A method and system for predicting compression ratio of a linear internal combustion power generation system

Abstract

The application provides a compression ratio prediction method and system of a linear internal combustion power generation system, relates to the technical field of performance prediction of a new type of hybrid power system, and comprises the following steps: a multi-physical field coupling simulation model of the linear internal combustion power generation system is constructed; a plurality of key design parameters affecting the change of the compression ratio in the stable operation process of the model are extracted; the numerical input range of each key design parameter is determined through parameter quantization analysis, and a key design parameter sample set is formed through Latin hypercube sampling; based on the key design parameter sample set, the compression ratio response under different design parameter combinations is obtained through the multi-physical field coupling simulation model; the key design parameter sample set and each compression ratio response are combined to form a simulation data set; a compression ratio prediction model based on a hybrid neural network is constructed, and model optimization is carried out according to the simulation data set and an adam optimizer; and the compression ratio prediction is carried out through the optimized compression ratio prediction model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new hybrid system performance prediction, in particular to a compression ratio prediction method and system of a free piston linear generator system. BACKGROUND

[0002] The free piston linear generator (FPLG) is a highly promising distributed and modular hybrid power system, which mainly consists of a free piston engine, a high-performance linear motor, an integrated control system, and auxiliary systems. The FPLG highly integrates and couples the free piston engine and the linear motor, and through the continuous and alternating expansion of the heat engine, the piston reciprocates to cut the magnetic lines of force, thereby realizing the continuous output of electric power. Since the piston of the FPLG is not constrained by the mechanism, the piston dead center position and the compression ratio of the FPLG heat engine are variable, and thus the FPLG can be applied to various types of fuels such as gasoline and diesel. In addition, the FPLG includes energy storage subsystems such as batteries and supercapacitors, which can decouple the heat engine-linear motor and the power load, so that the system works at a relatively good operating point in terms of fuel consumption and emissions.

[0003] Current researches are mostly focused on the design and performance optimization of the FPLG, including the control of free piston motion, the adjustment of combustion process, and the efficient coupling between the motor and the heat engine. Various control strategies are adopted in the prior art to adjust the piston position and the compression ratio, so as to improve the system efficiency and reduce the fuel consumption and emissions. Through the optimization and prediction of different design parameters of the system, the optimal matching of the heat engine-linear motor can be achieved to some extent, and the stability and reliability of the FPLG in actual application can be improved.

[0004] However, the existing methods lack prediction models for the change of the compression ratio under different design parameters and operating conditions, making it difficult to accurately evaluate and predict the performance of the FPLG system under various operating conditions. SUMMARY

[0005] In order to solve the technical problem that the existing methods lack prediction models for the change of the compression ratio under different design parameters and operating conditions, making it difficult to accurately evaluate and predict the performance of the FPLG system under various operating conditions, the present application provides a compression ratio prediction method and system of a free piston linear generator system.

[0006] The technical solutions provided by the embodiments of the present application are as follows:

[0007] First aspect:

[0008] The compression ratio prediction method of the free piston linear generator system provided by the embodiments of the present application comprises:

[0009] S1: Construct a multi-physics field coupling simulation model of a linear internal combustion power generation system to describe a stable working process of the linear internal combustion power generation system.

[0010] S2: Based on the multi-physics field coupling simulation model, a plurality of key design parameters affecting the change of the compression ratio in the stable operation process are extracted.

[0011] S3: Through parameter quantization analysis, the numerical input range of each key design parameter is determined.

[0012] S4: Through Latin hypercube sampling, uniform sampling is performed from the numerical input range of each key design parameter to form a key design parameter sample set.

[0013] S5: Based on the key design parameter sample set, the multi-physics field coupling simulation model is used to obtain the compression ratio response under different design parameter combinations in the stable power generation process.

[0014] S6: The key design parameter sample set and each compression ratio response are combined to form a simulation data set.

[0015] S7: A compression ratio prediction model based on a hybrid neural network is constructed.

[0016] S8: According to the simulation data set, the compression ratio prediction model is optimized by an adam optimizer.

[0017] S9: Real-time key design parameters are obtained.

[0018] S10: According to the real-time key design parameters, the compression ratio is predicted by the optimized compression ratio prediction model.

[0019] Second aspect:

[0020] The compression ratio prediction system of the linear internal combustion power generation system provided by the embodiment of the application comprises:

[0021] A processor;

[0022] A memory, wherein the memory stores computer readable instructions, and the computer readable instructions are executed by the processor to implement the compression ratio prediction method of the linear internal combustion power generation system according to the first aspect.

