CN117311133A - Ship central control and security monitoring system based on simulation - Google Patents

Abstract

The invention discloses a ship central control and security monitoring system based on simulation, which comprises a redundant distributed control platform and a core control system, wherein the redundant distributed control platform is used for providing hardware support required by system operation and realizing system data acquisition, action execution driving, power supply and communication; the core control system comprises a liquid cargo monitoring system, a cabin monitoring system, a safety monitoring system and a simulation test system, wherein the simulation test system simulates actual equipment operation by establishing a simulation prediction model of the equipment, and generates a test scene library for direct calling during testing, so that simulation and verification of control logic of functions of the liquid cargo monitoring system, the cabin monitoring system and the safety monitoring system are realized. And the simulation test system is used for verifying simulation and control logic of functions of the liquid cargo monitoring system, the cabin monitoring system and the safety monitoring system. The invention realizes the simulation and test verification of the whole flow operation process of the central control and security monitoring system through a digital virtual simulation technology.

Description

Ship central control and security monitoring system based on simulation

Technical Field

The invention relates to ship control, in particular to a ship central control and security monitoring system based on simulation.

Background

The existing ship central control and security monitoring system based on simulation provides a manual operation mode, an operator manually controls related equipment and operation through buttons of an interface, a new shipman does not have a high-precision simulation test system before boarding to train the shipman, the operation of a complex operation process brings high requirements to the operator, and certain safety risks exist. Therefore, a system and a high-precision simulation system capable of realizing automatic operation are needed to improve the convenience, reliability and safety of the LNG ship operation.

For example, a distributed monitoring alarm and control system for a ship disclosed in chinese patent No. CN107807567a provides a distributed monitoring alarm and control system for a ship for system architecture and communication, for example, an intelligent ship comprehensive information redundancy monitoring system disclosed in chinese patent No. CN111614502B provides a data comprehensive data redundancy monitoring solution for an intelligent ship, but none of the above patents relates to operation simulation training.

Disclosure of Invention

The invention aims to provide a ship central control and security monitoring system based on simulation, which realizes the simulation and verification of control logic of functions of a liquid cargo monitoring system, a cabin monitoring system and a safety monitoring system, is convenient for training operators, and solves the problems of low efficiency and high error rate of manually setting scene parameters in the past.

The technical scheme for realizing the purpose of the invention is as follows: the ship central control and security monitoring system based on simulation comprises a redundant distributed control platform and a core control system, wherein the redundant distributed control platform is used for providing hardware support required by system operation and realizing system data acquisition, action execution driving, power supply and communication; the core control system comprises a liquid cargo monitoring system, a cabin monitoring system, a safety monitoring system and a simulation test system, wherein:

the liquid cargo monitoring system is used for realizing the whole flow control of cargo loading, cargo unloading, cargo storage, cargo transportation and cargo unloading;

the cabin monitoring system is used for realizing power distribution and equipment automatic control of the whole ship;

the safety monitoring system is used for realizing the safe operation of each system and equipment of the LNG ship;

the simulation test system simulates the operation of actual equipment by establishing a simulation prediction model of the equipment, generates a test scene library for direct calling during testing, and realizes the verification of simulation and control logic of functions of the liquid cargo monitoring system, the cabin monitoring system and the safety monitoring system.

Further, the redundant distributed control platform comprises an operation station, a control station, a remote IO station, a power station and a network station; the operation station is used for operator monitoring and human control of field devices and is connected with the control station through a redundant Ethernet; the control station is used for providing control, monitoring and alarming of the system, is connected with the remote IO station through an internal IO bus, the remote IO station is used for providing input and output signal management of the system, the power station adopts redundant power supply configuration and is used for providing redundant power supply, and the network station is used for communication between devices.

Further, the operation station is provided with a real-time monitoring device, supports one machine with multiple screens, provides a monitoring interface for control grouping, an operation panel, diagnosis information, trend, alarm information and system state information, can acquire process information and event alarm through an operator station, performs real-time control on field equipment, directly acquires real-time data from a control station, and sends an operation command to the control station.

Further, the control station comprises a redundant CPU module, a remote I/O bus module, a power module and a vertical cabinet, and each control station is installed in a cargo distribution room, an engine room, a high-voltage distribution room and a low-voltage distribution room in a distributed mode.

Further, the remote IO station comprises a remote I/O bus module, an I/O module, a power module and a vertical cabinet, and each remote I/O control station is installed in an engine room, a high-voltage distribution room, a low-voltage distribution room and a storage room in a distributed mode.

