用合成图像训练CNN，实现工业级颗粒尺寸分布实时测量。
Instant Particle Size Distribution Measurement Using CNNs Trained on Synthetic Data
- 用Blender生成逼真合成颗粒图像，模拟真实工业场景
- EfficientNet-B0模型在预测d10/d50/d90时精度高且推理快
- 适合需要实时颗粒检测的矿山、制药等工业场景
精确的颗粒尺寸分布（PSD）测量在采矿、制药和化肥制造等行业至关重要，直接影响产品质量与运行效率。传统方法如筛分和激光衍射存在人工操作、耗时长、颗粒重叠限制等问题。近年来，卷积神经网络（CNN）使直接从颗粒图像中实现自动化、实时的PSD估计成为可能。本文提出一种基于CNN的方法，使用Blender的高级渲染功能生成逼真的合成颗粒图像数据集。该方法可通过系统调节颗粒形状、纹理、光照和空间排列，复现多种工业场景。我们评估了三种CNN架构：ResNet-50、InceptionV3和EfficientNet-B0，用于预测关键PSD参数d10、d50、d90。结果表明各模型精度相当，其中EfficientNet-B0在计算效率上表现最优，适用于实时工业部署。该方法验证了真实合成数据在构建鲁棒CNN模型方面的有效性，为自动化工业PSD监控提供了巨大潜力。代码已公开于：https://github.com/YasserElj/Synthetic-Granular-Gen
原文摘要 · Abstract (English)
Accurate particle size distribution (PSD) measurement is important in industries such as mining, pharmaceuticals, and fertilizer manufacturing, significantly influencing product quality and operational efficiency. Traditional PSD methods like sieve analysis and laser diffraction are manual, time-consuming, and limited by particle overlap. Recent developments in convolutional neural networks (CNNs) enable automated, real-time PSD estimation directly from particle images. In this work, we present a CNN-based methodology trained on realistic synthetic particle imagery generated using Blender's advanced rendering capabilities. Synthetic data sets using this method can replicate various industrial scenarios by systematically varying particle shapes, textures, lighting, and spatial arrangements that closely resemble the actual configurations. We evaluated three CNN-based architectures, ResNet-50, InceptionV3, and EfficientNet-B0, for predicting critical PSD parameters (d10, d50, d90). Results demonstrated comparable accuracy across models, with EfficientNet-B0 achieving the best computational efficiency suitable for real-time industrial deployment. This approach shows the effectiveness of realistic synthetic data for robust CNN training, which offers significant potential for automated industrial PSD monitoring. The code is released at : https://github.com/YasserElj/Synthetic-Granular-Gen
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。