After ten months of integration, tuning and testing of the Goizper demonstrator at STAM laboratory in Italy, at the end of March 2022 the demonstrator was totally dismounted and packaged to be shipped to Goizper facilities, in the Basque Country.
The activities carried out at STAM were a preliminary benchmark of the whole robotic solution for the assembly of rotary tables, with the scope of accelerating the integration, while the demonstrator was mounted at the Technical Coach’s home, where corrections and improvements were much easier and quicker to make. Some preliminary validation tests were performed at STAM laboratory, to understand if the developed solution was meeting the targets and requirements set at the beginning of the project. The promising results reached during the testing phase marked the end of the activities to be carried out at STAM.
|Torque applied by Sharework system||Same as manual||Same as manual|
|Bolts correctly fixed vs total bolts fixed||98%||98%|
|Operator gestures correctly interpreted vs total received operator gestures||95%||95%|
|Estimated max time for bolts positioning & screwing for a pattern of 16 bolts||220 sec||270 sec|
|Estimated time for one turn table quality inspection||45 min||30-40 min|
All the material arrived in Goizper mid-April 2022, where a special area of its shopfloor has been dedicated to the installation of the demonstrator. Efforts have been made to reproduce, as faithfully as possible, the same layout of the cell of STAM, so to minimize the possible software changes due to modifications in the configuration of the robotic cell. Once decided the final layout, some adaptation works to the assembly area were performed (e.g. the electricity was installed and the floor smoothed) and then it was possible to proceed with the installation of the hardware and electronics components.
From the software point of view, after transferring the demonstrator from the laboratory to the industrial environment, few tuning steps were required:
- Re-calibrate the network of the cameras mounted at the corners of the workspace. This is necessary to have a common frame between the four different cameras.
- Re-train the classification algorithm used to recognize the bolts inserted by the operator in the rotary table. Since the environment and the lighting condition of the workspace is changed with respect to the one in STAM laboratory, the re-training of the algorithm allows to maximize its accuracy.
- Integrate the Sharework software module responsible for the tablet interface, which was the only one that was not already integrated while the demonstrator was at STAM’s facilities.
Once all software tuning activities have been completed, the integration in the industrial environment was considered terminated and it was possible to proceed with training Goizper operators on how to interact with the system and perform the new collaborative processes of assembling rotary tables.
In the next two months before the end of the project, Goizper demonstrator will be fully tested in the industrial environment evaluating the overall performance of the system. The KPIs selected at the beginning of the project will be assessed, comparing the performance level obtained in Goizper with the target values.
Francesca Canale, Project Engineer at STAM S.r.l. She received the Master Degree in Robotics Engineering at the University of Genova, Italy, in 2020. During her studies she was involved in several projects where she experienced different aspects of robotics, including robot programming, computer vision, machine learning, control of robots, software architectures. In 2020, she started working as Project Engineer in STAM, an Italian engineering SME very active in the European Research and Development frame through the participation to several H2020 projects. Francesca is currently involved in the undertaking of technical activities from different R&D projects in the field of robotics and mechatronics
STAM is a private engineering company based in Genova, Italy, providing engineering services to industries. Specialized in design and manufacturing of innovative robotics and mechatronics mechanical systems, STAM leads the system conceptualization and use case definition and is responsible for the demonstrator integration and monitoring.