Hybrid Quantum-Classical AI for Industrial Defect Classification in Welding Images

2026-03-30

AI Summary

This work addresses the task of defect classification in industrial welding images by proposing two hybrid quantum-classical approaches: a quantum kernel-based classifier and a variational quantum circuit model. The methodology first employs a convolutional neural network to extract image features, which are subsequently processed using parameterized quantum feature maps, angle encoding, and a variational quantum linear solver for classification. Notably, this study introduces, for the first time in industrial quality inspection, an analysis of quantum kernel condition numbers. The proposed methods are evaluated on a real-world welding dataset, demonstrating competitive performance against classical CNNs in both binary and multiclass classification tasks. Experimental results indicate that the hybrid models achieve comparable accuracy to their classical counterparts, highlighting their potential for near-term practical deployment.

Abstract

Hybrid quantum-classical machine learning offers a promising direction for advancing automated quality control in industrial settings. In this study, we investigate two hybrid quantum-classical approaches for classifying defects in aluminium TIG welding images and benchmarking their performance against a conventional deep learning model. A convolutional neural network is used to extract compact and informative feature vectors from weld images, effectively reducing the higher-dimensional pixel space to a lower-dimensional feature space. Our first quantum approach encodes these features into quantum states using a parameterized quantum feature map composed of rotation and entangling gates. We compute a quantum kernel matrix from the inner products of these states, defining a linear system in a higher-dimensional Hilbert space corresponding to the support vector machine (SVM) optimization problem and solving it using a Variational Quantum Linear Solver (VQLS). We also examine the effect of the quantum kernel condition number on classification performance. In our second method, we apply angle encoding to the extracted features in a variational quantum circuit and use a classical optimizer for model training. Both quantum models are tested on binary and multiclass classification tasks and the performance is compared with the classical CNN model. Our results show that while the CNN model demonstrates robust performance, hybrid quantum-classical models perform competitively. This highlights the potential of hybrid quantum-classical approaches for near-term real-world applications in industrial defect detection and quality assurance.

Problem

• industrial defect classification
• welding images
• hybrid quantum-classical AI
• quality control
• defect detection

Innovation

• hybrid quantum-classical
• quantum kernel
• variational quantum circuit
• defect classification
• welding image analysis