CN114961985B - Hydrogen fuel aviation rotor engine performance intelligent prediction method and system - Google Patents
Hydrogen fuel aviation rotor engine performance intelligent prediction method and system Download PDFInfo
- Publication number
- CN114961985B CN114961985B CN202210510695.2A CN202210510695A CN114961985B CN 114961985 B CN114961985 B CN 114961985B CN 202210510695 A CN202210510695 A CN 202210510695A CN 114961985 B CN114961985 B CN 114961985B
- Authority
- CN
- China
- Prior art keywords
- hydrogen fuel
- rotor engine
- indicated
- engine
- hydrogen
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000000446 fuel Substances 0.000 title claims abstract description 162
- 229910052739 hydrogen Inorganic materials 0.000 title claims abstract description 132
- 239000001257 hydrogen Substances 0.000 title claims abstract description 132
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000002485 combustion reaction Methods 0.000 claims abstract description 76
- 238000004088 simulation Methods 0.000 claims abstract description 48
- 238000003062 neural network model Methods 0.000 claims abstract description 42
- 239000007789 gas Substances 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000002347 injection Methods 0.000 claims description 21
- 239000007924 injection Substances 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 8
- 230000001052 transient effect Effects 0.000 claims description 8
- 238000004134 energy conservation Methods 0.000 claims description 6
- 238000007906 compression Methods 0.000 claims description 5
- 238000010304 firing Methods 0.000 claims description 4
- 230000017525 heat dissipation Effects 0.000 claims description 4
- 238000010438 heat treatment Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims 1
- 238000011217 control strategy Methods 0.000 abstract description 3
- 238000013461 design Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 description 6
- 230000000704 physical effect Effects 0.000 description 6
- 238000009413 insulation Methods 0.000 description 5
- 230000006835 compression Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 229910052799 carbon Inorganic materials 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 125000004435 hydrogen atom Chemical group [H]* 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000003350 kerosene Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
- F02B53/00—Internal-combustion aspects of rotary-piston or oscillating-piston engines
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
- F02B53/00—Internal-combustion aspects of rotary-piston or oscillating-piston engines
- F02B53/04—Charge admission or combustion-gas discharge
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
- F02B55/00—Internal-combustion aspects of rotary pistons; Outer members for co-operation with rotary pistons
- F02B55/02—Pistons
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
- F02B55/00—Internal-combustion aspects of rotary pistons; Outer members for co-operation with rotary pistons
- F02B55/14—Shapes or constructions of combustion chambers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
- F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
- F02B77/00—Component parts, details or accessories, not otherwise provided for
- F02B77/08—Safety, indicating, or supervising devices
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/40—Application of hydrogen technology to transportation, e.g. using fuel cells
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The invention discloses an intelligent prediction method and system for performance of a hydrogen fuel aviation rotor engine, which comprises the following specific steps: constructing a zero-dimensional performance simulation model of the hydrogen fuel aviation rotor engine based on the actual gas physical parameters and the laminar flame propagation speed of the hydrogen fuel combustion process; obtaining the engine indicated power, the indicated heat efficiency and the indicated oil consumption rate according to the zero-dimensional performance simulation model to obtain a rotor engine zero-dimensional performance simulation data set; constructing a hydrogen fuel rotor engine performance neural network model based on a Bayesian regularization algorithm, and training the hydrogen fuel rotor engine performance neural network model by adopting a simulation data set; predicting and obtaining the indicated power, the indicated heat efficiency and the indicated fuel consumption rate of the hydrogen fuel rotor engine by utilizing the hydrogen fuel rotor engine performance neural network model; the invention can realize quick and accurate prediction of the engine performance and can provide firm theoretical support for the control system design of the engine and the establishment of the optimal control strategy of the engine.
Description
Technical Field
The invention belongs to the field of aviation power, and particularly relates to an intelligent prediction method and system for performance of a hydrogen fuel aviation rotor engine integrating a zero-dimensional model and a neural network.
Background
The distributed and clustered air combat operation style relies on a distributed and clustered combat platform composed of a plurality of small unmanned aerial vehicles, and compared with the traditional single omnipotent unmanned aerial vehicle, the distributed and clustered air combat platform has more urgent requirements on a power system of a clustered platform of the small unmanned aerial vehicle with high efficiency, low cost and long endurance. For microminiature unmanned aerial vehicles with thrust power requirements within 1kN/50kW, piston engines, rotor engines, turbojet engines and electric drive systems are commonly adopted as power sources. The rotary engine, namely the Wankel engine, has the advantages of simple and compact structure, high power-weight ratio, small vibration and noise, relatively low oil consumption and the like, and has outstanding performance in a small unmanned aerial vehicle power device.
With the carbon reduction demand of aviation industry, more environment-friendly low-carbon hydrogen is being used for replacing traditional high-carbon emission gasoline, kerosene and other fuels. The performance prediction of the hydrogen fuel aviation rotor engine under the complex working condition is crucial to the safe operation of the aviation rotor engine. The existing performance prediction method of the aviation rotor engine mainly adopts three-dimensional CFD numerical simulation software, and has the defects of slow simulation prediction speed, huge occupied computing resources, high memory up to above GB and the like. The current one-dimensional simulation commercial software AVL BOOST and GT-POWER are mainly suitable for the traditional reciprocating piston engine, and the prediction method for replacing the rotor engine by using the three-cylinder four-stroke piston engine model has the defect of low prediction precision. In addition, the ideal gas physical properties are adopted in the calculation process of the current three-dimensional CFD numerical simulation software and the one-dimensional simulation commercial software. However, the water content of the combustion products of the hydrogen fuel is far greater than that of the conventional hydrocarbon fuel, and its actual physical properties are severely deviated from theoretical gas physical properties, so that it is not suitable to calculate the combustion products of the hydrogen fuel using ideal gas physical properties.
