scholarly journals Reinforcement learning for robotic assembly of fuel cell turbocharger parts with tight tolerances

2020 ◽  
Vol 14 (4) ◽  
pp. 407-416
Author(s):  
Franziska Aschersleben ◽  
Rudolf Griemert ◽  
Felix Gabriel ◽  
Klaus Dröder
Keyword(s):  
Reinforcement Learning ◽  
Fuel Cell ◽  
Learning Strategy ◽  
Measurement Data ◽  
Robotic Assembly ◽  
Assembly Process ◽  
Current Contact ◽  
Manufacturing Accuracy ◽  
The Individual ◽  
Insertion Process

Abstract The efficiency of a fuel cell is not only dependent on the stack, but also to a large extent on the turbocharger, which is responsible for providing the required airflow. Since the individual components, especially those of the rotor, are subject to high demands on manufacturing accuracy, it is crucial to ensure a precise and robust assembly. In order to achieve a scalable assembly process, this paper presents a method for a robot-based assembly of the rotationally symmetric components of the rotor. The assembly task has been reduced to the two essential problems: search and insertion. On this basis, a system was developed, which is able to learn the joining process independently and compensate for positioning inaccuracies with the help of reinforcement learning in combination with a position-controlled robot. The applied reinforcement learning strategy is based on the measurement data of a 6-axis force/torque sensor, with which the current contact state can be evaluated and a decision for the next step can be made. The experimental verification shows that an automation of the assembly process is possible with the proposed strategy. The robot is able to perform the search operation successfully, whereas limitations to the achievable accuracies of the insertion process could be found.

scholarly journals Bridging the Gap between Automated Manufacturing of Fuel Cell Components and Robotic Assembly of Fuel Cell Stacks

Energies ◽  
2019 ◽  
Vol 12 (19) ◽  
pp. 3604
Author(s):  
Devin Fowler ◽  
Vladimir Gurau ◽  
Daniel Cox
Keyword(s):  
Fuel Cell ◽  
Alternative Energy ◽  
Vision System ◽  
Department Of Energy ◽  
Robotic Assembly ◽  
Assembly Process ◽  
Work Cycle ◽  
Cell Components ◽  
Dual Arm Robot ◽  
Manufacturing Technologies

Recently demonstrated robotic assembling technologies for fuel cell stacks used fuel cell components manually pre-arranged in stacks (presenters). Identifying the original orientation of fuel cell components and loading them in presenters for a subsequent automated assembly process is a difficult, repetitive work cycle which if done manually, deceives the advantages offered by either the automated fabrication technologies for fuel cell components or by the robotic assembly processes. We present for the first time a robotic technology which enables the integration of automated fabrication processes for fuel cell components with a robotic assembly process of fuel cell stacks into a fully automated fuel cell manufacturing line. This task uses a Yaskawa Motoman SDA5F dual arm robot with integrated machine vision system. The process is used to identify and grasp randomly placed, slightly asymmetric fuel cell components, to reorient them all in the same position and stack them in presenters in preparation for a subsequent robotic assembly process. The process was demonstrated as part of a larger endeavor of bringing to readiness advanced manufacturing technologies for alternative energy systems, and responds the high priority needs identified by the U.S. Department of Energy for fuel cells manufacturing research and development.

scholarly journals Application of Deep Reinforcement Learning to Predict Shaft Deformation Considering Hull Deformation of Medium-Sized Oil/Chemical Tanker

2021 ◽  
Vol 9 (7) ◽  
pp. 767
Author(s):  
Shin-Pyo Choi ◽  
Jae-Ung Lee ◽  
Jun-Bum Park
Keyword(s):  
Reinforcement Learning ◽  
Reaction Force ◽  
Measurement Data ◽  
System Stability ◽  
Main Bearing ◽  
Shaft System ◽  
Novel Approach ◽  
Design Changes ◽  
Prediction Techniques ◽  
Shaft Deformation

The enlargement of ships has increased the relative hull deformation owing to draft changes. Moreover, design changes such as an increased propeller diameter and pitch changes have occurred to compensate for the reduction in the engine revolution and consequent ship speed. In terms of propulsion shaft alignment, as the load of the stern tube support bearing increases, an uneven load distribution occurs between the shaft support bearings, leading to stern accidents. To prevent such accidents and to ensure shaft system stability, a shaft system design technique is required in which the shaft deformation resulting from the hull deformation is considered. Based on the measurement data of a medium-sized oil/chemical tanker, this study presents a novel approach to predicting the shaft deformation following stern hull deformation through inverse analysis using deep reinforcement learning, as opposed to traditional prediction techniques. The main bearing reaction force, which was difficult to reflect in previous studies, was predicted with high accuracy by comparing it with the measured value, and reasonable shaft deformation could be derived according to the hull deformation. The deep reinforcement learning technique in this study is expected to be expandable for predicting the dynamic behavior of the shaft of an operating vessel.

