Identification of defects in the inner layers of composite components based on capacitive sensing.

This paper describes the development and validation of a rapid internal defect detection method for multilayer composite components. Coplanar array capacitive imaging is based on electrical capacitance tomography, in which all electrodes are arranged in a single plane. The coplanar array capacitive sensor system is based on the capacitive edge effect and reconstructs the dielectric distribution in the sensitive area by measuring the capacitance of the sensor. A 4 × 3 array of coplanar electrode sensors is established and used to image the defects in the inner layers of multilayer composite components. Using a 3D model of the sensor and the sensitivity field, the variation pattern of the sensitivity field is analyzed. By placing different objects into the sensitivity area of the system, changes in the dielectric constant can be observed. Multilayer composite components with void defects are placed in the measurement area for defect detection. The dielectric distribution is visualized by reconstruction algorithms from the capacitance data and sensitivity field data. The results show that the imaging system based on a coplanar array capacitive sensor can reproduce the location of defects and realize the nondestructive testing of complex multilayer composite components.

A new attention-based 3D densely connected cross-stage-partial network for motor imagery classification in BCI.

Objective. The challenge for motor imagery (MI) in brain-computer interface (BCI) systems is finding a reliable classification model that has high classification accuracy and excellent robustness. Currently, one of the main problems leading to degraded classification performance is the inaccuracy caused by nonstationarities and low signal-to-noise ratio in electroencephalogram (EEG) signals.Approach. This study proposes a novel attention-based 3D densely connected cross-stage-partial network (DCSPNet) model to achieve efficient EEG-based MI classification. This is an end-to-end classification model framework based on the convolutional neural network (CNN) architecture. In this framework, to fully utilize the complementary features in each dimension, the optimal features are extracted adaptively from the EEG signals through the spatial-spectral-temporal (SST) attention mechanism. The 3D DCSPNet is introduced to reduce the gradient loss by segmenting the extracted feature maps to strengthen the network learning capability. Additionally, the design of the densely connected structure increases the robustness of the network.Main results. The performance of the proposed method was evaluated using the BCI competition IV 2a and the high gamma dataset, achieving an average accuracy of 84.45% and 97.88%, respectively. Our method outperformed most state-of-the-art classification algorithms, demonstrating its effectiveness and strong generalization ability.Significance.The experimental results show that our method is promising for improving the performance of MI-BCI. As a general framework based on time-series classification, it can be applied to BCI-related fields.

Defect Detection of Adhesive Layer of Thermal Insulation Materials Based on Improved Particle Swarm Optimization of ECT.

This paper studies the defect detection problem of adhesive layer of thermal insulation materials. A novel detection method based on an improved particle swarm optimization (PSO) algorithm of Electrical Capacitance Tomography (ECT) is presented. Firstly, a least squares support vector machine is applied for data processing of measured capacitance values. Then, the improved PSO algorithm is proposed and applied for image reconstruction. Finally, some experiments are provided to verify the effectiveness of the proposed method in defect detection for adhesive layer of thermal insulation materials. The performance comparisons demonstrate that the proposed method has higher precision by comparing with traditional ECT algorithms.

Redundancy Analysis of Capacitance Data of a Coplanar Electrode Array for Fast and Stable Imaging Processing.

A coplanar electrode array sensor is established for the imaging of composite-material adhesive-layer defect detection. The sensor is based on the capacitive edge effect, which leads to capacitance data being considerably weak and susceptible to environmental noise. The inverse problem of coplanar array electrical capacitance tomography (C-ECT) is ill-conditioning, in which a small error of capacitance data can seriously affect the quality of reconstructed images. In order to achieve a stable image reconstruction process, a redundancy analysis method for capacitance data is proposed. The proposed method is based on contribution rate and anti-interference capability. According to the redundancy analysis, the capacitance data are divided into valid and invalid data. When the image is reconstructed by valid data, the sensitivity matrix needs to be changed accordingly. In order to evaluate the effectiveness of the sensitivity map, singular value decomposition (SVD) is used. Finally, the two-dimensional (2D) and three-dimensional (3D) images are reconstructed by the Tikhonov regularization method. Through comparison of the reconstructed images of raw capacitance data, the stability of the image reconstruction process can be improved, and the quality of reconstructed images is not degraded. As a result, much invalid data are not collected, and the data acquisition time can also be reduced.