Overview
Complexity in modern aircrafts is increasing significantly. They incorporate more electric systems since other subsystems that used to be pneumatic or hydraulic are being replaced by electric systems. As a consequence, the wire harnesses that are used to connect those systems to each other must also convey more signals. The industrial-grade wiring harness acts as the central nervous system to many device and vehicle electronics designs, particularly in the aeronautic and aerospace segments. As applications become increasingly complex, innovation in wiring harness design and manufacturing techniques becomes more critical. This project researched and implemented new methods for more efficiently driving design data toward fully automated design optimization so to better analyse costs, to help ensure the successful design and manufacture of new wiring harness products.
For this purpose, the goal of this project was to link the unique state-of-the-art surrogate modelling technologies available at Noesis to develop new surrogate-based optimization techniques and software solutions suitable to solve wire harness large scale optimisation problems. The resulting hybrid, adaptive and robust optimization strategy allowed the optimisation of high dimensional systems (HAROS-HD, Hybrid Adaptive Robust Optimization Strategy for High Dimensional systems) by means of smart adoption of model order reduction techniques coupled with surrogate models.
The main advantages of this approach include:
- Design engineers do not need to spend time and effort trying to understand their design space before choosing a suitable optimization algorithm. HAROS-HD will learn about the design space and employ the appropriate algorithms as it proceeds toward finding an optimized solution.
- Design engineers are not required to be experts in optimization algorithms and applications, because HAROS-HD will intelligently adapt the optimization strategy by selecting the most appropriate method to use.
Funding
Results
Executive Summary:
In today’s engineering endeavour, it is common to run computer simulations to understand the behaviour of complex systems and optimise their parameters to obtain satisfactory designs before actual physical prototypes are built. The objective of the engineer is not only the optimisation of the systems but also to understand what makes a good design. The question - particularly in the early stage of the design process - is often not about finding the best parameter values but is about what parameter ranges would generate competitive designs or solutions. In a more pragmatic simulation level, engineers often want to confine the simulation runs to parameter settings for which results are trustworthy. Such information may not be available until one actually runs the simulation (e.g. whether it crashes/converges or not).
The Haros-HD concept originated from engineering design situations in which accuracy of optimised result is as important as the efficient identification of the “good input space” (also called “feasibility region”).
Based on this consideration, the HAROS-HD challenge has been addressed by developing a different approach based on the pre-conditioning of the optimization problem with machine learning algorithms applied to engineering cases. As such, the effort is shifted from the optimization challenge to the ‘feature discovery’ process, where engineering features of the design and solution spaces are ‘discovered’ and exploited to perform a much faster and tailored optimization process.
This machine learning process starts with an analysis of the entities and relations of the electrical wire harness topology to identify subsystems that are independent or loosely coupled between themselves and that can be optimized separately with relatively small or no error (in case of total independence). Once the problem is decomposed according to its inherent structure, two machine learning algorithms are started to reduce the newly created subsystems and to learn, for each of them, the feasible region – that is the region of the output space where no constraints are active. In this context, the SOMBAS and the Deep Learning algorithms are used.
The output of this process is not only the definition of the feasible region, but also a set of optimisation starting points that are best candidates for the subsequent subsystem optimisation. The information discovered by the machine learning approach is used by specific optimisation algorithms like Cross-Entropy and Annealed Hook&Jeeves that exploit this knowledge by starting from the best points found in the feasible region, thus removing the challenge to handle constraints (that, for the 48 harness, can be up to more than 10000). These optimisation algorithms will then iterate till final convergence to the optimal solution for each subsystem. Once this is achieved, the overall system is then reassembled to take into account the various subsystem dependencies and converge to the final optimal configuration for the entire wire harness problem at hand.
The Haros-HD optimization strategy has been implemented and tested in a fully functional software prototype based on the Noesis Optimus 10.x platform and will be made available, together with its key enabling technologies, as commercial modules of the platform itself.