Explore the vast range of titles available.

With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have gradually become a hot topic in the industrial field. As a fundamental problem in the field of computer vision, how to achieve object detection in the industry while taking into account the accuracy and real-time detection is an important challenge in the development of intelligent detection systems. The detection of defects on steel surfaces is an important application of object detection in the industry. Correct and fast detection of surface defects can greatly improve productivity and product quality. To this end, this paper introduces the MSFT-YOLO model, which is improved based on the one-stage detector. The MSFT-YOLO model is proposed for the industrial scenario in which the image background interference is great, the defect category is easily confused, the defect scale changes a great deal, and the detection results of small defects are poor. By adding the TRANS module, which is designed based on Transformer, to the backbone and detection headers, the features can be combined with global information. The fusion of features at different scales by combining multi-scale feature fusion structures enhances the dynamic adjustment of the detector to objects at different scales. To further improve the performance of MSFT-YOLO, we also introduce plenty of effective strategies, such as data augmentation and multi-step training methods. The test results on the NEU-DET dataset show that MSPF-YOLO can achieve real-time detection, and the average detection accuracy of MSFT-YOLO is 75.2, improving about 7% compared to the baseline model (YOLOv5) and 18% compared to Faster R-CNN, which is advantageous and inspiring.

Tool wear is a key factor in the machining process, which affects the tool life and quality of the machined work piece. Therefore, it is crucial to monitor and diagnose the tool condition. An improved CaAt-ResNet-1d model for multi-sensor tool wear diagnosis was proposed. The ResNet18 structure based on a one-dimensional convolutional neural network is adopted to make the basic model architecture. The one-dimensional convolutional neural network is more suitable for feature extraction of time series data. Add the channel attention mechanism of CaAt1 to the residual network block and the channel attention mechanism of CaAt5 automatically learns the features of different channels. The proposed method is validated on the PHM2010 dataset. Validation results show that CaAt-ResNet-1d can reach 89.27% accuracy, improving by about 7% compared to Gated-Transformer and 3% compared to Resnet18. The experimental results demonstrate the capacity and effectiveness of the proposed method for tool wear monitor.

Feature selection and dimensionality reduction are important for the performance of wind turbine condition monitoring models using supervisory control and data acquisition (SCADA) data. In this paper, an improved random forest algorithm, namely Feature Simplification Random Forest (FS_RF), is proposed, which is capable of identifying features closely correlated with wind turbine working conditions. The Euclidian distances are employed to distinguish the weight of the same feature among different samples, and its importance is measured by means of the random forest algorithm. The selected features are finally verified by a two-layer gated recurrent unit (GRU) neural network facilitating condition monitoring. The experimental results demonstrate the capacity and effectiveness of the proposed method for wind turbine condition monitoring.

The static/dynamic stiffness of the ball screw feed system has an important influence on the machining accuracy and stability of the machine tool. To study the static/dynamic stiffness characteristics of the ball screw feed system under different support methods, a dynamic model of the ball screw feed system is established using the lumped parameter method. Then, the variation of the system’s static/dynamic stiffness is studied, and the influence of workpiece mass and placement position on the system’s static/dynamic stiffness is also concerned. The results show that as the stroke increases, the static/dynamic stiffness of the system with fixed supports at both ends first decreases and then increases, while that of the system with one end fixed and the other end floating always decreases. Comparing the two systems, the dynamic stiffness of the one with fixed supports at both ends is more sensitive to the workpiece’s mass and placement position. At the same time, as the workpiece mass increases, the natural frequency of the ball screw feed system decreases. The closer the workpiece is to the center of gravity of the worktable, the smaller its influence on the system’s natural frequency.

Microflow catalysis is a cutting-edge approach to advancing chemical synthesis and manufacturing, but the challenge lies in developing efficient and stable multiphase catalysts. Here we showcase incorporating amine-containing metal-organic cages into automated microfluidic reactors through covalent bonds, enabling highly continuous flow catalysis. Two Fe 4 L 4 tetrahedral cages bearing four uncoordinated amines were designed and synthesized. Post-synthetic modifications of the amine groups with 3-isocyanatopropyltriethoxysilane, introducing silane chains immobilized on the inner walls of the microfluidic reactor. The immobilized cages prove highly efficient for the reaction of anthranilamide with aldehydes, showing superior reactivity and recyclability relative to free cages. This superiority arises from the large cavity, facilitating substrate accommodation and conversion, a high mass transfer rate and stable covalent bonds between cage and microreactor. This study exemplifies the synergy of cages with microreactor technology, highlighting the benefits of heterogenous cages and the potential for future automated synthesis processes Microflow catalysis represents a cutting-edge method for advancing chemical synthesis and manufacturing, though developing efficient and stable multiphase catalysts remains challenging. Here the authors demonstrate the incorporation of amine-containing metal-organic cages into automated microfluidic reactors through covalent bonds, facilitating highly continuous flow catalysis.

