A Multimodal IoT Sensing System With Hybrid LSTM–CNN Model for Predictive Fault Diagnosis in Elevators
IEEE Sensors Journal · 15.10.2025 · 25 (20) · 38829-38836
DOI: 10.1109/jsen.2025.3606488 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.10.2025. Verfasst von Jiayu Luo und 7 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: Beijing Science and Technology Project, Guangdong Guangri Elevator Industry Company Ltd.
Abstract (Originalsprache)
This article presents a multimodal Internet of Things (IoT)-enabled sensing system integrated with a hybrid deep learning framework for predictive fault diagnosis in elevator systems. The proposed system incorporates a compact sensor node that combines triaxial accelerometers, gyroscopes, temperature, humidity, and microwave radar modules, all managed by an STM32 microcontroller and ESP8266 wireless unit. These modules enable real-time acquisition and cloud-based transmission of operational and environmental data from elevators. To enable accurate fault classification, a dual-branch neural network is developed, combining long short-term memory (LSTM) and convolutional neural network (CNN) architectures. The LSTM module captures temporal dependencies in time-series data, while the CNN module extracts local features from frequency-domain representations. Experimental validation under three operational scenarios—normal operation, guide shoe wear, and sensor-induced start-up anomalies—demonstrates that the hybrid model achieves a classification accuracy of 99.88%, outperforming traditional machine learning (ML) methods and single-model baselines. This work offers a scalable and efficient framework for real-time monitoring and predictive maintenance of vertical transportation systems, with broader applicability to industrial equipment health monitoring.
Förderung
- Beijing Science and Technology Project
- Guangdong Guangri Elevator Industry Company Ltd
Zitieren
APA
Luo, J., Guo, Y., Huo, P., Liu, S., Huang, S., Dai, Q., Zeng, M., & Li, Q. (2025). A Multimodal IoT Sensing System With Hybrid LSTM–CNN Model for Predictive Fault Diagnosis in Elevators. IEEE Sensors Journal, 25(20), 38829-38836. https://doi.org/10.1109/jsen.2025.3606488
Vancouver
Luo J, Guo Y, Huo P, Liu S, Huang S, Dai Q, et al. A Multimodal IoT Sensing System With Hybrid LSTM–CNN Model for Predictive Fault Diagnosis in Elevators. IEEE Sensors Journal. 2025;25(20):38829-38836. doi:10.1109/jsen.2025.3606488
BibTeX
@article{Luo2025,
author = {Luo, Jiayu and Guo, Yusen and Huo, Pengyu and Liu, Sican and Huang, Sisi and Dai, Qingyou and Zeng, Min and Li, Qiliang},
title = {A Multimodal IoT Sensing System With Hybrid LSTM–CNN Model for Predictive Fault Diagnosis in Elevators},
journal = {IEEE Sensors Journal},
year = {2025},
volume = {25},
number = {20},
pages = {38829--38836},
doi = {10.1109/jsen.2025.3606488}
}
EUVIMED