Bioinspired Generative Design of Multi-Stage Axial Compressors (September 2026).

This paper was presented by Zhenyuan Qin at the 42nd International Manufacturing Conference (IMC42), co-organized by the Irish Manufacturing Council and Queen’s University Belfast, which was held on 10 and 11 September 2026 in Belfast, Northern Ireland. The plenary sessions of the conference occurred on the 10th September at the Advanced Manufacturing Innovation Centre (AMIC), Global Point, Newtownabbey, followed by technical sessions and a tour of AMIC facilities in the afternoon.

Abstract
The engineering design of multi-stage axial compressors conventionally relies on stage-by-stage parameter tuning, resulting in a time-consuming process with limited exploration of the design space. This paper extends a bio-inspired EvoDevo framework to this domain. It uses a cell concept as a parameter container that stores the design variables of a rotor or stator, showing promise for an efficient automated design process. The cell here represents functional rather than structural components. A Gene Regulatory Network reads the cell state computed by a 1D meanline solver and generates updates to design parameters, while an outer NSGA-II loop maximises the total pressure ratio and polytropic efficiency. Starting from a one-stage seedling, the proposed framework automatically grows the design until the target total pressure ratio is achieved, yielding a Pareto front of physically consistent multi-stage axial compressor designs.

The link to the full paper will be provided in due course.