Self-correcting online detection system for exhaust gas concentration of marine ammonia fuel engines

Abstract

The present invention discloses a self-correcting online detection system for exhaust gas concentration of a marine ammonia-fueled engine, comprising: an exhaust gas pretreatment and concentration detection module, which pre-treats high-temperature and high-pressure exhaust gas to meet the applicable range of an all-in-one online gas detection sensor and absorbs water vapor to achieve exhaust gas pretreatment and concentration detection; an exhaust gas concentration self-correction and display module, which includes an exhaust gas concentration self-correction model. This module receives the output concentration values ​​of each gas from the all-in-one online gas detection sensor and inputs set temperature and pressure. The exhaust gas concentration self-correction model performs corrections and finally displays the result. The self-correction model provides a real exhaust gas environment with variable working conditions by building an exhaust gas simulation test bench, so as to carry out test scheme design under different environments and concentrations and generate a large amount of measured data. The present invention not only ensures the effectiveness of the online detection system, but also realizes online self-correction of exhaust gas concentration detection, greatly improving the detection accuracy of exhaust gas concentration of marine ammonia-fueled engines.

Description

Technical Field

[0001] The present invention relates to the technical field of marine ammonia fuel engines, and in particular to a self-correcting online detection system for exhaust gas concentration of marine ammonia fuel engines. Background Art

[0002] At present, marine ammonia fuel engines are under development, and there is no mature technical reserve and accurate online detection solution for exhaust gas concentration. The country's exhaust emission standards for engines are also very strict, and there is an urgent need for a marine ammonia fuel engine exhaust gas concentration detection system. Due to the high temperature, high pressure, variable concentration or other different working conditions in the exhaust gas detection process, they will interfere with the detection of exhaust gas, which brings considerable challenges to the research and development of marine ammonia fuel engine combustion and exhaust gas control. In order to ensure the full combustion of ammonia fuel, the working environment of the combustion chamber of the ammonia fuel engine must be high temperature and high pressure. Therefore, the existing ammonia fuel engine detection system equipment generally first uses a pre-treatment device to cool the standard gas so that the temperature can meet the measurement temperature range of the gas sensor, and then detects the treated mixed gas (such as SCR post-treatment NO X Concentration or unburned ammonia, escape ammonia concentration), it is impossible to achieve online detection of mixed gases under special working conditions such as high temperature and high pressure. Therefore, it is urgent to develop a device that can predict the concentration of each gas in the mixed gas under high temperature and high pressure conditions. In addition, due to the problems of slow combustion speed, low flame temperature, narrow flammable range and high ignition energy in ammonia combustion, in order to improve the measurement accuracy, it is also necessary to consider the interference of different temperatures, different pressures, different exhaust components and their concentrations. In the actual combustion process, ammonia fuel cannot achieve complete combustion of all fuels, and the combustion products of incomplete combustion are N2O, NO X 、SO X and some unburned NH3, which may cause the exhaust gases to react or coexist in a complex environment, thereby affecting the detection accuracy, such as the effect of water vapor on the detection of unburned ammonia, the effect of unburned ammonia on NO X In order to carry out ammonia fuel engine development, combustion analysis and emission detection technology research, based on the above technical problems, it is urgent to design a marine ammonia fuel engine exhaust concentration self-correction online detection system for high-precision online detection under the above-mentioned complex operating conditions of actual marine ammonia fuel engines, so as to improve the accuracy and effectiveness of the detection system. Summary of the Invention

[0003] The main purpose of the present invention is to provide a self-correcting online detection system for exhaust gas concentration of a marine ammonia fuel engine. The exhaust gas pretreatment and concentration detection modules can solve the adaptability of the online detection system to the harsh exhaust gas environment and ensure the effectiveness of the online detection system. By building an exhaust gas simulation test bench, a real exhaust gas environment with variable working conditions is provided for the exhaust gas concentration online detection system, so as to carry out the design of test schemes under different environments and concentrations, generate a large amount of measured data, analyze the sensitivity and anti-interference of influencing factors, and establish a self-correcting model under multi-input and multi-output conditions, thereby eliminating the interference of the exhaust gas pretreatment and concentration detection modules and the outside world on the exhaust gas concentration detection accuracy, realize the online self-correction function of the exhaust gas concentration detection, and form a self-correcting online detection system for exhaust gas concentration of a marine ammonia fuel engine that can meet flexible and variable environments such as different pressures, temperatures, and exhaust gas concentration ratios, thereby greatly improving the exhaust gas concentration detection accuracy of the marine ammonia fuel engine.

