A method for optimizing inter-cylinder fins of a multi-cylinder air-cooled diesel engine

Abstract

This invention discloses an optimized design method for inter-cylinder fins in a multi-cylinder air-cooled diesel engine, belonging to the field of engine cooling structure optimization. The method involves: obtaining performance and state parameters of the air-cooled engine through bench tests; constructing a one-dimensional simulation model of the air-cooled engine to obtain gas state parameters during the thermodynamic cycle within the cylinder; establishing a three-dimensional temperature field simulation model of the air-cooled diesel engine cylinder; combining the inter-cylinder airflow distribution characteristics and local heat load differences of the multi-cylinder air-cooled diesel engine, using a zonal optimization strategy to divide the fin design area and define optimization variables for each area; constructing a neural network prediction model between the optimization variables and the objective function; and using multi-objective optimization and decision algorithms to select the optimal inter-cylinder fin optimization results from the frontier solution set. This invention provides a core cooling structure for power enhancement of air-cooled diesel engines by precisely matching the heat load requirements after power enhancement, simultaneously achieving efficient heat dissipation, uniform cooling, and low flow resistance.

Description

Technical Field

[0001] This invention belongs to the field of engine cooling structure optimization technology, and particularly relates to an optimization design method for inter-cylinder fins of a multi-cylinder air-cooled diesel engine. Background Technology

[0002] Air-cooled diesel engines hold an irreplaceable position in water-scarce and high-temperature environments such as high-altitude mountainous areas and arid regions due to their excellent environmental adaptability. However, the inherent cooling capacity limitations of air-cooling systems generally result in lower power enhancement potential compared to water-cooled diesel engines, restricting their application in scenarios with higher power demands. With the continuous increase in productivity demands across various sectors, it is necessary to further enhance the power output of air-cooled engines. However, this power increase inevitably leads to a significant increase in engine thermal load, posing unprecedented challenges to the cooling capacity of air-cooling systems.

[0003] The core of an air-cooled engine's heat dissipation efficiency lies in its cooling system, especially the design of the cooling fins that directly exchange heat with the air. The rationality of the fin design directly determines whether the air-cooling system can meet the increased heat load demands after power enhancement. Traditional cooling fins often employ simplified designs with single parameters, making it difficult to cope with the complex cooling requirements brought about by increased power. On the one hand, the limited internal space of the engine and the constraint of fan performance on cooling airflow necessitate fins to maximize heat transfer efficiency under limited conditions. On the other hand, uneven airflow distribution in multi-cylinder engines can easily lead to excessive temperature differences between cylinders, with hotter cylinders bearing higher heat loads, making them prone to thermal fatigue damage and failure. Furthermore, blindly optimizing the fin structure to pursue greater heat dissipation area can cause a surge in flow resistance, reducing the effective cooling airflow and affecting the overall heat dissipation effect. Therefore, it is necessary to control flow resistance while ensuring sufficient heat dissipation area. In summary, efficient heat dissipation, uniform cooling, and low flow resistance are the three core objectives for solving the cooling bottleneck during the power enhancement process of air-cooled diesel engines, and also the key areas for breakthroughs in cooling fin design. Summary of the Invention

[0004] The purpose of this invention is to provide an optimized design method for inter-cylinder fins in a multi-cylinder air-cooled diesel engine. By precisely matching the heat load requirements after power enhancement, it simultaneously achieves efficient heat dissipation, uniform cooling, and low flow resistance, providing core cooling structure support for power enhancement of air-cooled diesel engines. This solves the technical bottlenecks of traditional fin designs being unable to adapt to high-power conditions, uneven multi-cylinder temperatures, and excessive flow resistance, and reduces the risk of thermo-mechanical load failure after power enhancement in actual engines.

[0005] The objective of this invention is achieved through the following technical solution:

[0006] This invention discloses an optimized design method for inter-cylinder fins in a multi-cylinder air-cooled diesel engine. Before optimizing the fin design, it is necessary to clarify the power enhancement requirements and potential of the target air-cooled diesel engine, as well as the allowable power increase (meaning that the thermal-mechanical load of the cylinder block, cylinder head, and fins under rated operating conditions has not reached the material's allowable upper limit). The fin optimization design of this invention can improve the inter-cylinder and intra-cylinder heat flow distribution, adapting to power enhancement without increasing the thermal-mechanical load of key components. Specifically, it includes the following steps:

[0007] S1. Obtain the performance parameters and status parameters of the air-cooled diesel engine through bench tests.

