---
title: Download ADT Publication | Machine Learning Based Optimization of a LH2 Turbopump with Combined Inducer Impeller
description: See how ML-based optimisation of a combined inducer-impeller LH2 turbopump delivers 18% NPSHr reduction and improved efficiency across the full operating range
---

Free Publication

# ADT Publication - Machine Learning Based Optimization of a LH2 Turbopump with Combined Inducer Impeller

Written by M. Mahdi Ghorani, Melvin Joseph and Prof. Mehrdad Zangeneh

## **What's inside?**

A multi-objective, multi-point optimisation framework was applied to a novel combined inducer-impeller LH2 turbopump using TURBOdesign1's machine learning-based RRS with CAE module. Trained on a small dataset, the system improved stage efficiency across 0.85–1.15 Qd, significantly enhanced cavitation resistance, and met head requirements, outperforming the conventional separate inducer-impeller configuration.

 

 

> An 18% reduction in NPSHr, achieved not by redesigning from scratch, but by optimising blade loading and throat area using a machine learning model trained on fewer than 80 CFD simulations.

![ASME-2026---LH2-Turbopump Paper](https://info.adtechnology.com/hs-fs/hubfs/Collateral%20Planning/Publications/Machine%20Learning%20%20Based%20Optimization%20of%20a%20LH2%20Turbopump%20with%20Combined%20Inducer%20Impeller/ASME-2026---LH2-Turbopump%20Paper.jpg?width=450&height=315&name=ASME-2026---LH2-Turbopump%20Paper.jpg)

 

### In this publication, you will:

1. **Discover** how combining inducer and impeller blades into a single compact configuration can match, and in some conditions exceed, the efficiency of a conventional separate design
2. **Learn** how a Kriging-based Machine Learning system, trained on fewer than 80 CFD simulations, simultaneously optimises efficiency across multiple operating points and enhances cavitation resistance.
3. **See **how targeted blade loading and throat area modifications deliver an 18% reduction in NPSHr, without compromising head performance or best efficiency point location.

![download](https://info.adtechnology.com/hubfs/ADT%20Live%20Asset%20-%20Hub/images/adt-image.svg)

**[Discover the Technology](https://www.adtechnology.com/technology?hsLang=en) | [Find Your Application](https://www.adtechnology.com/technology/applications?hsLang=en) | [Knowledge Hub](https://www.adtechnology.com/knowledge-hub?hsLang=en) | [Our Offerings](https://www.adtechnology.com/technology/turbodesign-suite?hsLang=en)**

**[Terms & Conditions](https://www.adtechnology.com/terms-and-conditions?hsLang=en) | [Privacy Policy](https://www.adtechnology.com/privacy-policy?hsLang=en)**

1998-2026 Advanced Design Technology Ltd