Abstract :

Industrial Components Are Frequently Exposed To Harsh Operational Environments, Leading To Defects Such As Corrosion, Cracks, Weld Failures, Overheating, And Paint Degradation. Timely And Accurate Detection Of These Defects Is Essential For Maintaining Product Quality, Ensuring Safety, And Preventing Unexpected Failures. Traditional Inspection Methods Rely On Manual Visual Assessment, Which Is Timeconsuming, Subjective, And Prone To Inconsistencies, Especially When Handling Large-scale Data Or Subtle Defect Patterns. This Research Proposes An Intelligent Automated Defect Detection System Integrating Deep Learning (DL) And Machine Learning (ML) Techniques. These Representations Are Processed Through A Hybrid ConvLogiDefect Model Combining Convolutional Neural Networks (CNN) And Logistic Regression (LR), Where CNN Is Used To Extract Meaningful Visual Patterns From Industrial Images, And LR Performs The Final Classification To Produce Accurate And Efficient Defect Predictions. In Addition, Traditional ML Models Such As K-Nearest Neighbors (KNN) And Decision Tree (DT) Are Implemented For Comparative Performance Analysis, Ensuring A Comprehensive Evaluation Of The Proposed Approach. The System Is Developed With A Tkinter-based Graphical User Interface (GUI) That Supports Dataset Upload, Preprocessing, Model Training, And Real-time Prediction. A Secure Databasedriven Authentication Mechanism Is Incorporated For Controlled Access. The Proposed System Achieves Fast, Consistent, And Scalable Defect Detection, Significantly Reducing Manual Effort While Improving Accuracy, Making It Suitable For Modern Industrial Automation And Smart Manufacturing Environments.

Published:

22-4-1-2026

Issue:

Vol. 26 No. 4-1 (2026)

Page Nos:

763-772

Section:

Articles

License:

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

How to Cite