Search

Abstract In this study, to address the issues of sluggish convergence and poor learning efficiency at the initial stages of training, the authors improve and optimise the Deep Deterministic Policy Gradient (DDPG) algorithm. First, inspired by the Artificial Potential Field method, the selection strategy of DDPG has been improved to accelerate the convergence speed during the early stages of training and reduce the time it takes for the mobile robot to reach the target point. Then, optimising the neural network structure of the DDPG algorithm based on the Long Short‐Term Memory accelerates the algorithm's convergence speed in complex dynamic scenes. Static and dynamic scene simulation experiments of mobile robots are carried out in ROS. Test findings demonstrate that the Artificial Potential Field method‐Long Short Term Memory Deep Deterministic Policy Gradient (APF‐LSTM DDPG) algorithm converges significantly faster in complex dynamic scenes. The success rate is improved by 7.3% and 3.6% in contrast to the DDPG and LSTM‐DDPG algorithms. Finally, the usefulness of the method provided in this study is similarly demonstrated in real situations using real mobile robot platforms, laying the foundation for the path planning of mobile robots in complex changing conditions.

Flexible manipulators have been widely used in industrial production. However, due to the poor rigidity of the flexible manipulator, it is easy to generate vibration. This will reduce the working accuracy and service life of the flexible manipulator. It is necessary to suppress vibration during the operation of the flexible manipulator. Based on the energy method and the Hamilton principle, the partial differential equations of the manipulator were established. Secondly, an improved radial basis function (RBF) neural network was combined with the fuzzy backstepping method to identify and suppress random vibration during the operation of the flexible manipulator, and the Lyapunov function and control law were designed. Finally, Simulink was used to build a simulation platform, three different external disturbances were set up, and the effect of vibration suppression was observed through the change curves of the final velocity error and displacement error. Compared with the RBF neural network boundary control method and the RBF neural network inversion method, the simulation results show that the effect of the RBF neural network fuzzy inversion method is better than the previous two control methods, the system convergence is faster, and the equilibrium position error is smaller.

Aiming at the problems of traditional grasping methods for mobile manipulators, such as single application scenarios, low accuracy, and complex grasping tasks, this paper proposes an object recognition grasping approach using Proximal Policy Optimization (PPO) with You Only Look Once v5 (YOLOv5), which combines a vision recognition algorithm with a deep reinforcement learning algorithm to achieve object recognition grasping. First, YOLOv5 is adopted to identify the object and obtain the location information. Second, the PPO algorithm is used for object grasping to obtain the grasping strategy. Third, the PPO algorithm is compared with the Soft Actor-Critic (SAC) and Trust Region Policy Optimization (TRPO) algorithms in batches 16 and 128, respectively. The average reward training results of the PPO, SAC, and TRPO algorithms are obtained in our work. Experimental results show that the proposed method, in terms of object recognition speed, outperforms the original YOLOv4 model. The YOLOv5 model achieves 96% precision on our own built recognition dataset, which has higher detection precision and lower hardware requirements than the YOLOv4 model. Our proposed method outperforms SAC and TRPO algorithms in object grasping, and the average reward of the PPO algorithm is improved by 93.3% and 41% compared to SAC and TRPO algorithms, respectively. Finally, through the comparison of ablation experiments, our method has the highest accuracy and mean average precision (mAP)@0.5 value of 92.3%. We demonstrate in actual physical experiments that the grasping success rate under our proposed approach reaches 100%, providing a new research strategy for object grasping by the robot manipulator.

Abstract Multi‐view image fusion can be used to extract features from redundant and complementary multisource images. And the technique of obtaining high quality fusion images has become one of the research hotspots for image processing. In order to realize defect detection and intelligent grinding smoothly, multi‐view fusion technology was applied in the field of overexposure and underexposure industrial welds, achieving high quality image enhancement. When preparing the data set of multi‐view images, a hybrid registration algorithm with high matching ability is proposed. The data set of overexposure and underexposure weld images was obtained successfully by using the registration algorithm. In order to improve the fusion ability of overexposure and underexposure industrial welds, we propose a novel multi‐view image fusion algorithm based on deep learning. The multi‐view fusion algorithm uses an autoencoder network structure, and its innovation lies in a parallel branch network with lightweight structure and strong generalization ability. The experimental results demonstrate that compared with other classical multi‐view algorithms, our proposed algorithm gets the best parameters on the industrial weld data set in peak signal to noise ratio (PSNR) and root mean square error (RMSE), reaching 59.12 and 0.084, respectively. And the ablation and performance comparison experiments verify that the proposed parallel branch network has better generalization ability and fusion accuracy than other classical multi branch networks.