Further, the network station provides RS485, profibus DP and NMEA communication, and simultaneously provides 5 sets of network plugs distributed at each position of the ship, and each set consists of two redundant Ethernet ports.

Further, the equipment in the simulation test system comprises a cargo hold, a liquid cargo pump, an LD/HD compressor, a gas combustion unit, a reliquefaction device and a generator; the test scene library comprises a test scene library of a cabin monitoring system and a test scene library of a liquid cargo monitoring system, wherein the test scene library of the cabin monitoring system comprises air pressure constant, steam pressure constant, liquid cargo system power supply and cabin system power supply, and the test scene library of the liquid cargo monitoring system comprises liquid cargo tank drying inerting, spray precooling, liquid cargo loading, cargo sailing, liquid cargo unloading, gas dispelling and degassing.

Furthermore, the simulation test system realizes the verification of simulation and control logic of functions of the liquid cargo monitoring system, the cabin monitoring system and the safety monitoring system through a simulation prediction model and a particle swarm optimization method based on a neural network based on a data model and a test scene library of equipment.

Further, the neural network structure comprises 4 parts, namely an input layer, a hidden layer, an output layer and an output layer, wherein during training, an input variable is transmitted into the hidden layer, the input variable is transmitted into the next output layer through the weight of a connecting node, the output of the upper layer is the input of the next layer, the output layer is weighted and summed, then the output layer is converted into a final output variable coupling force according to a nonlinear equation, then training set data are normalized, a neural network and network parameter configuration are constructed, meanwhile, test set data are normalized, finally, error calculation is carried out on a prediction result inverse normalization and a simulation output variable, and error comparison is carried out on a prediction value of a test set and corresponding operation data to judge whether requirements are met.

Further, the simulation prediction model specifically comprises:

β _t ＝g _t (β _t-1 ，γ)

wherein Y(s) is the observed value obtained at the input spatial variable s in the system, N is the total number of kernel components, ε is Gaussian random noise, w _i (s) a non-negatively weighted kernel, f _i (s)＝(f _i1 (s)，…，f _ip (s)) ^T Is a set of known basis functions, beta _t Is the vector of model parameters g _t (. Cndot.) is a nonlinear evolution model, and γ is process noise.

Compared with the prior art, the invention has the remarkable advantages that:

(1) By establishing an operation data simulation model of the equipment, the problems of high modeling difficulty and low precision of the mechanism of the reset equipment are solved, the self-adaptive capacity is high, any complex nonlinear relation is fully approximated, and the method is suitable for a multivariable system. The typical test scene libraries of the cabin monitoring system and the liquid cargo monitoring system are generated for direct calling during testing, so that the scene testing efficiency and the scene setting accuracy are greatly improved, and the problems of low efficiency and high error rate of manually setting scene parameters in the past are solved;

(2) The redundant distributed control platform is designed, so that the data acquisition of field equipment, the driving of an actuating mechanism and the power supply and communication of the whole system are realized, the safety performance of the ship is improved, the accident risk is reduced, the management efficiency of the ship is improved, and the safety of crews and the ship is ensured through the redundant design.

The invention is described in further detail below with reference to the accompanying drawings.

Drawings

FIG. 1 is a schematic diagram of a simulation-based marine central control and security monitoring system in one embodiment.

FIG. 2 is a schematic diagram of a redundant distributed control platform in one embodiment.

FIG. 3 is a schematic diagram of a liquid cargo monitoring system in one embodiment.

Fig. 4 is a schematic diagram of a cargo handling module in one embodiment.

FIG. 5 is a schematic diagram of a gas management module in one embodiment.

FIG. 6 is a schematic diagram of an overload control module according to an embodiment.

FIG. 7 is a schematic diagram of a weir heating control in one embodiment.

Fig. 8 is a full-automatic switching control logic diagram of a redundant device.

FIG. 9 is a diagram of a genetic algorithm tuning PID control architecture.

Fig. 10 is a logic diagram of heavy oil/light oil switching control of the starboard side host fuel supply pump inlet three-way valve.

Fig. 11 is a logic diagram of heavy oil/light oil switching control of the starboard side main engine fuel supply pump return three-way valve.

FIG. 12 is a schematic diagram of the simulated test system components in one embodiment.

FIG. 13 is a flowchart of an algorithm for optimizing a neural network model particle swarm in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

In one embodiment, in conjunction with FIG. 1, a simulation-based marine central control and security monitoring system is provided, comprising a redundant distributed control platform and an intelligent cargo management platform;

the redundant distributed control platform provides hardware support of an operation station, a control station, a power supply station and a network station and is used for realizing data acquisition of field devices, driving of an actuating mechanism and power supply and communication of the whole system;

the core control system is used for real-time on-line monitoring and control of cargo loading, gas management, insulation space protection and ballast control, has the functions of monitoring, alarming and controlling, and realizes the full-flow control of cargo loading, storage, transportation and unloading of LNG ships.

