A marine heat source coupled power generation system

Abstract

The application discloses a ship heat source coupled power generation system, which simultaneously utilizes scavenging air, cylinder jacket water and flue gas waste heat to generate power through two cycles, and controls the two cycle loops through a control device to improve waste heat source utilization efficiency. The power generation system comprises a waste heat source power generation device and a control device, the waste heat source power generation device comprises a first cycle loop and a second cycle loop, and the evaporation pressure and superheat degree in the first cycle loop and the second cycle loop are controlled through the control device; the control device collects wave and wind speed data, predicts main engine power and heat source temperature by using a convolutional neural network, outputs corresponding optimal evaporation pressure and optimal superheat degree according to the prediction, and controls the evaporation pressure and superheat degree of the first cycle loop and the second cycle loop by controlling the rotating speed of an expander and the rotating speed of a working medium pump in the first cycle loop and the second cycle loop through a nonlinear model prediction algorithm, so that the power generation device outputs maximum power.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of ship power generation and specifically relates to a ship heat source coupled power generation system. BACKGROUND

[0002] Most of the ships in ocean navigation use internal combustion engines as the main power, and the ship internal combustion engine consumes a large amount of fuel in the process of operation. Only 30% to 50% of the energy in the fuel is effectively utilized, and most of the heat is discharged in the form of waste heat through scavenging air, cylinder jacket water and flue gas. The exhaust gas temperature of the main engine of the ship is usually high, and a large amount of heat energy contained therein is directly discharged into the atmosphere, which not only causes energy waste but also causes thermal pollution to the environment. At the same time, the cylinder jacket water absorbs a large amount of heat in the process of cooling the engine, and is usually simply cooled and discharged without fully recycling and utilizing the heat.

[0003] At present, there are some ship waste heat power generation devices. However, these waste heat power generation devices can only recover the heat of a single heat source, such as recovering only the flue gas waste heat, and cannot comprehensively utilize multiple heat sources, so the utilization of heat sources is insufficient and the energy utilization efficiency is low. Moreover, the existing control mode is mostly simple, and basically controls the power generation device based on the real-time working condition, which leads to a lag of the control strategy and reduces the conversion efficiency of heat energy to electric energy. In addition, the control system of the existing power generation device does not consider the factors such as sea wave condition, wind speed and real-time power of the main engine, and cannot intelligently and accurately control the power generation device, so that the power generation device cannot operate in the best state, further affecting the energy recovery and utilization efficiency. SUMMARY

[0004] In order to make up for the deficiencies of the prior art, the application aims to provide a technical scheme of a ship heat source coupled power generation system, which simultaneously utilizes scavenging air, cylinder jacket water and flue gas waste heat for power generation through two cycles, and predicts the power of the main engine and the temperature of the heat source by collecting wave and wind speed data, and realizes collaborative optimization of power generation of multiple heat sources by combining with the intelligent control strategy of neural network, so as to improve the utilization efficiency of waste heat sources.

[0005] To achieve the above-mentioned purpose, the application can be realized through the following specific technical scheme:

[0006] The ship heat source coupled power generation system comprises a waste heat source power generation device and a control device, the waste heat source power generation device comprises a first circulation loop and a second circulation loop, the evaporation pressure and the superheat degree in the first circulation loop and the second circulation loop are controlled by the control device, and the three kinds of waste heat, namely the scavenging air, the cylinder jacket water and the flue gas, can be simultaneously utilized to generate power; the control device collects wave and wind speed data, utilizes a convolutional neural network to predict the main engine power and the heat source temperature, outputs the corresponding optimal evaporation pressure and optimal superheat degree according to the prediction, and controls the evaporation pressure and the superheat degree of the first circulation loop and the second circulation loop by controlling the rotation speed of the expander and the working medium pump in the first circulation loop and the second circulation loop through a nonlinear model prediction algorithm, so that the power generation device outputs the maximum power.

[0007] Further, the first circulation loop and the second circulation loop are both based on the organic Rankine cycle technology to generate power, the first circulation loop is used for recycling the flue gas waste heat of the ship main engine and generating power by utilizing the flue gas, and the second circulation loop is used for recycling the waste heat in the scavenging air and the cylinder jacket water and generating power by utilizing the scavenging air and the cylinder jacket water; the first circulation loop and the second circulation loop are jointly connected with a plate heat exchanger, the power output by the two circulation loops is connected into the ship power grid through an inverter, a temperature sensor and a pressure sensor are arranged at the outlet of each evaporator of the power generation system, an encoder is arranged on the rotation shaft of the expander to measure the rotation speed of the expander, and the data is transmitted to the control device through bus communication; the rotation speed of the working medium pump in the waste heat source power generation device is controlled by a frequency conversion driven motor, the rotation speed of the expander is controlled by controlling the current size of the rectifier, and the control signal is transmitted to the frequency converter and the rectifier in the waste heat source power generation device through bus communication of the control device.

[0008] Further, the first circulation loop comprises a liquid storage tank I, a working medium pump I, a shell-and-tube heat exchanger, a screw expander I and a plate heat exchanger which are connected in series, the screw expander I is further connected with a generator I, a rectifier I and an inverter I in series, the working medium pump I is connected with a motor I, the motor I is driven by a frequency converter I to drive the working medium pump I to extract the subcooled liquid from the liquid storage tank I, and then the subcooled liquid is pumped into the shell-and-tube heat exchanger; the working medium absorbs the heat of the flue gas waste heat in the shell-and-tube heat exchanger to become high-temperature and high-pressure gas, the high-temperature and high-pressure gas enters the screw expander I to perform isentropic expansion, drives the screw expander I to rotate, the high-temperature and high-pressure gas becomes low-pressure gas after coming out of the screw expander I, the low-pressure gas coming out of the screw expander I enters the plate heat exchanger to perform condensation and becomes subcooled liquid; meanwhile, the plate heat exchanger transmits heat to the second circulation loop to make it become high-pressure gas, and the subcooled liquid coming out of the plate heat exchanger enters the liquid storage tank I, so that the circulation in the first circulation loop is completed.

