Newsfeeds

Measurement Science and Technology - latest papers

Latest articles for Measurement Science and Technology

IOPscience

  • Enhancing scene understanding and modal alignment in vision-language navigation via spatial–temporal graph
    Planning paths according to instructions in a complex environment is the current great challenge for the vision language navigation (VLN) task. Most research focuses on capturing individual visual representations of the objects in the current scene to identify the path matching the instruction. However, these methods cannot capture the correlation between objects within a scene as well as between consecutive scenes, resulting in incomprehensive scene and temporal understanding. To address this challenge, we propose a spatial–temporal-enhanced VLN model (STE-VLN). In this model, the spatial–temporal graph is proposed to enhance the model’s understanding of historical and current scenes by integrating spatial positional relationships of objects at adjacent moments. Meanwhile, a graph-wise attention module is proposed to screen visual graph information aligned with instructions and make more appropriate path planning. When evaluated in the target-oriented VLN dataset REVERIE and the room-oriented dataset R2R-LAST, STE-VLN significantly outperforms current state-of-the-art methods across multiple metrics like success rate and remote grounding success. Experimental results show our STE-VLN outperforms all metrics on a challenging coarse-grained VLN R2R-LAST and REVERIE dataset, exceeding the baseline by 3% and 2.92% in success rate respectively. Furthermore, extensive ablation studies and comprehensive analyses have been adopted, proving that the explicit enhancement of the spatial–temporal map and graphical attention improves the model’s path-planning ability and generalization.

  • Structured moment matching with discriminative enhancement contrastive learning for domain generalization in rotating machinery fault diagnosis
    Domain shift caused by varying operating conditions severely limits the practical application of intelligent fault diagnosis in rotating machinery. To address this challenge, this paper proposes a domain generalization method based on structured moment matching with discriminative enhancement contrastive learning (SMM-DECL). The method designs a structured moment matching strategy that hierarchically aligns first-order moments and correlation structures of feature distributions, preserving structured dependencies across domains while avoiding information loss from traditional distribution alignment. A discriminative enhancement contrastive learning framework is constructed with a hard sample mining strategy to optimize intra-class aggregation and inter-class separation losses, enhancing model discriminability while maintaining cross-domain feature consistency. An end-to-end collaborative optimization framework integrates structured alignment and discriminative enhancement. Experimental validation on bearing and gearbox fault datasets demonstrates that SMM-DECL achieves the best performance across all transfer tasks, significantly outperforming existing domain generalization methods and providing an effective solution for cross-domain fault diagnosis in rotating machinery.

  • Fast neutron spectroscopy with 4H-SiC solid-state detectors up to 500 °C for nuclear fusion applications
    Silicon carbide (SiC)-based detectors offer exceptional radiation hardness and thermal stability, making them suitable for neutron spectroscopy in fusion reactor environments, which are characterized by high temperatures and intense neutron fluxes. In this study we demonstrate a 250 µm-thick 4 H-SiC p–n junction detector that maintains stable deuterium–tritium neutron detection performance across the full temperature range from 25 °C to 500 °C, thereby overcoming the limitations commonly encountered with diamond-based detectors. These results highlight the potential of thick SiC detectors for monitoring neutron flux and performing neutron spectroscopy in harsh environments, such as the breeding blanket of fusion reactors.

  • A dynamic spatial-temporal graph transformer with multi-frequency attention for remaining useful life prediction
    The remaining useful life (RUL) prediction is essential for cost-effective production and reliable predictive maintenance in intelligent manufacturing. Existing deep learning-based approaches often struggle to capture complex degradation patterns across temporal, spatial, and frequency domains. To address this limitation, a dynamic spatial-temporal graph transformer with multi-frequency attention (DSTGT-MFA) is proposed in this paper for RUL prediction. The proposed DSTGT-MFA model consists of three key components: a multi-scale gated convolutional neural network for extracting hierarchical local features, a graph convolution transformer for modeling long-term spatial-temporal dependencies with dynamic and static adjacency matrices, and a multi-frequency spatial-temporal attention mechanism to enhance temporal and spatial attention in the frequency domain. This integrated architecture enables the model to comprehensively capture degradation trends and fuse multi-domain features. Extensive experiments conducted on the commercial modular aero-propulsion system simulation (CMAPSS) and new CMAPSS datasets demonstrate that the DSTGT-MFA model achieves superior prediction accuracy compared to twelve baseline methods.

  • Single-view iterative measurement of rotary axis radial error motion utilizing line-structured light
    Currently, optical measurement technology has distinct advantages in evaluating the radial error of the axis of rotation. However, a significant challenge persists: how to rapidly characterize this error from the spherical point cloud captured at a single viewing angle. As a symmetric geometric object, the reference sphere necessitates precise calibration of the structured light plane to its center to extract radial runout point clouds, and the calibration is often intricate and time-consuming. Moreover, installation eccentricity and random optical noise increase the complexity of accurately extracting radial runout data. To overcome these issues, a novel single-view iterative measurement framework (SVIMF) is proposed for the first time to enable rapid characterization of radial errors in eccentric shafts. The SVIMF comprises four primary modules: calibration, parameter adjustment, measurement, and evaluation. A three-step centering model based on reference sphere features is developed to determine the optimal measurement position within the structured light field of view. Furthermore, a radial runout point cloud reconstruction methodology is proposed, and a detection framework correlating the radial dimensional variation of the rotation axis with the radial runout point cloud established. Finally, the Fourier transform is employed for harmonic decomposition and synchronous error extraction, thereby enabling the quantitative characterization of the radial error of the rotation axis. Experimental results validate the feasibility and substantial application potential of the proposed SVIMF.