Further, in one embodiment, in conjunction with fig. 2, the redundant distributed control platform includes an operation station, a control station, a remote IO station, a power station, and a network station; the operation station is connected with the control station through a redundant Ethernet; the control station is connected with the remote IO station through an internal IO bus.

The operating stations OS01, OS11, OS12, OS13, OS21, OS22 and OS23 are provided with real-time monitoring software, support high-resolution display, support one-machine multi-screen, and provide monitoring interfaces for control packets, operation panels, diagnosis information, trends, alarm information, system state information and the like. The operator station can acquire process information and event alarms and control the field device in real time. The operator station obtains real-time data directly from the control station and sends operating commands to the control station.

The control stations AFS03, AFS04, AFS05, AFS06, AFS07, AFS08, AFS10, AFS11, AFS12 and AFS13 comprise redundant CPU modules, remote I/O bus modules, power modules, vertical cabinets and other devices for providing control, monitoring and alarm of the system. Each site control station is distributed and installed at the positions of a goods distribution room, an engine room, a high-voltage distribution room, a low-voltage distribution room and the like.

The remote IO stations AFS01, AFS02, AF03, AF14, AF15, AF16 and AF17 comprise equipment such as a remote I/O bus module, an I/O module, a power module, a vertical cabinet and the like and are used for providing input and output signal management of the system. Each remote I/O control station is distributed and installed at the positions of an engine room, a high-voltage distribution room, a low-voltage distribution room, a storage room and the like. The remote IO stations AFS01, AFS02 and AFS09 are communicated with the control stations AFS04, AFS06 and AFS05 through redundant Ethernet respectively, and the remote IO stations AFS14, AFS16 are communicated with the control station AFS11 through redundant Ethernet; the remote IO stations AFS15 and AFS17 and the control station AFS13 realize communication through redundant Ethernet;

the power supply stations PDB01 and PDB02 adopt redundant power supply configuration, one path is 220V and 60HZ commercial power, the other path is 220V and 60HZ UPS power supply, redundant power supplies are provided for field devices such as an operation station, a control station, a remote IO station, a network station and the like, and when one path of power supply fails, the other path of power supply is automatically switched to ensure the safety of electricity consumption.

The network stations NDU01 and NDU02 provide RS485, profibus DP and NMEA communication, and simultaneously provide 5 sets of network plug VDU distributed at each position of the ship. Each group consists of two redundant Ethernet ports, and information monitoring is realized at each position of the ship.

The core control system comprises a liquid cargo monitoring system, a cabin monitoring system, a safety monitoring system and a simulation test system, wherein the liquid cargo monitoring system comprises a cargo loading and unloading module, a gas management module, an insulating space protection module and a ballast control module, so that the cargo loading and unloading, storage, transportation and unloading complete flow control is realized;

the cabin monitoring system comprises a power management system PMS and an auxiliary mechanical system, wherein the auxiliary mechanical system comprises a fuel oil system, a fuel gas system, a lubricating oil system, a seawater cooling system, a fresh water cooling system, a bilge system, an air system, a steam system and the like, so that comprehensive control and management of power supply, dispatching and consumption of the LNG carrier and monitoring of all system equipment are realized; the Power Management System (PMS) consists of four sets of generator sets, an emergency diesel generator, a circuit breaker and a distribution board; it should be noted that the components of the auxiliary machine system and the power management system are prior art and are not described in detail herein

The safety monitoring system comprises a control method and a man-machine interface, wherein the control method comprises the steps of realizing emergency shutdown triggering/resetting control of an emergency shutdown system ESD, realizing liquid cargo tank protection control, realizing ESD test control, realizing ESD shielding control, realizing override control and realizing offshore/harbor switching control; the man-machine interface comprises a user operation interface and a monitoring interface, and is used for realizing online operation and control information display comprising the modules, displaying the liquid level and the pressure of the LNG ship, checking alarm, shutting down conditions and shutting down equipment.

The simulation test system comprises a liquid cargo monitoring simulation system, a cabin monitoring simulation system and a safety monitoring simulation system, the actual equipment operation is simulated by establishing an equipment data model, a typical test scene library is generated for direct calling during testing, and the simulation and the verification of control logic of functions of the liquid cargo monitoring system, the cabin monitoring system and the safety monitoring system are realized.

