Development of a real time monitoring and adaptive control system for laser flame cutting

Abstract

A real-time, adaptive control and optimization system for laser flame cutting of thick plates of mild steel has been developed. The proposed system consists of two subsystems: a process monitoring system and a control and optimization system. The first subsystem aims at the on-line observation of the process status and corresponding cut quality. Since the different cut quality characteristics (e.g. cutting edge striations or dross) cannot be measured directly, the proposed system is based on so-called sensing parameters, which are easily-observable physical parameters that correlate well with the quality characteristics of the cut surface. The applicability of different optical sensors (photodiodes and a NIR-camera) has been investigated. The most optimal configuration of the process monitoring system is presented, including an overview of the selected set of sensing parameters. The second subsystem, the real-time control and optimization system, supports the adaptation of the process parameters, based on the cut quality information obtained from the process monitoring system. A suitable hardware configuration for the real-time control and optimization is presented, starting from the original platform (i.e. an industrial 2D laser cutting machine). A generic expert strategy, has been designed for the control and optimization purpose. Using the developed experimental platform, the performance of the expert system was verified and optimized for different material-thickness combinations. The obtained results demonstrate the effectiveness of the chosen approach in terms of increased autonomy, productivity, and efficiency of the process, as well as elimination of the need for manual quality control and the possibility to automatically generate quality reports.

Anticipating heat accumulation in laser oxygen cutting of thick metal plates

“…The most common one is adaptive control, which adjusts process parameters to successfully perform a cut. 18 In theory, the tool path could also be changed when quality deterioration is eminent in order to provide time for cooling of the current preheated contour. This would require tool path optimization to be performed on the fly or to apply a rule-based system to add waiting times or to skip contours that could be processed later.…”

Dross attachment estimation in the laser-cutting process via Convolutional Neural Networks (CNN)

“…Related works employ photodiodes [7], [8], to transduce the cut image from an optical signal to an electrical one. More recently, camera based monitoring systems are used, which guarantee a much more high quantity of information of the cut, [9], [10], [11], Fig. 2.…”

Analysis of Photodiode Monitoring in Laser Cutting

“…The main objective of the adaptive control systems is to maximize productivity by means of increasing the cutting velocity, but without losing the quality. Duflou et al [20] proposed as control variables the monitored NIR images, the laser power, cutting velocity, assist gas pressure, and the duty cycle of the laser beam. Wen et al [21] included sparking behavior as a variable to monitor.…”