[0009] Further, the second circulation loop comprises, in sequence, a liquid storage tank II, a working medium pump II, a scavenging air heat exchanger, a cylinder jacket water heat exchanger, a plate heat exchanger, a screw expander II and a condenser, the screw expander II further connecting a generator II, a rectifier II and an inverter II, and the condenser connecting a seawater pump; the working medium pump II connecting a motor II, and driving the working medium pump II to extract the subcooled liquid from the liquid storage tank II and then pump it into the scavenging air heat exchanger for first heating by the motor II driven by a frequency converter II; the working medium after the first heating in the scavenging air heat exchanger enters the cylinder jacket water heat exchanger for further heating, and the preheated working medium after the further heating enters the plate heat exchanger to absorb the heat from the working medium in the first circulation loop to become high-pressure gas, which enters the screw expander II for isentropic expansion to drive the screw expander II to rotate, and the low-pressure gas after the isentropic expansion in the screw expander II enters the condenser for condensation to become subcooled liquid, and the heat of the working medium is transferred to the seawater in the condenser at this time, and the subcooled liquid after the condensation in the condenser enters the liquid storage tank II, so that the circulation in the second circulation loop is completed.

[0010] Further, the screw expander I rotates to drive the generator I to generate electricity, the generated electricity is rectified into direct current by the rectifier I, then is inverted into power frequency alternating current by the inverter I, and is input into the ship power grid; the screw expander II rotates to drive the generator II to generate electricity, the generated electricity is rectified into direct current by the rectifier II, then is inverted into power frequency alternating current by the inverter II, and is input into the ship power grid.

[0011] Further, the control device comprises a data acquisition module, a main engine power and waste heat source temperature prediction module, an intelligent decision-making module and a bottom control module, the data acquisition module is used to collect environmental data, main engine power, heat source and operation data of the power generation device; the main engine power and waste heat source temperature prediction module is used to predict the power of the main engine and the temperature of the waste heat source by analyzing the collected data; the intelligent decision-making module is used to obtain the optimal evaporation pressure and superheat degree according to the table lookup based on the predicted heat source temperature; and the bottom control module controls the corresponding working medium pump and expander speed control signal by a nonlinear model predictive control algorithm, so that the evaporation pressure and superheat degree at the outlet of the power generation device reach the set value, thereby the system outputs the maximum power.

[0012] Further, the data acquisition module comprises environmental data acquisition, power generation device data acquisition and main engine power and heat source temperature data acquisition, the environmental data acquisition collects the wave height, water flow rate and flow direction, wind speed and wind direction data in real time by installing wave sensors and anemometers on the ship; the power generation device data acquisition is used to collect the pressure and temperature at the outlet of the evaporator in each loop of the power generation device, and the expander speed in the power generation device; and the main engine power and heat source temperature data acquisition is used to collect the power of the main engine, and the temperatures of the flue gas, cylinder jacket water and scavenging air.

[0013] Further, the host power and waste heat source temperature prediction module obtains environmental data and power generation device operation data by communicating with the data acquisition module to predict the ship host power and waste heat source temperature; the host power and waste heat source temperature prediction module contains a host power prediction algorithm, a model continuous learning algorithm, and a waste heat source temperature prediction algorithm.

[0014] Further, in the working process of the intelligent decision module, first, a dynamic mechanism model containing all devices is established, the core input parameters of the dynamic mechanism model are heat source temperature and cold source temperature, and the to-be-optimized variables are evaporation pressure and superheat degree; then, the core output parameter of the dynamic mechanism model is the net output power of the system, under the condition of given heat source temperature and cold source temperature, the evaporation pressure and superheat degree are changed in a continuous scanning manner to form a plurality of parameter combinations; for each parameter combination, the parameter combination is input into the dynamic mechanism model, the corresponding system net output power is simulated and calculated in combination with the current heat source temperature and cold source temperature; all simulation results are compared, and the evaporation pressure and superheat degree parameter combination corresponding to the maximum net output power is screened out; for different heat source temperature intervals and cold source temperature intervals, a mapping relationship table of “heat source temperature-cold source temperature-optimal evaporation pressure-optimal superheat degree” is established, and the optimal parameters in the whole working condition range are quickly called.

[0015] Further, after the bottom control module receives the optimal evaporation pressure and optimal superheat degree reference values, corresponding working medium pump speed and expander speed signals are output by using a nonlinear model predictive control algorithm, the evaporation pressure and superheat degree of the first circulating loop and the second circulating loop in the waste heat source coupled power generation device are changed by controlling the working medium pump and expander speed, so that the evaporation pressure and superheat degree reach the optimal value; the working medium pump speed signal is sent to the frequency converter for driving the working medium pump through RS485 communication, the frequency converter controls the motor speed, and then changes the speed of the working medium pump; the expander speed signal is sent to the rectifier through RS485 communication, and the rectifier controls the speed of the generator and the expander connected with the generator through the rigid coupling by controlling the output current.

[0016] Compared with the prior art, the application has the following advantages:

[0017] The power generation system can recover the waste heat in the scavenging air of the ship, the cylinder jacket water and the flue gas at the same time, and improve the energy utilization efficiency through the double circulating loop coupling; and the intelligent control device predicts the host power according to the sea wave condition, water flow rate and wind speed, and then predicts the recoverable heat, so that the power generation device is accurately controlled and always operates in an efficient state. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 The figure is a structural block diagram of the power generation system of the application;

[0019] Figure 2 The schematic diagram of the mechanism of the power generation system of the present application;

[0020] Figure 3 The module diagram of the control device of the present application; wherein, ① is the outlet temperature of the first circulating evaporator, ② is the outlet pressure of the first circulating evaporator, ③ is the rotating speed of the first circulating expander, ④ is the outlet temperature of the second circulating evaporator, ⑤ is the outlet pressure of the second circulating evaporator, ⑥ is the rotating speed of the second circulating expander, ⑦ is the rotating speed control signal of the first circulating working medium pump, ⑧ is the rotating speed control signal of the second circulating working medium pump, ⑨ is the rotating speed control signal of the first circulating expander, and ⑩ is the rotating speed control signal of the second circulating expander;

[0021] Figure 4 The flow chart of the control device of the present application.

