Search

Aiming at the problems of low accuracy, low efficiency and weak versatility in artillery barrel attitude measurement, a specialized marker and a new measurement algorithm based on this marker were designed within a monocular vision measurement system. In this method, we find an auxiliary line that can present azimuthal angle information in real time, and propose a pitch angle calculation formula through the mapping relationship. In addition, We fuse the required information into the marker, and capture the marker image by the camera, so that the attitude angle of the artillery barrel can be calculated by a single image (No need for reference images). The experimental results show that within a wide range of artillery barrel attitude angles, spanning azimuth angles of ±40° and pitch angles of 0-35°, the azimuth angle error is less than 0.1°, and the pitch angle error is less than 0.24°,and the measurement accuracy of the method can meet the needs of engineering practice.

Nonwoven fabric defect detection is an essential part of the production process, and it is important to realize fast and accurate nonwoven fabric defect detection to improve production efficiency. Aiming at the problems of nonwoven fabric defect detection in which most defect targets are small and traditional industrial cameras are unable to recognize foreign impurities of the same color, a nonwoven fabric defect detection method based on hyperspectral imaging and improved YOLOv5 is proposed. Specifically, hyperspectral imaging technology is used to replace traditional vision and solve the problem of homochromatic foreign matter impurities from the dimension of spectrum. In addition, the LSK attention module is introduced into the YOLOv5 backbone network, which enables the network to learn the key feature information and enhance the detection of small targets. Finally, an improved light repetitive group frequency permutation network (Light-RepGFPN) is proposed in the neck structure, by which the feature fusion capability of the model is enhanced, so that the high-level semantic information and the low-level spatial information are fully fused to improve the detection accuracy. Combined with the LSK and Light-RepGFPN modules, we propose an improved YOLOv5 (LL-YOLOv5) defect detection network. It is experimentally proved that LL-YOLOv5 can achieve an average accuracy mean 90.3% in the nonwoven fabric hyperspectral image defects dataset, which is 2.2% higher than that of the original model, respectively.

Automatic traffic sign detection has great potential for intelligent vehicles. In recent years, traffic sign detection has made significant progress with the rise of deep learning. Detecting small traffic signs in real-world scenarios is still a challenging problem due to the complex and variable traffic environment. In this paper, a model with a small number of parameters is proposed to improve the accuracy of small traffic sign detection. Firstly, the cross-stage attention network module is proposed to enhance the feature extraction capability of the network. Secondly, a dense neck structure is proposed to make the detail information and semantic information fully fused. Finally, for the model’s loss function, SIOU with direction information is introduced to optimize the model’s training process. Tests on the challenging public datasets TT100K, CCTSDB2021, and VOC show that our approach achieves significant performance improvement with the minimum number of parameters compared to existing algorithms.

Augmented reality museums allow visitors to jointly view and interact with exhibits. However, real-time exhibit browsing does not accommodate latecomers to museums and offers limited support to temporally separated visitors. To stimulate asynchronous exhibit browsing, we developed a distance-driven user interface that divided the augmented reality exhibit-egocentric space into four distance ranges, each having a set of social networking features and different privileges for exhibit viewing and interaction. The user interface enables asynchronous exhibit browsing for visitors participating at different times. We conducted empirical studies to evaluate how the user interface affected visitors’ collaborative exhibit browsing in terms of perceived usability and learning gains. The results show that the perceived usability of the user interface is consistently high across all distance ranges. The user interface stimulates collaborative exhibit browsing with significant improvements in learning efficiency and learning attention durations, although learning satisfaction showed no difference across the participants. Implications for how the distance-driven user interface can be generalized for other interactive applications are discussed.

This paper studies multiple inverse kinematics solutions for a 7-DOF human redundant manipulator with a special joint configuration. A method is proposed for determining the continuous joint angle vector by selecting the inverse solution from discrete multiple solutions to the continuous end path of the mechanical arm. The elbow angle constraint is introduced, and the mapping relationship from the elbow angle to the joint angle is established. Subspaces are found in the multiple solution spaces to avoid joints exceeding the limit to obtain elbow angle interval, and then combined with the collision detection technique, subspaces are sought in multiple solution spaces to avoid collisions between robotic arms and obstacles. Two subspaces are then obtained, and with use of their intersection, all feasible manipulator inverse kinematic solutions that avoid the joint limit and the obstacles at a given pose are obtained. The above method explicitly determines the complete feasible kinematic inverse solution of redundant manipulators. Finally, the validity of the methods is verified via kinematic simulations.