The fatigue life prediction model of self-piecing riveting components of aluminum alloy is established and the effects of roughness and residual stress on fatigue life are analyzed by the model. Finite element software ABAQUS and fatigue analysis software FE-SAFE are used to study the effects of roughness and residual stress on the fatigue life of self-piecing riveting components through finite element simulation and mathematical statistics multivariate orthogonal regression experiment. The quantitative relations between fatigue life and three variables (roughness, residual stress and maximum stress) are fitted, and the variation trend of fatigue life with roughness and residual stress is obtained. The order of influence of roughness, residual stress, maximum stress and two interactions on fatigue life is as follows: residual stress, interaction between roughness and residual stress, roughness. When the maximum stress is fixed, the fatigue life increases with the decrease of residual stress with a certain roughness, and the fatigue life decreases with the increase of roughness with a certain residual stress. The average error between the fatigue experiment results and the simulation results is 9.27%, which proves that the simulation results are reliable.

Weld recognition is the premise of automatic weld polishing, and weld image segmentation can provide key area information for robots. With the advent of large segmentation model, it will be more convenient to realize weld image segmentation. With the emergence of complex scenes such as smoke, how to achieve high precision weld image segmentation under different smoke concentrations has become a challenge. To solve this problem, we propose a lightweight weld segmentation approach in smoke scenes. The feature transformation can better realize the feature processing of the smoke weld image, and further combine with the large segmentation model to realize the smoke weld image segmentation. The experimental data show that the segmentation accuracy of the weld segmentation approach we proposed achieves 98.18% in everything mode, increasing by 0.67% and 11.64% compared with the typical comparison methods, respectively. And the feature transformation is relatively lightweight. [ABSTRACT FROM AUTHOR]

To study the method of trajectory tracking for robotic arms, the traditional tracking method has low accuracy and cannot realize the complex tracking tasks. Compared with traditional methods, deep reinforcement learning is an effective scheme with the advantages of robustness and solving complex problems. This study aims to improve the tracking efficiency of robotic arms based on deep reinforcement learning. Thereby, we propose an approach to improve the proximal policy optimization (Improved-PPO) in this paper, which can be applied to multiple degrees of freedom robotic arms for trajectory tracking. In this study, proximal policy optimization (PPO) and model predictive control (MPC) are integrated to provide an effective algorithm for robotic arm applications. MPC is employed for trajectory prediction to design the controller. Further, the Improved-PPO algorithm is employed for trajectory tracking. The Improved-PPO algorithm is further compared with the asynchronous advantage actor-critic (A3C) and PPO algorithms. The simulation results show that the convergence speed of the Improved-PPO algorithm is increased by 84.3% and 15.4% compared with the A3C and PPO algorithms. This method provides a new research concept for robotic arm trajectory tracking. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy and speed of extracting the center of the line structured light stripe when using the vision measurement technology to get the 3D information of the weld sample, this paper proposes a center extraction approach based on the idea of data dimensionality reduction. First, use the weighted gray centroid approach to get the initial center point of the light stripe. Then, build a 7×7 template centered on the pixel block where the initial point is located and performs singular value decomposition on the 49×3 matrix within the template to get the normal direction of the initial point. Finally, calculate the stripe's exact center points through second-order Taylor expansion and smooth repair by cubic spline interpolation of breakpoints. The comparison experimental results show that this approach can effectively reduce the influence of the noise outside the light stripe on the center extraction, reduce the extraction time while ensuring the measurement accuracy, which can lay a good foundation for the point cloud data processing and surface reconstruction. [ABSTRACT FROM AUTHOR]