[0023] Third aspect:

[0024] The computer readable storage medium provided by the embodiment of the application stores a computer program, and the program is executed by the processor to implement the compression ratio prediction method of the linear internal combustion power generation system according to the first aspect.

[0025] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0026] (1) In the embodiment of the present application, by constructing a multi-physics field coupling simulation model, extracting and quantifying key design parameters, and using Latin hypercube sampling technology to uniformly sample the design parameter range, the compression ratio response under different design conditions is obtained, thereby effectively improving the accuracy of compression ratio prediction. The compression ratio prediction model is constructed by a hybrid neural network, and the Adam optimizer is used to optimize the compression ratio prediction model, which further improves the accuracy of the compression ratio prediction, so that the performance of the FPLG system under various operating conditions can be accurately evaluated and predicted. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0028] Figure 1 A flowchart of a compression ratio prediction method of a linear internal combustion power generation system provided by the embodiment of the present application is shown.

[0029] Figure 2 A structure diagram of a compression ratio prediction system of a linear internal combustion power generation system provided by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0030] The technical solutions in the present application will be described below with reference to the drawings.

[0031] In the embodiments of the present application, the words "example", "for example", etc. are used to represent an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be either one of the two.

[0032] In the embodiments of the present application, "image" and "picture" can be used interchangeably. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent. "Of", "corresponding" and "corresponding" can be used interchangeably. It should be pointed out that when the distinction is not emphasized, the meanings expressed are consistent.

[0033] In the embodiments of the present application, sometimes the subscript such as W1 may be written in the form of non-subscript such as W1, and the meanings expressed thereby are consistent when the difference is not emphasized.

[0034] To make the technical problems, technical solutions and advantages to be solved by the present application clearer, specific embodiments will be described in detail below with reference to the drawings.

[0035] Reference is made to the accompanying drawings Figure 1 , which shows a flowchart of a compression ratio prediction method of a linear internal combustion power generation system according to an embodiment of the present application.

[0036] The present application provides a compression ratio prediction method of a linear internal combustion power generation system, which can be implemented by a compression ratio prediction device of a linear internal combustion power generation system. The compression ratio prediction device of a linear internal combustion power generation system can be a terminal or a server. The processing flow of the compression ratio prediction method of a linear internal combustion power generation system can include the following steps:

[0037] S1: Construct a multi-physics field coupling simulation model of a linear internal combustion power generation system to describe the stable working process of the linear internal combustion power generation system.

[0038] In one possible implementation, S1 is specifically:

[0039] Based on the Matlab mathematical calculation software and the Simulink graphical modeling tool, a multi-physics field coupling simulation model of a linear internal combustion power generation system is constructed.

[0040] Wherein, Matlab is a high-efficiency mathematical calculation software, which is widely used in mathematical modeling, data analysis, algorithm development, signal processing, image processing, control system design, robot and financial analysis fields.

[0041] Wherein, Simulink is a graphical modeling and simulation tool based on Matlab, which is widely used in system modeling, simulation, control design, signal processing, communication, mechanical system, power system and other fields. Simulink provides a graphical interface, and users can build system models by dragging icons and connecting modules without writing a large amount of code. It is particularly suitable for modeling and simulation of dynamic systems, especially control systems, electronic systems, mechanical systems and other fields.

[0042] In one possible implementation, the multi-physics field coupling simulation model includes a dynamics model and a thermodynamics model.

[0043] Wherein, the dynamics model is mainly used to describe the motion law of each component (such as piston, motor, etc.) in the system, and helps us understand how these components interact. It focuses on the relationship between force, motion and acceleration.

[0044] wherein the thermodynamic model is mainly used to describe the energy conversion process in the system, especially the conversion between thermal energy and mechanical energy. In the internal combustion power generation system, the compression and expansion processes of the gas involve the mutual conversion between thermal energy (from the combustion process and the heat exchange between the gas and the cylinder wall) and mechanical energy (the force generated by the gas acting on the piston).

[0045] In one possible implementation, the dynamic model is specifically:

[0046]

[0047] wherein F p_left represents the force of the left-side in-cylinder gas, F p_right represents the force of the right-side in-cylinder gas, F e represents the electromagnetic resistance of the linear motor, F f represents the system friction, x represents the displacement of the moving component, t represents time, p represents the in-cylinder pressure, A represents the piston bottom area, F p represents the force of the in-cylinder gas.