In view of the foregoing, there is a need for a fast, high-precision prediction method and system for a hydrogen-fueled aircraft rotor engine.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides the intelligent prediction method and the intelligent prediction system for the performance of the hydrogen fuel aviation rotor engine, which integrate a zero-dimensional model based on actual gas physical parameters and flame propagation speed and a neural network model based on a Bayesian regularization algorithm, and realize that the indicated power, the indicated thermal efficiency and the indicated fuel consumption rate of the aviation rotor engine under various operating conditions can be rapidly and accurately predicted by given the core geometric parameters of the hydrogen fuel engine.
In order to achieve the above purpose, the present invention provides the following technical solutions: an intelligent prediction method for performance of a hydrogen fuel aviation rotor engine comprises the following specific steps:
S1, constructing a zero-dimensional performance simulation model of a hydrogen fuel aero-rotor engine based on transient mass conservation, energy conservation, actual gas physical parameters and laminar flame propagation speed in a hydrogen fuel combustion process;
S2, given the core geometric parameters of the hydrogen fuel rotor engine, under the condition of any combination of the hydrogen fuel injection quantity, the rotating speed and the ignition advance angle, the indicated power, the indicated heat efficiency and the indicated fuel consumption rate of a zero-dimensional performance simulation model of the hydrogen fuel aviation rotor engine are obtained, and a rotor engine zero-dimensional performance simulation data set is obtained;
S3, constructing a hydrogen fuel rotor engine performance neural network model based on a Bayesian regularization algorithm, and training the hydrogen fuel rotor engine performance neural network model by adopting a rotor engine zero-dimensional performance simulation data set;
And S4, inputting the hydrogen fuel injection quantity, the rotating speed and the ignition advance angle which are arbitrarily combined into a hydrogen fuel rotor engine performance neural network model, and predicting to obtain the indicated power, the indicated thermal efficiency and the indicated fuel consumption rate of the hydrogen fuel rotor engine.
Further, in step S1, the zero-dimensional performance simulation model of the hydrogen-fuelled aero-rotor engine includes air intake, compression, combustion, expansion, and exhaust process modules, in which a geometric sub-model, a thermodynamic sub-model, a heat exchange loss sub-model, a mass leakage sub-model, and a combustion heat release sub-model are embedded, wherein the geometric sub-model is used for obtaining the volume V of each working chamber in the aero-rotor engine; the thermodynamic submodel is used for obtaining the pressure P of the working chamber through an actual gas physical state equation; the heat exchange loss submodel is used for obtaining the heat convection loss Q w of the gas in the working chamber of the engine and the wall surface of the engine, and the combustion heat release submodel is used for obtaining the combustion heat release Q B of the hydrogen fuel according to the laminar flame propagation speed S; the mass leakage sub-model is used for acquiring leakage mass m leak of gas between adjacent chambers at the top of the rotor.
Further, in step S1, the combustion heat release sub-model predicts the combustion heat release amount Q B of the hydrogen fuel by using a weber heat release model, and specifically:
wherein: LHV is the lower heating value of the fuel; η B is the combustion efficiency; Is the combustion sustaining angle; /(I) Is the firing angle; m is the combustion quality coefficient.
Further, in step S1, the laminar flame propagation speed S in the hydrogen combustion process determines the combustion duration angleThe laminar flame propagation speed S under different temperature and pressure conditions is obtained by correcting the laminar flame propagation speed S ref under the standard conditions, as shown in formulas 6-8.
γ＝2.18-0.8(φ-1) (7)
σ＝-0.16+0.22(φ-1) (8)
Wherein: gamma is a temperature correction coefficient; sigma is a pressure correction coefficient; phi is the equivalence ratio.
Further, in step S1, the combustion duration angleIs calculated according to the formula:
Wherein S des is the flame propagation speed under the rated working condition.
Further, in step S1, the working chamber pressure P is obtained from a benefect-Webb-Rubin actual gas physical state equation, specifically:
Wherein: m c is the working medium mass of the working chamber; u is the internal energy of the working medium of the cavity; q B is combustion heat release quantity; m in intake air mass; h in is the intake air enthalpy; m fuel intake fuel mass; h fuel is the intake fuel enthalpy; m exh is the exhaust mass; h exh is the exhaust enthalpy; m leak is the leakage mass; h leak is the enthalpy value of the leaked working medium; q w is the heat dissipation between the chamber gas and the cylinder and rotor wall; v m is the molar volume; r is a gas constant; a 0,B0,C0, a, b, c, α, γ are constants.
Further, in step S3, the performance neural network model of the hydrogen fuel rotor engine includes 3 input layer network node numbers, 20 hidden layer network node numbers, and 3 output layer network node numbers; an input layer x= [ x 1,x2,x3]T, wherein x 1、x2、x3 represents hydrogen fuel injection amount, rotation speed and ignition advance angle x 3, respectively; output layer y= [ y 1,y2,y3]T, where y 1、y2、y3 represents indicated power y 1, indicated heat efficiency y 2, and indicated fuel consumption y 3, respectively.
Further, in step S3, the hydrogen-fuelled rotary engine performance neural network model is specifically:
wherein S i is hidden layer node data in the ith iteration, K is an activation function max (0.1 x, x), w, U and v are weight coefficients, and b is the data_Y of the output layer and the data of the actual output layer of the kth iteration prediction Deviation of (2); /(I)Is the normalized input layer; Is the normalized output layer.
Further, in step S3, the predicted output layer data_y is inversely normalized to 'reverse', and then predicted actual output layer node data y= [ Y 1,y2,y3]T ] is obtained, that is, the indicated power Y 1, the indicated thermal efficiency Y 2, and the indicated fuel consumption Y 3 of the hydrogen fuel rotor engine are specifically:
wherein: ps is a mapping of output layer data.