The Micro-Opto-Electro-Mechanical Systems (MOEMS) accelerometer is a new type of accelerometer that combines the merits of optical measurement and Micro-Electro-Mechanical Systems (MEMS) to enable high precision, small volume, and anti-electromagnetism disturbance measurement of acceleration, which makes it a promising candidate for inertial navigation and seismic monitoring. This paper proposes a modified micro-grating-based accelerometer and introduces a new design method to characterize the grating interferometer. A MEMS sensor chip with high sensitivity was designed and fabricated, and the processing circuit was modified. The micro-grating interference measurement system was modeled, and the response sensitivity was analyzed. The accelerometer was then built and benchmarked with a commercial seismometer in detail. Compared to the previous prototype in the experiment, the results indicate that the noise floor has an ultra-low self-noise of 15 ng/Hz1/2.

The cavity optomechanical accelerometer based on photonic crystal microcavities combines mechanical resonators with high-quality factor photonic crystal cavities. The mechanical vibrator is sensitive to weak force/displacement in mechanical resonance modes, which can achieve extremely low noise levels and theoretically reach the standard qillatum noise limit. It is an important development direction for high-precision accelerometers. This article analyzes the principle and structural characteristics of a zipper type photonic crystal cavity optomechanical accelerometer, and designs a silicon-based zipper type photonic crystal cavity and mechanical vibrator structure applied to the accelerometer. The influence of the structural parameters of the zipper cavity on the optical Q factor was analyzed in detail. The resonant frequency of the optical cavity was controlled around 195 THz by adjusting the structural parameters, and the mechanical resonance characteristics of the mechanical vibrator and the optical cavity were analyzed. The effective mass of the optical cavity was 30 pg, and, with the addition of the mechanical vibrator, the effective mass was 3.1 ng. The optical mechanical coupling rate reached the GHz/nm level, providing guidance for the manufacturing and characterization of silicon-based zipper cavity accelerometers.

Photocatalytic hydrogen peroxide (H2O2) production through the oxygen reduction reaction (ORR) pathway has emerged as a promising sustainable alternative. However, a significant challenge in this field lies in the development of highly efficient photocatalysts capable of achieving high‐concentration H2O2 production. Here the rational design of two O2 reduction cores into one polymer framework is showcased for synergistically facilitating H2O2 production via the “self‐marketing & cooperation” strategy. Photoactive units of pyrrolo[3,2‐b] pyrrole and porphyrin are successfully settled in covalent organic polymers (COPs) through polycyclizations of the relevant aldehydes, anilines, and butane‐2,3‐dione. Two orderly separated active sites not only involve each of them in the oxygen reduction reaction but also mutually promote the production of H2O2, which is demonstrated by electron spin resonance experiments, in situ diffuse reflectance infrared Fourier transform spectroscopy, and a series of control experiments. Remarkably, PP‐COP‐4 delivers an outstanding H2O2 concentration of 16.2 mM in a continuous‐flow system, demonstrating its strong potential for scalable, solar‐driven production of commercial‐grade H2O2. Here the rational design of two O2 reduction cores into one polymer framework is showcased for synergistically facilitating H2O2 production via the “selfmarketing & cooperation” strategy. Photoactive units of pyrrolo[3,2‐b]pyrrole and porphyrin are successfully settled in covalent organic polymers (COPs) through polycyclizations of the relevant aldehydes, anilines, and butane‐2,3‐dione. PP‐COP‐4 delivers an outstanding H2O2 concentration of 16.2 mM in a continuous‐flow system, demonstrating its strong potential for scalable, solar‐driven production of commercial‐grade H2O2.

In order to clarify the distribution characteristics and potentially environmental effect of phosphorus (P) chemical speciation in river sediments from a typical geological P-rich (GPR) watershed, South China. Forty-eight sediment samples collected from the Huangbai River watershed, Yichang city, Hubei province. The levels of TP in Huangbai River wathershed were remarkably higher than those in most Chinese lakes, reservoirs, and river. The Ca-P and Res-P were the two dominant species that accounted for 78.7% and 13.3% of TP, respectively. Based on the sediment quality guideline (SQGs) and background values of Chinese soil and sediment, the majority of the mean TP concentrations in surface sediments were higher than their background values. The unique distribution pattern of P species in the Huangbai River watershed depends on local environment conditions and P sources. These findings improve our understanding of the eutrophication and P cycle in the GPR watershed.

This article develops a rapid performance evaluation approach for lower mobility hybrid robot, which provides guidance for manipulator evaluation, design, and optimization. First, a general position vector model of gravity center for the lower mobility hybrid robot in the whole workspace is constructed based on a general inverse kinematic model. A performance evaluation index based on gravity-center position is then proposed, where the coordinates pointing to the supporting direction are selected as the evaluation index of the robot performance. Furthermore, the credibility of the evaluation approach is verified from a 5-DOF hybrid robot (TriMule) by comparing with the condition number and the first natural frequency. Analysis results demonstrate that the evaluation index can not only reflect the performance spatial distribution in the whole workspace but also is sensitive to the performance difference caused by mass distribution. The proposed performance evaluation approach provides a new index for the rapid design and optimization of the cantilever robot.