apparatus of lane detection | |
| CN114584571B (en) | Space calculation technology-based digital twin synchronous communication method for power grid station | |
| US5126978A (en) | Undersea data collection, analysis, and display system | |
| CN102663921A (en) | Multi-channel and multi-screen three dimensional immersion simulation system of ship steering and operation | |
| Fonseca et al. | A standards-based digital twin of an experiment with a scale model ship | |
| CN116931448A (en) | Intelligent ship state monitoring and control system based on digital twin | |
| US11475551B2 (en) | System and method of operation for remotely operated vehicles for automatic detection of structure integrity threats | |
| Minami et al. | Development of the Comprehensive Simulation System for Autonomous Ships | |
| My et al. | An Artificial Neural Networks (ANN) Approach for 3 Degrees of Freedom Motion Controlling | |
| CN113656918B (en) | Four-rotor simulation test method applied to finished product overhead warehouse scene | |
| CN113345095B (en) | System based on digital twin revolutionary relic damage monitoring and early warning method | |
| KR20230143444A (en) | System and method for estimating drift path of marine floating body | |
| Ridao et al. | Graphical simulators for AUV development | |
| Liu et al. | Trajectory risk cognition of ship collision accident based on fusion of multi-model spatial data | |
| CN117768626B (en) | Patrol system based on digital twinning | |
| Wu et al. | Research on the Application of Digital Twin Technology in the Structural Safety Assessment of Deep-Water Semi-Submersible Platforms | |
| Fonseca | A Standards-Based Approach to Modelling of Digital Twin Ship Data-Assessment of current standards and methods for future standardisation | |
| Parola et al. | Structural Damage Localization via Deep Learning and IoT Enabled Digital Twin. | |
| CN115468778B (en) | Vehicle testing method and device, electronic equipment and storage medium | |
| CN117708740A (en) | Multi-machine-field non-invasive zone alarm detection method in remote tower mode | |
| CN117826632A (en) | Digital twin system for deep sea mining | |
| KR102526736B1 (en) | Measurement system and method for measuring lng cargo | |
| Wang et al. | Intelligent situation awareness based on the fractal dimension and multidimensional reconstruction |
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 |