[0022] In the figure: 1 is a liquid storage tank I, 2 is a working medium pump I, 3 is a tube-shell heat exchanger, 4 is a screw expander I, 5 is a plate heat exchanger, 6 is a cylinder jacket water heat exchanger, 7 is a scavenging air heat exchanger, 8 is a working medium pump II, 9 is a liquid storage tank II, 10 is a condenser, 11 is a screw expander II, 12 is a generator I, 13 is a generator II, 14 is a rectifier I, 15 is an inverter I, 16 is a rectifier II, 17 is an inverter II, 18 is a seawater pump, 19 is an electric motor I, 20 is a frequency converter I, 21 is an electric motor II, 22 is a frequency converter II, 23 is a seawater pump motor, and 24 is a control device. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0024] As shown in Figure 1 and Figure 2 , a ship heat source coupled power generation system includes a waste heat heat source power generation device and a control device. The waste heat heat source power generation device includes a first circulating loop and a second circulating loop. The evaporation pressure and superheat degree in the first circulating loop and the second circulating loop are controlled by the control device. The system can simultaneously utilize scavenging air, cylinder jacket water and flue gas three kinds of waste heat to generate power. The control device collects wave and wind speed data, uses a convolutional neural network to predict the main engine power and heat source temperature, outputs the corresponding optimal evaporation pressure and optimal superheat degree according to the prediction, and controls the rotating speed of the expander and the rotating speed of the working medium pump in the first circulating loop and the second circulating loop by a nonlinear model prediction algorithm to control the evaporation pressure and superheat degree of the first circulating loop and the second circulating loop, so that the power generation device outputs maximum power, thereby improving the utilization efficiency of waste heat heat source.

[0025] The power generation system comprises two circulating loops, which can simultaneously utilize the three kinds of waste heat of scavenging air, cylinder jacket water and flue gas to generate power. The first circulating loop and the second circulating loop are both based on the organic Rankine cycle technology to generate power. The first circulating loop is used for recovering the waste heat of the flue gas of the main engine of the ship and generating power by using the flue gas. The second circulating loop is used for recovering the waste heat in the scavenging air and the cylinder jacket water and generating power by using the scavenging air and the cylinder jacket water. The first circulating loop and the second circulating loop are jointly connected with a plate heat exchanger 5. The power output by the two circulating loops is connected to the ship power grid through an inverter. The outlet of each evaporator of the power generation system is provided with a temperature sensor and a pressure sensor. An encoder is arranged on the rotating shaft of the expander to measure the rotating speed of the expander and transmit data to the control device through bus communication. The rotating speed of the working medium pump in the excess heat power generation device is controlled by a frequency conversion driven motor. The rotating speed of the expander is controlled by the current of the rectifier. The control signal is transmitted to the frequency converter and the rectifier in the excess heat power generation device through bus communication of the control device.

[0026] Specifically, the first circulating loop comprises a liquid storage tank 11, a working medium pump 12, a tube shell heat exchanger 3, a screw expander 14, a plate heat exchanger 5 connected in series. The screw expander 14 is further connected in series with a generator 112, a rectifier 114 and an inverter 115. The working medium pump 12 is connected with a motor 119. The motor 119 drives the working medium pump 12 to extract the subcooled liquid from the liquid storage tank 11 and then pumps the liquid into the tube shell heat exchanger 3 through a frequency converter 120. The working medium absorbs the heat of the flue gas waste heat in the tube shell heat exchanger 3 to become a high-temperature and high-pressure gas. The gas enters the screw expander 14 to expand isentropically, drives the screw expander 14 to rotate, and then becomes a low-pressure gas. The low-pressure gas enters the plate heat exchanger 5 to condense and become a subcooled liquid. At the same time, the plate heat exchanger 5 transfers heat to the second circulating loop to become a high-pressure gas. The subcooled liquid from the plate heat exchanger 5 enters the liquid storage tank 11 to complete the circulation in the first circulating loop.

[0027] Further, the second circulation loop comprises, in series, a liquid storage tank II 9, a working medium pump II 8, a scavenging air heat exchanger 7, a cylinder jacket water heat exchanger 6, a plate heat exchanger 5, a screw expander II 11, and a condenser 10. The screw expander II 11 is further connected in series with a generator II 13, a rectifier II 16, and an inverter II 17. The condenser 10 is connected with a seawater pump 18. The working medium pump II 8 is connected with a motor II 21, which drives the working medium pump II 8 to extract the subcooled liquid from the liquid storage tank II 9 and then pumps the liquid into the scavenging air heat exchanger 7 for the first heating. The working medium, after being heated in the scavenging air heat exchanger 7, enters the cylinder jacket water heat exchanger 6 for further heating. The preheated working medium, after being heated in the cylinder jacket water heat exchanger 6, enters the plate heat exchanger 5 to absorb the heat from the working medium of the first circulation loop and becomes high-pressure gas. The high-pressure gas enters the screw expander II 11 for isentropic expansion, driving the screw expander II 11 to rotate. The low-pressure gas, after being expanded in the screw expander II 11, enters the condenser 10 for condensation and becomes subcooled liquid. At this time, the heat of the working medium is transferred to the seawater in the condenser 10. The subcooled liquid, after being condensed in the condenser 10, enters the liquid storage tank II 9, and the circulation in the second circulation loop is completed.

