This paper proposes a novel motion planning algorithm based on model predictive control (MPC) and fuzzy logic to address the coordinated motion planning problem in terms of optimal energy consumption while maintaining specific driving style. The MPC controller based on the linear time-varying (LTV) vehicle dynamics model is constructed to deal with the calculation of trajectory tracking accuracy, while the optimal energy consumption term is also integrated into the evaluation function. To transform the non-convex optimization problem into quadratic programming (QP), the tracking error is further linearized. Noting that differentiated control objectives lead to potential abnormal acceleration fluctuations, the weight adjustment mechanism is adopted to handle the adjustment of vehicle’s dynamic behavior. In the process of adaptive weight configuration, the fuzzy logic controller based on driving intention and deviation level is designed to achieve the goal of maintaining the preset driving style. Therefore, by leveraging the correlation between driving style definition and acceleration/deceleration decisions, the trade-off problem in motion planning and the riding comfort issue can be addressed simultaneously. Moreover, the improved algorithm under three different driving styles and the original MPC planner are tested and compared in the typical cornering scenario. By introducing the optimal energy consumption term at the cost of a 4.08% extension in scenario passage time, the proposed algorithm achieves up to a 29.76% reduction in trajectory deviation and a 38.89% decrease in approximate driving energy consumption. Visual analysis of driving objectives’ trade-off further indicates that different driving style presets lead to distinct optimization potentials, while trajectory tracking still plays a dominant role in the overall control objectives.

A four-steering-wheel heavy-duty Automated Guided Vehicle (AGV) is prone to lateral instability and wheel slippage during acceleration, climbing, and small-radius turns. To address this issue, a trajectory tracking strategy considering lateral stability and an optimal driving torque distribution strategy considering load transfer and tire adhesion coefficient are proposed. Firstly, a three-degree-of-freedom AGV trajectory tracking model is established, tracking error and sideslip angle are incorporated into the cost function, and an improved model predictive trajectory tracking controller is proposed. Secondly, the longitudinal and yaw dynamic model of AGV is established, and vertical load transfer is analyzed. With the goal of minimizing tire adhesion utilization rate, quadratic programming is used for the optimal distribution of driving torque. Finally, through co-simulation using ADAMS and MATLAB on a narrow “climbing straight+ S-curve” road, the maximum tracking error is 0.0443 m. Compared to the unimproved model predictive control and average driving torque distribution strategy, the sideslip angle is reduced by 58.18%, the maximum tire adhesion utilization rate is reduced by 6.62%, and climbing gradeability on wet roads is enhanced.

During the operation of outdoor heavy-duty Automated Guided Vehicle (AGV), the stability and safety of AGV are easily reduced due to load transfer. In order to solve this problem, a trajectory tracking control strategy considering load transfer is proposed to realize the trajectory tracking of AGV and the adaptive distribution of driving torque. The three-degree-of-freedom (3-DOF) kinematics model and pose error model of heavy-duty AGV vehicles are established. The lateral load transfer and longitudinal load transfer rules are analyzed. The vehicle trajectory tracking control strategy is composed of an improved model predictive controller (IMPC) and drive motor torque adaptive distribution controller considering load transfer. By optimizing the lateral acceleration of the vehicle body, the IMPC controller improves the problem of large driving force difference between the left and right sides of the wheel caused by the lateral transfer of the load and the problem of large wheel adhesion rate caused by the longitudinal transfer of the load is improved by the speed controller and the torque proportional distribution controller. The joint simulation platform of MATLAB/Simulink and CarSim is built to simulate and analyze the trajectory tracking of heavy-duty AGV under different pavement adhesion coefficients. The simulation results have shown that compared with the control strategy without considering load transfer, on the two types of pavements with different adhesion coefficients, the maximum lateral acceleration is reduced by 19.7%, and the maximum tire adhesion rate is reduced by 11.5%.