The invention also provides an intelligent prediction system for the performance of the hydrogen fuel aviation rotor engine, which comprises
The simulation model building module is used for building a zero-dimensional performance simulation model of the hydrogen fuel aviation rotor engine based on transient mass conservation, energy conservation, actual gas physical parameters and laminar flame propagation speed in the hydrogen fuel combustion process;
The simulation data set establishing module is used for obtaining the indication power, the indication heat efficiency and the indication oil consumption rate of the zero-dimensional performance simulation model of the hydrogen fuel aviation rotor engine under the condition of giving the core geometric parameters of the hydrogen fuel rotor engine and combining the injection quantity, the rotation speed and the ignition advance angle of the hydrogen fuel at random to obtain a rotor engine zero-dimensional performance simulation data set;
The network model building training module is used for building a hydrogen fuel rotor engine performance neural network model based on a Bayesian regularization algorithm and training the hydrogen fuel rotor engine performance neural network model by adopting a rotor engine zero-dimensional performance simulation data set;
The prediction module is used for inputting the hydrogen fuel injection quantity, the rotating speed and the ignition advance angle which are arbitrarily combined into the hydrogen fuel rotor engine performance neural network model, and predicting to obtain the indicated power, the indicated thermal efficiency and the indicated fuel consumption rate of the hydrogen fuel rotor engine.
Compared with the prior art, the invention has at least the following beneficial effects:
According to the intelligent prediction method for the hydrogen fuel aviation rotor engine, provided by the invention, a zero-dimensional model based on actual gas physical parameters and laminar flame propagation speed and a neural network model based on a Bayesian regularization algorithm are integrated, the prediction of the aviation rotor engine for indicating power, indicating thermal efficiency and indicating fuel consumption rate can be rapidly carried out under the conditions of different hydrogen fuel injection amounts, different rotating speeds and different ignition advance angles, the rapid and accurate prediction of the engine performance is realized, a firm theoretical support can be provided for the design of a control system of the engine and the formulation of an optimal control strategy of the engine, and the predicted engine performance data can be used for evaluating the performance degradation condition of the hydrogen fuel aviation rotor engine by comparing with the actual test performance data.
According to the intelligent prediction method for the hydrogen fuel aviation rotor engine, provided by the invention, the actual gas physical parameters comprising the internal energy u, the enthalpy h, the specific heat capacity c p at a constant pressure, the specific heat capacity c v at a constant pressure and the heat insulation coefficient k are obtained by an interpolation method based on a self-built working medium thermophysical software library, the pressure of a working chamber is solved by adopting an actual gas state equation instead of a traditional ideal gas state equation, the temperature and the pressure of the working chamber obtained by simulation are closer to the actual state, the calculation precision is improved, and the determination coefficient R 2 of a prediction result reaches more than 0.98.
The intelligent prediction method for the hydrogen fuel aviation rotor engine is strong in expansibility, the performance prediction of the rotor engine with different structures can be realized by only changing the core parameters of the rotor engine, and the method converts the iterative solution of a plurality of complex differential equations in the traditional simulation calculation method into the intelligent calculation of a neural network model, realizes the improvement of the prediction speed and the reduction of the calculation memory by reducing the calculation task amount, the prediction speed can reach millisecond level, and the algorithm occupies little computer memory and is only KB level.
Drawings
FIG. 1 is a hydrogen fuelled aero rotor engine performance intelligent prediction method;
FIG. 2 is a schematic illustration of a rotary engine configuration;
FIG. 3 is a zero-dimensional simulation model structure of a hydrogen-fuelled rotary engine;
FIG. 4 is a plot of the variation of the volume V of each working chamber of the rotary engine with the eccentric shaft rotation angle;
FIG. 5 shows the variation trend of the hydrogen combustion heat release rate with the eccentric shaft rotation angle in the rotary engine;
FIG. 6 is a graph showing the variation trend of the flame propagation speed S ref of the hydrogen combustion laminar flow with the equivalence ratio under the standard condition;
FIG. 7 is a comparison of simulated operating pressure of a zero-dimensional model of a rotary engine with an experiment;
FIG. 8 is a comparison of simulated operating temperature of a zero-dimensional model of a rotary engine with an experiment;
FIG. 9 is a graph of indicated fuel consumption rate trend for a hydrogen fueled aircraft rotor engine at different rotational speeds;
FIG. 10 is an indicated power trend of a hydrogen fuelled aircraft rotorblock at different speeds;
FIG. 11 is an indicated thermal efficiency trend for a hydrogen fuelled aircraft rotorblock at different speeds;
FIG. 12 is an indicated fuel consumption rate trend for a hydrogen fuelled aircraft rotary engine with varying amounts of hydrogen fuel injected;
FIG. 13 is an indicated power trend of a hydrogen fuelled aircraft rotary engine with varying amounts of hydrogen fuel injection;
FIG. 14 is an indicated thermal efficiency trend for a hydrogen fuelled aircraft rotary engine with varying amounts of hydrogen fuel injection;
FIG. 15 is a graph of indicated fuel consumption rate trend for a hydrogen fuelled aircraft rotary engine at different spark advance angles;
FIG. 16 is an indicated power trend for a hydrogen fuelled aircraft rotary engine at different spark advance angles;
FIG. 17 is an indicated thermal efficiency trend for a hydrogen fuelled aircraft rotary engine at different spark advance angles;
FIG. 18 is a schematic diagram of a neural network model structure;
fig. 19 is a neural network model fitting result.
Detailed Description
In order to make the purposes, technical effects and technical solutions of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention are clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention; it will be apparent that the described embodiments are some of the embodiments of the present invention. Other embodiments, which may be made by those of ordinary skill in the art based on the disclosed embodiments without undue burden, are within the scope of the present invention.
As shown in FIG. 1, the intelligent prediction method for the performance of the hydrogen-fueled aero-rotor engine integrates a zero-dimensional model based on actual gas physical parameters and laminar flame propagation speed in the hydrogen-fueled combustion process and a neural network model based on a Bayesian regularization algorithm, and can rapidly and accurately predict the indicated power, the indicated thermal efficiency and the indicated fuel consumption rate of the aero-rotor engine under various operating conditions by given core geometrical parameters of the hydrogen-fueled aero-rotor engine, and the method comprises the following specific steps:
the first step M1 is to construct a zero-dimensional performance simulation model of the hydrogen fuel aviation rotor engine based on transient mass conservation, energy conservation, actual gas physical property state parameters and laminar flame propagation speed in the hydrogen fuel combustion process.
