Abstract :

Industrial Components Are Routinely Subjected To Demanding Operational Conditions, Which Can Result In Defects Such As Corrosion, Cracks, Weld Imperfections, Overheating, And Surface Degradation. Early And Precise Identification Of These Defects Is Crucial For Maintaining Reliability, Ensuring Safety, And Minimizing Maintenance Costs. Traditional Inspection Methods Rely Heavily On Manual Observation, Which Is Not Only Time-consuming But Also Inconsistent And Error-prone, Particularly When Dealing With Large Datasets Or Subtle Defect Patterns. This Study Introduces An Automated Defect Detection System That Leverages Both Deep Learning (DL) And Machine Learning (ML) Techniques To Overcome These Challenges. The Core Of The Proposed Approach Is A Hybrid ConvLogiDefect (CLD) Model That Integrates Convolutional Neural Networks (CNN) With Logistic Regression (LR). The CNN Is Employed To Capture And Learn Complex Visual Features From Industrial Images, While The LR Classifier Efficiently Categorizes These Features Into Specific Defect Classes. To Ensure A Thorough Evaluation, Conventional ML Models Such As K-Nearest Neighbors (KNN) And Decision Tree (DT) Are Also Implemented And Compared Against The Proposed Method. The System Is Designed With A Tkinter-based Graphical User Interface (GUI), Enabling Users To Perform Dataset Upload, Preprocessing, Model Training, And Real-time Predictions In An Intuitive Manner. Additionally, A Secure Authentication Module Is Incorporated To Restrict Access And Protect System Integrity. The Proposed Framework Offers A Reliable, Scalable, And Efficient Solution For Defect Detection, Reducing Dependency On Manual Inspection While Significantly Improving Accuracy, Thereby Supporting Advanced Industrial Automation And Smart Manufacturing Systems

Published:

09-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

2107-2116

Section:

Articles

License:

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

How to Cite