Completion of the SARATROF Project

SARATROF (an acronym for System for the Analytical Assessment of Worker and Robot Aggregate Performance in Manufacturing Operations) is a research project launched in 2021. Its objective is to develop a system to evaluate company performance by aggregating data from machines and workers. This initiative aims to enhance production competitiveness by leveraging Information and Communication Technologies (ICT) and Artificial Intelligence (AI). The project is a collaborative effort involving Ancora, Ledisson, Situm, and Beta Implants.

SARATROF is part of the Conecta Hubs 2021 program, funded by the Galician Innovation Agency (Axencia Galega de Innovación, GAIN) and financially supported by the European Union (co-funded through the ERDF under the Operational Programme ERDF Galicia 2014–2020). It also benefits from the backing of the Second Vice-Presidency and the Department of Economy, Enterprise, and Innovation of the Xunta de Galicia.

The value brought by this project lies in enhancing company productivity through the integration of the various information silos that typically exist within an organization and often do not communicate with each other. The objective is to enable the information generated in each silo to be integrated into a unified platform, allowing data analysis to inform decisions aimed at improving overall company productivity from a more comprehensive perspective.

EDNON

In this final milestone of the project, Ednon’s efforts have focused on optimizing data acquisition and enrichment processes and, fundamentally, on refining analytics processes. This has allowed for improvements in the accuracy of the Machine Learning models themselves and validation of results with the continuous data collected from Beta Implants’ pilot plant. All the information obtained enables a better understanding of the factory’s operation and performance based on different parameters.

With the work carried out throughout the project, the objectives assigned to Ednon have been met:

• Deployment of an interoperable metaplatform.
• Execution of Machine Learning and data analytics processes.

In conclusion, this project has enabled the acquisition of new knowledge to define new work lines in the field of Industry 4.0. Additionally, a sufficiently flexible and modular framework and methodology have been established to be extrapolated to other industrial areas. This opens a range of opportunities and future collaborations for the company.

ANCORA

In this third year, Ancora’s activities have revolved around the pilot deployed at Beta Implants using the modules developed throughout the project, as well as the acquisition and analysis of data from these modules. Close collaboration with Beta Implants has made it possible to introduce improvements in a new implementation of Ancora Worker Connect with analytical capabilities for production. These new analytical capabilities have been implemented through a proprietary module capable of generating real-time results regarding operator performance in conjunction with other factory elements, with the aim of providing operators with feedback on their performance and action guidelines.

The combination of analytical capabilities with operator digitization and assistance has resulted in improvements for Beta Implants’ workers and the company itself, including access to information, real-time production management, and traceability.

The results obtained this year also reflect the outcomes of tasks executed in previous years. The SARATROF project has allowed Ancora to meet the objectives initially set, including:

• Designing and developing an industrial intelligence module to assist workers, thereby improving their competitiveness and efficiency.
• Applying various technologies and strategies to improve worker efficiency on the factory floor.
• Generating worker efficiency metrics and integrating them into the Ancora Worker Connect interface to provide real-time feedback on their performance.

Additionally, interaction with Beta Implants and the work carried out in the pilot have enabled improvements in the deployment and monitoring processes of Ancora’s solution in high-availability manufacturing environments.

LEDISSON

This year, Ledisson has continued collecting data from all types of machines installed at the end-user (Beta). The greatest challenge arose with the FANUC 32i-B CNC machine, which has an integrated PLC, preventing data extraction via that route.

We decided to obtain information from the electrical impulses generated by this machine during its production process. First, we reviewed the electrical schematics to identify the most suitable and interesting signals for this purpose.

The only commercial element incorporated into the CNC machine’s electrical cabinet was a RevPi* with a digital input module. Upon reviewing the electrical cabinet, we discovered that most signals were directly soldered onto PCB boards, making it impossible to connect these signals to the RevPi. Bearing this in mind, during the electrical schematic review, we initially selected 22 possible signals that we could connect to our RevPi.

Of these 22 signals, most were discarded for various reasons, but 5 signals provided satisfactory responses. These 5 signals belonged to 5 contactors installed in the electrical cabinet, providing information such as when the coolant pump was activated, when the spindle cooling was activated, when the finished part extraction belt was activated, as well as two contactors installed in the cabinet that did not appear in the electrical schematics but could be useful for discovering their purpose.

Once the RevPi was connected with its signals, it was confirmed that everything was functioning correctly, and data collection began.

• A RevPi is a miniature industrial PC, and its function in this project is to translate the machine’s digital signals into a visual environment that allows us to view the data collected on a computer screen, which, thanks to its Wireless connectivity, can be accessed from anywhere.

SITUM

In this final year, Situm has primarily focused on piloting the solutions developed during the project together with Beta to extract the greatest amount of intelligence from the production process.

In this pilot, the geoanalytics developed using real data were put to use, and the platform was scaled to handle the traffic of a real environment like Beta’s production line.

Additionally, work continued on detecting scenarios where the localization system’s precision decreases, in order to indicate the potential need for corrective maintenance of the system.

New ideas were also generated during the pilot to continue improving the use of geolocation technologies in industrial environments for future projects, such as applying geolocation to materials and using trackers instead of mobile phones for geolocation.

Conclusion

This project has enabled the acquisition of new knowledge to define new work lines in the field of Industry 4.0. Additionally, a sufficiently flexible and modular framework and methodology have been established to be extrapolated to other industrial areas. This opens a range of opportunities and future collaborations for the company.