http://ir.lib.ruh.ac.lk/handle/iruor/7484 2026-05-12T14:34:07Z 2026-05-12T14:34:07Z Batuwatta-Gamage, C.P. Rathnayaka, C.M. Karunasena, H.C.P. Jeong, H. Wijerathne, W.D.C.C. Karim, M.A. Welsh, Z.G. Gu, Y.T. http://ir.lib.ruh.ac.lk/handle/iruor/9283 2024-10-24T06:31:16Z 2022-01-01T00:00:00Z

A physics-informed neural network-based surrogate framework to predict moisture concentration and shrinkage of a plant cell during drying Batuwatta-Gamage, C.P.; Rathnayaka, C.M.; Karunasena, H.C.P.; Jeong, H.; Wijerathne, W.D.C.C.; Karim, M.A.; Welsh, Z.G.; Gu, Y.T. This paper presents a Physics-Informed Neural Network-based (PINN-based) surrogate framework, which can couple time-based moisture concentration and moisture-content-based shrinkage of a plant cell during drying. For this, a set of differential equations are coupled to two distinct multilayer feedforward neural networks: (a) PINN-MC to predict Moisture Concentration (MC) with Fick's law of diffusion; and (b) PINN-S to predict Shrinkage (S) with ‘free shrinkage’ hypothesis. Results indicate that compared to a regular deep neural network (DNN), the PINN-MC with fundamental physics guidance produces 53% and 81% accuracy values when unknown data has the lowest five timesteps and the lowest 27 data points, respectively. Moreover, its accuracy is 80% better when predicting any unknown spatiotemporal domain variations. PINN-MC further demonstrates stable and accurate MC predictions irrespective of drying process parameters and microstructural variations. In addition, the PINN-S separately proves that utilising a derived relationship based on the ‘free shrinkage’ hypothesis can improve shrinkage predictions into a realistic behaviour. Also, the PINN-based surrogate framework combines multiple physics for predicting moisture concentration and shrinkage, reassuring its capability as a powerful tool for investigating complicated drying mechanisms. Accordingly, to the best of the authors' knowledge, this surrogate framework is the first of its kind in food engineering applications.

2022-01-01T00:00:00Z Rathnayaka , C.M. Karunasena, H.C.P. Gu, Y.T. Guan, L. Senadeera, W. http://ir.lib.ruh.ac.lk/handle/iruor/9101 2024-11-01T09:36:43Z 2018-01-01T00:00:00Z

Three-dimensional (3-d) numerical modelling of morphogenesis of dehydrated fruits and vegetables Rathnayaka , C.M.; Karunasena, H.C.P.; Gu, Y.T.; Guan, L.; Senadeera, W. Food drying is one of the key techniques of preserving fruits and vegetables. Grid-based methods and meshfree methods are the two most viable techniques applicable for numerical modeling of food structures during drying. This chapter assesses various attempts made to numerically model plant cells and tissues during drying, along with subsequent phenomena. It evaluates the accuracy, versatility, and the potential influence toward the enhancement of the drying operation performance both in the current context and future. The chapter also discusses the information about different numerical modeling techniques and a recent application of meshfree methods for modeling plant cellular structures. It provides the development of a novel Three-Dimensional (3D) single plant cell drying model using a Smoothed Particle Hydrodynamics-coarse-grained (SPH-CG) numerical approach. The vertex tissue model investigates the relationship between water transport characteristics and the structural deformations observed in plant cellular structure under slow dehydration, which usually happens during the general storage conditions.

2018-01-01T00:00:00Z Karunasena, H.C.P. Senadeera, W. http://ir.lib.ruh.ac.lk/handle/iruor/9099 2024-10-24T06:31:00Z 2016-01-01T00:00:00Z

Numerical modelling of morphological changes of food plant materials during drying Karunasena, H.C.P.; Senadeera, W. Food plant materials, particularly fruits and vegetables, when undergoing drying are subjected to higher levels of morphological changes, leading to alteration of various physical properties characterizing the dried food product. The main factors driving such morphological changes are the moisture content, drying temperature, atmospheric conditions, rate of moisture removal, and properties of the food plant variety. Prediction of such morphological changes is critical for improving the product quality and processing efficiency in food engineering. In that context, different modeling techniques are being researched, each having its own pros and cons depending on the fundamental nature of the technique and its level of advancement achieved, targeting a given application. Among these modeling techniques, numerical modeling has gained considerable attention since the recent past, and which holds true for the present too. In this background, this chapter initially presents an overview of the different modeling techniques used in the field, and then it specifically presents a novel numerical modeling technique available its key applications, limitations, and future prospects.

2016-01-01T00:00:00Z