Link Quality Estimation for Wireless ANDON Towers Based on Deep Learning Models

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 17; p. 6383
• Main Authors: Cortes-Aguilar, Teth Azrael, Cantoral-Ceballos, Jose Antonio, Tovar-Arriaga, Adriana
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 24.08.2022; MDPI
• Subjects: Algorithms; Artificial intelligence; Automation; Classification; Decision making; Deep learning; Evaluation; failure detection; link quality estimation; Machine learning; Management; Neural networks; Neurons; Pattern recognition; Real-time data processing; Reliability (Engineering); Software; wireless sensor network; Wireless sensor networks; Mexico
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22176383

Data reliability is of paramount importance for decision-making processes in the industry, and for this, having quality links for wireless sensor networks plays a vital role. Process and machine monitoring can be carried out through ANDON towers with wireless transmission and machine learning algorithms that predict link quality (LQE) to save time, hence reducing expenses by early failure detection and problem prevention. Indeed, alarm signals used in conjunction with LQE classification models represent a novel paradigm for ANDON towers, allowing low-cost remote sensing within industrial environments. In this research, we propose a deep learning model, suitable for implementation in small workshops with limited computational resources. As part of our work, we collected a novel dataset from a realistic experimental scenario with actual industrial machinery, similar to that commonly found in industrial applications. Then, we carried out extensive data analyses using a variety of machine learning models, each with a methodical search process to adjust hyper-parameters, achieving results from common features such as payload, distance, power, and bit error rate not previously reported in the state of the art. We achieved an accuracy of 99.3% on the test dataset with very little use of computational resources.