Intelligent wireless control system for crystallization using Ultrasound Tomographic Imaging and Deep Reinforcement Learning
- 28 April 2026
- journal article
- Published by Wydawnictwo SIGMA-NOT, sp. z.o.o. in PRZEGLĄD ELEKTROTECHNICZNY
- Vol. 1 (4) , 31-35
Abstract
This study presents a wireless edge-intelligent control framework for crystallization processes that integrates ultrasound tomography (UST) with deep reinforcement learning (DRL). Ultrasound tomography delivers non-invasive in-situ images of opaque media which makes it possible to observe precipitation fronts and spatial heterogeneity directly. A dedicated measurement platform acquires raw signals reconstructs images compresses salient tomographic features and forwards them to an edge controller for real-time inference. The reconstructed images serve as the state for a Proximal Policy Optimization agent that autonomously modulates cooling dosing and stirring to shorten cycle time while safeguarding product morphology. Simulation results indicate fast policy convergence and more than a twenty percent reduction in average crystallization time relative to baseline controllers. The principal contribution is the use of tomographic images as the decision substrate which elevates tomography from purely diagnostic use to a core component of closed-loop control. A wireless and modular architecture underscores suitability for Industry 4.0 settings and points toward adaptive image-driveKeywords
This publication has 8 references indexed in Scilit:
- Improving the reliability of industrial reactors by using differential neural network architecture in ultrasonic tomographyEksploatacja i Niezawodność – Maintenance and Reliability, 2025
- Assessment of changes in vitamin content and morphological characteristics in strawberries modified with a pulsed electric field using chromatography and optical coherence tomographyNFS Journal, 2025
- Application of machine learning in electrical process tomography with variable frequency measurement sequencesMeasurement, 2025
- A Deep Reinforcement Learning Algorithm for Robotic Manipulation Tasks in Simulated EnvironmentsEngineering Proceedings, 2023
- Prediction of textile pilling resistance using optical coherence tomographyScientific Reports, 2022
- Real-Time Fault Detection and Diagnosis of CaCO3 Reactive Crystallization Process by Electrical Resistance Tomography MeasurementsSensors, 2021
- Ultrasonic Time-of-Flight Computed Tomography for Investigation of Batch Crystallisation ProcessesSensors, 2021
- Process Monitoring of Antisolvent Based Crystallization in Low Conductivity Solutions Using Electrical Impedance Spectroscopy and 2-D Electrical Resistance TomographyApplied Sciences, 2020