[0048] In one possible implementation, the thermodynamic model is specifically:

[0049]

[0050] wherein P represents the current in-cylinder pressure, t represents time, γ represents the adiabatic coefficient, Q c represents the heat released by the combustion process, Q ht represents the heat lost by the heat exchange between the in-cylinder gas and the cylinder wall, V represents the current in-cylinder volume, i represents the intake process, e represents the exhaust process, 1 represents the leakage process of the gas through the piston ring, m n represents the mass of the gas in the intake process or the exhaust process, m l represents the mass of the leaked gas, m air represents the mass of the current in-cylinder gas, LHV represents the low heat value of the fuel, AFR represents the air-fuel ratio, a, b represent empirical parameters, t c represents the combustion duration, t0 represents the starting time of the combustion, exp represents the exponential function, T represents the current in-cylinder temperature, represents the average speed of the piston moving component, A cyl represents the area contacted by the high-temperature gas, T w represents the wall reference temperature, m j represents the mass of the in-cylinder gas involved in the intake process, the exhaust process or the leakage process, C d represents the flow coefficient, A d represents the reference area of the fluid, P uP represents the gas pressure on the high-pressure side, R represents the gas constant, and T represents the gas temperature on the high-pressure side u P represents the gas pressure on the high-pressure side, R represents the gas constant, and T represents the gas temperature on the high-pressure side d P represents the gas pressure on the high-pressure side, R represents the gas constant, and T represents the gas temperature on the high-pressure side

[0051] In the present application, the powerful tools provided by Matlab and Simulink can accurately simulate the dynamic response and heat transfer process of the internal combustion power generation system, especially in complex nonlinear systems, these tools can effectively capture the interaction of different physical processes. At the same time, by establishing a multi-physical field coupling simulation model, detailed system performance analysis can be carried out at the design stage, the performance of the system under different working conditions can be predicted, and then the design is optimized, the system efficiency, stability and reliability are improved.

[0052] Further, the combination of thermodynamic model and dynamic model can help analyze the response of the system under different working conditions, and provide data support for the design of control system.

[0053] S2: Based on the multi-physical field coupling simulation model, extract multiple key design parameters that affect the change of compression ratio during stable operation.

[0054] Optionally, the key design parameters specifically include: air-fuel ratio, ignition position, intake pressure, starting compression ratio, electromagnetic damping coefficient and moving component mass.

[0055] It should be noted that the key design parameters should include both engine design parameters and linear motor design parameters, and the change of variable value should have a significant impact on the response of the compression ratio.

[0056] In the present application, by focusing on key design parameters, the design optimization process can be more accurately simulated, and the change of compression ratio can be more accurately predicted. At the same time, it is clear which design parameters have a significant impact on the compression ratio, which can provide a basis for the design of the control system, so that in the actual operation process, the control strategy can be adjusted according to the change of these key parameters, for example, by automatically adjusting the ignition position or intake pressure, so that the system is always in the best working state.

[0057] S3: Determine the numerical input range of each key design parameter through parameter quantization analysis.

[0058] Parameter quantization analysis is a process for analyzing and determining the impact of system parameters within a certain range on system behavior or performance. It analyzes the numerical value of each key design parameter in the system to determine its reasonable value range, so that the system can run stably and efficiently.

[0059] It should be noted that, in order to ensure that the FPLG system can generate electricity stably during actual operation and not exceed the system's instability threshold, when determining the value range of key design parameters, it should be ensured that the energy generated by the thermodynamic cycle under the set of key design parameters is matched with the system load. This ensures that the energy generated by the thermodynamic cycle is not insufficient, which would prevent the system from overcoming the motor load and friction load to reach the preset ignition position and causing system shutdown, and that the energy generated by the thermodynamic cycle is not too high, which would cause knocking, misfire, and cylinder collision.

[0060] In this invention, by using a reasonable range of design parameters, the energy generated by the thermodynamic cycle is matched with the system load, avoiding system overload or underload, thereby ensuring stable system operation.

[0061] S4: Through Latin hypercube sampling, uniform sampling is performed from the numerical input range of each key design parameter to form a key design parameter sample set.