Further, in one embodiment, in conjunction with fig. 3, the liquid cargo monitoring system includes a cargo handling module, a gas management module, an insulating space protection module, and a ballast control module, so as to implement cargo handling, storage, transportation, and unloading overall process control.

Further, in one embodiment, in conjunction with FIG. 4, the cargo handling module includes a handling operation control layer and a cargo equipment control layer;

the loading and unloading operation control layer is used for automatically controlling LNG loading, LNG unloading and BOG revetment control, and realizing the loading and unloading whole flow control of LNG ship cargoes.

The equipment control layer realizes equipment control of a liquid cargo pump, a cabin sweeping pump, an HD compressor, a related valve and the like; the control of the pump comprises manual start-stop control, automatic start-stop control and interlocking safety cut-off control of the pump; the control of the HD compressor comprises the start-stop control of the main motor of the HD compressor, the start-stop control of the auxiliary lubrication motor, the anti-surge control and the flow control; the control of the valve comprises position control, load control and pressure control of the valve; load control, namely indirectly realizing load control of the pump through opening control of the outlet valve; and (3) controlling the pressure, and controlling the pipeline pressure by adjusting the opening of the valve.

Further, in one embodiment, in conjunction with FIG. 5, the gas management includes sailing mode, cargo hold pressure control, equipment control layer;

the sailing pressure mode realizes the measurement of the pressure of the cargo hold through three modes of full absolute pressure, full relative pressure and ballast relative pressure.

The cargo hold pressure control realizes the protection of the cargo hold pressure and reduces the loss of cargoes by three BOG treatment methods of fuel supply, GCU reburning and ventilation mast emptying.

The device control layer realizes the control of devices such as a fuel pump, an LD compressor, a forced carburetor, a related valve and the like, provides driving support for automatic assembly and disassembly, and has the functions of local/remote automatic/remote manual mode, manual start/stop, automatic start/stop and interlocking safety cut-off.

Further, in one embodiment, in conjunction with fig. 6, the ballast control module includes ballast/de-ballast control, ballast equipment control.

The ballast/de-ballast control realizes that the ship is in good trim and trim states during departure, arrival, specific loading conditions or offshore handover by the liquid level control of the ballast tank according to the measurement of the draft, trim and trim of the ship by the third party system. The remote measurement system calculates the draft of the ship by using a trigonometric function relation through a bow and stern draft sensor, and the calculation steps are as follows:

step 1: mar=x1 (pv.lt 5491) + (I-4) E/16 d

Step 2: mav=x1+ (pv.lt 5490) + (I-4) E/16 d

Step 3: TAR=MAR+ [ (MAR-MAV)/L ]

Step 4: TAV = MAV- [ (MAR-MAV)/L2 ]

X1: distance between ultrasonic level transducer and base line (4 meters)

I: reading measured value (mA)

D: density (sea water 1.025)

E: upper limit in meters (sensor scale: e=20ma represents upper limit in meters, 4mA represents 0 meter)

L: design value 248 meters

L1: design value 21.7 meters

L2: design value 4.4 meters

MAV: measurement of bow draft

TAV: calculated vertical draft of bow

MAR: stern draft measurement

TAR: calculated stern vertical draft

Further, in one embodiment, in conjunction with FIG. 3, the remote measurement system calculates the vessel trim angle using trigonometric functions from the in starboard and port draft sensors. The calculation steps are as follows:

step 1: TNAα= (MATBD-MPS)/a

MSTBD: draft measurement in starboard ship

MPS: draft measurement in port

a: design value 43.35 meters

Step 2: and calculating the transverse inclination angle value through an inverse trigonometric function.

Further, in one embodiment, in conjunction with fig. 4, the remote measurement system calculates the trim angle of the ship by using trigonometric functions from the calculated draft of the bow and stern, and the calculation formula is as follows:

TNAγ＝(TAR-TAV)/(L+L1+L2)

l: design value 248 meters

L1: design value 21.7 meters

L2: design value 4.4 meters

TAV: calculated vertical draft of bow

TAR: calculated stern vertical draft

The measured and calculated draft, trim angle and trim angle of the ship are used for calculating the liquid level value of each ballast tank for maintaining the stability of the ship (the calculation of the liquid level value of the ballast tank is well known in the art and is not accumulated here), the liquid level value of the ballast tank is used for the liquid level control of the subsequent ballast tank, and the stability of the subsequent ship during loading and unloading of cargoes is ensured

The ballast equipment control realizes the control of equipment such as a ballast pump, related valves and the like, provides driving support for automatic ballasting/unloading, and has the functions of local/remote automatic/remote manual mode, manual starting/stopping, automatic starting/stopping and interlocking safety cut-off.