[0028] The screw expanders I 4 and II 11 are rigidly connected with the generators I 12 and II 13 through shaft couplings, respectively, to ensure that the mechanical energy output by the screw expanders I 4 and II 11 can be efficiently transmitted to the generators I 12 and II 13, respectively, to convert the mechanical energy into electrical energy. In order to obtain a higher efficiency of the system, the rotational speeds of the generators I 12 and II 13 need to be controlled. Therefore, the rear ends of the generators I 12 and II 13 in the two circulation loops are connected with rectifiers I 14 and II 16, respectively. The rotational speeds of the generators and the expanders connected therewith can be controlled through the rectifiers. The electrical energy output by the rectifiers is converted into alternating current through inverters and is input into the ship power grid. That is, the screw expander I 4 drives the generator I 12 to generate electricity. The generated electricity is rectified by the rectifier I 14 into direct current, and then is inverted by the inverter I 15 into power frequency alternating current and is input into the ship power grid. The screw expander II 11 drives the generator II 13 to generate electricity. The generated electricity is rectified by the rectifier II 16 into direct current, and then is inverted by the inverter II 17 into power frequency alternating current and is input into the ship power grid.

[0029] The power generation system of the application, the liquid storage tank I 1 is used for storing the condensed liquid from the condenser, as a buffer part; the working medium pump I 2 provides circulating power for the working medium flow in the first circulating loop; the tubular heat exchanger 3 is used for heat exchange with the flue gas waste heat, and at the same time heats the working medium to become high pressure and high temperature steam; the screw expander I 4 converts the energy carried in the high temperature and high pressure steam into mechanical energy output; the plate heat exchanger 5 condenses the working medium in the first circulating loop to become liquid, and at the same time heats the working medium in the second circulating loop to become high pressure and high temperature steam; the cylinder sleeve water heat exchanger 6 is used to absorb the heat in the cylinder sleeve water, and at the same time heats the working medium in the second circulating loop; the scavenging air heat exchanger 7 is used to absorb the heat in the scavenging air, and at the same time heats the working medium in the second circulating loop; the working medium pump II 8 provides circulating power for the working medium flow in the second circulating loop; the liquid storage tank II 9 is used for storing the condensed liquid from the condenser, as a buffer part; the condenser 10 condenses the gaseous circulating working medium to become liquid; the screw expander II 11 converts the energy carried in the high temperature and high pressure steam into mechanical energy output; the generator I 12 converts mechanical energy into electrical energy; the generator II 13 converts mechanical energy into electrical energy; the rectifier I 14 converts the alternating current generated by the generator I 12 into direct current, and at the same time, by controlling the output current, the speed of the screw expander I 4 can be controlled; the inverter I 15 converts the direct current into alternating current of power frequency, which can be connected to the ship power grid; the rectifier II 16 converts the alternating current generated by the generator II 13 into direct current, and at the same time, by controlling the output current, the speed of the screw expander II 11 can be controlled; the inverter II 17 converts the direct current into alternating current of power frequency, which can be connected to the ship power grid; the seawater pump 18 draws seawater into the condenser 10 of the second circulating loop; the motor I 19 provides power for the working medium pump I 2, driving the working medium pump I 2 to rotate; the frequency converter I 20 drives the motor I 19, and the speed of the motor I 19 can be controlled through the frequency converter I 20, thereby the speed of the working medium pump I 2 can be controlled; the motor II 21 provides power for the working medium pump II 8, driving the working medium pump II 8 to rotate; the frequency converter II 22 drives the motor II 21, and the speed of the motor II 21 can be controlled through the frequency converter II 22, thereby the speed of the working medium pump II 8 can be controlled; the seawater pump motor 23 provides power for the seawater pump 18; the control device 24 controls the evaporation pressure and superheat degree in the system by controlling the speed of the working medium pump I 2, the working medium pump II 8 and the speed of the screw expander I 4, the screw expander II 11 in the excess heat source power generation device.

[0030] Continue to refer to Figure 2It can be seen that the liquid storage tank 11 is connected with the working medium pump 12 and the tube-shell heat exchanger 3 through copper pipes, the screw expander 14 is connected with the tube-shell heat exchanger 3 and the plate heat exchanger 5 through high-pressure copper pipes, the cylinder liner water heat exchanger 6 is connected with the scavenging air heat exchanger 7 and the plate heat exchanger 5 through copper pipes, the working medium pump 28 is connected with the scavenging air heat exchanger 7 and the liquid storage tank 29 through copper pipes, the screw expander 111 is connected with the condenser 10 and the plate heat exchanger 5 through copper pipes. The screw expander 14 is connected with the generator 112 through a rigid coupling 201, the generator 112 is connected with the rectifier 114 through a three-phase cable 203, the rectifier 114 is connected with the inverter 115 through a direct-current cable, and the inverter 115 is connected with the ship power grid 209 through a bus.

[0031] The screw expander 111 is connected with the generator 113 through a rigid coupling. The generator 113 is connected with the rectifier 116 through a three-phase cable 204, the rectifier 116 is connected with the inverter 117 through a direct-current cable, and the inverter 117 is connected with the ship power grid 209 through a bus. The speed converter control signals 401 of the working medium pump 12, the speed converter control signals 402 of the working medium pump 28, the speed control signals 403 of the screw expander 14, the speed control signals 404 of the screw expander 111, the evaporator outlet pressure signal 412 of the first circulation loop, the evaporator outlet temperature signal 413 of the second circulation loop, the evaporator outlet pressure signal 414 of the second circulation loop, the speed signals 415 and 416 of the screw expander 14, and the speed signals of the screw expander 111 are all communicated through the RS485 communication and the control device 24.

