Accurate vehicle state information is crucial for safe driving and dynamic control of vehicles. Vehicle state estimation under unknown noise conditions is an important research topic. A state estimation method based on enhanced adaptive unscented Kalman filter (EAUKF) is proposed to solve vehicle estimation under unknown noise conditions. The general exponential attenuation adaptive Kalman filter algorithm does not attenuate the historical data enough when the noise statistics change rapidly, thus leading to the state variable’s inaccurate estimation. To improve the estimation accuracy of vehicle state variables, the exponential attenuation factor $B$ was further designed according to the variation of noise variance, and the influence of the latest data on state estimation was more considered. Based on the longitudinal dynamics modeling, the EAUKF method is applied to vehicle state estimation. Compared with the standard exponential weighted adaptive Kalman filtering algorithm and the average weighted adaptive Kalman filtering algorithm, the state variable estimation accuracy of the vehicle in this article is improved.

Domain generalization detection of fault categories in industrial equipment diagnosis is a challenging problem, as it demands a model with high generalization performance. Previous methods have primarily focused on a closed set, implying that the label spaces of the training and testing sets are identical. However, this approach is insufficient to reason about the intricate industrial dynamics. In this article, we fuse domain generalization and open-set recognition to introduce a new domain generalization fault diagnosis scenario, called open-set domain generalization. It learns from different source domains to achieve high performance on unknown target domains, where the distribution and label set can be different for each source and target domain. The problem can be more applicable to real-world industrial applications. In addition, we propose a multidomain contrastive coding (MDCC) framework to learn open-set domain generalizable representations. We conduct multidomain contrastive coding by designing a new contrastive coding task and loss to preserve domain-unique knowledge and generalize knowledge across domains simultaneously. Experimental results on two multidomain datasets demonstrate that the proposed MDCC framework outperforms prior methods in open-set domain generalization.