[0062] Latin hypercube sampling (LHS) is a probabilistic sampling method commonly used in high-dimensional parameter spaces, particularly suitable for uncertainty analysis, Monte Carlo simulation, and optimization. Its main advantage lies in its ability to sample uniformly across a multidimensional space, effectively covering the entire design space while avoiding the uneven data distribution that can result from traditional random sampling methods.

[0063] Specifically, the multidimensional key design parameters are stratified by Latin hypercube sampling, so that the collected samples are evenly distributed in the input vector space and arranged in a random order.

[0064] In this invention, stratified sampling is performed within each dimension, ensuring that each interval represents a sample, thus avoiding sample deficiency in certain areas and making the sampling more comprehensive. Simultaneously, Latin hypercube sampling can more comprehensively explore the entire design space with a given number of samples, thereby reducing the number of samples and avoiding a large amount of unnecessary computation. This significantly improves computational efficiency when performing simulations and optimizations in high-dimensional spaces.

[0065] S5: Based on the key design parameter sample set, the compression ratio response under different combinations of design parameters during stable power generation is obtained through a multi-physics field coupled simulation model.

[0066] Compression ratio response describes the dynamic response or variation of the system's compression ratio as design parameters (such as air-fuel ratio, ignition position, and intake pressure) change. In multiphysics coupled simulation models, the compression ratio response is obtained through simulation calculations, which helps us understand and predict the behavior of the compression ratio under different operating conditions.

[0067] In a possible implementation, the formula for calculating the compression ratio response is specifically as follows:

[0068]

[0069] wherein CR L represents the left cylinder compression ratio, V0 represents the total volume of the cylinder, A represents the piston bottom area, L represents the half stroke of the cylinder from the design stroke midpoint, x c represents the remaining volume corresponding to the cylinder length, x TDC represents the top dead center, CR R represents the right cylinder compression ratio, x BDC represents the bottom dead center.

[0070] Optionally, the identification method of the top dead center x TDC and the bottom dead center x BDC is as follows:

[0071] After the stable power generation working process of the multi-physical field coupling simulation model starts, the position of the motion assembly when the system is in the compression process and the speed becomes 0 is recorded as the top dead center x TDC ; the position of the motion assembly when the system is in the expansion process and the speed becomes 0 is recorded as the bottom dead center x BDC .

[0072] In the present application, the positions of the top dead center and the bottom dead center are calculated by simulation, so that the compression ratio can be calculated more accurately, thereby ensuring that the matching degree of the simulation result and the actual working condition is higher. Meanwhile, since the top dead center and the bottom dead center of the piston are affected by multiple factors such as combustion pressure, intake pressure, load and the like, by calculating these parameters in real time, more accurate data can be provided for the control system, to help optimize the combustion process, reduce energy loss and improve system stability.

[0073] S6: Combine the key design parameter sample set and each compression ratio response to form a simulation data set.

[0074] It should be noted that the simulation data set is shaped into a seven-dimensional shape: containing six key design parameter inputs: air-fuel ratio, ignition position, intake pressure, starting compression ratio, electromagnetic damping coefficient, and motion assembly mass, and one stable running process compression ratio output, the data is saved as an Excel file, the first six columns are input, the seventh column is output, and the number of rows is the sample amount.

[0075] S7: Construct a compression ratio prediction model based on a hybrid neural network.

[0076] In a possible implementation, the mixed neural network-based compression ratio prediction model in S7 specifically comprises a CNN layer, an unfolding layer, a smoothing layer, an LSTM layer, and a fully connected layer.

[0077] The CNN layer further comprises a convolution layer, an activation layer, and a pooling layer.

[0078] In a possible implementation, S7 specifically comprises:

[0079] S701: Randomly shuffle the simulation data set, and divide the training data set and the test data set according to a preset ratio.

[0080] S702: Normalize the training data set and the test data set:

[0081]

[0082] wherein y represents the normalized data, x represents the original data, y max represents the maximum value of the target normalization, y min represents the minimum value of the target normalization, x max represents the maximum value of the original data, x min represents the minimum value of the original data.

[0083] S703: Convolve the normalized training data set by the convolution layer to obtain a first target feature map.

[0084] S704: Activate the first target feature map by the activation layer.

[0085] S705: Input the first target feature map after the activation operation into the pooling layer, reduce the size of the first target feature map after the activation operation by taking the average value, and obtain a second target feature map.