[0004] The technical solution adopted in the present invention is:

[0005] An exhaust concentration self-correction online detection system for a marine ammonia fuel engine, comprising an exhaust gas pretreatment and concentration detection module, and an exhaust gas concentration self-correction and display module;

[0006] The exhaust gas pretreatment and concentration detection module includes a water vapor absorption module, a third condenser, a water vapor filter, an exhaust pump, a mass flow meter, and an all-in-one online gas detection sensor; the exhaust gas to be detected is connected to the water vapor absorption module, the water vapor absorption module is connected to the third condenser via an exhaust pump, the third condenser is connected to the water vapor filter, the water vapor filter is connected to the mass flow meter via an exhaust pump, and the mass flow meter is connected to the all-in-one online gas detection sensor;

[0007] The exhaust gas concentration self-correction and display module includes an exhaust gas concentration self-correction model. The exhaust gas concentration self-correction and display module receives the output concentration values ​​of each gas from the all-in-one online gas detection sensor, and inputs the set temperature and pressure, and finally displays the values ​​after correction by the exhaust gas concentration self-correction model. The establishment of the exhaust gas concentration self-correction model includes the following steps:

[0008] S1. Build a marine ammonia fuel engine exhaust simulation test bench, including an exhaust component generation module and an exhaust state control module. The exhaust component generation module is used to simulate the internal gas generation of an ammonia fuel engine during operation, including N2O, NO X 、NH3、SO X , water vapor and oil mist; the exhaust gas state control module mixes the simulated exhaust gas and adjusts the concentration of each gas through the dynamic gas distribution device, and adjusts it to the required temperature and pressure; then the output end of the exhaust gas state control module is connected to the water vapor absorption module of the exhaust gas pretreatment and concentration detection module;

[0009] S2. According to the actual combustion conditions of the ammonia fuel engine, the exhaust gas temperature T, exhaust gas pressure P, NH3 concentration N, N2O concentration K, NO X The concentration Z is divided into different temperature sets, pressure sets, and concentration sets according to a certain scale step size. A comprehensive experiment is conducted using a marine ammonia-fueled engine exhaust simulation test bench. A large amount of test data is obtained from the comprehensive experiment. The test data is formed into training sets and test sets according to the designed ratio. The training set is used to train the established BP neural network self-correction model, and the accuracy of the test model is verified by the test set.

[0010] S3, according to the test results, single factor influence and anti-interference analysis is carried out, by defining temperature T, pressure P, and the concentration data set m2 measured by the multi-in-one online gas detection sensor as input, N2O, NO in the dynamic gas distribution instrument X , the NH3 sensor output concentration data set m1 is used as the output to ensure the convergence of the self-correcting model and the error between the actual concentration prediction value and the concentration detection value in the dynamic gas distribution instrument is controlled within the set range, thereby realizing the establishment of the self-correcting model.

[0011] In the above solution, the water vapor absorption module includes a first condenser, a first polymer chemically pure membrane, a second condenser, and a second polymer chemically pure membrane connected in sequence by pipelines. The first polymer chemically pure membrane is connected to the drain outlet via a first drain pump, and the second polymer chemically pure membrane is connected to the drain outlet via a second drain pump.

[0012] In the above solution, a pressure regulating valve is provided on the pipeline after the third condenser, and the pipeline after the pressure regulating valve is divided into two branches, one of which is connected to the water vapor filter, and the other is connected to the drain outlet through a drain pump.

[0013] In the above solution, the water vapor filter is divided into two branches, one of which is connected to the exhaust pump, and the other is connected to the drain outlet after passing through the fourth condenser and the peristaltic pump in sequence.

[0014] In the above scheme, the exhaust gas component generation module includes N2O standard gas cylinder, NO X Standard gas cylinder, NH3 standard gas cylinder, SO X Standard gas cylinder, electric heating water vapor generator, oil mist generation and concentration control device;

[0015] The exhaust gas state control module includes a dynamic gas distribution instrument, a pipeline mixed gas pressure and temperature feedback control type heating device, and an oil-gas mixer;

[0016] The N2O standard gas cylinder, NO X Standard gas cylinder, NH3 standard gas cylinder, SO XThe standard gas cylinder and the electric heating water vapor generator are respectively connected to the dynamic gas distributor through pipelines, the dynamic gas distributor is connected to the pipeline mixed gas pressure temperature feedback control heating device, the pipeline mixed gas pressure temperature feedback control heating device and the oil mist generation and concentration control device are respectively connected to the oil-gas mixer; the oil-gas mixer is connected to the water vapor absorption module.

[0017] In the above scheme, pressure control valves and flow meters are respectively installed on each standard gas cylinder and the pipeline connecting the electric heated water vapor generator and the dynamic gas distribution instrument. The pressure required for the test is controlled by the pressure control valve, and the flow rate is controlled by the flow meter.

[0018] In the above scheme, the oil mist generating and concentration control device includes an oil transfer tank, an oil inlet collecting tank, a first filter, an electric heater, a fan and a porous nozzle which are connected in sequence through pipelines. A first flow regulating valve and a first flow meter are provided on the pipeline between the first filter and the electric heater.

[0019] In the above scheme, the oil mist generation and concentration control device also includes an intelligent controller. The first flow regulating valve, the first flow meter, the electric heater, and the fan are respectively communicated with the intelligent controller. The first flow meter transmits the measured flow signal to the intelligent controller, and the intelligent controller controls the opening of the first flow regulating valve, the temperature of the electric heater, and the fan speed.

[0020] In the above scheme, the dynamic gas distribution device contains N2O, NO X , NH3 concentration sensor, each concentration sensor is respectively communicated with the exhaust gas concentration self-correction model.