To improve the accuracy of surface electromyography (sEMG)-based gesture recognition, we present a novel hybrid approach that combines real sEMG signals with corresponding virtual hand poses. The virtual hand poses are generated by means of a proposed cross-modal association model constructed based on the adversarial learning to capture the intrinsic relationship between the sEMG signals and the hand poses. We report comprehensive evaluations of the proposed approach for both frame- and window-based sEMG gesture recognitions on seven-sparse-multichannel and four-high-density-benchmark databases. The experimental results show that the proposed approach achieves significant improvements in sEMG-based gesture recognition compared to existing works. For frame-based sEMG gesture recognition, the recognition accuracy of the proposed framework is increased by an average of +5.2% on the sparse multichannel sEMG databases and by an average of +6.7% on the high-density sEMG databases compared to the existing methods. For window-based sEMG gesture recognition, the state-of-the-art recognition accuracies on three of the high-density sEMG databases are already higher than 99%, i.e., almost saturated; nevertheless, we achieve a +0.2% improvement. For the remaining eight sEMG databases, the average improvement with the proposed framework for the window-based approach is +2.5%.

The accurate and rapid identification of safflower filaments is a prerequisite for automating harvesting. This paper proposes a lightweight, high-precision detection model for safflower filaments based on YOLOv5s, named YOLOv5s-MCD, to address the issues of large existing network model sizes and low detection accuracy in complex natural environments. The Backbone of the YOLOv5s-MCD model was optimized into a lightweight improved network MobileNetv2 with DSC and CA modules, and the neck part incorporated the CA attention mechanism. The loss function is improved from DIoU’s non-maximum suppression method to CIoU to reduce the model size and improve the detection accuracy and speed. The experimental results show that the size of the YOLOv5s-MCD model is its size by 7.69 MB compared to the original YOLOv5s model, with a mean Average Precision (mAP) of 95.6% and an average detection time of only 3.2ms per image. When tested under unobstructed, obstructed, backlighting, shaking, and wide-angle natural environments, the improved YOLOv5s-MCD model increased the mAP value by 4.4, 0.7, 3.3, 3.4, and 1.0 percentage, respectively, compared with the YOLOv5s model, with improved F1 scores and confidence levels. This indicates that the improved lightweight model can achieve fast, real-time, and accurate detection of the safflower filaments in complex environments. The research results can provide a technical reference for the development of field safflower filament-harvesting robots.

A decomposition-coordination optimization method termed as analytical target cascading-based exterior penalty function (ATC-EPF) is proposed to investigate the reliability allocation aiming at the low computational efficiency for large complex systems. Firstly, the optimization model is established via ATC-EPF, which is decomposed into the models of subsystems. Then the subsystems are calculated in parallel, which reduces the computational cost greatly in the condition of keeping the computational accuracy. The results are fine which are verified by two study cases including one numerical case and one engineering case. This research is of great significance to large-scale system planning and design.

A method to reduce waveform distortion is proposed and experimentally verified for vibrators driven by voice coil motors. In this method, a current including high-order harmonics is synthesized to drive the vibrator. The amplitudes and phases of the high-order harmonics are calculated based on the measured parameters which are correlated with the distortion. These parameters include the displacement dependence of the vibrator stiffness and that of the magnetic force per unit current. The calculation model is built on the nonlinear vibrator dynamic equation. By minimizing the lower order harmonics of the output acceleration, a series solution is obtained to synthesize the driving current. The feasibility has been demonstrated by Simulink simulation. Applying this strategy to a home-made vibrator, the waveform distortion of vibration acceleration has been reduced from 9.60% to 1.22%. The proposed method provides an alternative technology to reduce the distortion. This technology is especially useful in case that it is difficult to reduce the nonlinearity of the vibrator.