Small target detection has important application value in military, cigarette defect detection, monitoring and remote sensing fields. However, due to the complex background interference of infrared images, the background and target features are confused with each other, which makes it difficult for existing detection methods to effectively distinguish the features of the background and the target, resulting in poor detection effect. Therefore, to solve this problem, this paper proposes a small target detection method based on confusion feature decoupling and decorrelation, aiming to achieve accurate detection of small targets in complex environments by extracting robust small target features. Specifically, in confusion feature decoupling and decorrelation, we propose a confusion feature decoupling and decorrelation module. By introducing a feature decoupling mechanism, the features of the input image are decomposed into independent background features and target features, and feature decorrelation is used to achieve independence between the target and the background. The target features after decoupling and decorrelation are purer, which helps to reduce background interference and thus improve detection performance. Systematic experimental results show that the detection performance of the proposed method on public small target detection datasets is much better than that of existing advanced detection methods.

The detection of appearance defects in cigarettes is crucial in the field of industrial defect detection. Most existing detection methods achieve defect detection by utilizing deep learning to learn feature representations of various types of defects. However, due to the complexity and randomness of the production and processing process, the differences between defects in different cigarettes are not significant, which greatly affects the detection performance. Therefore, to address this issue, this article proposes a cigarette defect detection method based on independent feature extraction constraints, called IFEC. The core idea of this method is to extract independent features of different defect categories to increase the differences between features of different categories, enhance the distinguishability of features, and achieve accurate cigarette defect detection. In IFEC, an independence feature extraction constraint module is proposed that constrains the network to extract highly independent defect features of different categories through feature decoupling and feature decorrelation. The sufficient experimental results indicate that the proposed IFEC has superior detection performance compared to existing detection methods.

AbstractCigarette defect detection is important in industrial production. Existing methods extract features for defect detection manually or using deep learning. However, due to the small size of cigarette defects, these methods are unable to effectively extract discriminative features, limiting detection performance. Hence, a deep learning‐based method called significant feature‐guided cigarette defect detection (SFGCD) is proposed, which combines saliency feature extraction methods with deep learning to enhance feature representation and improve detection. First, edge saliency features are extracted using the proposed target gradient saliency feature extraction (GSFE) strategy. Then, a dense multi‐level feature fusion network is designed to combine the original features with the saliency features obtained from the target gradient saliency feature extraction strategy. This network enriches feature representation and improves detection by fusing original and saliency features at different levels and scales. Experimental results demonstrate that the proposed method achieves a higher accuracy of 0.02 mean average precision (MAP) value and a detection speed of 5 frames per second (FPS) on the authors' own labeled cigarette defect dataset compared to existing state‐of‐the‐art methods.

To address the issues of poor detection accuracy and the large number of target detection model parameters in existing AGV monocular vision location detection algorithms, this paper presents an AGV vision location method based on Gaussian saliency heuristic. The proposed method introduces a fast and accurate AGV visual detection network called GAGV-net. In the GAGV-net network, a Gaussian saliency feature extraction module is designed to enhance the network’s feature extraction capability, thereby reducing the required output for model fitting. To improve the accuracy of target detection, a joint multi-scale classification and detection task header are designed at the stage of target frame regression to classification. This header utilizes target features of different scales, thereby enhancing the accuracy of target detection. Experimental results demonstrate a 12% improvement in detection accuracy and a 27.38 FPS increase in detection speed compared to existing detection methods. Moreover, the proposed detection network significantly reduces the model’s size, enhances the network model’s deployability on AGVs, and greatly improves detection accuracy.

Aiming at the shortcomings of RRT (Rapidly-exploring Research Tree) algorithm such as long time cost and low utilization of sampling points, an improved RRT algorithm is proposed. By adopting the sampling strategy based on dynamic probability, the robot is prevented from falling into a local minimum during the sampling process. At the same time, the adopt of variable step strategy as the random tree expands reduces the number of sampling points. Finally, the initial path is optimized to make it more suitable for the robot to walk. The improved RRT algorithm is compared with the RRT algorithm and the Goal-bias RRT algorithm in both simulations on MATLB and experiments on robot based on ROS (Robot Operating System). And the results show that improved RRT algorithm increases the speed of path planning, reduces the length of path, and the planned path is smoother and more suitable for the real robot to move.

