文献类型：期刊文献

英文题名：A MID-1DC+LRT Multi-Task Model for SOH Assessment and RUL Prediction of Mechanical Systems

作者：Yang, Hai Yang, Xudong Sun, Dong Hu, Yunjin

第一作者：Yang, Hai

通信作者：Yang, XD[1]

机构：[1]Guizhou Univ, Sch Mech Engn, Guiyang 550025, Peoples R China;[2]Guizhou Inst Technol, Guiyang 550003, Peoples R China;[3]Guizhou Univ, Key Lab Adv Mfg Technol, Minist Educ, Guiyang 550025, Peoples R China

第一机构：Guizhou Univ, Sch Mech Engn, Guiyang 550025, Peoples R China

通信机构：corresponding author), Guizhou Univ, Sch Mech Engn, Guiyang 550025, Peoples R China.

年份：2025

卷号：25

期号：5

外文期刊名：SENSORS

收录：;EI(收录号：20251118049249);Scopus(收录号：2-s2.0-86000635601);WOS:【SCI-EXPANDED(收录号:WOS:001443448800001)】；

基金：This research was funded by Research on Optimization of Sorting Scheduling and Delivery Service Based on Business Flow Data Driven, grant number Qianyanzhuke[2022]No.1.

语种：英文

外文关键词：predictive health management; state of health; remaining useful life; multi-task model; low-rank transformer

摘要：Predictive health management (PHM) plays a pivotal role in the maintenance of contemporary industrial systems, with the evaluation of the state of health (SOH) and the prediction of remaining useful life (RUL) constituting its central objectives. Nevertheless, existing studies frequently approach these tasks in isolation, overlooking their interdependence, and predominantly concentrate on single-condition settings. While Transformers have demonstrated exceptional performance in RUL prediction, their substantial parameter requirements pose challenges to computational efficiency and practical implementation. Further, multi-task learning (MTL) models often experience performance deterioration as a result of imbalanced weighting in their loss functions. To address these challenges, the MID-1DC+LRT model was proposed in the present study. The proposed model integrates a multi-input data 1D convolutional neural network (1D-CNN) and low-rank transformer (LRT) within an MTL framework. This model processes high-dimensional sensor data, multi-condition data, and health indicator data, optimizing the Transformer structure to reduce computational complexity. A homoscedastic uncertainty-based method dynamically adjusts multi-task loss function weights, improving task collaboration and model generalization. The results demonstrate that the proposed model significantly outperformed existing methods in SOH assessment and RUL prediction under multi-condition scenarios, demonstrating superior prediction accuracy and computational efficiency, especially in complex and dynamic environments.