Search results

Workpiece sorting is a key link in industrial production lines. The vision-based workpiece sorting system is non-contact and widely applicable. The detection and recognition of workpieces are the key technologies of the workpiece sorting system. To introduce deep learning algorithms into workpiece detection and improve detection accuracy, this paper aims to propose a workpiece detection algorithm based on the single-shot multi-box detector (SSD).

Propose a multi-feature fused SSD network for fast workpiece detection. First, the multi-view CAD rendering images of the workpiece are used as deep learning data sets. Second, the visual geometry group network was trained for workpiece recognition to identify the category of the workpiece. Third, this study designs a multi-level feature fusion method to improve the detection accuracy of SSD (especially for small objects); specifically, a feature fusion module is added, which uses “element-wise sum” and “concatenation operation” to combine the information of shallow features and deep features.

Experimental results show that the actual workpiece detection accuracy of the method can reach 96% and the speed can reach 41 frames per second. Compared with the original SSD, the method improves the accuracy by 7% and improves the detection performance of small objects.

This paper innovatively introduces the SSD detection algorithm into workpiece detection in industrial scenarios and improves it. A feature fusion module has been added to combine the information of shallow features and deep features. The multi-feature fused SSD network proves the feasibility and practicality of introducing deep learning algorithms into workpiece sorting.

A measuring system for automatic process parameter acquisition in garment sewing operations has been presented. The measuring equipment is based upon the usage of a very powerful portable notebook IBM compatible personal computer, equipped with an AD converter, measuring instruments and adequate software packages for data storing and analysis. Characteristics of measuring instruments and sensors have also been given, together with measuring process description, all connected with two independent video‐camera systems, working in two planes, used for working operation analysis at workplaces in garment sewing operations.

Presently, 6 Degree of Freedom (6DOF) visual pose measurement methods enjoy popularity in the industrial sector. However, challenges persist in accurately measuring the visual pose of blank and rough metal casts. Therefore, this paper introduces a 6DOF pose measurement method utilizing stereo vision, and aims to the 6DOF pose measurement of blank and rough metal casts.

This paper studies the 6DOF pose measurement of metal casts from three aspects: sample enhancement of industrial objects, optimization of detector and attention mechanism. Virtual reality technology is used for sample enhancement of metal casts, which solves the problem of large-scale sample sampling in industrial application. The method also includes a novel deep learning detector that uses multiple key points on the object surface as regression objects to detect industrial objects with rotation characteristics. By introducing a mixed paths attention module, the detection accuracy of the detector and the convergence speed of the training are improved.

The experimental results show that the proposed method has a better detection effect for metal casts with smaller size scaling and rotation characteristics.

A method for 6DOF pose measurement of industrial objects is proposed, which realizes the pose measurement and grasping of metal blanks and rough machined casts by industrial robots.

With the development of materials science and technology, composite workpieces are increasingly used. This paper aims to discuss a non-destructive testing (NDT) solution for semi-enclosed composite workpieces. A dual-robot system with one robot that grips an irregular-shaped ultrasonic probe (tool) is established.

According to robotics, this paper defines the orientations of the discrete points coordinate frames in trajectory and proposes an orientation constraint rule between the tool coordinate frame and the scanning trajectory. A four-posture calibration method for calibrating the transformation relationship of the irregular-shaped tool frame relative to the robot flange frame is presented in detail.

Calibration and verification experiments were performed, and good-quality C-scan images were obtained by applying the constraint rule and the calibration method. Experimental results show that the calibration method used to determine the tool centre point (TCP) position is correct, effective and efficient; the TCP orientation constraint rule can ensure the extension pole of the irregular-shaped ultrasonic probe is parallel to the axis of the semi-enclosed cylindrical workpieces; and the ultrasonic transducer axis is perpendicular to the surface of the workpiece.

This paper proposes a constraint method for the posture of an irregular-shaped tool in this scheme. Theoretical foundations for the four-posture calibration method of the irregular-shaped tool for dual-robot-assisted ultrasonic NDT are presented in detail. This strategy has been successfully applied in the NDT experiment of semi-enclosed composite workpieces.

The purpose of this paper is to explore the role that computer vision can play within new industrial paradigms such as Industry 4.0 and in particular to support production line improvements to achieve flexible manufacturing. As Industry 4.0 requires “big data”, it is accepted that computer vision could be one of the tools for its capture and efficient analysis. RGB-D data gathered from real-time machine vision systems such as Kinect ® can be processed using computer vision techniques.

This research exploits RGB-D cameras such as Kinect® to investigate the feasibility of using computer vision techniques to track the progress of a manual assembly task on a production line. Several techniques to track the progress of a manual assembly task are presented. The use of CAD model files to track the manufacturing tasks is also outlined.