The dust removal technology of welding seam image has important practical significance for promoting the development of weld instance segmentation and target tracking. In this paper, we propose a welding seam image dust removal algorithm based on fusion of dual-scale dark channel and bright channel, which is to solve the problem that the color distortion and halo effect of dark channel prior image restoration algorithm in weld depth of field sudden change area and bright region. Firstly, the results of the minimum filtering of two scale windows are adaptively weighted and fused to obtain the fused dark channel. Secondly, the dark channel prior and the bright channel prior fusion strategy is adopted to obtain the fused atmospheric light to make the rough transmittance estimation more accurate. Finally, the weighted guided filtering is combined with up-sampling and down-sampling to optimize the rough transmittance, and the weld image is restored by combining the atmospheric scattering model. The experimental results indicate that our algorithm can restore the color and edge details of welding seam images and effectively suppress the halo effect. The objective comparison with several typical algorithms proves the feasibility and superiority of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The fatigue life prediction model of self-piecing riveting components of aluminum alloy is established and the effects of roughness and residual stress on fatigue life are analyzed by the model. Finite element software ABAQUS and fatigue analysis software FE-SAFE are used to study the effects of roughness and residual stress on the fatigue life of self-piecing riveting components through finite element simulation and mathematical statistics multivariate orthogonal regression experiment. The quantitative relations between fatigue life and three variables (roughness, residual stress and maximum stress) are fitted, and the variation trend of fatigue life with roughness and residual stress is obtained. The order of influence of roughness, residual stress, maximum stress and two interactions on fatigue life is as follows: residual stress, interaction between roughness and residual stress, roughness. When the maximum stress is fixed, the fatigue life increases with the decrease of residual stress with a certain roughness, and the fatigue life decreases with the increase of roughness with a certain residual stress. The average error between the fatigue experiment results and the simulation results is 9.27%, which proves that the simulation results are reliable. [ABSTRACT FROM AUTHOR]

This paper presents a newtype of strapdown north finder. A simplified configuration is proposed, including three parts: a pendulous force-feedback accelerometer, a ring laser gyroscope, and a single-axis rotating platform. The dynamic northfinding scheme of continuous rotation is adopted to eliminate the lock-in region of the laser gyroscope and to modulate the weak attitude signals; meanwhile the complex leveling process is avoided in this proposed configuration. To suppress the drift noises of the accelerometer and gyroscope, two digital lock-in amplifiers are used to extract the weak attitude signals. Simulation results show that the north finder can determine the heading angle in 72 s, when the rotating rate is 10°/s with the maximum heading error less than 1.0'; meanwhile the horizontal attitude angles as well as the constant drift noises of the inertial components could also be obtained. [ABSTRACT FROM AUTHOR]

Sensitivity analysis plays a key role in structural optimization, but traditional methods of sensitivity analysis in strength and stiffness are time consuming and of high cost. In order to effectively carry out structural optimization of hydraulic press, this paper presents a novel sensitivity analysis method in structural performance of hydraulic press, which saves a great deal of time and design costs. The key dimension parameters of the optimization of design variables, which remarkably impact on the structural performance of hydraulic press, are efficiently selected. The impact order of various sensitivity parameters in strength and stiffness of machine tools is consistent with the sensitivity ranking of regression analysis. The research results provide the basis for the hydraulic machine design and references in research of machine tools and equipment. [ABSTRACT FROM AUTHOR]

This paper, through the theory of multi-objective parameter optimization, the finite-element analysis and central composite test of the blanking process of the locating plate of the breaker are carried out. The optimal blanking process parameters of the positioning plate of the circuit breaker are determined, and the influence laws of the independent variable blanking gap, the punch edge radius and the blanking speed on the maximum blanking force and the length of the bright belt are obtained. The experimental results show that the production efficiency of the positioning plate of the circuit breaker is increased by 25%, and the actual machining error is only 4%, which provides a certain guiding significance for optimizing the blanking process parameters. [ABSTRACT FROM AUTHOR]