用生成模型实现高速药厂产线缺陷检测，仅需正常样本训练
Integration of deep generative Anomaly Detection algorithm in high-speed industrial line
- 基于残差自编码器与密集瓶颈的生成对抗框架
- 280万张正常图像训练，500毫秒内完成检测
- 可定位异常位置，适合高精度工业质检场景
制药生产线的工业视觉检测要求在严格的节拍时间、硬件尺寸和运行成本约束下保持高精度。人工在线检测仍普遍存在，但受操作员差异性和吞吐量限制。传统规则式计算机视觉流程往往僵化，难以适应高度多变的生产环境。为此，我们提出一种基于生成对抗架构的半监督异常检测框架，采用残差自编码器与密集瓶颈结构，专为高速吹灌封（BFS）产线在线部署设计。模型仅使用正常样本进行训练，通过重建残差实现异常分类与空间定位（热图输出）。训练集包含2,815,200张灰度图像块。真实工业测试数据表明，该方法在满足500毫秒采集周期的前提下，实现了优异的检测性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。