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

arXiv cs.CV / 4/1/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper studies two hybrid quantum-classical machine learning methods to classify defects in aluminum TIG welding images, aiming to improve automated industrial quality control.
A CNN is first used to compress weld images into compact feature vectors that are then fed into quantum components via two distinct encoding/training strategies.
In one approach, a parameterized quantum feature map produces quantum states, a quantum kernel matrix is computed from state inner products, and an SVM optimization is solved using a Variational Quantum Linear Solver (VQLS).
In the second approach, angle encoding feeds features into a variational quantum circuit trained with a classical optimizer, and the study compares both quantum methods on binary and multiclass tasks.
Results indicate the classical CNN remains robust, while hybrid quantum-classical models achieve competitive performance, suggesting potential for near-term quantum-assisted defect detection despite current limitations.

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.