To solve the problems of slow detection speed and poor robustness of existing infrared (IR) small target detection methods in complex environments, a lightweight detection model MiniIR-net is proposed in this letter. In the MiniIR-net model, to reduce the number of parameters required for model fitting, a multiscale target context feature extraction (TCVE) module is proposed to enrich the feature expression of the target. In addition, to improve the feature mapping capability of MiniIR-net, a feature mapping upsampling network by fusing the deep and shallow features is designed. In the process of feature mapping upsampling, the network uses target features with different depths to make up for the loss of target features caused by pooling. It is proven by the experiment that the proposed MiniIR-net network is superior to the existing detection methods in detection speed, accuracy and robustness in a complex environment. The model size of MiniIR-net is at least 1/260 of the current detection model, and the detection accuracy is improved by at least 5%. The source code of this article can be obtained at https://github.com/yangzhen1252/MiniIR-net .

In order to solve the demand for low-power microcomputers and micro-electro-mechanical system components for continuous energy supply, a magnetic coupling piezoelectric–electromagnetic composite galloping energy harvester (MPEGEH) is proposed. It is composed of a piezoelectric energy harvester (PEH) and an electromagnetic energy harvester (EEH) coupled by magnetic force. The bistable nonlinear magnetic coupling structure improves the output power of the MPEGEH. The advantages and output performance of the MPEGEH are analyzed. The prototype of the energy harvester is made, and the nonlinear output characteristics under different load resistances are analyzed. Through the experiment on the key parameters of the composite energy harvester, it is found that the higher the coupling degree of the two parts of the MPEGEH, the stronger the nonlinear characteristics and the better the output characteristics. The results show that the onset wind velocity and output power of the MPEGEH are better than the classic galloping piezoelectric energy harvester (CGPEH). At the same wind speed, with the increase in the distance d0 between magnets A and B, the output power of both the PEH and the EEH decreases. When d0 is 37 mm, the output power of the EEH is the largest. The distance s0 between magnets B and C has little influence on the output power of the PEH but has a great influence on the EEH. When s0 is 23 mm, the EEH has the best output characteristics. Compared with the CGPEH, the onset wind velocity is reduced by 28%, and the output power is increased by 136% when the wind speed is 11 m/s.

The machine vision-based defect detection for cylinder liner is a challenging task due to irregular shape, various and small defects on the cylinder liner surface. To improve the accuracy of defect detection by machine vision a deep learning-based defect detection method for cylinder liner was explored in this paper. First, a machine vision system was designed based on the analysis of the causes and types of defects to obtain the field images for establishing an original dataset. Then the dataset was augmented by a modified augmentation method which combines the region of interest automatic extraction method with the traditional augmentation methods. Except for introduction of the anchor configuration optimization method, an XML file-based method of highlighting defect area was proposed to address the problem of tiny defect detection. The optimal model was experimentally determined by considering the network model, the training strategy and the sample size. Finally, the detection system was developed and the network model was deployed. Experiments are carried out and the results of the proposed method compared with those of the traditional methods. The results show that the detection accuracies of sand, scratch and wear defects are 77.5%, 70% and 66.3% which are improved by at least 26.3% compared with the traditional methods. The proposal can be used for field defect detection of cylinder liner.

To widen the operation wind speed bandwidth of a classic vortex shedding induced vibration piezoelectric energy harvester, a piezoelectric-electromagnetic hybrid energy harvester based on vortex shedding induced vibration is designed. The hybrid vortex shedding induced vibration energy harvester (HVSIVEH) includes a vortex shedding induced vibration piezoelectric energy harvester (VSIVPEH) and an electromagnetic vibration energy harvester (EVEH). The electromechanical coupled vibration model of the hybrid structure was established. By comparing the variations of the output power as a function of the wind speed of the HVSIVEH and the classic VSIVPEH, it is found that the power response curve of the HVSIVEH has two peaks. The hybrid structure can broaden the working wind speed range. The lower the requirement on the output power level, the more obvious the effect of widening the wind speed range. By the solution and analysis of the electromechanical coupled model, better values of related parameters of the HVSIVEH are obtained. The first and second peaks of the output power of the HVSIVEH show better values of 1.9 and 2.2 mW, respectively, under these parameters.

