ISOC 2026 – AI Spray Monitoring of Slurry Spray Droplets

At ISOC 2026 in Kyoto, Japan, we present a new method for AI spray monitoring of coal particles inside droplets of a slurry spray. The method combines optical spray measurement, continuous light scattering signals, and ParticleTensorAI®. As a result, it can analyze particle-loaded droplets in complex spray processes.

A slurry spray is a challenging multiphase system. It contains liquid droplets and solid particles. Both components influence the optical signal, spray behavior, and process stability. Therefore, classical droplet measurement alone often does not provide enough information.

For this reason, AI spray monitoring offers an important advantage. It can extract additional material information from complex light scattering signals. In addition, it supports real-time analysis of particle-loaded sprays.

ParticleTensorAI® converts continuous detector signals into tensor-based data formats. In this study, the detector signals form image-like representations. For example, different detector channels can create RGB images. Each color channel then represents one optical signal stream.

These ParticleTensorAI® representations contain information about coal particle size and mass concentration inside slurry spray droplets. Convolutional neural networks analyze this data. After that, the AI model classifies different material conditions.

The measurement system records continuous light scattering signals from droplets. These droplets pass through a shaped light beam. Four optical detectors collect scattered light at different angles.

As a result, the system creates synchronized signal streams. These signals describe the droplet flow and particle-related properties. In this way, AI spray monitoring extends classical optical spray diagnostics.

The method also supports trigger-free evaluation of light scattering data. Therefore, it keeps more information from the continuous signal stream than many classical approaches.

This method creates new possibilities for slurry spray monitoring, particle characterization, spray measurement technology, and industrial process diagnostics. Although the study focuses on coal monoethylene glycol slurry spray, the concept can also support other particle-loaded liquid sprays.

The work shows how optical measurement technology and artificial intelligence can work together. Moreover, it demonstrates how ParticleTensorAI® can extract process-relevant information from complex light scattering signals in real time.

Abstract: We present a novel method for characterizing the average size and mass concentration of coal particles within droplets in a coal monoethylene glycol slurry spray. The method is based on the analysis of continuous light scattering signals from individual droplets interacting with a shaped light beam. The experimental setup employs four detectors that collect scattered light at different angles, generating four distinct data streams corresponding to the droplet flow. These signals are transformed into Particle-Tensor-AI (PTA) representations, which can be constructed in various formats. In this work, we implement a format in which detector signals are mapped into RGB images, with each color channel representing a specific detector. The PTAs, labeled with the average coal particle size and mass concentration, are used to train convolutional neural networks (CNNs) for classification tasks. Various detector combinations, downsampling strategies, and material conditions were investigated. Validation experiments demonstrated proof-of-principle feasibility, achieving prediction accuracies up to 95%. This approach enables trigger-free, information-preserving analysis of light scattering data, offering strong potential for advanced diagnostics not only in coal monoethylene glycol sprays but also in other droplet and particle flows.