An ultra‐low power dynamic comparator is proposed with low dynamic offset variation for successive approximation register (SAR) analogue‐to‐digital converter (ADC). Dynamic offset can be cancelled with the cascode current source. Moreover, the power consumption can be reduced because it has no power consumption during the reset phase. With body‐driven technology and cross‐coupled inverter, the positive feedback during the regeneration is enhanced, which reduces remarkably delay time. Simulation results in a 0.18 μm CMOS technology confirm the performance of the proposed comparator. It is shown that the fluctuation of the total offset voltage (mean + 3std) is 0.15 and 0.39 mV with common‐mode voltage from 0.5 V _DD to V _DD at supply 1.2 and 0.6 V through Monte Carlo simulation, respectively. Furthermore, the delay of the proposed structure can be decreased to 1.837 and 118.2 ns at supply voltages of 1.2 and 0.6 V, while the power consumption is only 18.6 μW and 144 nW, respectively.

Due to the impact of the production environment, there may be quality issues on the surface of printed circuit boards (PCBs), which could result in significant economic losses during the application process. As a result, PCB surface defect detection has become an essential step for managing PCB production quality. With the continuous advancement of PCB production technology, defects on PCBs now exhibit characteristics such as small areas and diverse styles. Utilizing global information plays a crucial role in detecting these small and variable defects. To address this challenge, we propose a novel defect detection framework named Defect Detection TRansformer (DDTR), which combines convolutional neural networks (CNNs) and transformer architectures. In the backbone, we employ the Residual Swin Transformer (ResSwinT) to extract both local detail information using ResNet and global dependency information through the Swin Transformer. This approach allows us to capture multi-scale features and enhance feature expression capabilities.In the neck of the network, we introduce spatial and channel multi-head self-attention (SCSA), enabling the network to focus on advantageous features in different dimensions. Moving to the head, we employ multiple cascaded detectors and classifiers to further improve defect detection accuracy. We conducted extensive experiments on the PKU-Market-PCB and DeepPCB datasets. Comparing our proposed DDTR framework with existing common methods, we achieved the highest F1-score and produced the most informative visualization results. Lastly, ablation experiments were performed to demonstrate the feasibility of individual modules within the DDTR framework. These experiments confirmed the effectiveness and contributions of our approach.

Distributed tactile pressure recognition is an important task in intelligent industry. In this article, convolutional neural network (CNN) has attracted attention for their ability to automatically extract features and complete recognition. However, there are still the following weaknesses. The pressure information is low-resolution based on sensor density, resulting in limited configurable network depth. The current CNNs are deep network for high-resolution image, so they are not applicable for pressure task. What CNN has learned from the pressure is not clear. Therefore, a bilinear feature fusion CNN (BF-CNN) is proposed. The bilinear features are used to improve the feature extraction capability by depicting second-order characteristics, and fusion strategy is applied to promote the efficiency of feature utilization through the complementarity of hierarchical features. To understand BF-CNN intuitively, we develop the fused gradient class activation map (F-Grad-CAM) algorithm to visualize the regions of interest of the samples in detail, using multi-scale features to provide high-resolution heat maps. We also construct a pressure image dataset of 26 (A-Z) letter-shapes with complex contours collected by a 16 × 16 pressure array to validate the proposed models. The results show our work achieved highest accuracy of 98.23% and provided a more detailed location on activated areas.

The spherical structure of hollow carbon spheres (HCSs) makes their contact resistance and tunnel resistance extremely sensitive to the distance between them, which can be used as a conductive filler for high-sensitivity pressure sensors. Compared with one- and two-dimensional carbon-based materials, HCSs require a higher filling concentration for constructing an effective conductive network due to their average conductivity, which affects the mechanical properties of the sensor. In a single-electron system, electrons are transferred by hopping between the nitroxyl radical monomers and when the distance between the monomers is shortened, the electron transfer rate of nitroxyl radical compounds can be increased, thus further improving their conductivity. In this work, a composite of nitroxyl radical-modified hollow carbon spheres (HCS-g-NO˙) and polydimethylsiloxane (PDMS) polymer is introduced, and the resistivity of HCS-g-NO˙ is about one magnitude lower than that of HCSs at the same filling concentration. A flexible piezoresistive sensor with HCS-g-NO˙@PDMS as the sensitive layer coated on the PET electrode is presented, in which the spacing between HCS-g-NO˙ changes, causing changes in the contact and tunnel resistances in the sensitive layer when mechanical stresses are applied. The sensor achieved a piezoresistive response of −0.55 kPa⁻¹ and the tensile response of 211 , and a sensor array of nine pixels was successfully demonstrated; thus, it can be used as a high sensitivity pressure and strain sensor.