Machine learning models have been widely used in the field of cutting tool wear identification, achieving favorable results. However, in actual industrial scenarios, obtaining sufficient labeled samples is time consuming and costly, while unlabeled samples are abundant and easy to collect. This situation significantly affects the model’s performance. To address this challenge, a novel semi-supervised method, based on long short-term memory (LSTM) networks, is provided. The proposed method leverages both small labeled and abundant unlabeled data to improve tool wear identification performance. The proposed method trains an initial tool wear regression model using LSTM, using a small amount of labeled samples. It then uses manifold regularization to generate pseudo-labels for the unlabeled samples. These pseudo-labeled samples are combined with the original labeled samples to retrain the MR–LSTM model iteratively to improve its performance. This process continues until a termination condition is met. The method considers the correlation between sample labels and feature structures, as well as the correlation between global and local sample labels. Experiments involving milling tool wear identification demonstrate that the proposed method significantly outperforms support vector regression (SVR) and recurrent neural network (RNN)-based methods, when a small amount of labeled samples and abundant unlabeled samples are available. The average R² values in terms of the proposed method’s predicted results can reach above 0.95. The proposed method is a potential technique for low-cost tool wear identification, without the need to collect a large number of labeled samples.

This study explores the mechanisms underlying the enhanced anti-wear and thermal fatigue performance of laser-treated bionic brake drums, aiming to extend their service life and improve design quality. Bionic brake drums treated with laser patterns—point, stripe, and grid—were tested with semi-metallic, non-asbestos organic (NAO), and ceramic brake pads. A mechanical model was developed to analyze wear performance, and bench tests were conducted to assess wear patterns. Thermal fatigue tests examined the impact of thermal cycling on the treated drums’ wear behavior. The results reveal that laser-treated bionic brake drums significantly outperformed untreated ones in both wear resistance and thermal fatigue. Among the treatments, the grid pattern showed the best wear performance, and thermal fatigue life was improved by 27% for the striped pattern and 38% for the grid pattern. The study concludes that laser treatment effectively enhances both wear resistance and thermal fatigue performance in bionic brake drums, especially for the grid pattern, offering valuable insights for future brake drum design.

Carbon fiber composites have the characteristics of light weight and high strength, and are widely used in automotive cover parts. This paper targets at the B-pillar reinforcement plate of the passenger compartment, and proposes a lightweight-oriented design of carbon fiber composite B-pillar reinforcement plate through topology optimization, structural design and initial layup design. The stiffness and three-point bending of the carbon fiber composite B-pillar reinforcement plate are compared, and its crashworthiness index is calibrated. Based on the side impact analysis of the whole vehicle model, the peak intrusion velocity of the carbon fiber composite B-pillar reinforcement plate is lower than that of the original steel material B-pillar reinforcement plate, and the intrusion velocities of the corresponding dummy's thorax, abdomen, and pelvis are reduced by 0.8 m/s, 0.5 m/s, and 0.5 m/s, and the intrusion amount is reduced by 8 mm, 14 mm, and 16 mm, respectively, compared with that of the original steel material B-pillar. The study shows that the carbon fiber composite B-pillar reinforcement plate can effectively improve the crashworthiness of the whole vehicle, and it is of value to be promoted in the study of carbon fiber composites applied to other structural parts of the body frame based on lightweight design.