Search

Perforation pipes are widely used in oil&gas exploration. Aligning a perforated pipe in different workstations is very important for quality control. Typically, a keyway in a perforated pipe is machined as the alignment feature. Once the angle of a keyway is measured, an industrial robot is used to rotate the perforated pipe to the desired location. However, due to various errors, the industrial robot cannot rotate the perforated pipe to the desired location using the measured angle once. In this paper, a method based on generalized regression neural network (GRNN) is proposed to predict the rotation angle such that an industrial robot can rotate a perforated pipe to the desired location. Training datasets are collected first to train a GRNN model. The model is then deployed to predict the rotation angle. Experiments were performed to validate the proposed method and the results show that the final keyway angle satisfies the requirement of keyway alignment. [ABSTRACT FROM AUTHOR]

Purpose – Paint path planning for industrial robots is critical for uniform paint distribution, process cycle time and material waste, etc. However, paint path planning is still a costly and time-consuming process. Currently paint path planning has always caused a bottle-neck for manufacturing automation because typical manual teaching methods are tedious, error-prone and skill-dependent. Hence, it is essential to develop automated tool path-planning methods to replace manual paint path planning. The purpose of this paper is to review the existing automated tool path-planning methods, and investigate their advantages and disadvantages. Design/methodology/approach – The approach takes the form of a review of automated tool path-planning methods, to investigate the advantages and disadvantages of the current technologies. Findings – Paint path planning is a very complicated task considering complex parts, paint process requirements and complicated spraying tools. There are some research and development efforts in this area. Based on the review of the methods used for paint path planning and simulation, the paper concludes that: the tessellated CAD model formats have many advantages in paint path planning and paint deposition simulation. However, the tessellated CAD model formats lack edge and connection information. Hence, it may not be suitable for some applications requiring edge following, such as welding. For the spray gun model, more complicated models, such as 2D models, should be used for both path planning and paint distribution simulation. Paint path generation methods should be able to generate a paint path for complex automotive parts without assumptions, such as presupposing a part with a continuous surface. Practical implications – The paper makes possible automated path generation for spray-painting process using industrial robots such that the path-planning time can be reduced, the product quality improved, etc. Originality/value – The paper provides a useful review of current paint path-planning methodologies based on the CAD models of parts. [ABSTRACT FROM AUTHOR]