And a second step M2 of verifying a zero-dimensional simulation model of the hydrogen fuel aero-rotor engine by adopting experimental data, and obtaining a zero-dimensional performance simulation data set of the aero-rotor engine by simulating at least 10000 groups of different hydrogen fuel injection amounts, different rotating speeds and different ignition advance angles when the core geometric parameters (the shape coefficient K, the eccentricity e, the cylinder body thickness B and the pit volume V c) of the given hydrogen fuel aero-rotor engine are obtained based on the zero-dimensional simulation model after experimental verification.
And step 3, constructing a hydrogen fuel rotor engine performance neural network model based on a Bayesian regularization algorithm, and training the hydrogen fuel rotor engine performance neural network model by adopting a rotor engine zero-dimensional performance simulation data set.
And a fourth step M4, namely appointing the core geometric parameters (the shape coefficient K, the eccentricity e, the cylinder body thickness B and the pit volume V c of the combustion chamber) of the hydrogen fuel rotor engine, and inputting the hydrogen fuel injection quantity, the rotating speed and the ignition advance angle into the performance neural network model of the hydrogen fuel rotor engine, wherein the performance neural network model of the hydrogen fuel rotor engine can rapidly and accurately predict the indication power, the indication thermal efficiency and the indication fuel consumption rate of the hydrogen fuel rotor engine.
In the first step, the zero-dimensional performance simulation model of the hydrogen-fuelled aviation rotor engine comprises air inlet, compression, combustion, expansion and exhaust process modules, wherein a geometric submodel, a thermodynamic submodel based on actual gas physical properties, a heat exchange loss submodel and a mass leakage submodel are embedded in each process module, and a combustion heat release submodel based on the propagation speed of the laminar flame of hydrogen is additionally embedded in the combustion module.
Wherein:
The geometric submodel is used for obtaining the volume of a working chamber, three chambers formed between a cylinder body and a triangular rotor of the rotor engine are all working chambers, and the working chambers are rotated along with the eccentric shaft Each working chamber volume V is given by equation 1:
wherein: k is a shape factor; e is the eccentricity; b is the thickness of the cylinder body; v k is the combustion chamber pit volume.
The thermodynamic submodel is used for obtaining the pressure P and the temperature T of the working chambers, the three working chambers are subjected to the same air inlet, compression, combustion, expansion and exhaust processes under different phases, the engine works for three times when the rotor rotates, mechanical energy is externally output through the eccentric shaft, the working temperature T of the chambers in each working process is obtained by transient energy (formula 2) and a mass conservation equation (formula 3), the working pressure of the chambers is obtained by a Benedict-Webb-Rubin actual gas physical state equation (formula 4), and physical parameters such as internal energy u, enthalpy h, specific pressure specific heat capacity c p, specific heat capacity c v, heat insulation coefficient k and the like which are related to the thermodynamic submodel are all called by interpolation of a self-building physical database.
Wherein: m c is the working medium mass of the working chamber; u is the internal energy of the working medium of the cavity; q B is combustion heat release quantity; m in intake air mass; h in is the intake air enthalpy; m fuel intake fuel mass; h fuel is the intake fuel enthalpy; m exh is the exhaust mass; h exh is the exhaust enthalpy; m leak is the leakage mass; h leak is the enthalpy value of the leaked working medium; q w is the heat dissipation between the chamber gas and the cylinder and rotor wall; v m is the molar volume; r is a gas constant; a 0,B0,C0, a, b, c, α, γ are constants.
The combustion heat release sub-model is used for obtaining the combustion heat release quantity Q B of the hydrogen fuel, and a Weber heat release model (formula 5) is adopted for predicting the heat release quantity Q B in the fuel combustion process.
Wherein: LHV is the lower heating value of the fuel; η B is the combustion efficiency; Is the combustion sustaining angle; /(I) Is the firing angle; m is the combustion quality coefficient.
Combustion sustaining angleIs determined by the laminar flame propagation speed S in the hydrogen combustion process, and the combustion duration angle/>, under the rated working conditionThrough three-dimensional CFD numerical simulation calibration, combustion sustaining angle/>, under other working conditionsObtained by equation 9.
The laminar flame propagation speed S under different temperature and pressure conditions is obtained by correcting the laminar flame propagation speed S ref under the standard conditions, as shown in formulas 6-8.
γ＝2.18-0.8(φ-1) (7)
σ＝-0.16+0.22(φ-1) (8)
Wherein: gamma is a temperature correction coefficient; sigma is a pressure correction coefficient; phi is the equivalence ratio; s des is the flame propagation speed under the rated working condition; Is the combustion duration angle under the rated working condition.
The heat exchange loss submodel is used for obtaining the heat convection loss quantity Q w of the gas in the working chamber and the wall surface of the engine, and is calculated by formulas 10-11:
Wherein: a w is the heat exchange area of the wall surface; alpha c is the convective heat transfer coefficient; u is the average speed of the rotor.
The mass leakage sub-model is used for obtaining leakage mass m leak of gas between adjacent chambers at the top of the rotor, the leakage loss is calculated by Bernoulli equation, the mass of subsonic leakage flow is obtained by equation 12 when the pressure of the working chamber is lower than the critical pressure (equation 14), and the mass of sonic leakage flow is obtained by equation 13 when the pressure of the working chamber is higher than the critical pressure.
Wherein: k is the air flow insulation coefficient; a leak is the leakage area; τ is time; p cr is critical pressure; p 0 is ambient pressure.
In the step 3, the performance neural network model of the hydrogen fuel rotor engine comprises 3 input layer network node numbers, 20 hidden layer network node numbers and 3 output layer network node numbers;
the input layer x= [ x 1,x2,x3]T network nodes respectively represent the hydrogen fuel injection quantity x 1, the rotating speed x 2 and the ignition advance angle x 3;
The output layer y= [ y 1,y2,y3]T network nodes represent the indicated power y 1, the indicated thermal efficiency y 2 and the indicated fuel consumption y 3 respectively.