[0032] In an embodiment, the flue gas in the first circulation loop passes through the shell of the tube-shell heat exchanger 3, and the organic working medium passes through the tube. In order to improve the heat exchange efficiency, the heat exchange pipe material is red copper. The circulating working medium adopts R245fa, which has good thermal physical properties and environmental protection characteristics. The working medium enters the screw expander 14 from the tube-shell heat exchanger 3 through the pipe 102, and the isentropic efficiency of the screw expander 14 is more than 80%. The working medium of the screw expander 14 enters the plate heat exchanger 5 through the pipe 103, and the plate heat exchanger 5 adopts a plate heat exchanger with higher heat exchange coefficient. The working medium from the plate heat exchanger 5 enters the liquid storage tank 11 through the pipe 105. The working medium pump 12 extracts the working medium from the liquid storage tank 11 through the pipe 105. The working medium pump 12 is a corrosion-resistant centrifugal pump driven by a motor driven by the frequency converter 120. The speed control signal 401 of the motor 119 driven by the frequency converter 120 is sent to the communication interface of the frequency converter 120 by the control device 24 through RS485 communication.

[0033] The screw expander II 11 in the second cycle loop is also a screw expander, and the circulating working medium is R134a. The condenser 10 is a corrosion-resistant plate condenser, and seawater is used to cool the working medium. The seawater is sent to the condenser 10 by the seawater pump 18. The working medium pump II 8 and the working medium pump I 2 are corrosion-resistant centrifugal pumps driven by the frequency converter II 22 and the motor II 21; the speed control signal 402 of the motor II 21 driven by the frequency converter II 22 is sent to the communication interface of the frequency converter II 22 by the intelligent control device through RS485 communication.

[0034] The screw expander I 4 and the generator I 112, the screw expander II 11 and the generator II 113 are connected by rigid couplings 201 and 202, respectively. The generator I 112 and the generator II 113 are permanent magnet synchronous generators, which have the characteristics of small size, light weight and high efficiency, and are suitable for use in limited space on ships. The control algorithm of the rectifier I 114 and the rectifier II 116 adopts zero d-axis current control strategy, the modulation strategy adopts space voltage vector PWM modulation algorithm, and the core device adopts IGBT. The inverter I 115 and the inverter II 117 have two modes of off-grid and grid-connected, and the grid-connected adopts grid voltage oriented vector control strategy, and the off-grid adopts V / F control algorithm; the same PWM modulation algorithm is also used, and the device selects IGBT. The excess heat source power generation device is provided with temperature and pressure sensors at the outlet of the evaporator in the first cycle loop and the second cycle loop, and encoders are arranged on the rotating shafts of the screw expander I 4 and the screw expander II 11 to measure the rotating speed. The rotating speed, temperature and pressure signals are sent to the control device 24 through RS485 field bus.

[0035] The output power of the excess heat source coupled power generation device is affected by the temperature of the heat source and the cold source. In order to make the power generation device output maximum power under given heat source and cold source temperature and run in the safe boundary, a corresponding control device 24 is needed. As shown in Figure 3 and Figure 4 The control device 24 includes a data acquisition module, a main engine power and waste heat source temperature prediction module, an intelligent decision module and a bottom control module. The data acquisition module is used to collect environmental data, main engine power, heat source and running data of the power generation device; the main engine power and waste heat source temperature prediction module is used to predict the power of the main engine and the temperature of the waste heat source by analyzing the collected data; the intelligent decision module is used to obtain the optimal evaporation pressure and superheat degree according to the table lookup by the predicted heat source temperature; and the bottom control module controls the corresponding working medium pump and expander rotating speed control signal by the nonlinear model predictive control algorithm, so that the outlet pressure and superheat degree of the evaporator in the power generation device reach the set value, thereby making the system output maximum power.

[0036] (1) The data acquisition module includes environment data acquisition, power generation device data acquisition, and main engine power and heat source temperature data acquisition. The environment data acquisition acquires real-time wave height, water flow rate and direction, wind speed and direction data by installing wave sensors and anemometers on the ship. The power generation device data acquisition acquires the pressure and temperature of the evaporator outlet in each loop of the power generation device and the rotational speed of the expander in the power generation device. The main engine power and heat source temperature data acquisition acquires the power of the main engine, the temperature of the flue gas, cylinder liner water, and scavenging air.

[0037] In a specific embodiment, the data acquisition module uses TI SN75176 as the RS485 communication module, and the data processing and data transceiver control after data acquisition use an STM32F103C8T6 chip.

[0038] (2) The main engine power and waste heat source temperature prediction module obtains environment data and power generation device operation data by communicating with the data acquisition module, and predicts the main engine power and waste heat source temperature. The main engine power and waste heat source temperature prediction module includes a main engine power prediction algorithm, a model continuous learning algorithm, and a waste heat source temperature prediction algorithm.

[0039] 1) The specific process of the main engine power prediction algorithm is as follows:

[0040] ① Data acquisition and preprocessing

[0041] Data acquisition range: historical data includes wave parameters (wave height, period, direction, flow rate) and wind speed parameters (wind speed, direction) when the ship is sailing, main engine power, sample size 200,000, time granularity 1 second / bar.

[0042] The preprocessing steps include outlier processing, normalization, and feature reconstruction. The 3σ criterion is used to remove outliers in wave, wind speed, and power data. In the normalization process, the input features are normalized to the [0, 1] interval. In the feature reconstruction process, time series data is converted into a two-dimensional feature matrix, with 10 seconds of continuous parameters forming a 10x6 feature matrix (10 time steps, 6 features) as the input sample of the convolutional neural network.