Further, in one embodiment, in conjunction with fig. 7, the insulation space protection includes inlet and outlet nitrogen pressure control of the barrier, cofferdam heating.

The inlet and outlet nitrogen pressure control module is used for controlling the inlet and outlet nitrogen pressure through the primary barrier and the secondary barrier, forming continuous nitrogen flow, preventing corrosion of the insulating space, and detecting leakage gas in each insulating space under the condition that the barrier is damaged and broken; the cofferdam heating control module comprises 10 sets of cofferdam temperature controllers and 8 sets of sleeve temperature controllers, temperature feedback is from temperature sensors arranged on the cofferdam and the sleeve, and the cofferdam is kept at a temperature not lower than +5 ℃ through the redundant cofferdam heating controllers. The inlet and outlet nitrogen pressure control module comprises a primary barrier pressure controller, a secondary barrier pressure controller and a standby pressure controller which are controlled by PID, the inlet and outlet nitrogen pressure measured value is used as a feedback value corresponding to the primary barrier pressure controller, the secondary barrier pressure controller and the standby pressure controller, the valves of the primary barrier pressure, the secondary barrier pressure and the standby pressure are controlled, and when the primary or secondary barrier valve fails, the standby pressure controller is connected with the failed primary barrier or secondary barrier through the regulating valve. .

According to the cofferdam heating system, the cofferdam is kept at a permanent environment temperature not lower than +5 ℃ through the redundant cofferdam heating controller, so that proper heat is provided for the cofferdam, the temperature is prevented from being reduced to below-40 ℃ when leakage occurs, and the steel hull is prevented from being damaged. The cofferdam heating control module comprises 10 sets of cofferdam temperature controllers and 8 sets of sleeve temperature controllers, temperature feedback is from temperature sensors arranged on the cofferdam and the sleeve, and the cofferdam is kept at a temperature not lower than +5 ℃ through the redundant cofferdam heating controllers.

The cabin monitoring system is characterized in that the redundant equipment is fully automatically switched, and in combination with fig. 8, the equipment is set to be in a 'remote automatic' state, the equipment enters a quasi-starting state, under the automatic state, the equipment 1 enters a starting running state through an external switching signal, and meanwhile, the system automatically detects and judges the state of the equipment 1 for a long time. Upon failure of the device 1, the device 2 enters an automatic start-up state, and the device 1 automatically stops in a speed-down mode. When the fault signal of the device 1 disappears, the next automatic start ready state is automatically entered via the system 3S confirmation.

The cabin monitoring system is based on the automatic modulation of the marine PMS frequency of the control Logix, a genetic algorithm setting PID control structure chart is shown in fig. 9, an upper-layer controller optimizes 3 parameters Kp, ki and Kd of the PID algorithm by using the genetic algorithm, the input is a difference value ef between the expected frequency and the current frequency of the generator, and the difference value ep between the expected power and the current power is output as the expected rotating speed of the generator. And calculating by an upper controller, designing a fitness function, ensuring the continuity and universality of the function, setting the maximum value of the fitness required by the PID function by using a genetic algorithm by taking the expected acceleration as a control quantity, and realizing the construction of an optimization algorithm for automatically adjusting the PMS frequency.

The adaptability is as follows:

wherein F is fitness and J is an objective function.

The objective function is:

wherein: w (w) ₁ 、w ₂ As the weight value, n _t Is the frequency.

Heavy oil/light oil switching control of the engine room monitoring system main engine fuel supply pump inlet three-way valve, in an automatic mode, the main engine fuel supply pump inlet three-way valve position is switched from a light oil level (opening 100%) to a heavy oil level (opening 0%), as shown in fig. 10:

1) The return three-way valve of the host fuel supply pump is switched to the supply pump position, and after the return three-way valve is fed back to the inlet three-way valve of the host fuel supply pump, the valve position of the inlet three-way valve of the valve host fuel supply pump is switched from the light oil level to the heavy oil level.

2) Switching of a host fuel circulation pump outlet three-way valve between heater and cooler positions

a. The viscosity of the host fuel is less than or equal to 5cST, and the outlet three-way valve of the host fuel circulating pump is switched from the heater position to the cooler position;

b. the viscosity of the host fuel is more than 5cST, and the three-way valve of the pump outlet of the host fuel circulating pump is switched from a cooler position to a heater position;

c. once the opening of the inlet three-way valve of the fuel supply pump of the host is not 100%, the three-way valve of the pump outlet of the fuel circulation pump of the host is switched from a cooler position to a heater position; namely, the situation that VIC6333/6343 is less than or equal to 5cST and the opening degree of the three-way valve at the inlet of the main engine fuel supply pump is not 100 percent exists

(2) In the automatic mode, the valve position heavy oil at the inlet of the valve main engine fuel supply pump is switched from (opening 0%) to light oil (opening 100%), as shown in fig. 11:

1) Switching control of return three-way valve of host fuel supply pump

The inlet three-way valve of the main engine fuel supply pump is completely switched to light oil (the opening is 100%), and after 60Min delay, the main engine fuel supply pump returns to the daily cabinet position where the three-way valve is switched from the supply pump position.

