A self-learning optimal control algorithm for episodic fixed-horizon manufacturing processes with time-discrete control actions is proposed and evaluated on a simulated deep drawing process. The control model is built during consecutive process executions under optimal control via reinforcement learning, using the measured product quality as reward after each process execution. Prior model formulation, which is required by state-of-the-art algorithms from model predictive control and approximate dynamic programming, is therefore obsolete. This avoids several difficulties namely in system identification, accurate modelling, and runtime complexity, that arise when dealing with processes subject to nonlinear dynamics and stochastic influences. Instead of using pre-created process and observation models, value function-based reinforcement learning algorithms build functions of expected future reward, which are used to derive optimal process control decisions. The expectation functions are learned online, by interacting with the process. The proposed algorithm takes stochastic variations of the process conditions into account and is able to cope with partial observability. A Q-learning-based method for adaptive optimal control of partially observable episodic fixed-horizon manufac-turing processes is developed and studied. The resulting algorithm is instantiated and evaluated by applying it to a simulated stochastic optimal control problem in metal sheet deep drawing.

A major goal of materials design is to find material structures with desired properties and in a second step to find a processing path to reach one of these structures. In this paper, we propose and investigate a deep reinforcement learning approach for the optimization of processing paths. The goal is to find optimal processing paths in the material structure space that lead to target-structures, which have been identified beforehand to result in desired material properties. There exists a target set containing one or multiple different structures, bearing the desired properties. Our proposed methods can find an optimal path from a start structure to a single target structure, or optimize the processing paths to one of the equivalent target-structures in the set. In the latter case, the algorithm learns during processing to simultaneously identify the best reachable target structure and the optimal path to it. The proposed methods belong to the family of model-free deep reinforcement learning algorithms. They are guided by structure representations as features of the process state and by a reward signal, which is formulated based on a distance function in the structure space. Model-free reinforcement learning algorithms learn through trial and error while interacting with the process. Thereby, they are not restricted to information from a priori sampled processing data and are able to adapt to the specific process. The optimization itself is model-free and does not require any prior knowledge about the process itself. We instantiate and evaluate the proposed methods by optimizing paths of a generic metal forming process. We show the ability of both methods to find processing paths leading close to target structures and the ability of the extended method to identify target-structures that can be reached effectively and efficiently and to focus on these targets for sample efficient processing path optimization.

In industrial applications of adaptive optimal control often multiple contrary objectives have to be considered. The relative importance (weights) of the objectives are often not known during the design of the control and can change with changing production conditions and requirements. In this work a novel model-free multiobjective reinforcement learning approach for adaptive optimal control of manufacturing processes is proposed. The approach enables sample-efficient learning in sequences of control configurations, given by particular objective weights.

Optimization along the chain processing-structure-properties-performance is one of the core objectives in data-driven materials science. In this sense, processes are supposed to manufacture workpieces with targeted material microstructures. These microstructures are defined by the material properties of interest and identifying them is a question of materials design. In the present paper, we addresse this issue and introduce a generic multi-task learning-based optimization approach. The approach enables the identification of sets of highly diverse microstructures for given desired properties and corresponding tolerances. Basically, the approach consists of an optimization algorithm that interacts with a machine learning model that combines multi-task learning with siamese neural networks. The resulting model (1) relates microstructures and properties, (2) estimates the likelihood of a microstructure of being producible, and (3) performs a distance preserving microstructure feature extraction in order to generate a lower dimensional latent feature space to enable efficient optimization. The proposed approach is applied on a crystallographic texture optimization problem for rolled steel sheets given desired properties.

In materials design, supervised learning plays an important role for optimization and inverse modeling of microstructure-property relations. To successfully apply supervised learning models, it is essential to train them on suitable data. Here, suitable means that the data covers the microstructure and property space sufficiently and, especially for optimization and inverse modeling, that the property space is explored broadly. For virtual materials design, typically data is generated by numerical simulations, which implies that data pairs can be sampled on demand at arbitrary locations in microstructure space. However, exploring the space of properties remains challenging. To tackle this problem, interactive learning techniques known as active learning can be applied. The present work is the first that investigates the applicability of the active learning strategy query-by-committee for an efficient property space exploration. Furthermore, an extension to active learning strategies is described, which prevents from exploring regions with properties out of scope (i.e., properties that are physically not meaningful or not reachable by manufacturing processes).