[0043] ② Convolutional neural network (CNN) model design

[0044] The CNN network comprises an input layer, two convolutional layers, two pooling layers, one full connection layer and an output layer. The input layer receives a 10x6 feature matrix; the first convolutional layer uses 16 3x3 convolutional kernels, with a step length of 1, a same padding mode and a ReLU activation function, and outputs a feature map with a size of 10x6x16; the first pooling layer uses 2x2 maximum pooling with a step length of 2, and outputs a feature map with a size of 6x3x16; the second convolutional layer uses 32 2x2 convolutional kernels, with a step length of 1, a valid padding mode and a ReLU activation function, and outputs a feature map with a size of 4x2x32; the second pooling layer uses 2x2 average pooling with a step length of 1, and outputs a feature map with a size of 3x1x32; and the output layer has one node (linear activation) and outputs a predicted host power.

[0045] ③ Model loss

[0046] The loss function uses the root mean square error (MSE) error, the optimizer uses the Adam optimizer, the initial learning rate is 0.001, and the learning rate is reduced by 10% every 50 rounds; the training strategy is 5-fold cross-validation, the training rounds are 200, and the early stopping strategy (stop if the MSE of the validation set does not decrease for 10 consecutive rounds).

[0047] ④ Model training

[0048] The real-time wave height, period, direction and flow rate collected by the wave sensor, and the real-time wind and wind direction collected by the anemometer are preprocessed to construct a 6-dimensional feature vector at time t; a sliding window is used to take the last 10 seconds of feature vectors to form a 10x6 real-time feature matrix; the trained CNN model is input, and the host power prediction value at time t is output.

[0049] 2) The specific process of the model continuous learning algorithm is as follows:

[0050] ① Online learning data input

[0051] The actual power of the host power sensor data and the data of the heat source temperature sensor (flue gas temperature, cylinder jacket water temperature and scavenging temperature) are collected in real time, and one sample is generated every 30 seconds; the error between the predicted power and the actual power is calculated, and when the error is greater than a preset threshold, the sample is marked as a “high-value sample”.

[0052] ② Incremental training strategy

[0053] First, data weight distribution, high-value sample weight set to 1.5, ordinary sample weight set to 1.0, historical sample according to time decay weight; Then incremental update, triggered every 24 hours incremental training, freeze the first 2 layers of CNN parameters, only update the fully connected layer, use small batch gradient descent, learning rate is 1 / 10 of the initial value, avoid catastrophic forgetting; Finally, model evaluation, using rolling validation set (7 days of data) to calculate MSE, when MSE drops ≥3%, save the updated model.

[0054] 3) The specific process of the residual heat source temperature prediction algorithm is as follows:

[0055] The prediction of residual heat source temperature is based on the first law of thermodynamics, and is calculated through the fitting formula of host power. The flue gas temperature prediction formula is as follows:

[0056] ,

[0057] Among them, T exh is the flue gas temperature, P t is the host power, a1, b1, c1 are fitting parameters, which are obtained by fitting the historical data power data and the measured flue gas temperature by least squares method.

[0058] The cylinder jacket water temperature prediction formula is as follows:

[0059] ,

[0060] Among them, T jac is the cylinder jacket water temperature, P t is the host power, a2, b2, c2 are fitting parameters, which are obtained by fitting the historical data power data and the measured cylinder jacket water temperature by least squares method.

[0061] The scavenging air temperature prediction uses the heat transfer calculation formula to calculate:

[0062] ,

[0063] Among them, T scav is the scavenging air temperature, K is the heat transfer coefficient, A is the heat transfer area, ΔT is the average heat transfer temperature difference, c is the specific heat capacity of scavenging air, m is the scavenging air flow, T in is the scavenging air inlet temperature, usually taking the ambient temperature.

[0064] In a specific embodiment, the host power and heat source temperature prediction module includes a core controller and multiple sensors. The core controller uses Nvidia Jetson TX2 NX, with a computing power of 1.33 TFLOPS. The wave sensor uses an acoustic Doppler wave velocity profiler, installed below the ship's waterline, which can accurately measure wave height, period, and water flow rate, etc. The wind speed sensor uses a high-precision marine wind speed and direction instrument, which needs to have corrosion-resistant characteristics. The mathematical model uses a convolutional neural network model, with input data including wave period, wave height, water flow rate, wind speed, wind direction, and heading, and output parameters including host power. The training data amount reaches more than 200,000 groups to ensure the accuracy of the model. The heat source temperature prediction module establishes a relationship model corresponding to multiple heat source temperature parameters based on the host power. Through experimental testing, the host power and the heat source temperature data of the scavenging air, cylinder sleeve water, and flue gas are obtained, and linear fitting is performed with a degree of 5. The host power and heat source temperature prediction module and the intelligent decision-making module use RS485 communication.

[0065] (3) In the working process of the intelligent decision-making module, first, a dynamic mechanism model containing all devices is established. The core input parameters of the dynamic mechanism model are heat source temperature and cold source temperature, and the variables to be optimized are evaporation pressure and superheat degree. The core output parameter of the dynamic mechanism model is the net output power of the system. Under the condition of given heat source temperature and cold source temperature, the evaporation pressure and superheat degree are changed in a continuous scanning manner to form multiple parameter combinations. For each parameter combination, it is input into the dynamic mechanism model, combined with the current heat source temperature and cold source temperature, and the corresponding system net output power is simulated and calculated. All simulation results are compared, and the parameter combination of evaporation pressure and superheat degree corresponding to the maximum net output power is selected. For different heat source temperature intervals and cold source temperature intervals, the above steps are repeated to establish a mapping relationship table of "heat source temperature-cold source temperature-optimal evaporation pressure-optimal superheat degree", realizing the fast calling of optimal parameters in the whole working condition range.

[0066] In a specific embodiment, the intelligent decision-making module uses an industrial-grade TMS320F280039C as the core controller. By establishing a mechanism model, the optimal evaporation pressure and optimal superheat degree corresponding to the maximum power output under different heat source temperatures are simulated. The data between the optimal evaporation pressure, optimal superheat degree, and corresponding heat source temperature are fitted and stored in the controller. When receiving the predicted data of the waste heat heat source temperature through RS485 communication, the reference values of the optimal evaporation pressure and optimal superheat degree are output through the fitting formula. The intelligent decision-making module and the bottom control module use RS485 communication.