2) Switching control of host fuel circulation pump outlet three-way valve

a. The inlet three-way valve of the main engine fuel supply pump is completely switched to light oil (opening 100%), and after 60Min delay, the outlet three-way valve of the main engine fuel circulation pump is switched from the heater to the cooler.

b. And after the host fuel viscosity is 3-3 cST and lasts for 5 seconds, the host fuel circulation pump outlet three-way valve is switched from the heater to the cooler.

The safety monitoring system comprises emergency shutdown triggering/resetting control, cargo tank protection control, ESD test control, ESD shielding control, override control and offshore/harbor switching control.

The ESD emergency shutdown triggering/resetting control method. Judging whether an ESD shutdown signal exists, shutting down corresponding equipment when the ESD shutdown signal exists, and keeping the system normal when the ESD shutdown signal does not exist; when the ESD turn-off signal is recovered, judging whether the total reset or the independent reset is carried out, when the total reset or the independent reset is carried out, turning off the output reset, recovering the system to be normal, and when the total reset or the independent reset is not carried out, the corresponding equipment is still turned off.

The liquid cargo tank protection control method. Judging whether a TPS shutdown signal exists, shutting down corresponding equipment when the TPS shutdown signal exists, and keeping the system normal when the TPS shutdown signal does not exist; when the TPS shutdown signal is recovered, judging whether the total reset or the independent reset is carried out, when the total reset or the independent reset is carried out, the output reset is turned off, the system is recovered to be normal, and when the total reset or the independent reset is not carried out, the corresponding equipment is still turned off.

The ESD test control method. The system has a turn-off signal, judges whether to perform a total test or an independent test, does not turn off corresponding equipment when performing the total test or the independent test, and returns to normal when the turn-off signal is recovered; when the total test or the individual test is not performed, the corresponding device is turned off.

The ESD shielding control method. Judging whether shielding is carried out or not by judging whether the shielding is a shore-to-ship ESD which turns off corresponding equipment or not when the shielding is carried out, and not turning off the corresponding equipment by the shore-to-ship ESD; and when the shielding is not performed, the corresponding equipment is turned off.

The override control method. Judging whether an ESD/TPS turn-off signal exists or not, judging whether to perform override when the ESD/TPS turn-off signal exists, and turning off the corresponding equipment when the override is performed and turning off the corresponding equipment when the override is not performed; without the ESD/TPS off signal, the system remains normal.

The marine/port mode control method. The system is judged to be in a mode with a turn-off signal, and corresponding equipment is turned off in a port mode; and in the offshore mode, judging whether the offshore mode is the shore-to-ship ESD, if so, turning off the corresponding equipment, and if not, turning off the corresponding equipment.

Further, in one embodiment, in conjunction with fig. 12, the simulation test system includes a liquid cargo monitoring simulation system, a cabin monitoring simulation system, a safety monitoring simulation system, and a central control and security monitoring system that form a hardware loop.

The liquid cargo monitoring simulation system is used for simulating real-time on-line monitoring and control of cargo loading, gas management, insulation space protection and ballast control, and realizes simulation of full-flow management and control of loading, storing, transporting and unloading of LNG ship cargo.

The cabin monitoring simulation system realizes the simulation of on-line monitoring and control of ship equipment such as a boiler system, a Power Management System (PMS), a lubricating oil system, a fuel oil system, sea/fresh water cooling water, a bilge system, a fire protection system and the like.

The safety monitoring simulation system realizes the simulation of emergency shutdown of equipment such as valves, pumps and the like of LNG transport ships in emergency.

Further, the three-large simulation system simulates actual equipment operation by adopting a closed-loop equipment data model, provides model support for the simulation system, establishes a neural network model according to real ship Guan Chongshe equipment operation data, and takes equipment input parameters as input variables and output parameters as output variables. The entire neural network structure includes 4 parts of input, hidden, output and output. The input part performs data input, the 1 hidden layers are used for improving prediction precision, the 1 output layers perform nonlinear conversion, and the output part performs data output.

