Aug 2026· Proceedings of the Institution of mechanical engineers. Part C, journal of mechanical engineering science· 0 citations· 31 references
Abstract
In low-pressure die casting (LPDC), there is a complicated relationship between the solidification behavior of the casting and the thermal stress of the mold. Conventional studies consider these two aspects separately, complicating global co-optimization. To address this, the present paper puts forward a methodology for the design of the process parameters and cooling system that is based on surrogate modelling and multi-objective inverse optimization. The LPDC of an aluminum alloy wheel hub was selected as a case study. Samples of process parameters and cooling structure parameters were obtained via optimal Latin hypercube design (OLHD). A thermo–mechanical coupled simulation was performed using ProCAST and Abaqus, resulting in a dataset for casting solidification time and maximum mold thermal stress. Within the framework of Bayesian optimization (BO), the predictive performance of three surrogate models, namely Support Vector Regression (SVR), Kriging, and Extreme Gradient Boosting (XGBoost), was compared. The study shows that BO-XGBoost exhibits lower predictive accuracy than the other two models, while BO-Kriging is marginally better for solidification time and BO-SVR is slightly superior for thermal stress. In addition, a comparative analysis was conducted on the performance of three multi-objective optimization algorithms, Non-dominated Sorting Genetic Algorithm II (NSGA-II), Multi-objective Particle Swarm Optimization (MOPSO), and Logistic Chaotic Mapping-based Sparrow Search Algorithm (LCSSA). The results show that LCSSA demonstrates optimal performance in terms of convergence, distribution, and stability. Consequently, it was selected to perform multi-objective optimization of solidification time and thermal stress. Combined with the surrogate models, an inverse optimization strategy was then employed to extract stable process parameter windows for various scenarios. Simulation verification demonstrates that the recommended parameter intervals satisfy target constraints. This study proposes a systematic methodology for the co-optimization of LPDC processes and mold design, enhancing the engineering applicability and stability of the process under variable working conditions.
This study proposes a data-driven surrogate modeling framework for predicting
solidification time and mold thermal stress during low-pressure die casting
(LPDC) of aluminum alloy wheels. The methodology employed an optimal Latin
hypercube design (OLHD) to sample key parameters including cooling channel
geometry and process conditions. A sequential simulation methodology combining
ProCAST and Abaqus was implemented to generate a comprehensive dataset of
solidification times and thermal stress distributions. Based on this dataset,
surrogate models were developed using Support Vector Regression, Kriging, and
Polynomial Response Surface Methodology, with their hyperparameters
automatically tuned through Bayesian Optimization (BO). The optimized models
were rigorously evaluated using four statistical metrics: Coefficient of
Determination (R2), Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root
Mean Squared Error (RMSE). The evaluation results show that the BO–SVR model
demonstrated superior prediction accuracy for both output responses and
exhibited exceptional nonlinear fitting capability. This work establishes an
effective modeling approach for simultaneous quality and efficiency optimization
in wheel manufacturing.
Fu-Hao Fan, Yunlang Zhan, Zhen-Fei Zhan et al.· SAE technical paper series· 0 citations
Cooling-slope (CS) process is a process in preparing the feedstock for the semi-solid process with minimal equipment required. In CS process, optimal selection of CS parameters is important in producing high-quality feedstock. A comprehensive investigation concerning the influence of CS parameters on feedstock quality specifically Tensile strength (TS) and Impact Strength (IS) through an experimental design is conducted. The experiment employs three full factorial designs with added center points for CS parameters, including Pouring temperature (Pt), Pouring distance (Pd), and Slanting angle (Sa). Data from the CS experiment are utilized to develop the mathematical model using regression analysis approach. The models were validated using analysis of variance (ANOVA) and the coefficient of determination (R2). The confirmatory test result shows 3.47% of difference between simulation and experimental. The optimal solution will provide flexibility to the process planner to choose the best parameter settings depending on the application.
M. Kamal, N. F. B. W. Anuar, R. M. Said et al.· International journal of res...· 0 citations
In this study, an efficient method for concurrent thermomechanical performance
and weight optimization under modal constraints is proposed to address the
coupled design challenges of thermomechanical characteristics (thermal capacity,
thermal deformation, and modal) and structural weight in straight-ribbed brake
discs. Based on high-fidelity computer-aided engineering (CAE) simulations of
brake disc thermomechanical behavior, a neural network (NN)-based surrogate
model and a ResNet-guided geometric feature recognition (RGFG) model for
automatic modality recognition were developed, and integrated with a particle
swarm optimization (PSO) framework for optimal solution exploration. When
applied to a passenger vehicle brake disc case study, the surrogate model of NN
demonstrates remarkable accuracy: it shows more than 95% agreement with the CAE
results in thermal capacity prediction, the prediction accuracy of thermal
deformation exceeds 90% compared to CAE results and 83.4% compared to test
result, thereby validating the method’s effectiveness. Compared with
conventional CAE approaches, the surrogate model of NN achieves a subsecond
prediction speed, significantly reducing computational costs. The surrogate
model of RGFG achieves a test accuracy exceeding 95%. Furthermore, the proposed
optimization framework offers valuable insights for the inverse design of brake
discs.