[0021] In the above scheme, the pipeline mixed gas pressure and temperature feedback controlled heating device includes a main valve body, a second filter, a second flow regulating valve, a second flow meter, a pipeline temperature controller, a pressure transmitter, a temperature sensor and a pressure sensor connected in sequence through pipelines, and also includes an intelligent actuator and a PID control cabinet; the intelligent actuator is respectively communicated with the pipeline temperature controller and the pressure transmitter to transmit the required temperature signal and pressure signal to the pipeline temperature controller and the pressure transmitter respectively; the temperature sensor, the pressure sensor and the intelligent actuator are respectively communicated with the PID control cabinet, and the temperature sensor and the pressure sensor transmit the collected data processed by the pipeline temperature controller and the pressure transmitter to the PID control cabinet, and the PID control cabinet detects whether the temperature and pressure meet the simulated working conditions. If there is a deviation, the PID control cabinet re-outputs an electrical signal to control the intelligent actuator to re-adjust the temperature and pressure of the mixed gas until it meets the requirements.

[0022] The beneficial effects produced by the present invention are:

[0023] 1. The present invention addresses the problem that existing detection systems are unable to accurately measure high-temperature and high-pressure (maximum temperature of 400°C and maximum pressure of 5 bar) gases. A tail gas pretreatment and concentration detection module is designed. This module not only pre-treats the high-temperature and high-pressure tail gas discharged by marine ammonia-fueled engines to meet the applicable range of the all-in-one online gas detection sensor, but also takes into account the problem of a small amount of water vapor in the pipeline being liquefied upon cooling to form water that absorbs tail gases such as ammonia and nitrogen oxides. Before detection, a high-temperature resistant polymer chemical pure membrane efficiently absorbs the high-temperature water vapor in the pipeline at multiple stages at different temperatures. While ensuring that other tail gases are not interfered with, the problem of poor detection accuracy caused by the high absorption rate of gases such as ammonia after the water vapor phase change is solved. Through multi-stage filtration of water vapor, condensation and water removal, temperature and pressure adaptation sensor adjustment to the appropriate range, and all-in-one online gas detection sensor, the pre-treatment and concentration detection of marine ammonia-fueled tail gas are achieved, solving the problem of the adaptability and effectiveness of the ammonia-fueled engine online detection system in the harsh environment of tail gas. At the same time, considering the problem of mutual reaction or interference between different exhaust components, and in order to restore the influencing factors of high temperature and high pressure in the exhaust, an exhaust concentration self-correction model was established to improve the measurement accuracy. Aiming at the detection interference problem between high temperature and high pressure and exhaust components and their concentrations, a test scheme that meets different environments and exhaust concentrations was designed. Through the analysis of multi-parameter influencing factors and anti-interference factors, a variable parameter sensitivity and weight analysis method for the exhaust concentration detection system of an ammonia fuel engine was formed; the experimental design obtained a large number of measured training and test data sets, and took the exhaust temperature, pressure and concentration of the all-in-one exhaust detection sensor as input under variable working conditions, and the N2O and NO in the dynamic gas distribution instrument were detected. X , the output concentration value of the NH3 sensor (i.e., standard gas) is defined and designed as the output. Combined with the data feature change law, variable parameter sensitivity and weight, a self-correcting model for high-precision concentration prediction is established, realizing high-precision online detection and self-correction of exhaust gas concentration in the harsh environment of ammonia fuel engine exhaust.

[0024] 2. In order to establish a self-correcting model for exhaust gas concentration, the exhaust gas simulation test bench for a marine ammonia-fueled engine constructed by the present invention realizes a true simulation of the exhaust gas concentration and composition of a marine ammonia-fueled engine, and can realize flexible control of a variety of exhaust gas components and their concentrations, exhaust gas high pressure and high temperature environment through the control devices of various parts of the exhaust gas component generation module. It can be used for simulating the internal exhaust gas state before and after SCR of a marine ammonia-fueled engine, and can also truly match the exhaust gas concentration of each working condition of a marine ammonia-fueled engine. It can provide an experimental data set for the research on the self-correcting model of exhaust gas concentration, and at the same time greatly reduce the test and verification cost of the exhaust gas-related detection system of a marine ammonia-fueled engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1 This is a schematic diagram of the installation relationship of the self-correcting online detection system for exhaust gas concentration of a marine ammonia fuel engine of the present invention and the constructed marine ammonia fuel engine exhaust gas simulation test bench;

[0027] Figure 2 It is a schematic diagram of the process of establishing the exhaust gas concentration self-correction model of the exhaust gas concentration self-correction online detection system for a marine ammonia fuel engine of the present invention;

[0028] Figure 3 2. It is a schematic structural diagram of a water vapor absorption module of a self-correcting online detection system for exhaust gas concentration of ammonia-fueled marine engines according to the present invention;

[0029] Figure 4 This is a structural schematic diagram of the oil mist generation and concentration control device of the marine ammonia fuel engine exhaust simulation test bench constructed by the present invention;

[0030] Figure 5 The present invention is a schematic structural diagram of a pipeline mixed gas pressure and temperature feedback controlled heating device for a marine ammonia fuel engine exhaust simulation test bench. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0032] It should be noted that the illustrations provided in the embodiments of the present invention are only schematic illustrations of the basic concept of the present invention. Therefore, the drawings only show components related to the present invention and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0033] In the present invention, it should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer" and the like are used to indicate positions or locations based on those shown in the accompanying drawings. These terms are intended solely to facilitate the description of the present application and to simplify the description. They are not intended to indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present application. Furthermore, the terms "first" and "second" are used solely for descriptive and distinguishing purposes and should not be construed as indicating or implying relative importance.

