A reliability‐based robust optimization design for the drum brake using adaptive Kriging surrogate model

Abstract

To decrease random parameters’ influence on the drum brake reliability, the reliability‐based robust optimization design (RBROD) of the electric vehicle brake is proposed. Based on the assumption that the maximum temperature of the brake cannot exceed the allowable temperature, a performance function model of thermal–mechanical coupling reliability of drum brakes is established by the adaptive Kriging method, and the analysis of reliability sensitivity and RBROD are conducted. The accuracy of the proposed model is verified by temperature measurement experiment under emergency braking condition. The robust optimization design improves the drum brake reliability to 0.99998 and reduce the influence of the design parameters on the reliability, with the absolute values of the reliability sensitivity and the weight of the drum brake are significantly smaller. Therefore, the objectives of reliability design, robustness design, and optimization design are simultaneously achieved by the proposed methods. Besides, the relative error of the proposed method is 0.373%, the number of function evaluations is 39, and the comparison with four meta‐model methods show that the proposed method holds high‐accuracy and high‐efficiency. This study provides a high‐precision theoretical explanation for the robust optimization design of drum brake.

Reliability analysis of heat source layout temperature field prediction considering uncertainty in deep neural network surrogate models

“…These methods use surrogate models to fit functional relationships in observed data and make predictions for unknown data, combined with Monte Carlo simulation methods for reliability analysis. Surrogate models that have been widely used in recent decades include polynomial chaos expansions, 9 kriging, 10 support vector machines, 11 support vector regression, 12 and neural networks 13,14 . In addition to the classical surrogate models mentioned above, adaptive surrogate models have also been proposed recently for reliability analysis 10,13,15,16 …”

“…Surrogate models that have been widely used in recent decades include polynomial chaos expansions, 9 kriging, 10 support vector machines, 11 support vector regression, 12 and neural networks 13,14 . In addition to the classical surrogate models mentioned above, adaptive surrogate models have also been proposed recently for reliability analysis 10,13,15,16 …”

“…13,14 In addition to the classical surrogate models mentioned above, adaptive surrogate models have also been proposed recently for reliability analysis. 10,13,15,16 In the last two decades, machine learning has made tremendous breakthroughs in various fields such as computer vision 17 and natural language processing, 18 especially deep learning techniques based on deep neural networks. Due to the nature of generic approximators, 19 deep neural networks can reveal unknown relationships between a large number of variables.…”

Study on reliability of emergency braking performance of high-speed and heavy-load monorail crane

“…Yang et al [28] used AK-MCS to develop a performance function model for the thermal-mechanical coupling reliability of drum brakes and carried out reliability optimization design.…”