Si-Miao Han, Da-Xin Jiang, Chao Han et al.· SAE technical paper series· 0 citations
To simultaneously suppress shrinkage-related defects and refine the solidification microstructure of Mn70Ni25Cr5 alloy ingots, ProCAST simulation was combined with Box–Behnken response surface methodology to optimize pouring temperature, filling time, and mold temperature. Porosity in the ingot body and secondary dendrite arm spacing (SDAS) were selected as the response variables, and quadratic regression models were established for both responses. The optimized casting parameters were determined using analysis of variance, response surface analysis, and the desirability function approach. The porosity and SDAS models were both statistically significant, with non-significant lack-of-fit terms and R2 values of 0.9906 and 0.9901, respectively. The optimal parameters were a pouring temperature of 1220.74 °C, a filling time of 6.34 s, and a mold temperature of 294.47 °C, corresponding to a predicted porosity of 0.426% and a predicted SDAS of 47.51 μm. A supplementary simulation and a validation casting experiment were then performed using practical process settings derived from the optimized solution. The supplementary simulation indicated that shrinkage-related defects were concentrated mainly in the riser, while metallographic examination revealed no large continuous shrinkage-porosity region in the examined ingot-body sections. The overall measured SDAS across the center, half-radius, and edge positions was 48.54 μm, differing from the response-surface prediction by approximately 2.2%. These results support the applicability of the combined ProCAST–RSM approach for simulation-assisted optimization of Mn70Ni25Cr5 alloy casting parameters within the investigated process range.
Shuicong Lu, De-Hong Lu, Yong-Kun Li et al.· Metals· 0 citations
Additive Manufacturing is an upcoming technology to produce metal structures in industry as complex near net-shaped structures can be built. One commonly used method is Laser Powder Bed Fusion (PBF-LB), that uses lasers to melt metal powder layer by layer. Alongside advantages that come with this technology, the variety of adjustable process parameters is challenging for optimizing the process due to complex correlations of those. Additionally, the resulting mechanical properties can be challenging to optimize empirically based on the vast multi-dimensional parameter space. To solve this problem, several Machine Learning (ML) approaches have been used in the scope of different applications. With the aim of predicting tensile properties of PBF-LB parts, printed with AlSi10Mg0.5, three ML models (Linear Regression, XGBoost, and Multi-Layer Perceptrons (MLP)) were trained as black box models on a newly created dataset. To include as much process information as possible in the training data, an additional mathematically based dimensionless metrics model was used. The model gained insights into the thermodynamic conditions of certain parameter sets, which enabled a more even distribution of different processing conditions in the dataset. This equation-based white box model, combined with the subsequent ML-based black-box models formed the grey-box modeling approach. Due to the small size of the dataset of only 50 data vectors, strong overfitting was observed. This could be minimized for the case of the MLP by means of a customized architecture and strong regularization. It was shown, that the dataset enabled sufficient predictions by the MLP model of yield and tensile strength with
$$\textit{R}^2_{test}$$
R
test
2
values of up to 88.3
$$\%$$
%
and 86.2
$$\%$$
%
, respectively. Elongation at break turned out to be more challenging to predict with an
$$\textit{R}^2_{test}$$
R
test
2
of up to 75.6
$$\%$$
%
. This highlighted the benefit of combining the phenomenological melt mode model for data creation and a ML model for sufficient prediction of mechanical properties in a resource efficient manner.
Florian Funcke, Tobias Forster, Marinus Kolbinger et al.· Journal of Intelligent Manuf...· 0 citations
The paper aims at rationalizing the distribution of grain structure parameters across a gas turbine engine (GTE) disk in order to minimize the disk’s mass while ensuring its safe operational conditions. For this purpose, advanced methods of digital design were improved and applied, including state-of-the-art approaches based on multilevel modeling of material structure and properties. The problem was solved using a combined approach. Macro-phenomenological models were employed to determine, during the flight cycle, the evolving fields of stress-strain state and temperature of the entire part. These results were then transferred into a multilevel model to analyze specific regions for the study of strength characteristics, namely, high-temperature strength (resistance to creep and long-term strength), fracture toughness, low-cycle fatigue strength, and thermal stability (resistance to recrystallization and grain boundary migration). Multilevel modeling was based on a comprehensive analysis of the literature data on the structure of the nickel alloy VV751P, as well as on the mechanisms of its deformation and failure. The results of digital design were obtained and analyzed, and recommendations were proposed for rationalizing the material’s grain structure to reduce the disk’s mass while maintaining strength characteristics. The developed approach proved to be effective in digital multilevel design for functionally critical components.
N. Kondratev, K. Romanov, Matvej Baldin et al.· Frontiers of Mechanical Engi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
