Graph-based process models as basis for efficient data-driven surrogates – expediting the material development process

TL;DR

This paper introduces a new method using graph-based models to speed up material development by efficiently training data-driven models.

Contribution

The novel contribution is a formalism combining graph-based process models and 'flowthings' to represent material development processes efficiently.

Findings

The proposed formalism generates a DAG representation of material development processes from acquired data.

Black box models trained on the derived database enable inverse optimization to maximize specific modulus under constraints.

The method demonstrates potential to accelerate material development through data-driven modeling.

Abstract

Shorter development cycles, increasing complexity and cost pressure are driving the need for more efficient development processes. Especially in the field of material development, the long and costly experiments are a major bottleneck. To address this bottleneck, data-driven models supporting the decision making process have recently gained popularity. However, such models require a structured representation of the development process to allow an efficient training. In this work, a formalism for deriving an efficient representation of material development processes (MDPs) is proposed, and demonstrated on the development of a high modulus steel (HMS). The formalism is based on the combination of graph-based process models and the recently proposed concept of “flowthings” [1]. This allows to efficiently derive a directed acyclic graph (DAG) representation of the MDP with the acquired data. From this, a database for subsequent training of surrogate models is derived, on which several black box models for the MDP are trained. Best-in-class models are chosen based on the root mean squared error (RMSE) on the test set and subsequently used for the inverse optimization of the MDP to maximize the specific modulus while meeting additional design constraints. This showcases the potential of the proposed formalism to accelerate the MDP through data-driven modeling.

Figures