Browsing by Author "Esteves, Arthur"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- Design for automation, edge services, and manufacturing – A React Native interface for collaborative robot palletizing systemsPublication . Torres, Pedro; Esteves, Arthur; Ribeiro, Fillipe; Barbosa, FláviaThis work is part of the PRODUTECH R3 mobilizing agenda project and provides a comprehensive overview of the concepts of Design-for-Automation (DfA), Design-for-Edge Services (DfES), and Design-for-Manufacturing (DfM), highlighting their importance within the Industry 4.0 paradigm. These principles are crucial for developing smart, efficient, and scalable industrial solutions. As a case study, the paper presents the development of an automatic configuration system for a collaborative robotic palletizer, implemented in React Native. The graphical interface simplifies the mosaic configuration process, improves the user experience, and ensures integration with the collaborative robot. Using cutting-edge computing resources, the solution achieves real-time performance and scalability, offering significant value to the company involved and its customers. The study demonstrates how the adoption of these design principles can drive innovation and efficiency in industrial processes, reinforcing the fundamental role of user-centered solutions in the digital transformation of production systems.
- Unsupervised anomaly detection in industrial machines supported by vibration analysis under data scarcity constraintsPublication . Torres, Pedro; Spencer, Geoffrey; Esteves, Arthur; Sousa, Fernando; Pereira, Fernando J.G.; Guerreiro, Rui M.L.The integration of the use of Artificial Intelligence (AI) in industrial environments often faces the lack of labeled data, as well as historical records. This lack of information becomes a problem when implementing predictive maintenance solutions, particularly in monitoring the condition of industrial machines and automatic fault detection. This work addresses this issue in an industrial scenario, through the analysis of vibrations in a spindle motor of an ornamental stone cutting machine. Unsupervised learning techniques are explored for anomaly detection through vibration data, using the training and implementation of an LSTM (Long Short-Term Memory) Autoencoder model. Datasets consist only of unlabeled accelerometer signals acquired during normal machine operation. An analysis based on the extraction of statistical features from the signal is adopted to use them as inputs of the Machine Learning algorithm, to learn the normal behavior of the machine and detect deviations that may correspond to potential anomalies. The experimental results show that even in the absence of labeled data, it is possible to extract meaningful insights from the machine state and establish a practical pipeline for anomaly detection in industrial machines through vibration analysis.