Firstly, a training data set is read, and data of each node of an input layer and an output layer are normalized to be between 0 and 1 to obtain a normalized input layerAnd output layer/>
Wherein: ps is a mapping of output layer data.
Secondly, a neural network is created, the total iterative computation times are set to be N times, hidden layer data S k-1 in the k-1 th iteration is stored in real time and fed back to be used for the k-1 th iteration computation; the weight coefficients w and U are random numbers, and the weight coefficients w and U are the same under each iteration; hidden layer data S k at the kth iteration is calculated by equation 17, where the activation function K (x) is max (0.1 x, x);
wherein: b is the k iteration prediction output layer data And actual output layer data/>Deviation of (2);
Further, the kth iteration predicts the output layer data Calculating by a formula 18, wherein the weight coefficient v is a random number, and the weight coefficient v is the same under each iteration;
Finally, after the output layer data is inversely normalized to 'reverse', predicted actual output layer node data Y= [ Y 1,y2,y3]T ] can be obtained, namely the indicated power Y 1, the indicated heat efficiency Y 2 and the indicated fuel consumption rate Y 3 of the hydrogen fuel rotor engine;
Based on the constructed neural network structure model, a Bayesian regularization algorithm is adopted to train the model, training data is at least 10000 sets of zero-dimensional performance simulation data sets selected randomly, wherein 80% of the training data sets are used for training the model, and 20% of the training data sets are used for testing the model. And iterating for N times until the prediction error b meets the training target error to obtain the hydrogen fuel rotor engine performance neural network model.
And (3) deriving a function corresponding to the neural network model with the qualified training, namely the decision coefficient R 2 not less than 0.98, so as to obtain the trained hydrogen fuel rotor engine performance neural network model.
The invention also provides an intelligent prediction system for the performance of the hydrogen fuel aviation rotor engine, which comprises the following steps:
The simulation model building module is used for building a zero-dimensional performance simulation model of the hydrogen fuel aviation rotor engine based on transient mass conservation, energy conservation, actual gas physical parameters and laminar flame propagation speed in the hydrogen fuel combustion process;
The simulation data set establishing module is used for obtaining the indication power, the indication heat efficiency and the indication oil consumption rate of the zero-dimensional performance simulation model of the hydrogen fuel aviation rotor engine under the condition of giving the core geometric parameters of the hydrogen fuel rotor engine and combining the injection quantity, the rotation speed and the ignition advance angle of the hydrogen fuel at random to obtain a rotor engine zero-dimensional performance simulation data set;
The network model building training module is used for building a hydrogen fuel rotor engine performance neural network model based on a Bayesian regularization algorithm and training the hydrogen fuel rotor engine performance neural network model by adopting a rotor engine zero-dimensional performance simulation data set;
The prediction module is used for inputting the hydrogen fuel injection quantity, the rotating speed and the ignition advance angle which are arbitrarily combined into the hydrogen fuel rotor engine performance neural network model, and predicting to obtain the indicated power, the indicated thermal efficiency and the indicated fuel consumption rate of the hydrogen fuel rotor engine.
Example 1
As shown in FIG. 2, in the geometric structural parameter of the rotor engine adopted in the embodiment, the eccentricity e is 15mm, the shape coefficient K is 7, the cylinder body thickness B is 70mm, the rotor combustion pit volume is 50cm 3, and the rotor top gap leakage area A leak is 0.01cm 2. The structural parameter is used for predicting the performance parameters of the engine under different working conditions, the rated rotation speed of the engine is 7000rpm, and the rated combustion ignition advance angle is 27 degrees.
The method comprises the steps of M1, constructing a zero-dimensional performance simulation model of the hydrogen fuel aero-rotor engine based on transient mass conservation, energy conservation, an actual gas thermophysical equation and a laminar flame propagation speed in a hydrogen fuel combustion process, and referring to FIG. 3;
In the geometric submodel, three chambers between the cylinder body of the rotor engine and the triangular rotor are all working chambers. With the rotation angle of the eccentric shaft Each working chamber volume V is derived from equation (1).
Wherein: k is a shape factor, example taking 7; e is the eccentricity, taking 15mm for example; b is the thickness of the cylinder body, and is exemplified by 70mm; v k is the combustion chamber pit volume, exemplified by 50cm 3.
Referring to fig. 4, the volume V of each working chamber of the rotary engine varies with the rotation angle of the eccentric shaftIs a variable value of (a).
The thermodynamic submodel is used for obtaining the pressure P and the temperature T of the working chambers, the three working chambers are subjected to the same air inlet, compression, combustion, expansion and exhaust processes under different phases, the engine works for three times when the rotor rotates, mechanical energy is externally output through the eccentric shaft, the working temperature T of the chambers in each working process is obtained by transient energy (formula 2) and a mass conservation equation (formula 3), the working pressure of the chambers is obtained by a Benedict-Webb-Rubin actual gas physical state equation (formula 4), and physical parameters such as internal energy u, enthalpy h, specific pressure specific heat capacity c p, specific heat capacity c v, heat insulation coefficient k and the like which are related to the thermodynamic submodel are all called by interpolation of a self-building physical database.
Wherein: m c is the working medium mass of the working chamber; u is the internal energy of the working medium of the cavity; q B is combustion heat release quantity; m in intake air mass; h in is the intake air enthalpy; m fuel intake fuel mass; h fuel is the intake fuel enthalpy; m exh is the exhaust mass; h exh is the exhaust enthalpy; m leak is the leakage mass; h leak is the enthalpy value of the leaked working medium; q w is the heat dissipation between the chamber gas and the cylinder and rotor wall; v m is the molar volume; r is a gas constant; a 0,B0,C0, a, b, c, α, γ are constants.
