New study accelerates AI-based particle size probe for medication manufacturing

Non-invasive estimation of particle size distribution has been a long-term desire in pharmaceutical drying, a critical step in producing medication and chemical compounds. To address this challenge, MIT scientists invented a method to accelerate a current particle size probe by 60 times, achieving the fastest non-invasive size monitoring. This high-speed probe is capable of detecting the size evolution in fast dynamical systems, broadening its potential applicability beyond pharmaceutical manufacturing to other industries.

The pharmaceutical manufacturing industry has long struggled with the issue of monitoring the characteristics of a drying mixture, a critical step in the production of medication and chemical compounds. Currently, two non-invasive characterization approaches are typically used: a sample is either imaged and individual particles are counted, or researchers use scattered light to estimate the particle size distribution (PSD). The former is time-intensive and leads to increased waste, making the latter a more attractive option.

In recent years, MIT engineers and researchers have developed a physics and machine-learning-based scattered light approach to improve pharmaceutical manufacturing processes, increasing efficiency and accuracy, and reducing failed batches, according to a new paper published in Light Science and Applications.

“Understanding the behavior of scattered light is one of the most important topics in optics,” says Qihang Zhang PhD ‘23, now an associate researcher at Tsinghua University. “By making progress in analyzing scattered light, we also invented a useful tool for the pharmaceutical industry. Locating the pain point and solving it by investigating the fundamental rule is the most exciting thing to the research team.”

The paper proposes a new PSD estimation method, based on pupil engineering, that reduces the number of frames needed for analysis. “Our learning-based model can estimate the powder size distribution from a single snapshot speckle image, consequently reducing the reconstruction time from 15 seconds to a mere 0.25 seconds,” the researchers explain.

“Our main contribution in this work is accelerating a particle size detection method by 60 times, with a collective optimization of both algorithm and hardware,” says Zhang. “This high-speed probe is capable of detecting the size evolution in fast dynamical systems, providing a platform to study models of processes in the pharmaceutical industry including drying, mixing and blending.”

The technique offers a low-cost non-invasive particle size probe by collecting backscattered light from powder surfaces. The compact and portable prototype is compatible with most drying systems in the market, as long as there is an observation window. This online measurement approach may help control manufacturing processes, improving efficiency and product quality. Further, the previous lack of online monitoring prevented the systematic study of dynamic models in manufacturing processes. This probe could bring a new platform to carry out a series of research and modeling for the particle size evolution.

This work, a successful collaboration between physicists and engineers, is generated from the MIT-Takeda program. Collaborators are affiliated with three MIT departments: Mechanical Engineering, Chemical Engineering, Electrical Engineering, and Computer Science. George Barbastathis, professor of mechanical engineering at MIT, is the article’s senior author.