Further, the input variable is transferred into the hidden layer, and transferred into the output layer of the next layer through the weight of the connection node, and the output of the upper layer is the input of the next layer. Weighted summation in the output layer and then conversion to a final output variable coupling force is performed according to a nonlinear equation. The whole data set is randomly divided into a training set and a testing set in the process of training the neural network model, and then the training set data is normalized to construct the neural network and the network parameter configuration (training times, learning rate, training target minimum error and the like). And normalizing the data of the test set, performing error calculation on the inverse normalization of the predicted result and the simulation output variable, and performing error comparison on the predicted value of the test set and the corresponding operation data.

Furthermore, in the establishment process of the neural network, the random setting of the connection weight can cause errors in the prediction result, and the gradient descent training has the defects of low speed and local minima, so that the training of the neural network is difficult to achieve global optimization. And optimizing the model by using a Particle Swarm Optimization (PSO) algorithm, and improving the prediction precision and generalization capability.

Further, with reference to fig. 13, the neural network model is optimized by using a particle swarm optimization method. The basic idea of particle swarm optimization algorithms is to find the optimal solution through collaboration and information sharing between individuals in the swarm. And taking the error of each predicted value of the neural network as an objective function of the particle swarm algorithm. And predicting an output value for each training set input parameter set, taking the error of the predicted value and the actual value as an objective function of an optimization algorithm, and taking the minimum value as the optimal value by using the objective function. And randomly initializing each particle, evaluating each particle to ensure that each particle is globally optimal, and updating the position and speed of each particle, evaluating the function adaptation value and the historical optimal position to obtain the global optimal.

Further, the whole data driving simulation model construction flow is as follows:

(1) Normalizing real ship operation data of the related heavy equipment, establishing a neural network based on the normalized real ship operation data, determining a topological structure, and initializing a weight and a threshold of the network;

(2) Initializing particle swarm parameters including parameters such as maximum iteration times, population size, individual learning factors, social learning factors, inertia weights and the like;

(3) Initializing population positions of particle swarms, and calculating the number of neural network variables to be optimized according to a neural network structure;

(4) Setting an fitness function in the particle swarm optimization algorithm as a mean square error of neural network prediction, circulating a particle swarm optimization process, continuously updating the position of the optimal particles until the maximum iteration times, and terminating the particle swarm optimization algorithm;

(5) The optimal weight threshold parameters after the optimization of the particle swarm optimization are endowed to the neural network, namely an optimal model is output, training and prediction are carried out by using the optimal model, and comparison analysis is carried out with the neural network before the optimization.

Further, spatially adjacent Guan Chongshe spare running data tend to have a stronger correlation. Therefore, considering spatial correlation is critical for estimating the observed data at a given point in time, the spatial data model at a particular point in time is as follows:

where Y(s) is the observed value obtained at the input spatial variable s in the system, N is the total number of kernel components, and ε(s) is Gaussian random noise. w (w) _i (s) a non-negatively weighted kernel. f (f) _i (s)＝(f _i1 (s)，…，f _ip (s)) T is a set of known basis functions, beta _i Is a vector of model parameters.

Further, to take into account the time dynamic effects, the spatial model is extended to include the time dynamic process, the parameter β is calculated by the evolution equation _t Linking up over time:

β _t ＝g _t (β _t-1 ，γ)

wherein g _t (. Cndot.) is a nonlinear evolution model, and γ is process noise. Thus, guan Chongshe the spatiotemporal dynamic model (simulation predictive model) is defined as:

further, the three-large simulation system is provided with a typical test scene library (air pressure is constant, steam pressure is constant, a liquid cargo system is powered, and the cabin system is powered) of the cabin monitoring system, and the typical test scene library (liquid cargo tank drying inerting, spray precooling, liquid cargo loading, cargo voyage, liquid cargo unloading, gas dispelling, degassing and the like) of the liquid cargo monitoring system can be directly called when a simulation function is developed. The scene library sets different initial running states and process running data change logics according to different running scenes of a typical process flow. In the loading operation of the scene library, the parameter value supports manual modification, and if the parameter value is not manually modified, the scene library default adopts the preset numerical value.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

It will be apparent to those skilled in the art that various modifications and variations can be made to the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims and the equivalents thereof, the present invention is also intended to include such modifications and variations.