[0067] (4) After receiving the optimal evaporation pressure and optimal superheat reference value, the bottom control module outputs the corresponding working fluid pump speed and expander speed signals using the nonlinear model predictive control algorithm, changes the evaporation pressure and superheat of the first circulation loop and the second circulation loop in the excess heat source coupled power generation device by controlling the working fluid pump and expander speed, so that the evaporation pressure and superheat reach the optimal value; the working fluid pump speed signal is sent to the frequency converter for driving the working fluid pump through RS485 communication, the frequency converter controls the motor speed, and then changes the working fluid pump speed; the expander speed signal is sent to the rectifier through RS485 communication, and the rectifier controls the speed of the generator and the expander connected with the generator through the rigid coupling by controlling the output current.

[0068] The nonlinear model predictive control (NMPC) algorithm used by the bottom controller algorithm realizes high-precision control of the optimal evaporation pressure and optimal superheat by fusing the nonlinear dynamic characteristics, multivariable constraints and rolling optimization mechanism of the power generation device, and the system can run within the safety boundary by setting boundary conditions. The control principle is to dynamically generate the control sequence of the working fluid pump and expander speed by solving the constrained nonlinear optimization problem based on real-time measurement information. The specific process is as follows:

[0069] ① Initialization and state perception (sampling time)

[0070] Based on the real-time acquisition of the current state: evaporation pressure, superheat, combined with working fluid pump and expander speed feedback, the accurate initial state is obtained by eliminating measurement noise through extended Kalman filter (EKF).

[0071] ② Rolling optimization (solving in prediction horizon)

[0072] Taking the initial state as the starting point, the state sequence of the future N steps is predicted based on the nonlinear dynamic model, and the control sequence that minimizes the objective function is solved under the premise of meeting the safety constraints (state, control variable and derived constraints) as the control time domain.

[0073] The optimization problem is solved by interior point method, which quickly converges by converting inequality constraints into barrier functions combined with gradient descent algorithm, ensuring that the calculation is completed within the sampling period.

[0074] ③ Control quantity execution

[0075] The first control quantity of the optimization sequence is executed, and the working fluid pump and expander speed signals are sent to the corresponding execution equipment to realize real-time regulation and control of the evaporation pressure and superheat.

[0076] ④ Feedback correction (entering the next sampling time)

[0077] The new state measurement value is collected, the prediction error is calculated, the initial state of the next round of prediction model is corrected through the state error compensation mechanism, the influence of model mismatch and external disturbance is offset, and the control robustness is ensured.

[0078] In a specific embodiment, the bottom control module selects TMS320F28P550SJ as the core controller, has a floating point and a hardware algorithm unit of trigonometric function, and has higher control real-time performance. The model predictive control algorithm is run in the controller, the solver is selected as the ACADO Codegen open source solver, the controller and the frequency converter and the rectifier communicate through RS485 communication. The bottom control module controls the speed of the working fluid pump and the expander through outputting the working fluid pump control signal to the working fluid pump frequency converter and outputting the expander speed control signal to the rectifier; the evaporation pressure and the superheat degree in each cycle of the power generation device are controlled by controlling the speed of the working fluid pump and the expander.

[0079] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A ship heat source coupled power generation system, characterized in that, The device includes a waste heat power generation unit and a control unit. The waste heat power generation unit comprises a first circulation loop and a second circulation loop. The evaporation pressure and superheat in the first and second circulation loops are controlled by the control unit. It can simultaneously utilize three types of waste heat—scavenging air, cylinder liner water, and flue gas—to generate electricity. The control unit collects wave and wind speed data, uses a convolutional neural network to predict the main unit power and heat source temperature, outputs the corresponding optimal evaporation pressure and optimal superheat based on the prediction, and controls the expander speed and working fluid pump speed in the first and second circulation loops through a nonlinear model prediction algorithm to control the evaporation pressure and superheat in the first and second circulation loops, so that the power generation unit outputs maximum power. Both the first and second circulation loops generate electricity based on organic Rankine cycle technology. The first circulation loop is used to recover waste heat from the flue gas of the ship's main engine and generate electricity using the flue gas. The second circulation loop is used to recover waste heat from the scavenging air and cylinder liner water and generate electricity using the cylinder liner water and scavenging air. The first and second circulation loops are connected to a plate heat exchanger (5). The electricity output from the two circulation loops is connected to the ship's power grid through an inverter. Each evaporator outlet of the power generation system is equipped with a temperature sensor and a pressure sensor. An encoder is installed on the expander shaft to measure the expander speed and transmits the data to the control device through bus communication. The speed of the working fluid pump in the waste heat source power generation device is controlled by a frequency converter-driven motor. The speed of the expander is controlled by the rectifier to control the current. The control signal is sent by the control device to the frequency converter and rectifier in the waste heat source power generation device through bus communication.

2. The ship heat source coupled power generation system according to claim 1, characterized in that, The first circulation loop includes a liquid storage tank I (1), a working fluid pump I (2), a shell-and-tube heat exchanger (3), a screw expander I (4), and a plate heat exchanger (5) connected in series. The screw expander I (4) is also connected in series with a generator I (12), a rectifier I (14), and an inverter I (15). The working fluid pump I (2) is connected to a motor I (19), which is driven by a frequency converter I (20) to drive the working fluid pump I (2) to draw subcooled liquid from the liquid storage tank I (1) and then pump it into the shell-and-tube heat exchanger (3). The working fluid in the shell-and-tube heat exchanger (3) 3) The heat absorbed by the flue gas is transformed into high-temperature and high-pressure gas. This gas will enter the screw expander I (4) for isentropic expansion, driving the screw expander I (4) to rotate. After the high-temperature and high-pressure gas comes out of the screw expander I (4), it becomes low-pressure gas. The low-pressure gas enters the plate heat exchanger (5) for condensation and becomes subcooled liquid. At the same time, the plate heat exchanger (5) will transfer heat to the second circulation loop, making it into high-pressure gas. The subcooled liquid from the plate heat exchanger (5) enters the storage tank I (1), thus completing the circulation in the first circulation loop.

