Over the last few decades, detecting surface defects has attracted significant attention as a challenging task. There are specific classes of problems that can be solved using traditional image processing techniques. However, these techniques struggle with complex textures in backgrounds, noise, and differences in lighting conditions. As a solution to this problem, deep learning has recently emerged, motivated by two main factors: accessibility to computing power and the rapid digitization of society, which enables the creation of large databases of labeled samples. This review paper aims to briefly summarize and analyze the current state of research on detecting defects using machine learning methods. First, deep learning-based detection of surface defects on industrial products is discussed from three perspectives: supervised, semi-supervised, and unsupervised. Secondly, the current research status of deep learning defect detection methods for X-ray images is discussed. Finally, we summarize the most common challenges and their potential solutions in surface defect detection, such as unbalanced sample identification, limited sample size, and real-time processing.

This paper focuses on the modeling and analysis of a four-groove passenger car tire, size 235/55R19, using finite element analysis. The Mooney–Rivlin material model is employed to define the hyperelastic behavior of the tire rubber compounds for all solid elements. The tire rim is modeled as a rigid body using aluminum alloy material, and the beads are modeled as beam elements using steel material. The tire model is validated in both static and dynamic domains through several simulations and is compared to published measured data. The tire is validated using footprint and vertical stiffness tests in the static domain. In the static footprint test, a steady-state vertical load is applied, and the tire–road contact area is computed. In the vertical stiffness test, a ramp vertical load is applied, and the tire’s vertical displacement is measured to calculate the tire’s vertical stiffness. In the dynamic domain, the tire is validated using drum-cleat and cornering tests. In the drum-cleat test, a drum with a 2.5 m diameter and a cleat with a 15 mm radius is used to excite the tire structure and obtain the frequency of the vertical and longitudinal first modes of vibration, that is, by applying the fast Fourier transformation (FFT) of the vertical and longitudinal reaction forces at the tire center. In addition to this test, the tire model is pre-steered on a flat surface with a two-degree slip angle and subjected to a steady state linear speed of 10 km/h to predict the cornering force and compute the cornering stiffness. In addition, the effect of tire longitudinal speed on the rolling resistance coefficient is then predicted at zero slip angle using the ISO 28580 rolling resistance test. The findings of this research work provide insights into passenger car tire–road interaction analysis and will be further used to perform tire rubber compound material model sensitivity analysis.

This paper presents a comprehensive literature review of the most popular and recent work on passenger and truck tires. Previous papers discuss a huge amount of work on the modeling of passenger car tires using finite element analysis. In addition, recent works on tire–road interaction and the validation of tires using experimental measurements have been described. Moreover, the history of the tire-road contact algorithms is explained. In addition, friction modeling that is implemented in tire–road interaction applications are discussed. Also, a summary of current state-of-the-art research work definitions and requirements of the tread rubber compound are covered from previous studies using various literature reviews and hyper-viscoelastic material models that are implemented for the tread top and the tread base rubber compound. Furthermore, the effect of tire temperature from previous works is presented here. Finally, this literature review also highlights the shortcomings of recent research work and describes the areas lacking in the literature.

This paper presents a motion planning algorithm for generating optimal collision-free paths for robotic vehicle with two trailers moving autonomously. The proposed algorithm is based on combination between artificial potential field method (APF) and optimal control theory. The optimal control theory is applied to generate an optimal collision-free path for robotic vehicle from a starting point to the goal point. On the other hand, the proposed APF is based on two-dimensional Gaussian function to represent goal location as attractor and obstacles as repulsors and consequently, will control the steering angle of the robotic vehicle so that it can reach to its target location safely avoiding collision. A linear two-degree-of-freedom vehicle model with linear tire characteristics is derived to represent the vehicle motion considering the lateral and yaw dynamics. Several simulations are carried out to check the fidelity of the proposed technique and the illustrated results demonstrated the generated path for the robotic vehicle with two trailers satisfy vehicle dynamics constraints, avoid collision with the obstacles and reach the target location safely. The simulations results demonstrated the efficiency of the proposed algorithm and its success in dealing with complex environments with different obstacles.

This paper aimed to investigate the cornering characteristics of a Regional Haul Steer II, RHS 315/80 R22.5 truck tire traveling on a dry, hard surface using the Finite element analysis (FEA). This research was carried out using commercial Finite Element software and Pam-Crash in an Explicit Environment. A finite element truck tire model was developed to apply the tire terrain cornering condition. The concentrated loads and boundary conditions for the rim and wheel were applied to the model. The rubber material was defined using the Mooney–Rivlin model. The truck tire cornering operating conditions, including three different speeds with respect to various positive slip angles, were investigated. Several simulations were repeated at various operating conditions, including three different inflation pressures and three different vertical loads. Subsequently, the tire lateral force was computed using the local and global frame coordinates. Additionally, the self-aligning moment was extracted from the tire cross-section at each operating condition. Finally, a comparison between the simulation results showed that the tire lateral force was highly sensitive to the variation of the slip angles at the higher domain, and also that the tire inflation pressure, regardless of the speed, was considered to be one of the main parameters directly affecting the tire-cornering properties.