In order to study the influence of vehicle body vibration caused by road excitation on the output performance of a vehicle piezoelectric electromagnetic hybrid energy harvester, the theoretical analysis of the energy harvester is carried out, and a corresponding electromechanical coupling model is established. The hybrid energy harvester includes a flutter piezoelectric energy harvester (FPEH) and an electromagnetic vibration energy harvester (EVEH). Sweep frequency experiments and wind tunnel experiments were carried out to verify the correctness of the coupling model. By establishing the road-vehicle coupling differential equations solving module, the vehicle body vibration under different road surfaces was simulated, and the influence of different roads on output performance is analyzed. The results show that when vehicle body vibration is not considered, the cut-in speed of the harvester is 32 km h −1 . When the vehicle speed is higher than 32 km h −1 , vehicle body vibration caused by road roughness will suppress the overall output performance. When the vehicle speed is less than 32 km h −1 , the vibration of the vehicle body will cause the energy harvester to have no obvious cut-in wind speed. And the higher the road level, the stronger the body vibration, and the better the output performance when the vehicle speed is less than 32 km h −1 . Under E-class road with vehicle body vibration considered, it has already power output at a vehicle speed of 20 km h −1 . When the vehicle speed reaches 57 km h −1 , the output power of hybrid FPEH and EVEH reach 1.74 and 2.51 mW under E-class road (2.88 and 3.25 mW under A-class road), respectively.

To meet the needs of low-power microelectronic devices for on-site self-supply energy, a galloping piezoelectric–electromagnetic energy harvester (GPEEH) is proposed. It consists of a galloping piezoelectric energy harvester (GPEH) and an electromagnetic energy harvester (EEH), which is installed inside the bluff body of the GPEH. The vibration at the end of the GPEH cantilever drives the magnet to vibrate, so that electromagnetic energy can be captured by cutting off the induced magnetic field lines. The coupling structure is a two-degree-of-freedom motion, which improves the output power of the energy harvester. Based on Hamilton’s variational principle and quasi-static hypothesis, the piezoelectric–electromagnetic vibrated coupling equation is established, and the output characteristics of GPEEH are obtained by the method of numerical simulation. Using the method of numerical simulation, studies a series of parameters on the output performance. when the wind speed is 9 m/s, the effective output power of the GPEEH is compared with the classical galloping piezoelectric energy harvester (CGPEH) who is no magnet. It is found that the output power of GPEEH 121% higher than the output power of CGPEH. Finally, set up an experimental platform, and test and verify. The experimental analysis results show that the simulated output parameter curves are basically consistent with the experimental drawing curves. In addition, when the wind speed is 9 m/s, under the same parameters, the effective output power of the GPEEH is 112.5% higher than that of the CGPEH. The correctness of the model is verified.

为解决大粗糙度的气缸套实现内孔直径自动化测量这一问题,基于电涡流传感器进行了测量方案的设计,并针对机械结构建立了测量过程的数学模型,得到了由机械结构引起的理论误差公式;通过MATLAB绘制出机械误差的三维曲面图,并得到了机械误差小于0.01 mm时各相关变量的取值范围;通过试验验证了自动测量机与内径百分表之间的测量误差,最小值和最大值误差均处于±0.015 mm内,平均值误差处于±0.01 mm内.该气缸套的内孔直径公差为±0.075 mm,结果表明,自动测量机满足现场使用要求.