[0008] The performance parameters of an air-cooled compressor include the intake airflow, cylinder pressure curve, and heat release rate under stable operating conditions. The status parameters of an air-cooled compressor include the fan speed, cooling airflow inlet temperature and pressure, temperature field measurement data for each cylinder, atmospheric pressure, and ambient temperature under stable operating conditions.

[0009] S2. Based on the design parameters of the air-cooled engine and the performance parameters collected in S1, a one-dimensional simulation model of the air-cooled engine is built to obtain the gas state parameters during the thermodynamic cycle process inside the cylinder.

[0010] The method for establishing a one-dimensional simulation model of the air-cooled machine is to use GT-POWER software for one-dimensional modular modeling based on the design parameters of the air-cooled machine. The core objective of this model is to accurately calculate the gas state parameters during the thermodynamic cycle process, ensuring that the simulation results are consistent with the actual performance parameters collected by S1.

[0011] S3. Based on the three-dimensional solid model of the air-cooled diesel engine, the state parameters of the air-cooled engine obtained in S1, and the state parameters of the in-cylinder gas obtained in S2, a three-dimensional temperature field simulation model of the air-cooled diesel engine cylinder is established.

[0012] The method for establishing a three-dimensional temperature field simulation model of an air-cooled diesel engine cylinder is as follows: based on the three-dimensional solid model of the air-cooled diesel engine, the flow domain of the air-cooling system is established using SOLID software, and the non-critical structures of the air-cooling system are simplified using a porous medium model; the experimentally measured state data in S1 is used to set the boundary conditions of the air flow domain for the three-dimensional temperature field simulation model; and the gas state parameters calculated based on the one-dimensional model in S2 are used to set the third type of boundary conditions for the cylinder wall of the simulation model.

[0013] The formula for calculating the third type of boundary condition is as follows:

[0014]

[0015] Where, α g and T gTo obtain the in-cylinder gas heat transfer coefficient and instantaneous temperature at each instant in one-dimensional performance simulation calculation, τ0 represents one cycle, and φ represents the crankshaft angle. The average heat transfer coefficient, This is the weighted average temperature.

[0016] S4. Combining the inter-cylinder airflow distribution characteristics and local heat load differences of multi-cylinder air-cooled diesel engines, a zoning optimization strategy is adopted to divide the fin design area and define the optimization variables for each area.

[0017] The method for dividing the fin design area and defining the optimization variables for each area is as follows: based on the simulation results or measured data of the heat load distribution of the target air cooler, the cylinder is divided into several characteristic areas, and the fin geometric parameters in each area are defined as optimization variables. Targeted heat dissipation optimization is achieved through independent control of each area.

[0018] S5. Combining the optimization variables defined in S4, design an orthogonal simulation experiment and define the optimization objective function. Based on the simulation model obtained in S3, conduct the simulation experiment, organize the obtained dataset, and then construct a neural network prediction model between the optimization variables and the objective function.

[0019] The method for defining optimization functions is to define them around core requirements. For example, heat dissipation performance aims to minimize the highest and average temperatures of the cylinders; uniformity targets minimizing the standard deviation of temperature distribution among cylinders in a multi-cylinder engine; and flow resistance is defined by minimizing the total pressure drop generated by the entire fin array. The specific calculation formula is as follows:

[0020]

[0021] Among them, T i For the temperature data of each cylinder measuring point, T avg T represents the average temperature at the cylinder measuring points. σ This represents the temperature standard deviation.

[0022] The method for constructing a high-precision neural network prediction model is as follows: an orthogonal experimental design method is adopted, a combination of fin geometric parameters is selected, orthogonal experiments are conducted on each combination of geometric parameters based on a three-dimensional simulation model, data samples are collected and organized, and then a neural network prediction model between the optimization variables and the objective function is constructed using the Bayesian optimization automatic adjustment hyperparameter method.

[0023] S6. Based on the neural network model built in S5, the optimal design scheme that meets the actual engineering needs is selected from the frontier solution set using multi-objective optimization and decision-making algorithms.