3. A ship heat source coupled power generation system according to claim 2, characterized in that, The second circulation loop includes a liquid storage tank II (9), a working fluid pump II (8), a scavenging air heat exchanger (7), a cylinder liner water heat exchanger (6), a plate heat exchanger (5), a screw expander II (11), and a condenser (10) connected in series. The screw expander II (11) is also connected in series with a generator II (13), a rectifier II (16), and an inverter II (17). The condenser (10) is connected to a seawater pump (18). The working fluid pump II (8) is connected to a motor II (21). The motor II (21) is driven by a frequency converter II (22) to drive the working fluid pump II (8) to draw subcooled liquid from the liquid storage tank II (9) and then pump it to the scavenging air heat exchanger (7) for the first time. Heating; After the working fluid comes out of the scavenging air heat exchanger (7), it enters the cylinder liner water heat exchanger (6) for further heating. The preheated working fluid then enters the plate heat exchanger (5) to absorb the heat in the working fluid of the first circulation loop and becomes high-pressure gas. This gas enters the screw expander II (11) for isentropic expansion, driving the screw expander II (11) to rotate. After coming out of the screw expander II (11), it becomes low-pressure gas and enters the condenser (10) for condensation, becoming subcooled liquid. At this time, the heat of the working fluid is transferred to the seawater in the condenser (10). The subcooled liquid coming out of the condenser (10) enters the storage tank II (9), thus completing the second circulation loop.

4. A ship heat source coupled power generation system according to claim 3, characterized in that, The screw expander I (4) drives the generator I (12) to generate electricity. The generated electricity is rectified into DC by rectifier I (14) and then inverted into AC by inverter I (15) and fed into the ship's power grid. The screw expander II (11) drives the generator II (13) to generate electricity. The generated electricity is rectified into DC by rectifier II (16) and then inverted into AC by inverter II (17) and fed into the ship's power grid.

5. A ship heat source coupled power generation system according to claim 3, characterized in that, The control device (24) includes a data acquisition module, a main unit power and waste heat source temperature prediction module, an intelligent decision-making module, and a low-level control module. The data acquisition module is used to collect environmental data, main unit power, heat source, and operating data of the power generation device. The main unit power and waste heat source temperature prediction module is used to predict the main unit power and waste heat source temperature by analyzing the collected data. The intelligent decision-making module is used to obtain the optimal evaporation pressure and superheat by looking up a table based on the predicted heat source temperature. The low-level control module controls the output of the corresponding working fluid pump and expander speed control signals through a nonlinear model predictive control algorithm, so that the evaporator outlet pressure and superheat in the power generation device reach the set value, thereby maximizing the system output power.

6. A ship heat source coupled power generation system according to claim 5, characterized in that, The data acquisition module includes environmental data acquisition, power generation device data acquisition, and main engine power and heat source temperature data acquisition. The environmental data acquisition is achieved by installing wave sensors and anemometers on the ship to collect real-time data on wave height, water flow velocity and direction, wind speed and direction. The power generation device data acquisition is used to collect the pressure and temperature at the evaporator outlet in each loop of the power generation device, and the speed of the expander in the power generation device. The main engine power and heat source temperature data acquisition is used to collect the power of the main engine, the temperature of flue gas, cylinder liner water, and scavenging air.

7. A ship heat source coupled power generation system according to claim 5, characterized in that, The main engine power and waste heat source temperature prediction module obtains environmental data and power generation device operation data through communication with the data acquisition module, and predicts the ship's main engine power and multiple waste heat source temperatures; the main engine power and waste heat source temperature prediction module includes a main engine power prediction algorithm, a model continuous learning algorithm, and a waste heat source temperature prediction algorithm.

8. A ship heat source coupled power generation system according to claim 5, characterized in that, In the operation of the intelligent decision-making module, a dynamic mechanism model encompassing all equipment is first established. The core input parameters of the dynamic mechanism model are the heat source temperature and the cold source temperature, while the variables to be optimized are the evaporation pressure and superheat. Then, the core output parameter of the dynamic mechanism model is the system's net output power. Given the heat source and cold source temperatures, the evaporation pressure and superheat are continuously scanned to create multiple parameter combinations. For each parameter combination, it is input into the dynamic mechanism model, and combined with the current heat source and cold source temperatures, the corresponding system net output power is simulated and calculated. All simulation results are compared, and the evaporation pressure and superheat parameter combination corresponding to the maximum net output power is selected. For different heat source and cold source temperature ranges, a mapping table of "heat source temperature - cold source temperature - optimal evaporation pressure - optimal superheat" is established to enable rapid retrieval of optimal parameters across the entire operating range.

9. A ship heat source coupled power generation system according to claim 5, characterized in that, After receiving the optimal evaporation pressure and optimal superheat reference values, the underlying control module uses a nonlinear model predictive control algorithm to output corresponding working fluid pump speed and expander speed signals. By controlling the speeds of the working fluid pump and expander, the evaporation pressure and superheat of the first and second circulation loops in the excess heat source coupled power generation device are changed, so that the evaporation pressure and superheat reach the optimal values. The working fluid pump speed signal is sent to the frequency converter used to drive the working fluid pump via RS485 communication. The frequency converter controls the motor speed, thereby changing the speed of the working fluid pump. The expander speed signal is sent to the rectifier via RS485 communication. The rectifier controls the output current to control the speed of the generator and the expander connected to the generator via a rigid coupling.

Images