Search results

Once an uneven substrate is aligned, traditional control theories and methods can be used on it, so aligning is of great significance for the development of wire and arc additive manufacturing (WAAM). This paper aims to propose a shape-driven control method for aligning a substrate with slopes to expand the application of WAAM.

A substrate with slopes must be aligned by depositing weld beads with slopes. First, considering the large height differences of slopes, multi-layer deposition is needed, and the number of layer of weld beads must be ascertained. Second, the change in the deposition rate is controlled as a ramp function to generate weld beads with slopes. Third, the variation of the deposition rate must be fine-tuned to compensate for the deviation between the actual and theoretical layer heights at the deposition of each layer. Finally, the parameters of the ramp functions at the deposition of each layer are determined through an optimization method.

First, to model the response function of layer height to deposition rate, the experiments are conducted with the deposition rate jumping from 4 to 8 mm/s and from 8 to 4 mm/s. When the deposition rate jumps from 4 to 8 mm/s and from 8 to 4 mm/s, the difference in the height of each layer decreases as the number of layer increases. Second, the variation of the deposition rate can be fine-tuned based on the deviation between the measured and theoretical layer heights because the variation of the deposition rate is proportional to the layer height when the initial and end deposition rates are near 4 or 8 mm/s, respectively. Third, the experimental results demonstrate that the proposed method is effective for single-layer aligning and aligning a substrate with one or more slopes.

The proposed method can expand the application of WAAM to an uneven substrate with slopes and lays the foundation for aligning tasks focused on uneven substrates with more complex shapes.

A new reverse educing method (REM) is presented to estimate the vibrational stress on rotating aeroengine blades from the actual fracture section. This method does not conform to the traditional calculating method, but involves the reverse solution idea. The value of the crack propagation ratio da/dN can be obtained from the actual fracture section of the blade, and then the vibrational stress on rotating blades can be calculated through static computation, modal analysis and crack stress intensity factor calculation. The result is very significant for fault diagnosing and shooting of aeroengine blades.

This paper aims to achieve automatically surface segmentation for painting different kinds of aircraft efficiently considering the demands of painting robot.

This project creatively proposed one method that accepts point cloud, outputs several blocks, each of which can be handled by ABB IRB 5500 in one station. Parallel PointNet (PPN) is proposed in this paper for better handling six dimensional aircraft data including every point normal. Through semantic segmentation of PPN, each surface has its own identity information indicating which part this surface belongs to. Then clustering considering constraints is applied to complete surface segmentation with identity information. To guarantee segmentation paintable and improve painting efficiency, different dexterous workspaces of IRB 5500 corresponding to different postures have been analyzed carefully.

The experiments confirm the effectiveness of the proposed surface segmentation method for painting different types of aircraft by IRB 5500. For semantic segmentation on aircraft data with point normal, PPN has higher precision than PointNet. In addition, the whole algorithm can efficiently segment one complex aircraft into qualified blocks, each of which has its own identity information, can be painted by IRB 5500 in one station and has fewer edges with other blocks.

As the provided experiments indicate, the proposed method can segment one aircraft into qualified blocks automatically, which highly improves the efficiency in aircraft painting compared with traditional approaches. Moreover, the proposed method is able to provide identity information of each block, which is necessary for application of different paint parameters and different paint materials. In addition, final segmentation results by the proposed method behaves better than k-means cluster on variance of normal vector distance.

Inspired by semantic segmentation of 3 D point cloud, some improvements based on PointNet have been proposed for better handling segmentation of 6 D point cloud. By introducing normal vectors, semantic segmentation could be accomplished precisely for close points with opposite normal, such as wing upper and lower surfaces. Combining deep learning skills with traditional methods, the proposed method is proved to behave much better for surface segmentation task in aircraft painting.

This paper aims to realize the automatic assembly process for multiple rigid peg-in-hole components.

This paper develops fuzzy force control strategies for the rigid dual peg-in-hole assembly. Firstly the fuzzy force control strategies are presented. Secondly the contact states and contact forces are analyzed to prove the availability of the force control strategies.

The rigid dual peg-in-hole assembly experimental results show the effectiveness of the control strategies.

This paper proposes fuzzy force control strategies for a rigid dual peg-in-hole assembly task.

This paper throws light on some of the nature of artificial intelligence (AI) development, which will serve as a starter for helping to advance its development.

This work reveals the evolutions and trends of AI from four dimensions: research, output, influence and competition through leveraging academic knowledge graph with 130,750 AI scholars and 43,746 scholarly articles.

The authors unearth that the “research convergence” phenomenon becomes more evident in current AI research for scholars' highly similar research interests in different regions. The authors notice that Pareto's principle applies to AI scholars' outputs, and the outputs have been increasing at an explosive rate in the past two decades. The authors discover that top works dominate the AI academia, for they attracted considerable attention. Finally, the authors delve into AI competition, which accelerates technology development, talent flow, and collaboration.