[0024] Based on the neural network model built in S5, a multi-objective optimization algorithm is used to iteratively optimize the fin design parameters and obtain the Pareto front solution set of the core objective. The TOPSIS professional decision algorithm is introduced to carry out comprehensive evaluation. Combined with the priority requirements of the air-cooled diesel engine application scenario, the evaluation logic is optimized by assigning differentiated weights to the optimization objectives. Finally, the optimal inter-cylinder fin optimization result of the multi-cylinder air-cooled diesel engine that meets the actual engineering requirements is selected from the front solution.

[0025] The optimization results of the inter-cylinder fins of the multi-cylinder air-cooled diesel engine obtained from S6 can directly guide the actual design and manufacturing of the inter-cylinder fins. Based on the optimization results, the geometric parameters of the fins are determined and adjusted so that the optimized fin design can not only meet the heat dissipation requirements of the multi-cylinder air-cooled diesel engine under high power conditions, but also effectively suppress the problem of uneven temperature between cylinders, and reduce the flow resistance of cooling air and the power consumption of cooling fan.

[0026] Beneficial effects:

[0027] 1. The present invention discloses an optimization design method for inter-cylinder fins of a multi-cylinder air-cooled diesel engine. It adopts a zonal optimization strategy to adapt to the differences in heat load and airflow distribution in different regions. By accurately matching the heat load requirements after power enhancement, it achieves three major goals: efficient heat dissipation, reduction of heat load in each cylinder and low flow resistance of the system. This reduces the risk of thermo-mechanical load failure after power enhancement of the actual engine and helps to enhance the power of air-cooled diesel engines.

[0028] 2. The present invention discloses an optimization design method for inter-cylinder fins of a multi-cylinder air-cooled diesel engine, which relies on the conventional design parameters and basic performance data of the target air-cooled engine, resulting in low data acquisition costs. Furthermore, the optimization framework is universal and can be easily extended to the fin design of other models or types of air-cooled engines.

[0029] 3. The present invention discloses an optimization design method for inter-cylinder fins of a multi-cylinder air-cooled diesel engine. Based on digital simulation and numerical optimization, it can complete most of the design iterations and performance verification in virtual space, reduce potential safety hazards in the whole engine test process and save test costs. Attached Figure Description

[0030] Figure 1 This is a flowchart illustrating an optimized design method for inter-cylinder fins in a multi-cylinder air-cooled diesel engine, according to an embodiment of the present invention.

[0031] Figure 2 This is a schematic diagram of the partitioning of the air-cooled machine according to an embodiment of the present invention;

[0032] Figure 3 This is a schematic diagram of the optimized variables for the inter-cylinder fins in an embodiment of the present invention;

[0033] Figure 4 This is a schematic diagram of a neural network according to an embodiment of the present invention. Detailed Implementation

[0034] To better illustrate the purpose and advantages of the present invention, the invention will be further described below in conjunction with the accompanying drawings and examples.

[0035] Example:

[0036] This embodiment uses the optimized inter-cylinder fin design of a 12-cylinder air-cooled engine as an example. This engine has a turbocharger system, a designed compression ratio of 17, a cylinder bore of 12 mm, a single-cylinder fuel injection quantity of 119 mg, and a power output of 440 kW. Figure 1 As shown in the figure, the method for optimizing the inter-cylinder fin design of a multi-cylinder air-cooled diesel engine disclosed in this embodiment has the following specific implementation steps:

[0037] S1. Conduct external characteristic bench tests using an engine bench to obtain the performance and status parameters of the air-cooled engine. Use a Siemens AC dynamometer in speed control mode to keep the air-cooled engine operating at a constant speed.

[0038] Cylinder pressure curves for the air-cooled engine were acquired using cylinder pressure sensors. After installing a crankshaft gauge, an AVL combustion analyzer was used for data acquisition, recording one data point for every 0.1° crankshaft rotation, resulting in 7200 data points collected within a single engine cycle of 720° crankshaft rotation. After stabilizing under the target operating condition for 3 minutes, cylinder pressure data for 50 engine cycles were collected, and the data was processed using the AGLindicom after-processing software.

