EUVIMEDEUVIMED entdecken
Crossref

Predictive Modeling and Failure Forecasting For AI-Controlled Electrical Systems in Robotics and Autonomous Vehicles

Shamsul Arifeen

Review of Applied Science and Technology · 01.12.2024 · 03 (04) · 367-401

DOI: 10.63125/ycc3n924 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Review of Applied Science and Technology, online erschienen am 01.12.2024. Verfasst von Shamsul Arifeen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study explores the application of predictive modeling and failure forecasting techniques for enhancing the reliability and operational safety of AI-controlled electrical systems in robotics and autonomous vehicles. As these systems rely heavily on interconnected electrical components such as sensors, actuators, battery systems, and embedded controllers, even minor faults can lead to significant performance degradation or safety risks. The research employs a combination of machine learning models, including Random Forest, Support Vector Machines (SVM), and Long Short-Term Memory (LSTM) networks, to analyze both historical and real-time sensor data. Experimental findings demonstrate that the proposed predictive framework achieves a fault detection accuracy of 94.6%, with LSTM-based models outperforming traditional approaches by improving prediction precision by approximately 12.3% in time-series forecasting tasks. Additionally, the model successfully predicts the remaining useful life (RUL) of critical components with a mean absolute error (MAE) of less than 8.7%, enabling more effective maintenance planning. The integration of digital twin simulations further enhances system monitoring by reducing diagnostic latency by 21% and improving anomaly detection rates by 18% compared to conventional threshold-based methods. Results also indicate that implementing edge computing for on-device analytics reduces response time by nearly 35%, which is crucial for real-time decision-making in autonomous environments. Despite these advancements, challenges related to data quality, model interpretability, and cybersecurity vulnerabilities persist, requiring further research and robust system design. Overall, the study highlights that predictive modeling and failure forecasting significantly reduce unexpected system failures by up to 40% and maintenance costs by approximately 25%, demonstrating their critical role in advancing resilient, efficient, and safe AI-driven electrical systems in robotics and autonomous vehicles.

Zitieren

APA

Arifeen, S. (2024). Predictive Modeling and Failure Forecasting For AI-Controlled Electrical Systems in Robotics and Autonomous Vehicles. Review of Applied Science and Technology, 03(04), 367-401. https://doi.org/10.63125/ycc3n924

Vancouver

Arifeen S. Predictive Modeling and Failure Forecasting For AI-Controlled Electrical Systems in Robotics and Autonomous Vehicles. Review of Applied Science and Technology. 2024;03(04):367-401. doi:10.63125/ycc3n924

BibTeX
@article{Arifeen2024,
  author = {Arifeen, Shamsul},
  title = {Predictive Modeling and Failure Forecasting For AI-Controlled Electrical Systems in Robotics and Autonomous Vehicles},
  journal = {Review of Applied Science and Technology},
  year = {2024},
  volume = {03},
  number = {04},
  pages = {367--401},
  doi = {10.63125/ycc3n924}
}
Kostenlos starten →