Transfer of a nanoparticle product between different mixers using latent variable model inversion

Abstract

An experimental nanoparticle preparation process by solvent displacement in passive mixers is considered. The problem under investigation is to estimate the operating conditions in a target device (Mixer B) in order to obtain a product of assigned properties that has already been manufactured in a source device of different geometry (Mixer A). A large historical database is available for Mixer A, whereas a limited historical database is available for Mixer B. The difference in device geometries causes a different mixing performance within the devices, which is very difficult to capture using mechanistic models. The problem is further complicated by the fact that Mixer B can only be run under an experimental setup that is different from the one under which the available historical dataset was obtained. A joint-Y projection to latent structures (JY-PLS) model inversion approach is used to transfer the nanoparticle product from Mixer A to Mixer B. The Mixer B operating conditions estimated by the model are tested experimentally and confirm the model predictions within the experimental uncertainty. Since the inversion of the JY-PLS model generates an infinite number of solutions that all lie in the so-called null space, experiments are carried out to provide (to the authors’ knowledge) the first experimental validation of the theoretical concept of null space. Finally, by interpreting the JY-PLS model parameters from first principles, the understanding of the system physics is improved

Advanced Process Decision Making Using Multivariate Latent Variable Methods

“…In the pharmaceutical industries, the use of LVMbased (feedforward) controllers was pioneered by García-Muñoz et al [51]. The authors designed four controllers for a high shear [63] wet granulation process: a pure feedforward controller based on the raw materials properties (the particle size distribution of the initial dry blend), and three mid-course correction controllers that adjusted the water addition rate and the impeller speed at a given decision point (1/3 of the way through the water addition step). The difference among the three mid-course correction controllers was the set of measurements used as inputs to evaluate the control moves: (1) temperature and power consumption profiles up to the decision point; (2) NIR spectra collected up to the decision points; (3) temperature and power consumption profiles and NIR spectra together.…”

“…Tomba et al [63] investigated the problem of transferring the production of polymer nanoparticles (to be used as drug carriers for controlled drug delivery) by solvent displacement in passive mixers between two devices of different size. The problem was complicated by the fact that the target device could only be run under a setup that was different from that under which the available historical dataset had been obtained.…”

A Federated Classification Approach of Waste Lubricant Oils in Geographically Distributed Laboratories

“…In this context, efforts were devoted to the development of analytical solutions that allow to move the knowledge acquired from one site or data source to another where our interest is focused, such as in the activities of scale-up, product transfer, and process monitoring. , A variety of model transfer approaches were developed for handling specifically spectroscopic data. − Techniques such as partial least-squares (PLS) model inversion, Joint-Y PLS, calibration/model transfer, ,, and, more recently, transfer learning ,,, and domain adaptation offer different paths to achieve the aforementioned goals. These methods address partially the aforementioned challenge of connecting multiple sites, but their objective is not to provide a global management platform but instead a way to transfer existing knowledge to a new context of interest.…”

Handling Variables, via Inversion of Partial Least Squares Models for Class-Modelling, to Bring Defective Items to Non-Defective Ones

“…(Ruiz et al, 2018), similar to the one in Lakshminarayanan et al (Lakshminarayanan et al, 2000) but for inverting PLS2 models. The use of PLS model inversion for product formulation is also noteworthy, especially in the context of Process Analytical Technology with pharmaceutical processes (Tomba et al, 2014;Bano et al, 2017;Palací-López et al, 2019).…”