Rapid mechanical evaluation of the engine hood based on machine learning

Abstract

With the development of machine learning and data mining, rapid design, rapid verification and rapid manufacturing have become the mainstream in the machinery industry. In this paper, the mapping function between the mechanical properties of the hood and its 11 dimensional parameters was mined using machine learning algorithms. By combining XGBoost and LightGBM algorithms with the bagging method, we proposed a hybrid model with hyperparameters optimized by the grey wolf algorithm. Subsequently, several machine learning models were trained and tested on a dataset of 6959 simulation samples, and the proposed hybrid model was found to have excellent predictive performance for the torsional stiffness ( R 2 of 0.9969 and root-mean-square error of 1.32185) and first-order modal frequency (0.9977 and 0.00989) of the hood. Moreover, the SHAP method (Shapley additive explanations) was used as a machine learning interpretation method to explain the predictive process of the mechanical performance. The results show that SHAP has great potential in model interpretation. This paper aims to develop a mathematical model of the mechanical properties of the hood, which can quickly predict the mechanical properties based on each key dimensional parameter. Therefore, engineers and designers can apply this approximate model in their design space exploration algorithms directly without training extra low-dimensional surrogate models.

A Novel Simulation-Based Optimization Method for Autonomous Vehicle Path Tracking with Urban Driving Application

“…SO techniques are wide-ranging, including random search, stochastic approximation, and especially Bayesian Optimization (BO) [24]. Among these, BO is widely recognized as the dominant algorithm, with applications spanning drug molecular design [25,26], material discovery [27], and automatic hyperparameter tuning [28,29]. BO originated with [30] and gained further prominence with the introduction of Efficient Global Optimization (EGO) by [31].…”

Digital Engineering Methods in Practical Use during Mechatronic Design Processes

“…Out of the total of 36 publications identified in the field of validation, around one-third, see [96,[102][103][104][105][106][107][108][109][110][111], are strongly related to manufacturing, while an equally large proportion, see [112][113][114][115][116][117][118][119][120][121][122][123][124], stems from the field of automotive and aerospace development. Still, five contributions, see [125][126][127][128][129], contemplate the development and production of integrated circuits.…”

Machine Learning–Assisted Design of Material Properties

“…Several techniques have been established to interpret the ML models used for material design, especially for ML models used for forward property prediction. For example, various feature importance scores that quantify the significance of individual descriptors on a material property can be computed using Shapley additive explanations (136,137), Gini importance analysis (59), and mean decrease accuracy (138). For deep artificial neural networks trained to predict material properties, the design parameters that strongly correlate with the material property can be identified by analyzing the weights of the trained networks (139,140).…”