[0086] In the present application, the average pooling layer is adopted to reduce the size of the feature map, so that the model is easier to learn the global information, and the calculation amount is reduced, and the training speed is improved.

[0087] S706: Unfold the second target feature map into a serializable form by the unfolding layer, and expand it into a one-dimensional vector by the smoothing layer.

[0088] S707: Input the one-dimensional vector into the LSTM layer to extract the time-dependent features of the one-dimensional vector.

[0089] S708: Input the time-dependent features into the fully connected layer to output the compression ratio prediction result, and complete the construction of the compression ratio prediction model.

[0090] Specifically, the mixed neural network is a CNN-LSTM, the CNN layer includes an input layer, a folding layer, a convolution layer, an activation layer and an average pooling layer, the number of filters of the convolution layer is 40, the activation layer adopts a ReLU activation function, the pooling layer reduces the size of the feature map by taking an average value, so that the model has higher tolerance to the change of local patterns in the feature map, the convolution output is unfolded into a form suitable for sequence processing through the unfolding layer between the CNN layer and the LSTM layer, the high-dimensional feature map is unfolded into a one-dimensional vector through the smoothing layer, two LSTM layers are included, the first LSTM layer includes 50 hidden units, and the second LSTM layer includes 58 hidden units, and a Dropout layer is added in the output layer, 20% of the neurons are randomly discarded to prevent overfitting.

[0091] In the application, through the convolution operation of 40 filters, the CNN can effectively capture the local change trend of the compression ratio without artificial design of features. Meanwhile, the CNN is responsible for local feature learning, and the LSTM is responsible for the extraction of time-dependent relationship, so that the prediction accuracy of the compression ratio can be effectively improved, and reliable support can be provided for optimizing engine parameter control, improving combustion efficiency, and improving system stability and energy efficiency.

[0092] S8: According to the simulation data set, the compression ratio prediction model is optimized through an adam optimizer.

[0093] In a possible implementation, S8 specifically includes:

[0094] S801: S801: Determine the mean square error loss function of the compression ratio prediction model:

[0095]

[0096] Wherein, RMSE represents the mean square error loss function, represents the predicted value of the compression ratio prediction model, y i represents the real value of the compression ratio obtained by simulation, and n represents the number of test samples.

[0097] S802: Input the normalized test data set into the compression ratio prediction model, and perform optimization processing through the Adam optimizer.

[0098] S803: When the function value of the loss function is less than the preset function value, stop optimization, and obtain the optimized compression ratio prediction model.

[0099] It should be noted that the size of the preset function value can be set by the person skilled in the art according to actual needs, and the application does not limit it here.

[0100] In the present application, RMSE is more sensitive to samples with larger prediction errors by amplifying larger errors by squaring, thereby helping the optimizer to adjust the model weights faster and make them fit the compression ratio trend more accurately. At the same time, since Adam is more efficient in computing gradients, it usually converges faster than traditional SGD (Stochastic Gradient Descent) methods and can achieve better optimization results in the same training time.

[0101] S9: Obtain real-time key design parameters.

[0102] S10: According to the real-time key design parameters, the compression ratio is predicted by the optimized compression ratio prediction model.

[0103] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0104] (1) In the embodiments of the present application, by constructing a multi-physical field coupling simulation model, extracting and quantifying key design parameters, and using Latin hypercube sampling technology to uniformly sample the design parameter range, the compression ratio response under different design conditions is obtained, thereby effectively improving the accuracy of the compression ratio prediction. The compression ratio prediction model is constructed by a hybrid neural network, and the Adam optimizer is used to optimize the compression ratio prediction model, which further improves the accuracy of the compression ratio prediction, so that the performance of the FPLG system under various operating conditions can be accurately evaluated and predicted.

[0105] Reference is made to the accompanying drawings Figure 2 , which shows a structure schematic diagram of a compression ratio prediction system of a linear internal combustion power generation system provided by the present application.

[0106] The present application also provides a compression ratio prediction system 20 of a linear internal combustion power generation system, which is applied to the compression ratio prediction method of the linear internal combustion power generation system as described above, and comprises:

[0107] A processor 201.

[0108] A memory 202, the memory 202 stores computer readable instructions, and when the computer readable instructions are executed by the processor 201, the linear internal combustion power generation system compression ratio prediction method as in the method embodiment is realized.

[0109] The compression ratio prediction system 20 of the linear internal combustion power generation system provided by the present application can execute the compression ratio prediction method of the linear internal combustion power generation system as described above, and achieve the same or similar technical effects. To avoid repetition, the present application will not be described again.

