A three-stage quality diagnosis platform for laser-based manufacturing processes
- PDF / 5,172,151 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 47 Downloads / 151 Views
ORIGINAL ARTICLE
A three-stage quality diagnosis platform for laser-based manufacturing processes Panagiotis Stavropoulos 1 & Alexios Papacharalampopoulos 1 & John Stavridis 1 & Kyriakos Sampatakakis 1 Received: 7 March 2020 / Accepted: 20 August 2020 / Published online: 18 September 2020 # The Author(s) 2020
Abstract Diagnosis systems for laser processing are being integrated into industry. However, their readiness level is still questionable under the prism of the Industry’s 4.0 design principles for interoperability and intuitive technical assistance. This paper presents a novel multifunctional, web-based, real-time quality diagnosis platform, in the context of a laser welding application, fused with decision support, data visualization, storing, and post-processing functionalities. The platform’s core considers a quality assessment module, based upon a three-stage method which utilizes feature extraction and machine learning techniques for weld defect detection and quality prediction. A multisensorial configuration streams image data from the weld pool to the module in which a statistical and geometrical method is applied for selecting the input features for the classification model. A Hidden Markov Model is then used to fuse this information with earlier results for a decision to be made on the basis of maximum likelihood. The outcome is fed through web services in a tailored User Interface. The platform’s operation has been validated with real data. Keywords Laser welding . Quality diagnosis . Weld defects . Monitoring platform . User Interface
1 Introduction Laser material processing includes a set of non-conventional machining [1] and joining methods [2] which have been well established in modern manufacturing. Furthermore, new developments in recent years in additive manufacturing (AM) [3] and micro/nano fabrication [4] have enabled new capabilities that lasers can bring to the manufacturing industry. As such, and with zero-defect manufacturing (ZDM) in mind, wrapping these processes with the appropriate infrastructure and tools for monitoring, quality diagnosis, and adaptive control [5] is of utmost importance. This way, the processes and the systems will be able to harmonize with the requirements of Industry 4.0, as depicted in the Fig. 1. Monitoring and quality control systems are critical and necessary tools in order for production results to be kept in
* Panagiotis Stavropoulos [email protected] 1
Laboratory for Manufacturing Systems and Automation, Department of Mechanical Engineering and Aeronautics, University of Patras, 265 00 Patras, Greece
desired boundaries [6] and be able to deal with changing conditions without requiring a complex and time-consuming manual setup. In this regard, systems for monitoring of Laser AM and 3D printing processes based on X-ray imaging have been developed allowing the exploitation of novel process insights [7, 8]. Furthermore, in the case of metal droplet fusion processes, industrial computer tomography scanning is utilized for defect identification of t
Data Loading...
