Currently, braking control systems used in regional railways are open-loop systems, such as metro and tramways. Given that the performance of braking can be influenced by issues such as wheel sliding or the properties of the friction components present in brake systems, our study puts forward a novel closed-loop mechanism to autonomously stabilize braking performance. It is able to keep train deceleration close to the target values required by the braking control unit (BCU), especially in terms of the electrical–pneumatic braking transform process. This method fully considers the friction efficiency characteristics of brake pads and encompasses running tests using rolling stock. The test results show that the technique is able to stabilize the actual deceleration at a closer rate to the target deceleration than before and avoid wheel sliding protection (WSP) action, especially during low-speed periods.

Longitudinal information in radiology reports refers to the sequential tracking of findings across multiple examinations over time, which is crucial for monitoring disease progression and guiding clinical decisions. Many recent automated radiology report generation methods are designed to capture longitudinal information; however, validating their performance is challenging. There is no proper tool to consistently label temporal changes in both ground-truth and model-generated texts for meaningful comparisons. Existing annotation methods are typically labor-intensive, relying on the use of manual lexicons and rules. Complex rules are closed-source, domain specific and hard to adapt, whereas overly simple ones tend to miss essential specialised information. Large language models (LLMs) offer a promising annotation alternative, as they are capable of capturing nuanced linguistic patterns and semantic similarities without extensive manual intervention. They also adapt well to new contexts. In this study, we therefore propose an LLM-based pipeline to automatically annotate longitudinal information in radiology reports. The pipeline first identifies sentences containing relevant information and then extracts the progression of diseases. We evaluate and compare five mainstream LLMs on these two tasks using 500 manually annotated reports. Considering both efficiency and performance, Qwen2.5-32B was subsequently selected and used to annotate another 95,169 reports from the public MIMIC-CXR dataset. Our Qwen2.5-32B-annotated dataset provided us with a standardized benchmark for evaluating report generation models. Using this new benchmark, we assessed seven state-of-the-art report generation models. Our LLM-based annotation method outperforms existing annotation solutions, achieving 11.3\% and 5.3\% higher F1-scores for longitudinal information detection and disease tracking, respectively.