[0110] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0111] (1) In the embodiment of the present application, by constructing a multi-physics field coupling simulation model, extracting and quantifying key design parameters, using Latin hypercube sampling technology to uniformly sample the design parameter range, the compression ratio response under different design conditions is obtained, thereby effectively improving the accuracy of the compression ratio prediction. The compression ratio prediction model is constructed by a hybrid neural network, and the Adam optimizer is used to optimize the compression ratio prediction model, which further improves the accuracy of the compression ratio prediction, so that the performance of the FPLG system under various operating conditions can be accurately evaluated and predicted.

[0112] It should be understood that the processor in the embodiment of the present application can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0113] It should also be understood that the memory in the embodiments of the present application can be volatile or nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory. The volatile memory can be random access memory (RAM) used as external cache. By way of example, and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0114] The above-described embodiments can be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0115] It should be understood that the term "and / or" herein merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects, but can also represent an "and / or" relationship, which can be understood in the context before and after.

[0116] In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or the like means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0117] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined by their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0118] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0119] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the devices, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0120] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0121] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0122] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0123] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0124] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the compression ratio prediction method of the linear internal combustion power generation system as described in the method embodiment.

[0125] The computer readable storage medium provided by the present application can realize the steps and effects of the compression ratio prediction method of the linear internal combustion power generation system of the above-mentioned method embodiment. To avoid repetition, the present application will not be described again.

[0126] The technical solutions provided by the embodiment of the present application have at least the following beneficial effects:

[0127] (1) In the embodiment of the present application, by constructing a multi-physics field coupling simulation model, extracting and quantifying key design parameters, and using Latin hypercube sampling technology to uniformly sample the design parameter range, the compression ratio response under different design conditions is obtained, thereby effectively improving the accuracy of the compression ratio prediction. The compression ratio prediction model is constructed by using a mixed neural network, and the Adam optimizer is used to optimize the compression ratio prediction model, which further improves the accuracy of the compression ratio prediction, so that the performance of the FPLG system under various operating conditions can be accurately evaluated and predicted.

[0128] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0129] The following points need to be explained:

[0130] (1) The drawings of the embodiment of the present application only relate to the structures involved in the embodiment of the present application, and other structures can be referred to the usual design.

[0131] (2) For clarity, in the drawings used to describe the embodiments of the present application, the thickness of layers or regions are exaggerated or reduced, that is, the drawings are not drawn on scale. It will be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, it can be "directly" on or under the other element or an intervening element can also be present.

[0132] (3) The embodiments of the present application and the features in the embodiments can be combined if there is no conflict.

[0133] The above merely describes the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for predicting the compression ratio of a linear internal combustion power generation system, characterized in that, include: S1: Construct a multiphysics coupling simulation model of the linear internal combustion power generation system to describe the stable operation process of the linear internal combustion power generation system; S2: Based on the multiphysics coupling simulation model, extract several key design parameters that affect the change of compression ratio during stable operation; S3: Determine the numerical input range of each of the key design parameters through parameter quantification analysis; S4: By using Latin hypercube sampling, uniform sampling is performed from the numerical input range of each of the key design parameters to form a key design parameter sample set; S5: Based on the key design parameter sample set, the compression ratio response under different combinations of design parameters during stable power generation is obtained through the multi-physics coupling simulation model; S6: Combine the key design parameter sample set and each compression ratio response to form a simulation dataset; S7: Construct a compression ratio prediction model based on a hybrid neural network; S8: Optimize the compression ratio prediction model using the adam optimizer based on the simulated dataset; S9: Obtain real-time key design parameters; S10: Based on the aforementioned real-time key design parameters, perform compression ratio prediction using the optimized compression ratio prediction model; Specifically, S1 is: A multi-physics coupling simulation model of a linear internal combustion power generation system was constructed based on Matlab mathematical calculation software and Simulink graphical modeling tool. The specific formula for calculating the compression ratio response is as follows: Among them, CR L V0 represents the compression ratio of the left cylinder, A represents the total volume of the cylinder, L represents the piston bottom area, and x represents the half stroke of the cylinder starting from the midpoint of the designed stroke. c x represents the length of the cylinder corresponding to the remaining volume. TDC Indicates the top dead center, CR R Indicates the compression ratio of the right cylinder, x BDC Indicates the lower endpoint.