The modular arc-linear flux switching permanent-magnet motor (MAL-FSPM) used for scanning system is researched in this paper by the finite element method (FEM). The MAL-FSPM combines characteristics of the flux switching permanent-magnet motor and linear motor and can realize the direct driving and limited angular movement. Due to the double salient effect, the cogging torque including slot torque and end torque is very high. In order to reduce the cogging torque, a method of magnetizing the permanent magnet in reverse direction combined with rotor segmentation is proposed. By means of the proposed method, peak-peak cogging torque and load torque ripple are reduced effectively. Besides, the smooth operation range and an average load torque of the motor are also optimized. The effectiveness of the method is verified by both 2D and 3D FE models.

This paper deals with the effects of permanent magnets (PMs) shapes and segmentation types on the trapezoidal degrees of the back electromagnetic force (EMF) and torque characteristics and rotor losses. The back-EMF waveforms with different PMs shapes and segmentation types are calculated through transient finite element method (FEM). It is found that the effects of PMs inward eccentricity and curvature have no influence on the shape of the back-EMF waveforms. The PMs asymmetrical segmentation with the middle sub-PMs applied with low magnetic energy product sintered ferrite magnet can obtain better trapezoidal back-EMF waveforms. Then, the torque characteristics and rotor losses of PMs' symmetrical and asymmetrical segmentations are investigated and evaluated. The results show that the PMs segmentation and applying low magnet energy product PMs of the middle sub-PMs can further improve the torque characteristics. Moreover, the outer PMs eddy current loss and rotor iron loss exhibit a great extent of decrement. Finally, a stator-ironless PM BLDC motor without the outer rotor PMs segmentation is manufactured and tested. The experimental results show good agreement with the FEM ones.

Three different radial flux ironless brushless dc (BLdc) motor types (motors without inner back-iron of the rotor, with inner back-iron of the rotor, and with dual-rotor) are investigated and compared in this paper. The magnetic field distribution, back electromagnetic force (EMF), axial end effect, and torque characteristics are investigated. First, the relationship between the magnetic field distribution and the motor size and pole pairs is investigated. It shows that the two parameters are not independent of each other and the magnetic field distribution is mainly related with the arc length of the permanent magnets. Second, the radial magnetic flux density in the coil regions of the three ironless BLdc motors is calculated and an evaluation factor is proposed to show the quality of the magnetic field distribution. Third, the influence of the winding configuration and the combination of slot and pole number on EMF is analyzed, and the corresponding evaluation factors are calculated and tabulated. Then, the axial end effect of the three ironless BLdc motors considering the fringe effect is investigated and compared. Next, the torque characteristics at full load and rated speed are studied for the three types of motors. Finally, the ironless BLdc motor without back-iron of the rotor is manufactured and tested. The experimental results are in good agreement with the finite-element method.

Controlling a grain dryer plant is a challenging task because of its complex drying mechanism. The aim of this paper is to investigate effective control strategies for a newly designed grain dryer plant, and to optimize the control performance, such as the overshoot, accuracy, and anti-disturbance abilities. In this paper, a genetically optimized fuzzy immune proportional integral derivative controller (GOFIP) is designed, which is a combination of intelligent fuzzy immune feedback control and traditional control. Fuzzy rules are used to imitate the biological immune feedback mechanism to automatically tune the proportional integral derivative (PID) parameters, and a genetic algorithm is used to optimize the controller's initial parameters, which can overcome the inadequacy of the general fuzzy immune PID controller. In addition, the dryer plant is introduced in this paper, and the classic drying model to verify the effectiveness of the proposed controller is fitted based on data from the practical drying experiments. Finally, simulation comparisons of control performances with three other controllers (the general PID controller, the fuzzy PID controller, and the fuzzy immune PID controller) are made, and anti-disturbance performance is tested based on the reformulated drying model in MATLAB. By simulating the step response of the outlet grain moisture content (MC), it is shown that the GOFIP controller has the best control performances to bring the outlet grain MC to the target value rapidly, enabling the drying control system to have no overshoot, better accuracy, and stronger anti-disturbance performance compared with the other three simulated controllers. The proposed controller has overcome the parameter adjustment difficulty of the traditional PID controller and can obtain the optimized control of grain drying by using the genetic optimization algorithm. The GOFIP controller is a reliable and precise control method incorporating uncertainty factors and may also provide an effective reference for controlling complex systems, such as those used in grain drying.