[0034] The present invention proposes an online detection system for exhaust gas concentration self-correction of a marine ammonia fuel engine, comprising an exhaust gas pretreatment and concentration detection module and an exhaust gas concentration self-correction and display module.

[0035] See also Figure 1 The exhaust gas pretreatment and concentration detection module includes a water vapor absorption module, a third condenser, a water vapor filter, an exhaust pump, a mass flow meter and an all-in-one online gas detection sensor. Figure 3The water vapor absorption module includes a first condenser, a first polymer chemically pure membrane, a second condenser, and a second polymer chemically pure membrane, which are sequentially connected by pipelines. The first polymer chemically pure membrane is connected to a drain outlet via a first drain pump, and the second polymer chemically pure membrane is connected to the drain outlet via a second drain pump. The exhaust gas to be detected is connected to the air inlet of the water vapor absorption module, and the air outlet of the water vapor absorption module is connected to a third condenser via a high-temperature resistant vacuum pump. A pressure regulating valve is installed on the pipeline after the third condenser. The pipeline after the pressure regulating valve is divided into two branches: one branch is connected to a water vapor filter, and the other branch is connected to the drain outlet via a drain pump. The pipeline after the water vapor filter is divided into two branches: one branch is connected to a mass flow meter and an all-in-one online gas detection sensor via an exhaust pump, and the other branch is connected to the drain outlet via a fourth condenser and a peristaltic pump. The exhaust gas pretreatment and concentration detection module mainly includes water vapor absorption, air extraction, pressure regulation, water vapor filtration, condensation and water removal, flow detection and exhaust gas concentration detection. The specific working process is as follows: the high-temperature and high-pressure exhaust gas to be detected (oil and gas mixed gas) is extracted by a high-temperature resistant vacuum pump and enters the water vapor absorption module. The mixed gas is adjusted to a certain temperature (about 200°C) by the first condenser, and then the water vapor at this temperature is absorbed by the first polymer chemical pure membrane multiple times. The absorbed water vapor can be discharged to the drain port through the drain pump, and the filtered gas enters the second condenser, and is condensed to another lower temperature (about 100°C) by the second condenser, and is discharged by the second high The molecular chemical pure membrane absorbs it again, and the treated mixed gas enters the high-temperature resistant vacuum pump and is transported to the third condenser. After the third condenser condenses the mixed gas to (-20~50℃), some water and lubricating oil on the pipeline will enter the drainage pump and be transported to the drain port for discharge, while the remaining dehydrated and deoiled mixed gas enters the water vapor filter for multiple condensation and filtration. The residual water vapor is condensed by the fourth condenser and transported to the peristaltic pump and can be directly discharged to the drain port, while the remaining mixed gas enters the exhaust pump, and the pressure is adjusted to (0.9~1.1bar) by the pressure reducing valve in the mass flow meter before entering the multi-in-one online gas detection sensor, and then the concentrations of various gases are measured respectively.

[0036] The exhaust concentration self-correction and display module includes an exhaust concentration self-correction model. The exhaust concentration self-correction and display module receives the output concentration values ​​of each gas from the multi-in-one online gas detection sensor, and inputs the set temperature and pressure, and finally displays the values ​​after correction through the exhaust concentration self-correction model. Figure 2 , the establishment of the exhaust gas concentration self-correction model includes the following steps:

[0037] S1. Build a marine ammonia fuel engine exhaust simulation test bench, including exhaust composition generation module and exhaust state control module, which can be found in Figure 1 The exhaust gas component generation module is used to simulate the internal gas generation when the ammonia fuel engine is running, including N2O, NO X、NH3、SO X , water vapor and oil mist; the exhaust gas state control module mixes the simulated exhaust gas and adjusts the concentration of each gas through the dynamic gas distributor, and adjusts the gas to the required temperature and pressure through the pipeline mixed gas pressure temperature feedback control heating device; then the output end of the exhaust gas state control module is connected to the water vapor absorption module of the exhaust gas pretreatment and concentration detection module.

[0038] S2. According to the actual combustion conditions of the ammonia fuel engine, the exhaust gas temperature T, exhaust gas pressure P, NH3 concentration N, N2O concentration K, NO X The concentration Z was divided into different temperature sets, pressure sets, and concentration sets according to a certain scale step size. A comprehensive experiment was conducted using a marine ammonia-fueled engine exhaust simulation test bench. A large amount of test data was obtained from the comprehensive experiment. The test data was divided into training and test sets in an 8:2 ratio. The established BP neural network self-correcting model was trained with the training set, and the accuracy of the experimental model was verified using the test set.

[0039] S3, according to the test results, single factor influence and anti-interference analysis are carried out, by defining temperature T, pressure P, and all-in-one online gas detection sensor to measure the concentration data set m2 = (m N2O ˊ,m NOX ˊ,m NH3 ˊ) as input, N2O, NO in the dynamic gas distribution instrument X 、NH3 sensor output concentration data set m1=(m N2O ,m NOX ,m NH3 ) as output, ensuring the convergence of the self-correcting model and keeping the error between the actual concentration prediction and the sensor detection value in the dynamic gas distribution instrument within the set range, thus establishing the self-correcting model. Program code is then generated, ultimately forming a dynamic library file that is embedded in an industrial control computer as an integrated display terminal. This terminal provides signal transmission, model correction and algorithm analysis, and result display.