This paper focuses on the analysis of the stability of the GW17 high-voltage disconnecting switch drive system. Firstly, the optimization model of the disconnector is established, and the simulation analysis is carried out by ADAMS (Automatic Dynamic Analysis of Mechanical Systems) and the simulation results are verified by experiments. Afterwards, ADAMS optimization design and particle swarm optimization algorithm (PSO) are used to optimize the drive system of the disconnector, and the results are verified on the experimental platform. After optimization, the space rod is reduced by 15 mm, the minimum corner angle of the lower conductive rod is reduced by 71.0%, the minimum folding arm angle is reduced by 88.7% and the maximum force of the ball pair is reduced by 35.7%, which realizes the lightweight of the rod, reduces the wear of the ball pair, and improves the stability of the equipment operation.

800 kV交流隔离开关是超高压变电站关键装备之一,其平衡弹簧是减轻所需外载荷、提高装备可靠性的重要组件.围绕800 kV高压隔离开关展开研究,首先基于运动简图进行主闸刀的机构运动分析,获得隔离开关结构势能的理论方程.然后通过虚拟样机技术,利用Adams平台建立隔离开关的动力学仿真模型,得到开、合闸动作时初始设计条件下平衡弹簧的弹性势能与运动机构重力势能差值的仿真结果.为进一步缩小弹簧势能和机构势能的差值,对平衡弹簧进行优化设计,仿真分析结果表明,优化后的平衡弹簧势能与机构势能差值的最大变化量比初始方案减少了约28％,即隔离开关工作时所需外载荷大大减小.

To realize the self-power of the vehicle micro-sensors, a piezo-electromagnetic hybrid vehicle-mounted energy harvester is proposed to recover the wind and vibration energy generated during driving. This energy harvester includes a flutter piezoelectric energy harvesting structure (FPEH) and an electromagnetic vibration energy harvester structure (EVEH). The combination of the two structures can improve the energy harvesting effect and reduce the cut-in wind speed. The coupled vibration mathematical model is established to predict the output performance of the wind energy harvesting effect. The effects of the different distances between magnets on the output are discussed. And the vibration characteristics of piezoelectric and electromagnetic vibrators are analyzed. Results show that the energy-harvesting effect is the best when the distance between magnets is 30mm. At the same time, the numerical simulation proves that the wind energy harvesting effect of the hybrid structure is better than the classic flutter structure. The experimental verification is carried out, and the experimental results are consistent with the theoretical prediction results, which verified the correctness of the theory. The optimal load of FPEH is 70kΩ , and the optimal load of EVEH is 60Ω. Under these conditions, when the wind speed is 18m/s, the peak output power of FPEH is 14.5mW, and that of EVEH is 31.8mW.

在实际工程领域中,零件的疲劳破坏给工程界带来了难以计量的损失.所谓疲劳,是指零件在承受远低于其屈服极限的循环载荷时突然失效的情况.疲劳问题一直受到广泛关注,关键距离法(TCD算法)最初由Taylor等人提出,该理论将试件缺口附近区域某点,线上的应力特征值作为疲劳失效判断准则.拟选用疲劳试验机对45#钢缺口试样在四种应力级下进行疲劳试验,对45#钢缺口试样的疲劳性能进行了试验研究.同时运用了传统TCD算法以及改进TCD算法对45#钢缺口试样的疲劳寿命进行了预测,与实验结果进行比较,改进的TCD算法相对于传统TCD算法获得的预测结果更令人满意.从而为工程上缺口构件的疲劳寿命预测提供了理论计算方法.

高压隔离开关是电网中广泛使用的开关设备,其性能的好坏直接决定了用电安全.为评价GW46-126型高压隔离开关在不同环境温度下的使用性能,在气候试验室±60℃温度环境范围内,对隔离开关的触头接触压力、动静触头相对位置、机构操作扭矩、机构输出角等机械参数和电学参数回路电阻随温度变化的规律进行试验研究.通过试验数据采集和分析,确定环境温度变化对隔离开关机械特性和电学特性的影响,为进一步优化GW46-126型高压隔离开关性能和提高环境温度适用性提供了重要的理论支持.