Integration of deep generative Anomaly Detection algorithm in high-speed industrial line

TL;DR

This work presents a semi-supervised anomaly detection framework based on a generative adversarial architecture with a residual autoencoder and a dense bottleneck, specifically designed for online deployment on a high-speed Blow-Fill-Seal (BFS) line.

Abstract

Industrial visual inspection in pharmaceutical production requires high accuracy under strict constraints on cycle time, hardware footprint, and operational cost. Manual inline inspection is still common, but it is affected by operator variability and limited throughput. Classical rule-based computer vision pipelines are often rigid and difficult to scale to highly variable production scenarios. To address these limitations, we present a semi-supervised anomaly detection framework based on a generative adversarial architecture with a residual autoencoder and a dense bottleneck, specifically designed for online deployment on a high-speed Blow-Fill-Seal (BFS) line. The model is trained only on nominal samples and detects anomalies through reconstruction residuals, providing both classification and spatial localization via heatmaps. The training set contains 2,815,200 grayscale patches. Experiments on a real industrial test kit show high detection performance while satisfying timing constraints compatible with a 500 ms acquisition slot.

Figures (29)

• Figure 1: (a) Original vial-region image $X$. (b) Same image with superimposed Perlin noise $X_n$. (c) Isolated Perlin noise map $N$. (d) Binary mask $M$ of the superimposed region.
• Figure 2: Three residual blocks in the encoder network. Only the last one halve the $(H,W)$ size of the layer
• Figure 3: Three residual blocks in the decoder network. Only the last one double the $(H,W)$ size of the layer
• Figure 4: The product: a BFS strip composed by 5 vials\ref{['foot:nda']}.
• Figure 5: The vial regions\ref{['foot:nda']}: the logic regions in which the vial is divided.