Newsfeeds

Measurement Science and Technology - latest papers

Latest articles for Measurement Science and Technology

IOPscience

  • ResNet50-3Cur-HGCN: a novel multimodal hybrid curvature space approach to bearing fault diagnosis
    As a consequence of its great load-bearing capacity, low friction loss, and low vibration and impact, bearings are employed extensively in a variety of applications. In response to the current issues in the process of fault signal identification using graph neural networks (GNNs), such as the insufficient expression of node data types, the inadequate exploration of feature information carried by the graph structure, and the singularity of mathematical space operations on graph data, this paper proposes a residual network-50-heterogeneous graph convolutional neural network (ResNet50-HGCN) model based on the combination of ResNet50 and HGCN. The model is trained in a threefold mixed curvature (3 Curvature, 3Cur) space environment for semi-supervised learning, aiming to achieve accurate classification of bearing fault signals. Specifically, first, the time-domain signals and the components of the time–frequency map obtained from the wavelet synchrosqueezing transform are used as the bimodal node information for HGCN. Then, the graph network is merged in the 3Cur space for training and weighted validation, obtaining the predicted category labels of the model under the 3Cur configuration space. Finally, experimental data analysis is conducted, sparse confusion matrices for predicted categories are drawn, and four types of accuracy-related evaluation metrics are calculated. The experimental results show that the proposed ResNet50-3Cur-HGCN classification model outperforms other models in the experiment, achieving an accuracy of 97.71%, which verifies the method’s beneficial effects with regard to precision and efficiency. It also provides a good methodological reference for bearing fault diagnosis approaches centered on GNNs.

  • Improved insulator defect detection network considering target characteristics and sample location classification
    Insulators are crucial components of the power system. An enhanced insulator detection network, based on YOLOv8, addresses unequal training samples, inadequate target localization and classification accuracy in the existing insulator unmanned aerial vehicle inspection algorithm. Firstly, the ADown down-sampling component and DynamicConv are incorporated into the backbone network to enhance feature representation. Secondly, Focal-IoU and Adaptive Training Sample Selection are used during training to adjust the weight of each sample based on their quantity and difficulty level, enhancing focus on rare and challenging targets. Finally, to address difficult target localization and classification, design a task-aligned detection head called ‘Align Head’ to strengthen the link between localization and classification branches. Experiments show that the proposed method increases mAP@0.5 (mean average precision at a threshold of 0.50) by 7.5% over the baseline, with an FPS of 81.57, demonstrating superior performance.

  • A multi-robot conflict elimination path planning approach for dynamic environments
    Path planning plays a crucial role in multi-robot systems, and its effectiveness directly impacts the system’s performance. A multi-robot conflict-elimination path planning method (CEPP) for dynamic environments is proposed. The method fuses the adaptive dynamic-window algorithm (ADWA) with the Repulsive function-based optimized A* algorithm (R–A*) to deal with multi-robot path planning (MRPP) and introduces a safe area radius and priority strategy to solve the multi-robot collision conflict problem. Among them, ADWA first adds the time cost and target point distance evaluation function to the original evaluation function and introduces adaptive weights to accelerate the efficiency of the robot in finding the target point. Then a target point detection waiting mechanism is introduced to solve the problem that the robot cannot find the endpoint. Finally, the effectiveness of the CEPP algorithm for MRPP in dynamic environments is verified by simulation. Meanwhile, the CEPP algorithm is compared and analyzed with the traditional fusion algorithm (A*-DWA), and the simulation results show that the average running time and path length of this method are better than the A*-DWA algorithm.

  • Research on fault component extraction and fault type identification of rotating machinery based on MDSM and a novel convolutional neural network
    Given the complexity and difficulty in extracting and recognizing multi-axis mechanical fault components, a method for fault extraction and identification based on the multi-Axis displacement superposition method (MDSM) and a novel convolutional neural network (NCNN) is proposed. In the proposed MDSM method, first, correlation analysis is used to determine the operational status of the mechanical system and to identify the location of faults in the multi-axis rotating mechanical system. Secondly, a simplified initial point selection process is introduced to segment the collected fault component. Subsequently, a signal superposition method with position offset correction is employed to perform position correction and superposition operations on the segmented signals, enhancing the accuracy of the fault signal. Finally, the front end of the superimposed signals is extracted as the fault component, completing the separation and extraction of the fault components. For the extracted fault signals, an NCNN is designed for fault-type identification. NCNN improves computational efficiency and effectively completes fault feature identification through a lightweight network architecture and a nonlinear learning rate scheduling strategy. The results of the experiment show that the proposed method can accurately determine the fault occurrence location, extract the fault components, and achieve high-accuracy fault type identification.

  • Natural gas production process fault localization based on direct transfer entropy with adaptive lag
    Natural gas production equipment has complex structures, numerous monitoring parameters, and intricate correlation relationships, making it challenging to trace the source of faults for abnormal events. This paper proposes a fault localization method for natural gas production processes based on direct transfer entropy with adaptive lag (AL-DTE). Firstly, a variable set is screened based on the contribution plot. To enhance the adaptability to multiple operating conditions and reduce the reliance on experience, this paper integrates the adaptively to DTE and proposed AL-DTE. A causal analysis is then constructed and the causality graph is utilized to visualize the abnormal propagation path and identify the root cause of the fault. The proposed method can locate abnormal and faulty sub-equipment without relying on historical experience, enabling rapid localization of unknown faults. The effectiveness of the method is verified through simulation data and real faults of a triethylene glycol dehydration equipment.