The combustion heat release sub-model is used for obtaining the combustion heat release quantity Q B of the hydrogen fuel, and the Weber heat release model (formula 5) is used for predicting the heat release quantity Q B in the fuel combustion process, and the hydrogen combustion heat release rate is shown in FIG. 5
Wherein: LHV is the lower heating value of the fuel; η B is the combustion efficiency; Is the combustion sustaining angle; /(I) Is the firing angle; m is the combustion quality coefficient, taking 3.
Combustion sustaining angleIs determined by the laminar flame propagation speed S in the hydrogen combustion process, and the combustion duration angle/>, under the rated working conditionThrough three-dimensional CFD numerical simulation calibration, combustion sustaining angle/>, under other working conditionsObtained by equation 9.
The laminar flame propagation speed S of the hydrogen combustion under different temperature and pressure conditions is obtained by correcting the laminar flame propagation speed S ref (refer to FIG. 6) under the standard conditions, as shown in formulas 6-8.
γ＝2.18-0.8(φ-1) (7)
σ＝-0.16+0.22(φ-1) (8)
Wherein: gamma is a temperature correction coefficient; sigma is a pressure correction coefficient; phi is the equivalence ratio; s des is the flame propagation speed under rated conditions.
The heat exchange loss submodel is used for obtaining the heat convection loss quantity Q w of the gas in the working chamber and the wall surface of the engine, and is calculated by formulas 10-11:
Wherein: a w is the heat exchange area of the wall surface; alpha c is the convective heat transfer coefficient; u is the average speed of the rotor.
The mass leakage sub-model is used for obtaining leakage mass m leak of gas between adjacent chambers at the top of the rotor, the leakage loss is calculated by Bernoulli equation, the mass of subsonic leakage flow is obtained by equation 12 when the pressure of the working chamber is lower than the critical pressure (equation 14), and the mass of sonic leakage flow is obtained by equation 13 when the pressure of the working chamber is higher than the critical pressure.
Wherein: k is the air flow insulation coefficient; a leak is the leakage area; τ is time; p cr is critical pressure; p 0 is ambient pressure.
And a second step M2 of verifying a zero-dimensional simulation model of the hydrogen fuel aero-rotor engine by adopting experimental data, and obtaining 10000 groups of data sets of data of the pilot power, the pilot thermal efficiency and the pilot oil consumption of the aero-rotor engine under different rotation speeds and different ignition advance angles, wherein the data sets of the pilot hydrogen fuel injection quantity, the different rotation speeds and the pilot oil consumption are given to the core geometric parameters (the shape coefficient K, the eccentricity e, the cylinder body thickness B and the pit volume V c) of the hydrogen fuel aero-rotor engine by simulation based on the zero-dimensional simulation model after experimental verification.
Referring to fig. 7 and 8, the simulation working pressure and working temperature of the zero-dimensional model of the aviation rotor engine are compared with the experimental result, and the predicted relative error is less than 5%.
Referring to fig. 9 to 11, the zero-dimensional model of the aero-rotor engine predicts the indicated power, the indicated thermal efficiency and the indicated fuel consumption rate variation trend of the hydrogen-fuelled aero-rotor engine at different rotation speeds.
Referring to fig. 12 to 14, the zero-dimensional model of the aero-rotor engine predicts the indicated power, the indicated thermal efficiency and the indicated fuel consumption rate variation trend of the aero-rotor engine with different hydrogen fuel injection amounts.
Referring to fig. 15 to 17, the zero-dimensional model of the aero-rotor engine predicts the indicated power, the indicated thermal efficiency and the indicated fuel consumption rate variation trend of the hydrogen fuel aero-rotor engine under different ignition advance angles.
And step 3, constructing a hydrogen fuel rotor engine performance neural network model based on a Bayesian regularization algorithm, and training the neural network model by adopting a rotor engine zero-dimensional performance simulation data set, referring to fig. 18.
As shown in fig. 18, the neural network model includes 3 input layer network node numbers, 20 hidden layer network node numbers, and 3 output layer network node numbers;
the three input layer network nodes respectively represent the injection quantity, the rotating speed and the ignition advance angle of hydrogen fuel;
The 20 hidden layer network node numbers are used for representing the inherent logic relationship between the input variable and the output variable;
the number of the 3 output layer network nodes respectively represents the indicated power, the indicated thermal efficiency and the indicated fuel consumption rate;
the neural network model adopts a Bayesian regularization algorithm to train the model, wherein 80% of training data in 10000 sets of zero-dimensional performance simulation data sets are randomly selected to train the model, and 20% of training data are used for testing the model. And (3) deriving a function corresponding to the neural network model with the training qualification, namely the decision coefficient R 2 not less than 0.98.
Referring to fig. 19, the neural network model fitting result is better, and the overall decision coefficient R 2 is 0.99621.
And a fourth step M4, namely appointing the core geometric parameters (the shape coefficient K, the eccentricity e, the cylinder body thickness B and the pit volume V c of the combustion chamber) of the hydrogen fuel rotor engine, inputting the injection quantity, the rotating speed and the ignition advance angle of any combination of hydrogen fuel in a reasonable range, and rapidly and accurately predicting the indication power, the indication heat efficiency and the indication fuel consumption rate of the hydrogen fuel rotor engine by using a neural network model.
The shape factor K of the hydrogen fuel rotor engine is set to 7, the eccentricity e is set to 15mm, the cylinder body thickness B is set to 70mm, the pit volume V c of the combustion chamber is set to 50cm 3, the arbitrary combination hydrogen fuel injection quantity of 1.141x10 -5 kg/cycle, the rotating speed of 6500rpm and the ignition advance angle of 40 DEG are input into the neural network model, the neural network model can rapidly and accurately predict the indicated power 38.04kW, the indicated heat efficiency of 21.99% and the indicated fuel consumption rate of 0.117 kg/(kW.h) of the hydrogen fuel rotor engine, and engine performance data predicted by the intelligent prediction method can be compared with actual test performance data to evaluate the performance degradation condition of the hydrogen fuel engine, and solid theoretical support can be provided for the design of a control system of the engine and the establishment of an optimal control strategy of the engine.