[0040] All-in-one online gas detection sensors can output gas concentration values ​​using RS485 signals. Therefore, the RS485 signals from each sensor can be integrated through an RS485 serial port server and converted to Ethernet for connection to an industrial computer. The integrated display terminal can communicate signals via various methods, including USB, RS485, Ethernet, and 4G. A dedicated app can be customized to provide real-time detection and communication data, which can then be managed in a database.

[0041] The present invention addresses the problem that existing detection systems are unable to accurately measure high-temperature and high-pressure (maximum temperature of 400°C and maximum pressure of 5 bar) gases, and designs an exhaust gas pretreatment and concentration detection module. This module can not only pretreat the high-temperature and high-pressure exhaust gas discharged by marine ammonia fuel engines to meet the applicable range of the all-in-one online gas detection sensor, but also takes into account the problem of a small amount of water vapor in the pipeline being liquefied upon cooling to form water, which absorbs exhaust gases such as ammonia and nitrogen oxides. Before detection, a high-temperature resistant polymer chemical pure membrane is used to efficiently absorb the high-temperature water vapor in the pipeline at multiple stages at different temperatures. Under the premise of ensuring that other exhaust gases are not interfered with, the problem of poor detection accuracy caused by the high absorption rate of gases such as ammonia after the phase change of water vapor is solved. Through multi-stage filtration of water vapor, condensation and dehydration, temperature and pressure adaptation sensor adjustment to the appropriate range, and all-in-one online gas detection sensor, marine ammonia fuel exhaust gas pretreatment and concentration detection are achieved, solving the problem of adaptability and effectiveness of the ammonia fuel engine online detection system to the harsh exhaust environment. At the same time, considering the problem of mutual reaction or interference between different exhaust components, and in order to restore the influencing factors of high temperature and high pressure in the exhaust, an exhaust concentration self-correction model was established to improve the measurement accuracy. Aiming at the detection interference problem between high temperature and high pressure and exhaust components and their concentrations, a test scheme that meets different environments and exhaust concentrations was designed. Through the analysis of multi-parameter influencing factors and anti-interference factors, a variable parameter sensitivity and weight analysis method for the exhaust concentration detection system of an ammonia fuel engine was formed; the experimental design obtained a large number of measured training and test data sets, and took the exhaust temperature, pressure and concentration of the all-in-one exhaust detection sensor as input under variable working conditions, and the N2O and NO in the dynamic gas distribution instrument were detected. X , the output concentration value of the NH3 sensor (i.e., standard gas) is defined and designed as the output. Combined with the data feature change law, variable parameter sensitivity and weight, a self-correcting model for high-precision concentration prediction is established, realizing high-precision online detection and self-correction of exhaust gas concentration in the harsh environment of ammonia fuel engine exhaust.

[0042] During the combustion process of marine ammonia fuel engines, the combustion products with pure oxygen under high temperature conditions are nitrogen and water. However, in actual situations, ammonia fuel cannot achieve complete combustion of all fuels, and the incomplete combustion products are N2O, NO X 、SO X and some unburned NH3, so the exhaust gas component generation module mainly simulates the generation of incompletely burned exhaust gas during operation. Figure 1 As shown, N2O standard gas cylinder, NO X Standard gas cylinder, NH3 standard gas cylinder, SO X The standard gas cylinder and the electric heating water vapor generator are used to provide the standard gas required for the experiment, including N2O, NO X 、NH3、SO XThe calibration gas cylinder can be adjusted to the pressure required for the experiment through a pressure regulating valve. The high-pressure gas in each calibration gas cylinder is released and transported out to directly provide calibration gas, while the electric heating water vapor generator heats water through a thermocouple to produce a certain mass of water vapor, which is then controlled by a pressure regulating valve to the pressure required for the experiment. The flow meter on each calibration gas cylinder adjusts the flow rate of the transported gas, and the gases can be mixed subsequently through a dynamic gas distributor, which adjusts the concentration of each gas. Considering that there may be a certain concentration of oil and gas in the engine, the oil mist generation and concentration control device generates, transports, and controls the oil mist state, such as Figure 4 As shown, the oil mist generating and concentration control device includes an oil transfer tank, an oil inlet and collection tank, a first filter, an electric heater, a fan, and a multi-hole nozzle, all connected in sequence via pipelines. A first flow control valve and a first flow meter are provided on the pipeline between the first filter and the electric heater. The oil mist generating and concentration control device also includes an intelligent controller, and the first flow control valve, first flow meter, electric heater, and fan are each communicatively connected to the intelligent controller. The operating principle of the oil mist generation and concentration control device is as follows: First, lubricating oil is delivered from the oil tank to the equipment through the oil inlet pipe. When the oil inlet volume is large, the lubricating oil is transported to the oil inlet collection tank through multiple oil inlet pipes. The lubricating oil is then filtered through the first filter, and the excess lubricating oil is returned to the oil tank through the overflow pipe for recycling. The purified lubricating oil after the first filter passes through the first flow control valve. The operator adjusts the flow value in the intelligent controller according to the test requirements. The intelligent controller outputs an electrical signal to intelligently adjust the opening of the first flow control valve to adjust the flow rate, and the actual flow rate is displayed on the first flow meter. The lubricating oil at a controlled fixed flow rate enters the electric heater. In the electric heater, the lubricating oil is heated by the capillary tube and the heat transferred by the thermocouple to heat the lubricating oil to the test temperature. The heated lubricating oil enters the fan, which pushes it into the multi-hole nozzle and sprays it out as oil mist. The oil mist mixes with other gases and enters the oil-gas mixer, completing the entire oil mist control and generation process.

