31 October 2023 in IEEE/ASME Transactions on Mechatronics
Intelligent machinery prognostics and health management (PHM) methods have been attracting growing attention in the past years, with the rapid development of the artificial intelligence algorithms. The remaining useful life (RUL) prediction problem is critical in prognostics for optimization of the maintenance strategy. Despite the promising advances, the current algorithms basically assume the training and testing entities are operating under identical condition, which is less practical in the real industries. In the cross-domain PHM studies, domain adaptation techniques have been successfully applied for building generalized data-driven models. However, the availability of target-domain data in full life cycle is basically required by the existing methods. In most scenarios, only the target data at early degradation period can be obtained, that poses great challenges in transfer learning. This article proposes a partial domain adaptation method for RUL prediction with incomplete target-domain data. Deep neural network-based adversarial learning strategy is adopted as the main framework, and the source-domain instance-weighted degradation fusion scheme is proposed for conditional domain adaptation at similar degradation levels. The source outliers can be well filtered out in learning generalized features across domains. Experiments of machine run-to-failure tests are implemented for validation, and the results indicate the proposed methodology is well suited for practical cross-domain RUL predictions.
1 April 2024 in IEEE/CAA Journal of Automatica Sinica
Dear Editor, As an important energy storage device, lithium-ion battery plays a vital role in electric aircrafts, which are new and promising equipment of transportation in the future with low carbon emissions. Accurate prediction of the state of charge (SOC) of lithium-ion batteries is of great importance in reducing the probability of abnormal accidents and ensuring flight safety. This paper proposes a novel Swin Transformer-based method for predicting the SOC of lithium-ion batteries. Firstly, the data are reconstructed and the features are extracted by using interpolation fitting to overcome noise generated by the battery during the data acquisition process in the practical industrial scenarios. Then, the learned features are processed by the Swin Transformer network to achieve accurate SOC prediction of lithium-ion batteries. This letter conducts experiments and verification based on the actual flight data of new energy electric aircrafts. The experimental results show that the proposed method has low prediction error and promising accuracy.
20 November 2025 in Applied Soft Computing
3 June 2026 in Green Energy and Intelligent Transportation