“…We will test the ability of n ∈ [1, 2, 3] agents to learn optimal fixturing positions, whilst examining the presence of an equilibrium position for a 2-player game. A drilling position is selected on the wing panel based on the framework outlined in [25], and a payout graph is constructed for 2 agents and a trained response for 1-3 agents is created in a similar manner to the multi-armed bandit model [18]. In figure 5a, the action numbers for each agent correspond to a fixture on the panel in figure 7, where the payout is the outcome from the Gaussian reward function.…”
Section: A Repeated Matrix Game For Fixture Placementmentioning
Within the realm of flexible manufacturing, fixture layout planning
allows manufacturers to rapidly deploy optimal fixturing plans that can
reduce surface deformation that leads to crack propagation in components
during manufacturing tasks. The role of fixture layout planning has
evolved from being performed by experienced engineers to computational
methods due to the number of possible configurations for components.
Current optimisation methods commonly fall into sub-optimal positions
due to the existence of local optima, with data-driven machine learning
techniques relying on costly to collect labelled training data. In this
paper, we present a framework for multi-agent reinforcement learning
with team decision theory to find optimal fixturing plans for
manufacturing tasks. We demonstrate our approach on two representative
aerospace components with complex geometries across a set of drilling
tasks, illustrating the capabilities of our method; we will compare this
against state of the art methods to showcase our method’s improvement at
finding optimal fixturing plans with 3 times the improvement in
deformation control within tolerance bounds.
“…We will test the ability of n ∈ [1, 2, 3] agents to learn optimal fixturing positions, whilst examining the presence of an equilibrium position for a 2-player game. A drilling position is selected on the wing panel based on the framework outlined in [25], and a payout graph is constructed for 2 agents and a trained response for 1-3 agents is created in a similar manner to the multi-armed bandit model [18]. In figure 5a, the action numbers for each agent correspond to a fixture on the panel in figure 7, where the payout is the outcome from the Gaussian reward function.…”
Section: A Repeated Matrix Game For Fixture Placementmentioning
Within the realm of flexible manufacturing, fixture layout planning
allows manufacturers to rapidly deploy optimal fixturing plans that can
reduce surface deformation that leads to crack propagation in components
during manufacturing tasks. The role of fixture layout planning has
evolved from being performed by experienced engineers to computational
methods due to the number of possible configurations for components.
Current optimisation methods commonly fall into sub-optimal positions
due to the existence of local optima, with data-driven machine learning
techniques relying on costly to collect labelled training data. In this
paper, we present a framework for multi-agent reinforcement learning
with team decision theory to find optimal fixturing plans for
manufacturing tasks. We demonstrate our approach on two representative
aerospace components with complex geometries across a set of drilling
tasks, illustrating the capabilities of our method; we will compare this
against state of the art methods to showcase our method’s improvement at
finding optimal fixturing plans with 3 times the improvement in
deformation control within tolerance bounds.
Etwa ein Drittel aller Nietbohrungen in der Flugzeugstrukturmontage werden unter Einsatz semi-automatischer Bohrmaschinen gefertigt. Diese Maschinen können mit internen Sensoren ausgerüstet werden, um Prozessdaten aufzuzeichnen. In diesem Beitrag werden zuverlässige und effiziente Methoden zur Klassifizierung von Prozesszuständen basierend auf internen Maschinendaten identifiziert. Diese können für die Implementierung einer intelligenten Prozessüberwachung oder zur Anomaliedetektion verwendet werden.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.