[0043] The exhaust gas state control module includes a dynamic gas distribution instrument, a pipeline mixed gas pressure temperature feedback control heating device, an oil-gas mixer; N2O standard gas cylinder, NO X Standard gas cylinder, NH3 standard gas cylinder, electric heating steam generator, SO X The standard gas cylinders are connected to the dynamic gas distributor through pipelines, the dynamic gas distributor is connected to the pipeline mixed gas pressure temperature feedback control heating device, the pipeline mixed gas pressure temperature feedback control heating device and the oil mist generation and concentration control device are connected to the oil-gas mixer respectively; the oil-gas mixer is connected to the water vapor absorption module. The exhaust gas state control module mainly converts the inflowing N2O and NO X , NH3, water vapor, SO XThe gas is mixed by the dynamic gas distribution instrument. The standard gases entering the dynamic gas distribution instrument are mixed with air. The concentration of each gas is obtained by the mass ratio of each standard gas and the mass of the mixed gas. When the dynamic gas distribution instrument reaches the gas concentration required for the experiment, it can be transported to the subsequent pipeline mixed gas pressure and temperature feedback control heating device to simulate the actual exhaust gas composition and environmental conditions after the combustion of ammonia fuel in the engine. In addition, the dynamic gas distribution instrument contains N2O, NO X , NH3 concentration sensor is used to detect the concentration of each gas data set m1 = (m N2O ,m NOX ,m NH3 ), each concentration sensor is respectively connected to the exhaust concentration self-correction model for communication.

[0044] like Figure 5 As shown, the pipeline mixed gas pressure-temperature feedback-controlled heating device includes a main valve body, a second filter, a second flow control valve, a second flow meter, a pipeline temperature controller, a pressure transmitter, a temperature sensor, and a pressure sensor, all connected in sequence via pipelines. It also includes an intelligent actuator and a PID control cabinet. The intelligent actuator is connected to the pipeline temperature controller and pressure transmitter, respectively; the temperature sensor, pressure sensor, and intelligent actuator are connected to the PID control cabinet, respectively. The operating principle of the pipeline mixed gas pressure-temperature feedback-controlled heating device is as follows: First, the main valve controls the inflow of the mixed gas, which passes through a second filter to remove any water and other impurities before being discharged through a drain outlet. Next, a second flow control valve controls the gas flow rate, which is displayed by a second flow meter. An intelligent actuator transmits the required temperature signal to a pipeline temperature controller, which adjusts the input power to the internal capillary tube to change the heating temperature of the mixed gas to achieve a preset value. The intelligent actuator then issues an electrical signal to adjust the pressure transducer to maintain the preset pressure of the heated mixed gas. The temperature and pressure sensors transmit processed data to a PID control cabinet, which checks whether the temperature and pressure meet the simulated operating conditions. If there are any deviations, the PID control cabinet outputs an electrical signal to control the intelligent actuator to adjust the temperature and pressure of the mixed gas until they meet the requirements. Finally, the treated mixed gas that meets the simulated operating conditions enters the oil-gas mixer and mixes with the processed oil and gas. The data can be output from the PID control cabinet to a custom app, allowing operators to remotely adjust the temperature and pressure data, enabling remote operation. At the same time, data communication can be used to the exhaust gas concentration self-correction and display module. When the experimental working conditions change, it is only necessary to adjust the required temperature and pressure conditions in the PID control cabinet to achieve the state conditions that simulate the actual working conditions.

[0045] In order to establish a self-correcting model for exhaust gas concentration, the exhaust gas simulation test bench for a marine ammonia-fueled engine constructed by the present invention realizes a true simulation of the exhaust gas concentration and composition of the marine ammonia-fueled engine, and can realize flexible control of a variety of exhaust gas components and their concentrations, exhaust gas high pressure and high temperature environment through the control devices of various parts of the exhaust gas component generation module. It can be used for simulating the internal exhaust gas state before and after SCR of the marine ammonia-fueled engine, and can also truly match the exhaust gas concentration of each working condition of the marine ammonia-fueled engine. It can provide an experimental data set for the research of the exhaust gas concentration self-correcting model, and at the same time greatly reduces the test and verification cost of the exhaust gas-related detection system of the marine ammonia-fueled engine.