Claims (10)

1. The ship central control and security monitoring system based on simulation comprises a redundant distributed control platform and a core control system, and is characterized in that the redundant distributed control platform is used for providing hardware support required by system operation and realizing system data acquisition, action execution driving, power supply and communication; the core control system comprises a liquid cargo monitoring system, a cabin monitoring system, a safety monitoring system and a simulation test system, wherein:

the liquid cargo monitoring system is used for realizing the whole flow control of cargo loading, cargo unloading, cargo storage, cargo transportation and cargo unloading;

the cabin monitoring system is used for realizing power distribution and equipment automatic control of the whole ship;

the safety monitoring system is used for realizing the safe operation of each system and equipment of the LNG ship;

the simulation test system simulates the operation of actual equipment by establishing a simulation prediction model of the equipment, generates a test scene library for direct calling during testing, and realizes the verification of simulation and control logic of functions of the liquid cargo monitoring system, the cabin monitoring system and the safety monitoring system.

2. The simulation-based ship center control and security monitoring system according to claim 1, wherein the redundant distributed control platform comprises an operation station, a control station, a remote IO station, a power supply station and a network station; the operation station is used for operator monitoring and human control of field devices and is connected with the control station through a redundant Ethernet; the control station is used for providing control, monitoring and alarming of the system, is connected with the remote IO station through an internal IO bus, the remote IO station is used for providing input and output signal management of the system, the power station adopts redundant power supply configuration and is used for providing redundant power supply, and the network station is used for communication between devices.

3. The simulation-based ship central control and security monitoring system according to claim 2, wherein the operation station is provided with a real-time monitoring device, supports one machine with multiple screens, provides a monitoring interface for control grouping, an operation panel, diagnosis information, trend, alarm information and system state information, can acquire process information and event alarms through an operator station, performs real-time control on field devices, directly acquires real-time data from the control station, and sends an operation command to the control station.

4. The simulation-based marine central control and security monitoring system of claim 3, wherein the control stations comprise a redundant CPU module, a remote I/O bus module, a power module and a vertical cabinet, each of the control stations being distributed and installed in a cargo distribution room, an engine room, a high voltage distribution room and a low voltage distribution room.

5. The simulation-based marine central control and security monitoring system of claim 4, wherein the remote IO station comprises a remote I/O bus module, an I/O module, a power module, and a vertical cabinet, each remote I/O control station being distributed and installed in an engine room, a high voltage distribution room, a low voltage distribution room, and a storage room.

6. The simulation-based marine central control and security monitoring system of claim 5, wherein the network station provides RS485, profibus DP, NMEA communication while providing 5 sets of network plugs distributed at each location of the marine, each set consisting of two redundant ethernet ports.

7. The simulation-based marine central control and security monitoring system of claim 1, wherein the equipment in the simulation test system comprises a cargo hold, a liquid cargo pump, an LD/HD compressor, a gas combustion unit, a reliquefaction device and a generator; the test scene library comprises a test scene library of a cabin monitoring system and a test scene library of a liquid cargo monitoring system, wherein the test scene library of the cabin monitoring system comprises air pressure constant, steam pressure constant, liquid cargo system power supply and cabin system power supply, and the test scene library of the liquid cargo monitoring system comprises liquid cargo tank drying inerting, spray precooling, liquid cargo loading, cargo sailing, liquid cargo unloading, gas dispelling and degassing.

8. The simulation-based ship central control and security monitoring system according to claim 7, wherein the simulation test system is based on a data model and a test scene library of equipment, and the simulation and control logic verification of functions of a liquid cargo monitoring system, a cabin monitoring system and a safety monitoring system is realized through a simulation prediction model and a particle swarm optimization method based on a neural network.

9. The simulation-based ship central control and security monitoring system according to claim 8, wherein the neural network structure comprises 4 parts including an input part, a hidden layer, an output layer and an output part, wherein during training, an input variable is transmitted into the hidden layer, the input variable is transmitted into a next output layer through the weight of a connecting node, the output of the upper layer is the input of the next layer, the output layer is weighted and summed, the output variable is converted into a final output variable coupling force according to a nonlinear equation, then training set data is normalized, a neural network and network parameter configuration is constructed, meanwhile, test set data is normalized, finally, error calculation is performed on a prediction result and a simulation output variable, and error comparison is performed on a predicted value of the test set and corresponding operation data to judge whether requirements are met.

10. The simulation-based ship central control and security monitoring system according to claim 9, wherein the simulation prediction model is specifically:

β _t ＝g _t (β _t-1 ，γ)

wherein Y(s) is the observed value obtained at the input spatial variable s in the system, N is the total number of kernel components, ε is Gaussian random noise, w _i (s) a non-negatively weighted kernel, f _i (s)＝(f _i1 (s)，…，f _ip (s)) ^T Is a set of known basis functions, beta _t Is the vector of model parameters g _t (. Cndot.) is a nonlinear evolution model, and γ is process noise.