CLAIRE: Compressed Latent Autoencoder for Industrial Representation and Evaluation -- A Deep Learning Framework for Smart Manufacturing

TL;DR

CLAIRE is a deep learning framework that combines unsupervised autoencoder-based feature extraction with supervised classification and interpretability techniques to improve fault detection in high-dimensional industrial data.

Contribution

It introduces a hybrid end-to-end framework integrating autoencoder-based representation learning with explainability for industrial fault detection.

Findings

Outperforms traditional classifiers on high-dimensional datasets

Effectively captures intrinsic data structure and suppresses noise

Provides feature importance analysis using game-theory-based interpretability

Abstract

Accurate fault detection in high-dimensional industrial environments remains a major challenge due to the inherent complexity, noise, and redundancy in sensor data. This paper introduces CLAIRE, i.e., a hybrid end-to-end learning framework that integrates unsupervised deep representation learning with supervised classification for intelligent quality control in smart manufacturing systems. It employs an optimized deep autoencoder to transform raw input into a compact latent space, effectively capturing the intrinsic data structure while suppressing irrelevant or noisy features. The learned representations are then fed into a downstream classifier to perform binary fault prediction. Experimental results on a high-dimensional dataset demonstrate that CLAIRE significantly outperforms conventional classifiers trained directly on raw features. Moreover, the framework incorporates a post hoc phase, using a game-theory-based interpretability technique, to analyze the latent space and identify the most informative input features contributing to fault predictions. The proposed framework highlights the potential of integrating explainable AI with feature-aware regularization for robust fault detection. The modular and interpretable nature of the proposed framework makes it highly adaptable, offering promising applications in other domains characterized by complex, high-dimensional data, such as healthcare, finance, and environmental monitoring.