Claims (4)
1. An intelligent prediction method for performance of a hydrogen fuel aviation rotor engine is characterized by comprising the following specific steps:
S1, constructing a zero-dimensional performance simulation model of a hydrogen fuel aero-rotor engine based on transient mass conservation, energy conservation, actual gas physical parameters and laminar flame propagation speed in a hydrogen fuel combustion process;
S2, given the core geometric parameters of the hydrogen fuel rotor engine, under the condition of any combination of the hydrogen fuel injection quantity, the rotating speed and the ignition advance angle, the indicated power, the indicated heat efficiency and the indicated fuel consumption rate of a zero-dimensional performance simulation model of the hydrogen fuel aviation rotor engine are obtained, and a rotor engine zero-dimensional performance simulation data set is obtained;
S3, constructing a hydrogen fuel rotor engine performance neural network model based on a Bayesian regularization algorithm, and training the hydrogen fuel rotor engine performance neural network model by adopting a rotor engine zero-dimensional performance simulation data set;
s4, inputting the hydrogen fuel injection quantity, the rotating speed and the ignition advance angle which are arbitrarily combined into a hydrogen fuel rotor engine performance neural network model, and predicting to obtain the indicated power, the indicated heat efficiency and the indicated fuel consumption rate of the hydrogen fuel rotor engine;
In the step S1, a zero-dimensional performance simulation model of the hydrogen fuel aviation rotor engine comprises an air inlet process module, a compression process module, a combustion process module, an expansion process module and an exhaust process module, wherein a geometric submodel, a thermodynamic submodel, a heat exchange loss submodel, a mass leakage submodel and a combustion heat release submodel are embedded in the modules, and the geometric submodel is used for acquiring the volume V of each working chamber in the rotor engine; the thermodynamic submodel is used for obtaining the pressure P of the working chamber through an actual gas physical state equation; the heat exchange loss submodel is used for obtaining the heat convection loss Q w of the gas in the working chamber of the engine and the wall surface of the engine, and the combustion heat release submodel is used for obtaining the combustion heat release Q B of the hydrogen fuel according to the laminar flame propagation speed S; the mass leakage sub-model is used for acquiring leakage mass m leak of gas between adjacent chambers at the top of the rotor;
In step S1, the combustion heat release model predicts the combustion heat release amount Q B of the hydrogen fuel by using a weber heat release model, and specifically:
Wherein: LHV is the lower heating value of the fuel; Is combustion efficiency; /(I) Is the combustion sustaining angle; /(I)Is the firing angle; m is the combustion quality coefficient, m fuel intake fuel mass,/>An eccentric shaft rotation angle;
In step S1, the laminar flame propagation speed S in the hydrogen combustion process determines the combustion duration angle The laminar flame propagation speed S under different temperature and pressure conditions is obtained by correcting the laminar flame propagation speed S ref under the standard conditions, as follows;
Wherein: is a temperature correction coefficient; /(I) Is a pressure correction coefficient; /(I)Is equivalent ratio;
In step S1, combustion duration angle Is calculated according to the formula:
wherein S des is the flame propagation speed under the rated working condition, Is the combustion continuous angle under the rated working condition;
in step S1, the working chamber pressure P is obtained by using a Benedict-Webb-Rubin actual gas physical state equation, specifically:
Wherein: m c is the working medium mass of the working chamber; u is the internal energy of the working medium of the cavity; q B is combustion heat release quantity; m in intake air mass; h in is the intake air enthalpy; h fuel is the intake fuel enthalpy; m exh is the exhaust mass; h exh is the exhaust enthalpy; m leak is the leakage mass; h leak is the enthalpy value of the leaked working medium; q w is the heat dissipation between the chamber gas and the cylinder and rotor wall; v m is the molar volume; r is a gas constant; a 0, B0, C0, a, b, c, , />Are all constant.
2. The intelligent prediction method for performance of a hydrogen-fueled aero-rotor engine according to claim 1, wherein in step S3, the hydrogen-fueled aero-rotor engine performance neural network model includes 3 input layer network node numbers, 20 hidden layer network node numbers, and 3 output layer network node numbers; an input layer x= [ x 1,x2,x3]T, wherein x 1、x2、x3 represents the hydrogen fuel injection amount, the rotation speed and the ignition advance angle, respectively; output layer y= [ y 1,y2,y3]T, where y 1、y2、y3 represents indicated power y 1, indicated heat efficiency y 2, and indicated fuel consumption y 3, respectively.
3. The intelligent prediction method for performance of a hydrogen-fueled aircraft rotor engine according to claim 2, wherein in step S3, the hydrogen-fueled aircraft rotor engine performance neural network model is specifically:
Wherein: s k is hidden layer node data in the kth iteration, K is an activation function max (0.1 x, x), w, U and v are weight coefficients, and b is the K iteration prediction output layer data And actual output layer data/>Deviation of (2); /(I)Is the normalized input layer; /(I)Is the normalized output layer.