[0046] The following is a process for establishing a self-correcting model for exhaust gas concentration in one embodiment of the present invention:

[0047] The temperature T and pressure P of the dynamic gas distribution instrument and the concentration data set m2 of the all-in-one exhaust gas detection sensor are used as the input signals of the exhaust concentration self-correction model. The exhaust concentration data set m1 of the dynamic gas distribution instrument is used as the output signal of the exhaust concentration self-correction model. According to the actual combustion conditions of the ammonia fuel engine, the simulation temperature range is set to 0-500℃ and divided into 10 groups of temperature values ​​with a graduation value step of 50℃: T1=50℃, T2=100℃...T 10 =500℃, the scale step can be adjusted as needed; set the simulation pressure range to 0-10bar, and divide it into 5 groups of pressure values ​​P1=2bar, P2=4bar...P5=100bar with a scale step of 2bar, and the scale step can be adjusted as needed; set the NH3 concentration range in the mixed gas to 0-500ppm, and divide it into 10 groups of concentration values ​​N1=50ppm, N2=100ppm...N with a scale step of 50ppm. 10 =500ppm, the scale step can be adjusted as needed; set the N2O concentration range in the mixed gas to 0-500ppm, and divide it into 10 groups of concentration values ​​with a scale step of 50ppm, K1=50ppm, K2=100ppm...K 10 =500ppm, the scale value step can be adjusted as needed; set the NO in the mixed gas X The concentration range is 0-500ppm, and is divided into 10 groups of concentration values ​​with a scale step of 50ppm: Z1=50ppm, Z2=100ppm...Z 10 =500ppm, the scale step can be adjusted as needed. According to the principle of comprehensive experiment, n comprehensive experiments were carried out. The output of the multi-in-one online gas detection sensor measured in the experiment was NH3 concentration N1ˊ, N2ˊ, N3ˊ...N n ˊ, N2O concentration K1ˊ, K2ˊ, K3ˊ...K n ˊ, NO X Concentration Z1ˊ, Z2ˊ, Z3ˊ...Zn ˊ; NH3 concentrations N1, N2, N3...N measured by sensors in the dynamic gas distribution instrument n , N2O concentration K1, K2, K3...K n , NO X Concentration Z1, Z2, Z3...Z n Through influencing factor analysis and anti-interference factor analysis, variable parameter sensitivity and weight analysis are carried out, and n test data are formed into training sets and test sets in an 8:2 ratio. The test correction model is trained with a training set consisting of 0.8n groups of data, and the accuracy of the test model is verified by a test set consisting of 0.2n groups of data, and the characteristic law is obtained. The characteristic law is then combined with the variable parameter sensitivity and weight analysis to ensure that the self-correction model converges and the error between the actual value of the concentration prediction and the detection value is controlled within the set range. Then, the BP neural network is embedded in the self-correction model of high-precision concentration prediction, and the model is formed into a code and a dynamic database file. The model code and dynamic database are embedded in the exhaust concentration self-correction display terminal to predict the exhaust concentration under high temperature and high pressure conditions.

[0048] At this time, the exhaust concentration self-correction model inputs a certain temperature, pressure, and exhaust concentration detected by the multi-in-one online gas detection sensor, and the high-precision concentration prediction self-correction model outputs the predicted N2O and NO before pretreatment. X , NH3, and other gas concentrations, and thus, the exhaust gas concentration can be predicted under high temperature and high pressure. If the operator requires a more precise measurement standard, they can increase the number of experiments and rebuild the self-correcting model until the error between the predicted results and the actual measurement results (i.e., the dynamic gas distribution instrument exhaust gas concentration dataset m1) is within 0.1%, achieving highly accurate exhaust gas concentration prediction and self-correction.

[0049] It should be pointed out that, according to the needs of implementation, the various steps / components described in this application can be split into more steps / components, or two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0050] The size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0051] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. A self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines, characterized in that: Including exhaust gas pretreatment and concentration detection module, exhaust gas concentration self-correction and display module; The exhaust gas pretreatment and concentration detection module includes a water vapor absorption module, a third condenser, a water vapor filter, an exhaust pump, a mass flow meter, and an all-in-one online gas detection sensor; the exhaust gas to be detected is connected to the water vapor absorption module, the water vapor absorption module is connected to the third condenser via an exhaust pump, the third condenser is connected to the water vapor filter, the water vapor filter is connected to the mass flow meter via an exhaust pump, and the mass flow meter is connected to the all-in-one online gas detection sensor; The exhaust gas concentration self-correction and display module includes an exhaust gas concentration self-correction model. The exhaust gas concentration self-correction and display module receives the output concentration values ​​of each gas from the all-in-one online gas detection sensor, and inputs the set temperature and pressure, and finally displays the values ​​after correction by the exhaust gas concentration self-correction model. The establishment of the exhaust gas concentration self-correction model includes the following steps: S1. Build a marine ammonia fuel engine exhaust simulation test bench, including an exhaust component generation module and an exhaust state control module. The exhaust component generation module is used to simulate the internal gas generation of the ammonia fuel engine during operation, including N2O, NO X 、NH3、SO X , water vapor and oil mist; the exhaust gas state control module mixes the simulated exhaust gas and adjusts the concentration of each gas through the dynamic gas distribution device, and adjusts it to the required temperature and pressure; then the output end of the exhaust gas state control module is connected to the water vapor absorption module of the exhaust gas pretreatment and concentration detection module; S2. According to the actual combustion conditions of the ammonia fuel engine, the exhaust gas temperature T, exhaust gas pressure P, NH3 concentration, N2O concentration, NO X The concentration is divided into different temperature sets, pressure sets, and concentration sets according to a certain scale step size. A comprehensive experiment is conducted using a marine ammonia-fueled engine exhaust simulation test bench. A large amount of test data is obtained from the comprehensive experiment. The test data is formed into training sets and test sets according to the designed ratio. The training set is used to train the established BP neural network self-correction model, and the accuracy of the test model is verified by the test set. S3, according to the test results, single factor influence and anti-interference analysis are carried out, by defining temperature T, pressure P, and all-in-one online gas detection sensor to measure the exhaust concentration data set m2 as input, N2O, NO in the dynamic gas distribution instrument X , the NH3 sensor output concentration data set m1 is used as the output to ensure the convergence of the self-correcting model and the error between the actual concentration prediction value and the concentration detection value in the dynamic gas distribution instrument is controlled within the set range, thereby realizing the establishment of the self-correcting model.