[0039] Nickel-chromium / nickel-silicon K-type thermocouples were used to measure the temperature of the cylinder head, cylinder liner, and inlet and outlet airflow. The temperature measurement range was 0℃-1300℃, with an accuracy of ±2℃. The inlet air pressure signal was transmitted to the bench steady-state data acquisition instrument via a QYB100 pressure transducer. Temperature changes at the cylinder head and cylinder liner measurement points were monitored. Instantaneous and steady-state test data were collected after the temperature at each measurement point stabilized for 5 minutes. The data acquisition time for the cylinder head and cylinder liner temperature measurements was 60 seconds, and the average temperature within 60 seconds was taken as the temperature at the measurement point under that operating condition.

[0040] S2. A one-dimensional simulation model of the air-cooled engine is established using the one-dimensional engine simulation software GT-POWER. The model includes the complete engine block, combustion chamber, valve train, fuel supply system, and turbocharger system. The combustion chamber model includes a combustion model and a heat transfer model, with the in-cylinder combustion model using a three-Weber function model. The fuel injector model on the combustion chamber is configured with injection timing, cyclic injection quantity, and injection pressure.

[0041] The model's valve train piping parameters were modeled based on actual aircraft scans and converted into a one-dimensional model using GEM 3D. Key parameters included length and pipe diameter. The turbocharger system MAP was provided by the manufacturer, while modeling data for other systems was obtained from the engine's design parameters. Design parameters such as cylinder bore, stroke, compression ratio, and firing order were set. Initial values ​​for critical cylinder block wall temperatures were assigned empirically; for example, the piston and cylinder head wall temperatures were set to 600K, and the cylinder liner wall temperature to 500K.

[0042] The one-dimensional simulation model is calibrated to ensure that the simulation results are consistent with the actual performance parameters collected.

[0043] S3. Establish a three-dimensional temperature field simulation model of the cylinder of a 12-cylinder air-cooled diesel engine. Use SOLID software to create a flow domain model of the air-cooling system. For non-critical structures other than the cylinder, use a porous medium model to simplify the model. Select a tetrahedral mesh with high fit to spatially discretize the flow domains of the air pressure chamber and the cylinder heat sink. Use an interface to exchange data between different flow domains.

[0044] Based on the relevant data measured in S1, the boundary conditions of the airflow domain were set. Based on the calculation results of the one-dimensional simulation model in S2, the wall temperature and heat transfer coefficient of the cylinder were set. The temperature field was calculated using the Fluent software, with the RNG k-ε model selected as the turbulence model. Finally, the simulation model was calibrated using the cylinder temperature field measurement data from S1.

[0045] S4, such as Figure 2 , 3 As shown, considering the inter-cylinder airflow distribution characteristics and local heat load differences of a 12-cylinder air-cooled diesel engine, the cylinder is divided into several characteristic regions. Based on cylinder position, the fins are divided into the fan-side cylinder region, the intermediate cylinder region, the cylinder region far from the fan side, and the airflow impact and diffusion region. Optimization targets are set for the different airflow attenuation characteristics of each region.

[0046] After partitioning, the fin geometry parameters of each region are defined as optimization variables, including fin height, thickness, and spacing. Targeted heat dissipation optimization is achieved through independent adjustment within each region. Appropriate constraints must be set for these optimization variables to ensure the optimization scheme can be practically implemented. These constraints include space limitations and manufacturing feasibility: the maximum fin height in each region must not exceed the overall design envelope; fin thickness must meet material processing requirements to avoid defects such as stamping deformation and breakage; and fin spacing must not be less than a specific value to prevent die-casting bridging and dust accumulation.

[0047] S5, such as Figure 4As shown, a high-precision neural network prediction model is constructed based on the simulation dataset. Combining the determined partitioning optimization variables and constraints, an orthogonal experimental design method is used to divide the parameters into reasonable combinations. The objective optimization function is defined as minimizing the highest and average temperatures of the cylinders, minimizing the standard deviation of the temperature distribution among the cylinders in a multi-cylinder engine, and minimizing the total pressure drop of the entire fin array.

[0048] Based on orthogonal experimental sample datasets obtained from CFD simulations, a neural network surrogate model was constructed using Bayesian optimization hyperparameter tuning methods. The hyperparameter search range covers key parameters of the neural network, such as the number of hidden layer neurons, learning rate, number of iterations, and batch size. Bayesian optimization can efficiently locate the optimal hyperparameter combination within a limited number of iterations. The trained neural network prediction model can quickly predict the heat dissipation performance of the fin design scheme, providing efficient data support for subsequent optimization algorithms, significantly reducing computational costs during the iteration process, and shortening the optimization design cycle.

