Instant Particle Size Distribution Measurement Using CNNs Trained on Synthetic Data

2025-07-01

AI Summary

Traditional particle size distribution (PSD) measurement methods—such as sieving and laser diffraction—are inefficient, susceptible to particle overlap artifacts, and challenging to deploy online in industrial settings. To address these limitations, this paper proposes a synthetic-image-driven convolutional neural network (CNN) framework for real-time PSD prediction. We innovatively leverage Blender to generate high-fidelity, multi-scenario synthetic particle images, thereby circumventing the need for large-scale manually annotated real-world datasets. The method integrates ResNet-50, InceptionV3, and EfficientNet-B0 architectures, enhanced by synthetic data augmentation and transfer learning. Experimental evaluation demonstrates that EfficientNet-B0 achieves superior prediction accuracy on key PSD metrics (d₁₀, d₅₀, d₉₀) while meeting industrial real-time constraints. The source code is publicly released, establishing a scalable, automated paradigm for online particle characterization.

Technology Category

• Machine Learning: Hardware-aware ML
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Computer Vision: Computational Photography, Image & Video Synthesis

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

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

Problem

• Automate particle size distribution measurement using CNNs
• Overcome limitations of manual and time-consuming traditional methods
• Train CNNs on synthetic data for real-time industrial deployment

Innovation

• CNNs trained on synthetic particle imagery
• Blender-generated realistic industrial scenarios
• EfficientNet-B0 for real-time PSD prediction