This research has found that RGB-D cameras can be suitable for object recognition within an industrial environment if a number of constraints are considered or different devices/techniques combined. Furthermore, through the use of a HMM inspired state-based workflow, the algorithm presented in this paper is computationally tractable.

Processing of data from robust and cheap real-time machine vision systems could bring increased understanding of production line features. In addition, new techniques that enable the progress tracking of manual assembly sequences may be defined through the further analysis of such visual data. The approaches explored within this paper make a contribution to the utilisation of visual information “big data” sets for more efficient and automated production.

It was verified that the micro-texture in the front and back of the tool at the same time had a positive effect on improving the milling behavior and surface quality of the tool. The purpose of this study is to explore the rationality of simultaneous placement of micro-textures on the front and rear surfaces of ball-end milling cutters, analyze the influence of micro-texture parameters on tool milling behavior and workpiece surface quality, reveal its internal mechanism, and obtain the best micro-texture parameters by optimization.

First, the mechanism of micro-texture is studied based on the energy loss model. Second, the orthogonal experiment is designed to analyze the influence of micro-texture parameters on tool milling behavior and reveal its mechanism by combining simulation technology and cutting experiment. Finally, the parameters are optimized based on the artificial bee colony algorithm.

The results show that the simultaneous placement of micro-texture on the rake face and flank face of the tool has a positive effect on improving the milling behavior and surface quality of the tool. Taking milling force, tool wear and surface roughness as the evaluation criteria, the optimal parameter combination is obtained: the rake face micro-texture diameter is 50 µm, the distance from the micro-texture is 200 µm and the distance from the cutting edge is 110 µm; the diameter of the micro-textured flank is 40 µm, the distance from the micro-texture is 170 µm and the distance from the cutting edge is 130 µm.

Taking milling force, tool wear and surface roughness as the evaluation criteria, the optimal parameter combination is obtained: the rake face micro-texture diameter is 50 µm, the distance from the micro-texture is 200 µm and the distance from the cutting edge is 110 µm; the diameter of the micro-textured flank is 40 µm, the distance from the micro-texture is 170 µm and the distance from the cutting edge is 130 µm, which provides theoretical support for the further study of the micro-textured tool.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-01-2023-0022/

The current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems.

On the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects.

The effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model.

This paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision.

The purpose of this research is to study and analyze the literature that integrates Lean Six Sigma (LSS) approach with blockchain technology in different sectors for improved quality management.

This study presents a scoping review on the application of integrated LSS and blockchain technology in the manufacturing and healthcare sector. Further, the authors examined existing blockchain-based solutions on a variety of dimensions, including application area, technical approach, methodology, application scenario, various blockchain platforms, purpose, and monitoring parameters. The authors study LSS approaches in detail, as well as the key benefits that blockchain technology can enable. Finally, the authors discuss significant research problems to be addressed in order to develop a highly efficient, resilient, and secure quality management framework using blockchain technology.

It has been observed that the adoption of blockchain technology for quality management and assurance is influenced by several factors such as transaction execution speed, throughput, latency. Also, prior blockchain-based solutions have neglected to leverage the benefits of LSS methodologies for effective quality management.

This is the first study to explores the influence of blockchain technology on quality management and assurance in manufacturing and healthcare industry. Furthermore, prior research has not examined how integrating the LSS methodology with blockchain technology can aid in the control of product quality management.

Unika is a prototype robot — the product of work by Unimation in the US and Kawasaki in Japan — which by means of vision can detect the deviation between a taught standard path and the actual welding seam. The robot system can then correct the path taken by the welding gun manipulator.

This paper aims to propose an identification method based on monocular vision for cylindrical parts in cluttered scene, which solves the issue that iterative closest point (ICP) algorithm fails to obtain global optimal solution, as the deviation from scene point cloud to target CAD model is huge in nature.

The images of the parts are captured at three locations by a camera amounted on a robotic end effector to reconstruct initial scene point cloud. Color signatures of histogram of orientations (C-SHOT) local feature descriptors are extracted from the model and scene point cloud. Random sample consensus (RANSAC) algorithm is used to perform the first initial matching of point sets. Then, the second initial matching is conducted by proposed remote closest point (RCP) algorithm to make the model get close to the scene point cloud. Levenberg Marquardt (LM)-ICP is used to complete fine registration to obtain accurate pose estimation.

The experimental results in bolt-cluttered scene demonstrate that the accuracy of pose estimation obtained by the proposed method is higher than that obtained by two other methods. The position error is less than 0.92 mm and the orientation error is less than 0.86°. The average recognition rate is 96.67 per cent and the identification time of the single bolt does not exceed 3.5 s.

The presented approach can be applied or integrated into automatic sorting production lines in the factories.

The proposed method improves the efficiency and accuracy of the identification and classification of cylindrical parts using a robotic arm.