The aluminum alloy drill pipe suffers long-term high-temperature conditions during ultra-deep well drilling. In this paper, the samples were prepared by vacuum hot pressing, followed by hot extrusion and T6 heat treatment. The mechanical properties of short carbon fiber reinforced 2024 aluminum alloy composites (SCFs/2024 Al) and the microstructure evolution at the interface region thermal exposure at 160 °C for 500 h are discussed. The experimental results showed that the effect of short carbon fiber on 2024 aluminum alloy remained steady throughout the whole process of the heat exposure experiment. The distribution and volume of interface products (Al₄C₃) changed with the prolonging of heat exposure time, and connected after coarsening. The evolution of the morphology of Al₄C₃ relieved the stress of the interface between carbon fiber and aluminum alloy matrix and enhanced the mechanical properties of the composite.

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.

To meet the increasing performance requirements of drilling pipes, including a reduced weight and enhanced mechanical and thermal properties, the application of aluminum alloys must be further advanced. Short-carbon-fiber-reinforced 2A12 aluminum alloy composites were fabricated via powder metallurgy. The density, hardness, and tensile strength of the composites were measured. The influence of the carbon fiber content on the composite’s mechanical properties was investigated across various temperatures. The composite material exhibited maximum yield strengths of 412 MPa at room temperature, 381 MPa at 180 °C, and 337 MPa at 220 °C. Incorporating carbon fibers increased the service temperature of a 2A12 aluminum alloy by approximately 40 °C. The strength increment of composites with a fiber content below 6 vol.% corresponded to the load transfer mechanism of carbon fiber, while the reason for non-conformity at a more than 6 vol.% fiber content was the continuous fracturing of carbon fibers, leading to the failure of the composites.