Abstract :

The Industrial Internet Of Things (IIoT) Has Transformed Modern Manufacturing By Enabling Continuous Monitoring Of Industrial Equipment Through Interconnected Sensors. However, Accurately Detecting Anomalies And Predicting Equipment Failures In Real Time Remains Challenging Due To The Complexity And High Volume Of Sensor Data. Traditional Machine Learning Methods Often Rely On Manual Feature Engineering And Are Less Effective In Capturing Complex Patterns Within Industrial Environments. This Paper Proposes A Deep Learning-Based Multi-Scale Feature Fusion (DL-MSFF) Framework For Real-time Anomaly Detection And Predictive Maintenance In Industrial IoT Networks. The Framework Employs Multi-scale Feature Extraction And Feature Fusion Techniques To Capture Both Local And Global Characteristics Of Sensor Data, Enabling Accurate Anomaly Detection And Early Fault Prediction. The Proposed Approach Aims To Improve Equipment Reliability, Reduce Unplanned Downtime, And Optimize Maintenance Scheduling. The Framework Is Evaluated Using Standard Performance Metrics, Including Accuracy, Precision, Recall, F1-score, And Inference Time. The Results Demonstrate That The Proposed Framework Provides Reliable Anomaly Detection With Low Computational Overhead, Making It Suitable For Real-time Predictive Maintenance Applications In Smart Manufacturing And Industry 4.0 Environments.

Published:

22-8-2024

Issue:

Vol. 24 No. 8 (2024)

Page Nos:

166-176

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite