Search

Standardization is one of the key steps to analyze locomotive overhaul data with a focus on reliability-centered maintenance (RCM). However, traditional manual methods encounter challenges such as small sample sizes, non-standardized data formats, analytical complexities, and high labour costs, hindering the achievement of data standardization. Large language models (LLM), featuring powerful performance in natural language processing comprehension and handling complex tasks, have made great academic and industrial progress in recent years. This study initially investigated the application performance of LLMs in information extraction from locomotive overhaul data, with the following three reveals, as the universal information extraction (UIE) LLM is suitable for information extraction in the field of locomotive overhaul; expanding the size of locomotive data helps improve the UIE performance in information extraction from locomotive overhaul data; balancing the types of fault labels does not notably help improve this performance. Subsequent explorations concentrated on difficulties in data annotation. The script writing method was utilized for automated annotation of data, and ChatGLM was leveraged to standardize locomotive overhaul data, yielding Bleu-4, Rouge-1, Rouge-2, and Rouge-L metrics of 86.87%, 89.60%, 87.54%, and 94.26%, respectively, in alignment with the requirements of engineering applications. Further developments introduced an auxiliary data standardization pre-processing tool to streamline the standardization process by encapsulating the LLM.

The surface anomaly detection of train parts is one of the key technologies to ensure the safe operation of a metro system. Its core often lies in image processing. However, some anomalies do not exhibit significant changes in color, shape, and texture features, making detection difficult on 2D images. 3D point clouds add depth information on top of 2D images. This can help reflect the surface features of components more precisely and contribute to accurate anomaly detection. This paper addresses the common feature that most metro vehicle underbody components are rigid structures, combined with the 3D point cloud processing technology, and induces a general anomaly detection method. This method adopts point cloud preprocessing, point cloud registration, etc., and can detect changes in the depth information of the surface of subway underbody rigid structure components. However, it doesn't perform well when processing parts with high-ablaze reflective surfaces and mesh surfaces. Therefore, the paper uses the High Voltage Distribution Box (HVB) joint area and the hollow reactor oblique area as examples to improve this method. For the HVB joint area, regional segmentation is first used to obtain pure joint and wire harness regions; then, the statistical method is used to complete the detection of the former, and the general detection method is used to complete the detection of the latter. For the hollow reactor inclined surface area, plane filtering is used to adjust the process of the general detection method, eliminating the interference of noise points behind the grid plane and avoiding the problem of poor point cloud registration caused by plane filtering. Finally, using actual data from a metro company as a test set, it was verified that the new method, while ensuring a detection rate not lower than the original method, eliminates over 90% of false alarms, significantly reducing false detection rates. This offers theoretical guidance for the practical application of related anomaly detection systems.

Background: There is an urgent need for blood oxygen saturation (SpO2) tests when participants are ambulatory, as in daily activity monitoring, sleep monitoring, or even athletes' cardiovascular function tests. In such situations, measuring equipment needs to be wearable. This restricts the processor volume, and the corresponding algorithm should be microprocessor compatible.Objective: This article proposes an anti-motion interference blood oxygen saturation algorithm for the microcontroller based on AC and DC analysis, named de-trended FFT.Methods: An experiment was conducted to compare the de-trended FFT algorithm with two other algorithms commonly used in the time and frequency domains. In the experiment, participants' oxygen saturation levels were calculated from Photoplethysmography (PPG) signals that were recorded continuously. Meantime, five types of hand motions were conducted, including hand trembling movements, horizontal hand movements, vertical hand movements, finger tapping, and finger bending, with each state lasting 2 minutes.Results: Results show significant performance of de-trended FFT in SpO2 calculation (P < 0.05), in both accuracy and stability.Conclusion: De-trended FFT stands out in both mean deviation and variance by eliminating trending influence when compared with the other two algorithms. The motion interference's influence on SpO2 calculation mainly comes from the AC component, not the DC. [ABSTRACT FROM AUTHOR]