ISBN
Formato digital
979-13-87837-54-9
Fecha de publicación
06-10-2025
Licencia
D. R. © Copyright 2025. Alma Y. Alanis, Jorge Galvez, Omar Avalos, Eduardo Méndez-Palos, Jorge D. Rios, Adriana Peña Perez-Negron & Gabriel Martínez Soltero
Todos los contenidos de esta obra se comparten bajo la licencia Creative Commons Atri-bución/Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0). Esto implica que no está autorizado el uso comercial de la obra original ni de las eventuales obras derivadas, las cuales deberán distribuirse bajo la misma licencia que rige la obra original. No obstante, se permite a terceros compartir el contenido siempre y cuando se reconozca debidamente la autoría y la publicación original en esta editorial.
Víctor Hugo Benítez Baltazar
Universidad de Sonora
0000-0002-3926-9352
Jesús Horacio Pacheco Ramirez
Universidad de Sonora
0000-0002-8636-5902
Alberto Fuentes Trasviña
Universidad de Guadalajara
Jesús H. Ramírez Romero
Universidad de Guadalajara
José R. Reyes Zarate
Universidad de Guadalajara
Guillermo Cuame Cruz
Universidad de Guadalajara
Acerca de
Traditional fault notification systems in industrial environments depend on conventional technology like stack lights and auditory alarms. These systems provide limited contextual information and require prior operator training for accurate operation interpretation. This paper proposes an avatar-based fault management system that enhances human-machine interaction by replacing conventional alarm mechanisms with AI-generated avatars delivering structured, real-time notifications. The system is implemented on a Raspberry Pi that processes sensor inputs, classifies detected anomalies, and selects the appropriate pre-recorded video message stored on an SD card. These videos feature realistic avatars designed to avoid the uncanny valley effect, ensuring effective and intu- itive communication.
The system operates based on a state machine model, transitioning between normal operation, anomaly detection, video selection, playback, and daily summary reporting. The avatar indicates various fault levels, ranging from minor deviations to critical failures, and issues daily status reports when no faults are detected. A preliminary proof of concept confirms the feasibility of the proposed system, while future work will evaluate its effectiveness compared to conventional fault notification methods. By integrating human-like virtual assistants into industrial fault management, this system proposes a more intuitive and engaging alternative to traditional alert mechanisms. It improves situational awareness, decreases cognitive load, and can be seamlessly incorporated into IoT and Industry 4.0 ecosystems, paving the way for more human-centered automation in the industry.
Referencias
M. Achouch et al., “On Predictive Maintenance in Industry 4.0: Overview, Models, and Challenges,” Applied Sciences 2022, Vol. 12, Page 8081, vol. 12, no. 16, p. 8081, Aug.
2022, doi: 10.3390/APP12168081.
T. Duricic, P. Müllner, N. Weidinger, N. ElSayed, D. Kowald, and E. Veas, “AI- Powered Immersive Assistance for Interactive Task Execution in Industrial Environ- ments,” Jul. 2024, doi: 10.3233/FAIA241037.
A. Toichoa Eyam and J. L. Martinez Lastra, “MetaStates: An Approach for Represent- ing Human Workers’ Psychophysiological States in the Industrial Metaverse,” IEEE Access, vol. 12, pp. 81682–81691, 2024, doi: 10.1109/ACCESS.2024.3411877.
A. Morris, J. Guan, N. Lessio, and Y. Shao, “Toward Mixed Reality Hybrid Objects with IoT Avatar Agents,” Conf Proc IEEE Int Conf Syst Man Cybern, vol. 2020-Octo- ber, pp. 766–773, Oct. 2020, doi: 10.1109/SMC42975.2020.9282914.
V. Phadnis, K. Moore, and M. G. Franco, “The Work Avatar Face-Off: Knowledge Worker Preferences for Realism in Meetings,” Apr. 2023, Accessed: Feb. 15, 2025. [Online]. Available: https://arxiv.org/abs/2304.01405v2