[0049] S6. Combining the high-precision neural network prediction model trained in S5, the NSGA-II genetic algorithm is used to perform iterative optimization of the fin design parameters. This algorithm continuously iterates within the preset parameter constraint space by simulating the selection, crossover, and mutation mechanisms of biological evolution, generating Pareto front solution sets for the three core objectives.

[0050] To select the optimal solution that best meets the actual engineering needs from numerous Pareto front solutions, the TOPSIS (Topology for Approximating Ideal Solutions) professional decision-making algorithm is introduced for comprehensive evaluation. First, the three target performance indicators are positiveized and standardized to eliminate the influence of differences in dimensions and inconsistencies in indicator types. Then, a positive ideal solution composed of the optimal values ​​of each target and a negative ideal solution composed of the worst values ​​of each target are defined, and the Euclidean distance from each solution to the positive and negative ideal solutions is calculated. Finally, the proximity coefficient of each solution is calculated through normalization. The closer the coefficient is to 1, the closer the solution is to the ideal state.

[0051] By considering the priority requirements of different application scenarios for air-cooled diesel engines, the evaluation logic can be optimized by assigning differentiated weights to three optimization objectives. Ultimately, the result with the highest approximation and strongest adaptability is selected as the optimal inter-cylinder fin optimization result for a multi-cylinder air-cooled diesel engine. The optimal inter-cylinder fin optimization result for a multi-cylinder air-cooled diesel engine can effectively control flow resistance while ensuring heat dissipation performance and temperature uniformity. This optimized fin design not only meets the heat dissipation requirements of a 12-cylinder air-cooled diesel engine under high-power conditions and balances the temperature distribution between cylinders, but also reduces fan power consumption and improves the overall engine's operating economy.

[0052] The above detailed description further illustrates the purpose, technical solution, and beneficial effects of the invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for optimizing the design of inter-cylinder fins in a multi-cylinder air-cooled diesel engine, characterized in that: Includes the following steps: S1. Obtain the performance parameters and status parameters of the air-cooled diesel engine through bench tests. S2. Based on the design parameters of the air-cooled engine and the performance parameters collected in S1, a one-dimensional simulation model of the air-cooled engine is built to obtain the gas state parameters during the thermodynamic cycle process inside the cylinder. S3. Based on the three-dimensional solid model of the air-cooled diesel engine, the state parameters of the air-cooled engine obtained in S1, and the state parameters of the in-cylinder gas obtained in S2, a three-dimensional temperature field simulation model of the air-cooled diesel engine cylinder is established. S4. Combining the inter-cylinder airflow distribution characteristics and local heat load differences of multi-cylinder air-cooled diesel engines, a zoning optimization strategy is adopted to divide the fin design area and define the optimization variables for each area. S5. Combining the optimization variables defined in S4, design an orthogonal simulation experiment and define the optimization objective function. Conduct the simulation experiment based on the simulation model obtained in S3, organize the obtained dataset, and then construct a neural network prediction model between the optimization variables and the objective function. S6. Based on the neural network model built in S5, the optimal inter-cylinder fin optimization results of the multi-cylinder air-cooled diesel engine that meet the actual engineering needs are selected from the frontier solution set using multi-objective optimization and decision-making algorithms.

2. The method for optimizing the inter-cylinder fin design of a multi-cylinder air-cooled diesel engine according to claim 1, characterized in that: The performance parameters of the air-cooled engine mentioned in S1 include the intake flow rate, cylinder pressure curve and heat release rate under stable operating conditions; the status parameters of the air-cooled engine include the fan speed, cooling airflow inlet temperature and pressure, temperature field measurement data of each cylinder, atmospheric pressure and ambient temperature under stable operating conditions.

3. The method for optimizing the design of inter-cylinder fins in a multi-cylinder air-cooled diesel engine according to claim 2, characterized in that: The method for establishing a one-dimensional simulation model of the air-cooled machine in S2 is to use GT-POWER software to perform one-dimensional modular modeling based on the design parameters of the air-cooled machine. The core objective of this model is to accurately calculate the gas state parameters in the thermodynamic cycle process to ensure that the simulation results are consistent with the actual performance parameters collected in S1.

