Enhancing Industrial Equipment Reliability Through an Optimized ANN-Powered Predictive Maintenance System DOI
Hiren Mewada, Nirav Bhatt, Nikita Bhatt

et al.

Advances in chemical and materials engineering book series, Journal Year: 2025, Volume and Issue: unknown, P. 383 - 404

Published: Feb. 5, 2025

Maintaining industrial equipment ensures efficiency, reduces downtime, and prevents costly failures. Routine inspections or equipment's reactive response breakdowns may not be efficient it can cause unexpected This chapter presents an automated framework for predictive maintenance using ANN. The independent parameters including air temperature, torque, rotational speed tool wear are used to estimate the failure of equipment. proposed ANN network is initially optimized by tuning its hyperparameters i.e. hidden layers, learning rate regularization parameter. Later validated quantitative accuracy, precision, recall F1-score. succeeded with 98% accuracy in prediction. real-time improve reliability reduction cost boost efficiency. customized integrated a management system further meet demand various prevent shutdown machinery.

Language: Английский

Enhancing Industrial Equipment Reliability Through an Optimized ANN-Powered Predictive Maintenance System DOI
Hiren Mewada, Nirav Bhatt, Nikita Bhatt

et al.

Advances in chemical and materials engineering book series, Journal Year: 2025, Volume and Issue: unknown, P. 383 - 404

Published: Feb. 5, 2025

Maintaining industrial equipment ensures efficiency, reduces downtime, and prevents costly failures. Routine inspections or equipment's reactive response breakdowns may not be efficient it can cause unexpected This chapter presents an automated framework for predictive maintenance using ANN. The independent parameters including air temperature, torque, rotational speed tool wear are used to estimate the failure of equipment. proposed ANN network is initially optimized by tuning its hyperparameters i.e. hidden layers, learning rate regularization parameter. Later validated quantitative accuracy, precision, recall F1-score. succeeded with 98% accuracy in prediction. real-time improve reliability reduction cost boost efficiency. customized integrated a management system further meet demand various prevent shutdown machinery.

Language: Английский

Citations

0