2. The compression ratio prediction method for a linear internal combustion power generation system according to claim 1, characterized in that, The multiphysics coupling simulation model includes a dynamic model and a thermodynamic model.

3. The compression ratio prediction method for a linear internal combustion power generation system according to claim 2, characterized in that, The specific dynamic model is as follows: Among them, F p_left F represents the force exerted by the gas inside the left cylinder. p_right F represents the force exerted by the gas inside the right cylinder. e F represents the electromagnetic resistance of a linear motor. f Let x represent the system friction force, t represent the displacement of the moving component, p represent the cylinder pressure, A represent the piston bottom area, and F represent the time. p This indicates the force exerted by the gas inside the cylinder.

4. The compression ratio prediction method for a linear internal combustion power generation system according to claim 2, characterized in that, The thermodynamic model is specifically as follows: Where P represents the current cylinder pressure, t represents time, γ represents the adiabatic coefficient, and Q... c Q represents the heat released during combustion. ht This represents the heat lost through heat transfer between the gas and the cylinder wall, where V represents the current cylinder volume, i represents the intake process, e represents the exhaust process, l represents the gas leakage through the piston rings, and m... n The mass of gas during the intake or exhaust process is represented by m. l The mass of the leaked gas, m air This indicates the current gas mass in the cylinder, LHV represents the lower heating value of the fuel, AFR represents the air-fuel ratio, a and b represent empirical parameters, and t c The value represents the duration of combustion, t0 represents the start time of combustion, exp represents the exponential function, and T represents the current in-cylinder temperature. A represents the average velocity of the piston moving assembly. cyl T represents the area of ​​contact between high-temperature gases. w Indicates the wall reference temperature, m j C represents the mass of in-cylinder gases involved in the intake, exhaust, or leakage processes. d A represents the flow coefficient. d P represents the reference area of ​​the fluid. u R represents the gas pressure on the high-pressure side, and T represents the gas constant. u P represents the gas temperature on the high-pressure side. d This indicates the gas pressure on the low-pressure side.

5. The compression ratio prediction method for a linear internal combustion power generation system according to claim 1, characterized in that, The compression ratio prediction model based on hybrid neural networks in S7 specifically includes: CNN layer, unfolding layer, smoothing layer, LSTM layer and fully connected layer; The CNN layer also includes: convolutional layers, activation layers, and pooling layers.

6. The compression ratio prediction method for a linear internal combustion power generation system according to claim 5, characterized in that, Specifically, S7 includes: S701: Randomly shuffle the simulated dataset and divide it into training and test datasets according to a preset ratio; S702: Normalize the training dataset and the test dataset: Where y represents the normalized data, and x represents the original data, y max y represents the maximum value of the objective normalization. min Let x represent the minimum value of the objective normalization. max x represents the maximum value of the original data. min This represents the minimum value of the original data; S703: Using the normalized training dataset as input, perform convolution operation through the convolutional layer to obtain the first target feature map; S704: The first target feature map is activated through the activation layer; S705: Input the first target feature map after the activation operation into the pooling layer, and reduce the size of the first target feature map after the activation operation by taking the average value to obtain the second target feature map; S706: Using the unfolding layer, the second target feature map is unfolded into a serializable form, and then unfolded into a one-dimensional vector through the smoothing layer; S707: Input the one-dimensional vector into the LSTM layer to extract the time-dependent features of the one-dimensional vector; S708: Input the time-dependent features into the fully connected layer, output the compression ratio prediction result, and complete the construction of the compression ratio prediction model.

7. The compression ratio prediction method for a linear internal combustion power generation system according to claim 6, characterized in that, S8 specifically includes: S801: Determine the mean squared error loss function of the compression ratio prediction model: Where RMSE represents the mean squared error loss function, y represents the predicted value of the compression ratio prediction model. i This represents the actual compression ratio obtained from the simulation, and n represents the number of test samples; S802: Input the normalized test dataset into the compression ratio prediction model and perform optimization processing through the adam optimizer; S803: When the value of the loss function is less than the preset function value, stop the optimization and obtain the optimized compression ratio prediction model.

8. A compression ratio prediction system for a linear internal combustion power generation system, characterized in that, include: processor; A memory storing computer-readable instructions, which, when executed by the processor, implement the compression ratio prediction method for a linear internal combustion power generation system as described in any one of claims 1 to 7.

Images