The work aims to throw light on the nature of AI development, which will serve as a starter for helping to advance its development. The work will help us to have a more comprehensive and profound understanding of the evolutions and trends, which bridge the gap between literature research and AI development as well as enlighten the way the authors promote AI development and its strategy formulation.

This paper aims to present an image-based visual servoing algorithm for a multiple pin-in-hole assembly. This paper also aims to avoid the matching and tracking of image features and the remaining robust against image defects.

The authors derive a novel model in the set space and design three image errors to control the 3 degrees of freedom (DOF) of a single-lug workpiece in the alignment task. Analytic computations of the interaction matrix that link the time variations of the image errors to the single-lug workpiece motions are performed. The authors introduce two approximate hypotheses so that the interaction matrix has a decoupled form, and an auto-adaptive algorithm is designed to estimate the interaction matrix.

Image-based visual servoing in the set space avoids the matching and tracking of image features, and these methods are not sensitive to image effects. The control law using the auto-adaptive algorithm is more efficient than that using a static interaction matrix. Simulations and real-world experiments are performed to demonstrate the effectiveness of the proposed algorithm.

This paper proposes a new visual servoing method to achieve pin-in-hole assembly tasks. The main advantage of this new approach is that it does not require tracking or matching of the image features, and its supplementary advantage is that it is not sensitive to image defects.

High precision assembly processes using industrial robots require the process parameters to be tuned to achieve desired performance such as cycle time and first time through rate. Some researchers proposed methods such as design-of-experiments (DOE) to obtain optimal parameters. However, these methods only discuss how to find the optimal parameters if the part and/or workpiece location errors are in a certain range. In real assembly processes, the part and/or workpiece location errors could be different from batch to batch. Therefore, the existing methods have some limitations. This paper aims to improve the process parameter optimization method for complex robotic assembly process.

In this paper, the parameter optimization process based on DOE with different part and/or workpiece location errors is investigated. An online parameter optimization method is also proposed.

Experimental results demonstrate that the optimal parameters for different initial conditions are different and larger initial part and/or workpiece location errors will cause longer cycle time. Therefore, to improve the assembly process performance, the initial part and/or workpiece location errors should be compensated first, and the optimal parameters in production should be changed once the initial tool position is compensated. Experimental results show that the proposed method is very promising in reducing the cycle time in assembly processes.

The proposed method is practical without any limitation.

The proposed technique is implemented and tested using a real industrial application, a valve body assembly process. Hence, the developed method can be directly implemented in production.

This paper provides a technique to improve the assembly efficiency by compensating the initial part location errors. An online parameter optimization method is also proposed to automatically perform the parameter optimization process without human intervention. Compared with the results using other methods, the proposed technology can greatly reduce the assembly cycle time.

The purpose of this paper is to systematically review the published slicing methods for additive manufacturing (AM), especially the multi-direction and non-layerwise slicing methods, which are particularly suitable for the directed energy deposition (DED) process to improve the surface quality and eliminate the usage of support structures.

In this paper, the published slicing methods are clarified into three categories: the traditional slicing methods (e.g. the basic and adaptive slicing methods) performed in the powder bed fusion (PBF) system, the multi-direction slicing methods and non-layerwise slicing methods used in DED systems. The traditional slicing methods are reviewed only briefly because a review article already exists for them, and the latter two slicing methods are reviewed comprehensively with further discussion and outlook.

A few traditional slicing approaches were developed in the literature, including basic and adaptive slicing methods. These methods are efficient and robust when they are performed in the PBF system. However, they are retarded in the DED process because costly support structures are required to sustain overhanging parts and their surface quality and contour accuracy are not satisfactory. This limitation has led to the development of various multi-direction and non-layerwise slicing methods to improve the surface quality and enable the production of overhangs with minimum supports.

An original review of the AM slicing methods is provided in this paper. For the traditional slicing methods and the multi-direction and non-layerwise slicing method, the published slicing strategies are discussed and compared. Recommendations for future slicing work are also provided.

This paper aims to present an optimization algorithm combined with the impedance control strategy to optimize the robotic dual peg-in-hole assembly task, and to reduce the assembly time and smooth the contact forces during assembly process with a small number of experiments.

Support vector regression is used to predict the fitness of genes in evolutionary algorithm, which can reduce the number of real-world experiments. The control parameters of the impedance control strategy are defined as genes, and the assembly time is defined as the fitness of genes to evaluate the performance of the selected parameters.

The learning-based evolutionary algorithm is proposed to optimize the dual peg-in-hole assembly process only requiring little prior knowledge instead of modeling for the complex contact states. A virtual simulation and real-world experiments are implemented to demonstrate the effectiveness of the proposed algorithm.

The proposed algorithm is quite useful for the real-world industrial applications, especially the scenarios only allowing a small number of trials.

The paper provides a new solution for applying optimization techniques in real-world tasks. The learning component can solve the data efficiency of the model-free optimization algorithms.