---
title: "IIT Bombay develops predictive models for sintering-induced shrinkage"
url: https://www.voxelmatters.com/iit-bombay-develops-predictive-models-for-sintering-induced-shrinkage/
date: 2026-02-23
modified: 2026-02-23
lang: en
author: "Joseph Caron-Dawe"
description: "Researchers at the Indian Institute of Technology (IIT) Bombay have developed predictive models that are capable of calculating sintering-induced shrinkage and deformation in 3D printed components, before manufacturing begins. The..."
categories:
  - "AM Research"
  - "Ceramic Additive Manufacturing"
  - "Ceramics"
  - "Materials"
  - "Metals"
tags:
  - "insights"
image: https://www.voxelmatters.com/wp-content/uploads/2026/02/Shrinkage-01-640x400.jpg
word_count: 421
---

# IIT Bombay develops predictive models for sintering-induced shrinkage

Researchers at the Indian Institute of Technology (IIT) Bombay have developed predictive models that are capable of calculating [sintering-induced shrinkage and deformation in 3D printed components](https://www.voxelmatters.com/ntu-researchers-develop-high-precision-ceramic-3d-printing-solution/), before manufacturing begins.

The work, led by Professor Gurminder Singh of the Department of Mechanical Engineering, and published across two studies covering ceramics and copper, focused on oven-sintered additive manufacturing.

One of the drawbacks of the process is the [shrinkage that leads to significant dimensional changes of printed parts during heat treatment](https://www.voxelmatters.com/hydrogel-photopolymerization-method-yields-low-shrinkage-ceramic-and-metal-3d-structures/). The studies showed that final part geometry can be determined at the design stage, rather than through iterative physical testing, a finding that could have many positive implications.

![Researchers at the Indian Institute of Technology (IIT) Bombay have developed predictive models that are capable of calculating sintering-induced shrinkage and deformation in 3D printed components, before manufacturing begins.](https://www.voxelmatters.com/wp-content/uploads/2026/02/Shrinkage-02-340x183.jpg)

In the ceramics study (full study [here](https://www.sciencedirect.com/science/article/abs/pii/S1526612525011776)), researchers Pranith Kumar Reddy Puchakayla and Professor Prasanna Gandhi worked with Singh using 3 mol% yttria-stabilised zirconia (3-YSZ), modelling the material as a viscous fluid during heating. 

The team measured density and viscosity changes across temperature intervals, which fed a simulation validated against three geometries: a cylinder, an I-section, and a branched “pine tree” structure. The model predicted final dimensions with an error range of just 0.8% to 2.03%.

“Viscosity governs the behavior during printing and indicates how easily the material flows, how well the layers stack, and how much internal stress is stored in the printed part,” stated Singh.

“Relative density, on the other hand, governs behaviour before sintering and indicates how much solid material is present and how much pore volume exists. Lower density before sintering means higher shrinkage and deformation.

“The weight load is applied to simulate real mechanical loading conditions. Without the weight, only pure thermal shrinkage is observed. With the weight, thermo-mechanical deformation is captured, which is much closer to the behaviour of real industrial parts.”

In the copper study (published [here](https://www.sciencedirect.com/science/article/abs/pii/S1359645425005129)), researcher Sri Bharani Ghantasala and Singh developed a hybrid model for copper.

They trained an artificial neural network (ANN) on experimental and computer-generated data across eight sintering experiments, with seven input variables. Using SHAP (SHapley Additive exPlanations) analysis, the team identified process time and heating rates as the dominant factors that influence final part geometry.

The hybrid model matched experimental results with a 98% success rate, and outperformed traditional computer models when predicting the final shape on complex overhanging geometries.

“This shifts the field from trial-and-error sintering toward predictive, model-based manufacturing, which represents a major paradigm change in advanced additive manufacturing science,” commented Singh.

“This type of framework can eventually lead to smart CAD tools where predicted shrinkage fields are automatically applied to the design, and pre-compensated geometries are generated directly.”