4. The intelligent prediction method for performance of hydrogen-fueled aero-rotor engine according to claim 3, wherein in step S3, the predicted output layer data is providedThe predicted actual output layer node data y= [ Y 1,y2,y3]T ] after inverse normalization, namely the indicated power Y 1, the indicated thermal efficiency Y 2 and the indicated fuel consumption Y 3 of the hydrogen fuel rotor engine, specifically comprises:
wherein: ps is a mapping of output layer data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210510695.2A CN114961985B (en) | 2022-05-11 | 2022-05-11 | Hydrogen fuel aviation rotor engine performance intelligent prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210510695.2A CN114961985B (en) | 2022-05-11 | 2022-05-11 | Hydrogen fuel aviation rotor engine performance intelligent prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114961985A CN114961985A (en) | 2022-08-30 |
| CN114961985B true CN114961985B (en) | 2024-05-07 |
Family
ID=82972277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210510695.2A Active CN114961985B (en) | 2022-05-11 | 2022-05-11 | Hydrogen fuel aviation rotor engine performance intelligent prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114961985B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115434802B (en) * | 2022-09-15 | 2024-05-07 | 西安交通大学 | Multi-objective optimization control strategy and system for ammonia-hydrogen dual-fuel aviation rotor engine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5551227A (en) * | 1994-12-22 | 1996-09-03 | General Electric Company | System and method of detecting partial flame out in a gas turbine engine combustor |
| CN104633856A (en) * | 2015-01-27 | 2015-05-20 | 天津大学 | Method for controlling artificial environment by combining CFD numerical simulation and BP neural network |
| CN105653829A (en) * | 2014-09-04 | 2016-06-08 | 中国人民解放军海军工程大学 | Oxyhydrogen combustion chamber dynamic characteristic rapid prediction method |
| CN110579962A (en) * | 2019-08-19 | 2019-12-17 | 南京航空航天大学 | Turbofan engine thrust prediction method based on neural network and controller |
| CN110738242A (en) * | 2019-09-25 | 2020-01-31 | 清华大学 | Bayes structure learning method and device for deep neural networks |
| CN113779894A (en) * | 2021-10-07 | 2021-12-10 | 北京航空航天大学 | Neural network-based prediction method for heat transfer and resistance coefficients of in-pipe hydrocarbon fuel |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10030602B2 (en) * | 2014-07-22 | 2018-07-24 | The Regents Of The University Of Michigan | Adaptive machine learning method to predict and control engine combustion |
| US20210209265A1 (en) * | 2020-01-02 | 2021-07-08 | Viettel Group | Mathematical modelling method for single spool turbojet engine |
-
2022
- 2022-05-11 CN CN202210510695.2A patent/CN114961985B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5551227A (en) * | 1994-12-22 | 1996-09-03 | General Electric Company | System and method of detecting partial flame out in a gas turbine engine combustor |
| CN105653829A (en) * | 2014-09-04 | 2016-06-08 | 中国人民解放军海军工程大学 | Oxyhydrogen combustion chamber dynamic characteristic rapid prediction method |
| CN104633856A (en) * | 2015-01-27 | 2015-05-20 | 天津大学 | Method for controlling artificial environment by combining CFD numerical simulation and BP neural network |
| CN110579962A (en) * | 2019-08-19 | 2019-12-17 | 南京航空航天大学 | Turbofan engine thrust prediction method based on neural network and controller |
| CN110738242A (en) * | 2019-09-25 | 2020-01-31 | 清华大学 | Bayes structure learning method and device for deep neural networks |
| CN113779894A (en) * | 2021-10-07 | 2021-12-10 | 北京航空航天大学 | Neural network-based prediction method for heat transfer and resistance coefficients of in-pipe hydrocarbon fuel |
Non-Patent Citations (3)
| Title |
|---|
| 基于神经网络的零维预测燃烧模型及建模方法;朱振夏等;内燃机学报;第33卷(第2期);第163-170页 * |
| 朱振夏等.基于神经网络的零维预测燃烧模型及建模方法.内燃机学报.2015,第33卷(第2期),第163-170页. * |
| 船用中速双燃料发动机放热规律神经网络预测模型的开发;贺玉海等;船舶工程;20180630;第40卷(第6期);第55-60页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114961985A (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zareei et al. | Optimization and study of performance parameters in an engine fueled with hydrogen | |
| Winterbone et al. | A wholly dynamic model of a turbocharged diesel engine for transfer function evaluation | |
| de Souza et al. | Study of intake manifolds of an internal combustion engine: A new geometry based on experimental results and numerical simulations | |
| CN111859746B (en) | Method for predicting variable working condition performance of turbomachinery based on flow field reconstruction | |
| CN114961985B (en) | Hydrogen fuel aviation rotor engine performance intelligent prediction method and system | |
| Fatigati et al. | Development and numerical modelling of a supercharging technique for positive displacement expanders | |
| CN113741211A (en) | Optimization method for integrated optimization matching of EGR system and supercharging system | |
| Liu et al. | An evaluation method for transient response performance of turbocharged diesel engines | |
| Khajezade Roodi et al. | Optimization of Spark Ignition Engine Performance using a New Double Intake Manifold: Experimental and Numerical Analysis | |
| Wang et al. | Implementation of a novel dual-layer machine learning structure for predicting the intake characteristics of a side-ported Wankel rotary engine | |
| CN117725700A (en) | System, method and equipment for managing split-axis gas turbine based on digital twin technology | |
| CN114934848B (en) | Fuzzy neural network modeling method for optimizing control of combustion performance of diesel engine | |
| Koutsakis et al. | An analytical approach for calculating instantaneous multilayer-coated wall surface temperature in an engine | |
| Omran et al. | Neural networks for real‐time nonlinear control of a variable geometry turbocharged diesel engine | |
| Di et al. | Chaos theory-based time series analysis of in-cylinder pressure and its application in combustion control of SI engines | |
| Cui et al. | Study on mixed pulse converter (MIXPC) turbocharging system and its application in marine diesel engines | |
| Naser et al. | Modelling and simulation of the turbocharged diesel engine with intercooler | |
| CN114357830A (en) | Engine performance prediction method and system based on state equation | |
| CN115434802B (en) | Multi-objective optimization control strategy and system for ammonia-hydrogen dual-fuel aviation rotor engine | |
| Mijit | Design, analysis, and experimentation of a micro internal combustion swing engine | |
| Shamekhi et al. | Engine Model-Based Pre-calibration and Optimization for Mid-level Hierarchical Control Design | |
| Yao et al. | Simulink-based modular modeling of a marine three-shaft gas turbine for performance study | |
| CN117235923A (en) | Combustion process simulation method for natural gas hydrogen-doped rotor engine | |
| Raju et al. | Computational experience with a three-dimensional rotary engine combustion model | |
| CN113807024B (en) | Gas turbine optimal dynamic working point selection method based on proxy model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |