Design to Acoustics Through Deep Learning

Prof. Dr.-Ing. Sabine C. Langer (Braunschweig)
Dr. Timo Lüddecke (Göttingen)

Motivation / Background

  • Design assistants are desirable in many areas of engineering
  • Large vibroacoustic models (e.g. aircraft):
    • Numerical methods are the standard approach (e.g. finite element models)
    • Extensive parameter samplings are computationally expensive and hardly possible to consider during early design stages
  • Deep Learning:
    • Increasingly used in scientific and engineering applications
    • Recent success in generative language and image modelling
Figure: Symmetric finite element model of an aircraft fuselage
Symmetric finite element model of an aircraft fuselage

Approach: Combine both


  • Neural networks can learn to represent vibroacoustic problems (Replacement of classic surrogates)
  • Neural network architectures are crucial for generalization to new scenes
  • Generative modeling is transferable to acoustic design spaces
  • Generative Adversarial Networks (GANs) enable fast one-shot proposals

Goals of the project

  • Design of vibroacoustic systems by generative neural networks
  • Transfer of insights and methods to other engineering disciplines
  • Application of generative models for engineering problems in acoustics
    • Desired scene (sound pressure levels):
      • (Input)  -> Generative deep learning model (acoustic design assistant)
      • (One-shot & acoustic design)  -> Preliminary aircraft design (dimensions, materials, sitting plan, etc.)

For SPP Integration


  • Generate design proposals for desirable acoustics.
  • Gathered insights and developed methods can be applicable for other engineering disciplines: FEM -> Representation -> Design proposals.

Potential synergies

  • Useful network topologies in deep learning
    • Bestle/Eberhard
  • Transient and non-linear systems in vibroacoustics
    • Stender
  • Physics-informed NNs for vibroacoustics
    • Peitz/Sextro
  • Meshing
    • Riedelbauch


1.Representation of vibroacoustic scenes

  • Fit a neural network to numerical solutions
    of vibroacoustic problems

2.Generalization to novel vibroacoustic scenes

  • Apply neural networks on unseen vibroacoustic problems
    (e.g. new frequencies, new mechanical input parameters)

3.Generation of designs (e.g. geometries, material properties/distributions)

  • Direct, gradient-based design space optimization
  • GAN-based one-shot proposal generation
Figure: Neural network for sound pressure level predictions
Neural network for sound pressure level predictions


Prof. Dr.-Ing. Sabine C. Langer
Technische Universität Braunschweig
Universitätspl. 2
38106 Braunschweig
Langer Kamp 19, Raum 104, 1.OG
Tel.: +49 531 391-8770

Further Information

Dr. Timo Lüddecke
Universität Göttingen

To the top of the page