2. The self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines according to claim 1 is characterized in that: The water vapor absorption module includes a first condenser, a first polymer chemical pure membrane, a second condenser, and a second polymer chemical pure membrane connected in sequence through pipelines. The first polymer chemical pure membrane is connected to a drain outlet through a first drain pump, and the second polymer chemical pure membrane is connected to the drain outlet through a second drain pump.

3. The self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines according to claim 1 is characterized in that: A pressure regulating valve is provided on the pipeline after the third condenser, and the pipeline after the pressure regulating valve is divided into two branches, one of which is connected to the water vapor filter, and the other branch is connected to the drain outlet through a drain pump.

4. The self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines according to claim 1 is characterized in that: The water vapor filter is divided into two branches, one of which is connected to the exhaust pump, and the other is connected to the drain port after passing through the fourth condenser and the peristaltic pump in sequence.

5. The self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines according to claim 1 is characterized in that: The tail gas component generation module includes N2O standard gas cylinder, NO X Standard gas cylinder, NH3 standard gas cylinder, SO X Standard gas cylinder, electric heating water vapor generator, oil mist generation and concentration control device; The exhaust gas state control module includes a dynamic gas distribution instrument, a pipeline mixed gas pressure and temperature feedback control type heating device, and an oil-gas mixer; The N2O standard gas cylinder, NO X Standard gas cylinder, NH3 standard gas cylinder, SO X The standard gas cylinder and the electric heating water vapor generator are respectively connected to the dynamic gas distributor through pipelines, the dynamic gas distributor is connected to the pipeline mixed gas pressure temperature feedback control heating device, the pipeline mixed gas pressure temperature feedback control heating device and the oil mist generation and concentration control device are respectively connected to the oil-gas mixer; the oil-gas mixer is connected to the water vapor absorption module.

6. The self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines according to claim 5 is characterized in that: Pressure control valves and flow meters are installed on each standard gas cylinder and the pipeline connecting the electric heating water vapor generator and the dynamic gas distribution instrument. The pressure required for the test is controlled by the pressure control valve, and the flow rate is controlled by the flow meter.

7. The self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines according to claim 5 is characterized in that: The oil mist generating and concentration controlling device comprises an oil transfer tank, an oil inlet collecting tank, a first filter, an electric heater, a fan and a porous nozzle which are sequentially connected through pipelines; a first flow regulating valve and a first flow meter are provided on the pipeline between the first filter and the electric heater.

8. The self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines according to claim 7 is characterized in that: The oil mist generation and concentration control device also includes an intelligent controller. The first flow regulating valve, the first flow meter, the electric heater, and the fan are respectively communicated with the intelligent controller. The first flow meter transmits the measured flow signal to the intelligent controller, and the intelligent controller controls the opening of the first flow regulating valve, the temperature of the electric heater, and the fan speed.

9. The self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines according to claim 5 is characterized in that: The dynamic gas distribution device contains N2O, NO X , NH3 concentration sensor, each concentration sensor is respectively communicated with the exhaust gas concentration self-correction model.

10. The self-correcting online detection system for exhaust gas concentration of ammonia fueled marine engines according to claim 5, characterized in that: The pipeline mixed gas pressure and temperature feedback controlled heating device includes a main valve body, a second filter, a second flow regulating valve, a second flow meter, a pipeline temperature controller, a pressure transmitter, a temperature sensor and a pressure sensor, which are connected in sequence through pipelines, and also includes an intelligent actuator and a PID control cabinet; the intelligent actuator is respectively communicated with the pipeline temperature controller and the pressure transmitter to transmit the required temperature signal and pressure signal to the pipeline temperature controller and the pressure transmitter respectively; the temperature sensor, the pressure sensor and the intelligent actuator are respectively communicated with the PID control cabinet, and the temperature sensor and the pressure sensor transmit the collected data processed by the pipeline temperature controller and the pressure transmitter to the PID control cabinet, and the PID control cabinet detects whether the temperature and pressure meet the simulated working conditions. If there is a deviation, the PID control cabinet re-outputs an electrical signal to control the intelligent actuator to re-adjust the temperature and pressure of the mixed gas until it meets the requirements.

Images