Meet our Project



About the Project

The research proposal of the REALM project concerns the development of a single cloud technology platform for monitoring and evaluation of the thermal welding process. The system will collect and record information and data during the process. Through the cloud technology platform, the data and results of the welding process will be available to production engineers.

Resistance Spot Welding

A Robotic system offers a flexible high parameterizable platform for performing remotely controlled Resistance Spot welding. The main process includes tow welding electrodes press the components together. Weld current is then switched on. The contact resistance results in thermo-electrical heating and the material melts. The current is then switched off and molten material hardens, forming a joint that cannot be separated. The pressure must be maintained while the melt is cooling to avoid pore formation.

Submerged Arc Welding

Submerged Arc Welding (SAW) machines are utilizing a DC source and an AC source (Tandem Arc) in accordance with ISO 4063 equipped with pulse modulation functions are offering control over penetration, slapping width and deposition Rate. During the welding process the electrodes and the molten weld are covered by being submerged under a layer of flux. The flux is melted under the heat of the welding arc forming a zone which protects the molten weld from corrosion and preventing hazardous events.

Real Time Monitoring Prototype System

A prototype system deployed in-situ, comprised by an infrared imaging system (Thermal Camera) connected to a PC, provides real-time monitoring capabilities. Hosting a local application enables the control of the Thermal Camera and performing real-time quality assessment of the welding events. Data and functionality are shared also to a cloud-base application.

Infrared Imaging Systems

A MWIR camera tailored for monitoring industrial welding processes, equipped with VDB PbSe-based FPA, offers high acquisition rate during RSW.

Quality Assessment Algorithms

Machine/Deep learning and statistics models are forming the core of the Quality Assessment algorithms. Selected and trained under highly diverse datasets can classify welds with high accuracy.

Tailored Real Time Cloud based Software Platform

Historical Data exploration and post-processing along with all the functionalities of the Real Time Monitoring Platform are available through a cloud-based application.

Project Glimpses

Prev / Next


The Consortium

The REALM Consortium consists of 3 partners with significant experience each in their respective fields of interest. K. LIAROMATIS, the project coordinator, holds a leading position in the domestic steel manufacturing industry. In this research project will be the industrial partner of the partnership, acting as the end user, hosting the pilot implementation of the project. The data for the development of the algorithms will be extracted through experiments carried out on its premises and through existing process monitoring systems. Finally, they will have the final exploitation of the deployed platform. IRIDA will focus on developing a process monitoring system as well as developing Machine Learning models. The scientific body of the project, the Laboratory for Manufacturing Systems and Automation (LMS) of the University of Patras, is responsible for the development of the REALM platform (hardware and software). In addition, it will conduct data collection experiments and ultimately be responsible for the integration of Machine Learning models and developed algorithms.

Laboratory for Manufacturing Systems & Automation, University of Patras

The Laboratory for Manufacturing Systems & Automation (LMS) is oriented on research and development in cutting edge scientific and technological fields. LMS is involved in a number of research projects funded by the CEU and European industrial partners. Particular emphasis is given to the co-operation with the European industry as well as with a number of "hi-tech" firms. LMS is under the direction and technical coordination of Professor George Chryssolouris. It is organized in three different groups:

  1. Manufacturing Processes Modelling and Energy Efficiency
  2. Robots, Automation and Virtual Reality in Manufacturing
  3. Manufacturing Systems


IRIDA Labs is bridging the gap between a camera and a human eye by bringing visual perception to any device.Our product and technology portfolio includes applications in Visual Perception/Analytics and Computational Photography addressing various markets such as mobile devices, action cameras, drones, surveillance, automotive, industrial and robot vision etc. We develop software in Computer Vision, using Image Processing and Machine Learning techniques made for any CPU, GPU or DSP/ASP platform or a combination of them using Heterogeneous Programming techniques


Our company, over the years established itself as a leader in engineering design and production of quality structural steelworks to meet constantly changing demands of: Energy Sector, Steel Buildings, Steel Bridges, E.O.T Cranes and Specialized Steel Constructions.