4. The method for optimizing the design of inter-cylinder fins in a multi-cylinder air-cooled diesel engine according to claim 3, characterized in that: The method for establishing the three-dimensional temperature field simulation model of the air-cooled diesel engine cylinder in S3 is as follows: based on the three-dimensional solid model of the air-cooled diesel engine, the flow field domain of the air-cooling system is established using SOLID software, and the non-critical structures of the air-cooling system are simplified using a porous medium model; the state data measured in S1 is used to set the boundary conditions of the air flow domain for the three-dimensional temperature field simulation model; and the gas state parameters calculated based on the one-dimensional model in S2 are used to set the third type of boundary conditions for the cylinder wall of the simulation model. The formula for calculating the third type of boundary condition is as follows: in, and To obtain the in-cylinder gas heat transfer coefficient and instantaneous temperature at each instant in one-dimensional performance simulation calculation, In one cycle, Represents crankshaft rotation angle. The average heat transfer coefficient, This is the weighted average temperature.

5. The method for optimizing the design of inter-cylinder fins in a multi-cylinder air-cooled diesel engine according to claim 4, characterized in that: The method described in S4 for dividing the fin design area and defining the optimization variables for each area is as follows: based on the simulation results or measured data of the heat load distribution of the target air cooler, the cylinder is divided into several characteristic areas, and the fin geometric parameters in each area are defined as optimization variables. Targeted heat dissipation optimization is achieved through independent control of the partitions.

6. The method for optimizing the design of inter-cylinder fins in a multi-cylinder air-cooled diesel engine according to claim 5, characterized in that: The method for defining the optimization function described in S5 is as follows: The optimization function is defined around the core requirements. For example, the heat dissipation performance objective is to minimize the highest and average temperatures of the cylinder; the uniformity objective focuses on minimizing the standard deviation of the temperature distribution between cylinders in a multi-cylinder engine; and the flow resistance objective is based on minimizing the total pressure drop generated by the entire fin array. The specific calculation formula is as follows: in, Temperature data for each cylinder measuring point. The average temperature at the cylinder measuring point. This represents the temperature standard deviation.

7. The method for optimizing the design of inter-cylinder fins in a multi-cylinder air-cooled diesel engine according to claim 5, characterized in that: The method for constructing a high-precision neural network prediction model described in S5 is as follows: using orthogonal experimental design, selecting horizontal combinations of fin geometric parameters, conducting orthogonal experiments on each horizontal combination of geometric parameters based on a three-dimensional simulation model, collecting and organizing data samples, and then using the Bayesian optimization automatic adjustment hyperparameter method to construct a neural network prediction model between the optimization variables and the objective function.

8. The method for optimizing the design of inter-cylinder fins in a multi-cylinder air-cooled diesel engine according to claim 6, characterized in that: The S6 implementation method is as follows: based on the neural network model built in S5, a multi-objective optimization algorithm is used to iteratively optimize the fin design parameters to obtain the Pareto front solution set of the core objective; the TOPSIS professional decision algorithm is introduced to carry out comprehensive evaluation, and combined with the priority requirements of the air-cooled diesel engine application scenario, the evaluation logic is optimized by assigning differentiated weights to the optimization objectives, and finally the optimal inter-cylinder fin optimization result of the multi-cylinder air-cooled diesel engine that meets the actual engineering requirements is selected from the front solution.

9. A method for optimizing the design of inter-cylinder fins in a multi-cylinder air-cooled diesel engine according to any one of claims 1, 2, 3, 4, 5, 6, 7, or 8, characterized in that: The optimization results of the inter-cylinder fins of the multi-cylinder air-cooled diesel engine obtained from S6 can directly guide the actual design and manufacturing of the inter-cylinder fins. Based on the optimization results, the geometric parameters of the fins are determined and adjusted so that the optimized fin design can not only meet the heat dissipation requirements of the multi-cylinder air-cooled diesel engine under high power conditions, but also effectively suppress the problem of uneven temperature between cylinders, and reduce the flow resistance of cooling air and the power consumption of cooling fan.

Images