EVA 2.0: Emotional and rational multimodal argumentation between virtual agents

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Niklas Rach ◽  
Klaus Weber ◽  
Yuchi Yang ◽  
Stefan Ultes ◽  
Elisabeth André ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
User Feedback ◽  
Virtual Agents ◽  
Multi Agent System ◽  
Dialogue Game ◽  
Multi Agent ◽  
The Individual ◽  
Minimal Bias ◽  
Intuitive Interface ◽  
Emotional Level

Abstract Persuasive argumentation depends on multiple aspects, which include not only the content of the individual arguments, but also the way they are presented. The presentation of arguments is crucial – in particular in the context of dialogical argumentation. However, the effects of different discussion styles on the listener are hard to isolate in human dialogues. In order to demonstrate and investigate various styles of argumentation, we propose a multi-agent system in which different aspects of persuasion can be modelled and investigated separately. Our system utilizes argument structures extracted from text-based reviews for which a minimal bias of the user can be assumed. The persuasive dialogue is modelled as a dialogue game for argumentation that was motivated by the objective to enable both natural and flexible interactions between the agents. In order to support a comparison of factual against affective persuasion approaches, we implemented two fundamentally different strategies for both agents: The logical policy utilizes deep Reinforcement Learning in a multi-agent setup to optimize the strategy with respect to the game formalism and the available argument. In contrast, the emotional policy selects the next move in compliance with an agent emotion that is adapted to user feedback to persuade on an emotional level. The resulting interaction is presented to the user via virtual avatars and can be rated through an intuitive interface.

scholarly journals Experimental and simulation-based analysis of asymmetrical spherical roller bearings as main bearings for wind turbines

2021 ◽  
Author(s):  
Amin Loriemi ◽  
Georg Jacobs ◽  
Sebastian Reisch ◽  
Dennis Bosse ◽  
Tim Schröder
Keyword(s):  
Wind Turbine ◽  
Wind Turbines ◽  
Measurement Data ◽  
Contact Angles ◽  
Suspension System ◽  
Roller Bearings ◽  
Axial Forces ◽  
Wind Turbine System ◽  
Bearing Life ◽  
The Individual

AbstractSymmetrical spherical roller bearings (SSRB) used as main bearings for wind turbines are known for their high load carrying capacity. Nevertheless, even designed after state-of-the-art guidelines premature failures of this bearing type occur. One promising solution to overcome this problem are asymmetrical spherical roller bearings (ASRB). Using ASRB the contact angles of the two bearing rows can be adjusted individually to the load situation occurring during operation. In this study the differences between symmetrical and asymmetrical spherical roller bearings are analyzed using the finite element method (FEM). Therefore, FEM models for a three point suspension system of a wind turbine including both bearings types are developed. These FEM models are validated with measurement data gained at a full-size wind turbine system test bench. Taking into account the design loads of the investigated wind turbine it is shown that the use of an ASRB leads to a more uniform load distribution on the individual bearing rows. Considering fatigue-induced damage an increase of the bearing life by 62% can be achieved. Regarding interactions with other components of the rotor suspension system it can be stated that the transfer of axial forces into the gearbox is decreased significantly.

A New Hybrid Deep Neural Architectural Search based Ensemble Reinforcement Learning Strategy for Wind Power Forecasting

2021 ◽  
pp. 1-1
Author(s):  
Seyed Mohammad Jafar Jalali ◽  
Gerardo J. Osorio ◽  
Sajad Ahmadian ◽  
Mohamed Lotfi ◽  
Vasco Campos ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Wind Power ◽  
Learning Strategy ◽  
Wind Power Forecasting ◽  
Power Forecasting

scholarly journals Revised Estimation Method for Emissions from Automated Plunger Lift Liquid Unloadings

Environments ◽  
2020 ◽  
Vol 7 (4) ◽  
pp. 25
Author(s):  
Adam Pacsi ◽  
David W. Sullivan ◽  
David T. Allen
Keyword(s):  
Direct Measurement ◽  
Oil And Gas ◽  
Measurement Data ◽  
Estimation Method ◽  
The United States ◽  
Gas Production ◽  
Small Subset ◽  
Emission Estimate ◽  
National Measurement ◽  
The Individual

A variety of liquid unloading techniques are used to clear accumulated liquids from the wellbore to increase production rates for oil and gas wells. Data from national measurement studies indicate that a small subset of wells with plunger lift assist, that vent with high frequency and short event duration, contribute a significant fraction of methane emissions from liquid unloading activities in the United States. Compared to direct measurement of emissions at 24 wells in a field campaign, the most commonly used engineering emission estimate for this source category, which is based on the volume of gas in the wellbore, does not accurately predict emissions at the individual well (R2 = 0.06). An alternative emission estimate is proposed that relies on the duration of the venting activity and the gas production rate of the well, which has promising statistical performance characteristics when compared to direct measurement data. This work recommends well parameters that should be collected from future field measurement campaigns that are focused on this emission source.

scholarly journals Severe Sexual Abuse Reduces Frontoparietal Network Activity during Model-Based Reinforcement Learning Updates

2019 ◽  
Author(s):  
Allison Letkiewicz ◽  
Amy L. Cochran ◽  
Josh M. Cisler
Keyword(s):  
Sexual Abuse ◽  
Reinforcement Learning ◽  
Learning Styles ◽  
Computational Models ◽  
Learning Strategy ◽  
Network Activity ◽  
Model Based ◽  
Model Free ◽  
Frontoparietal Network ◽  
Assaultive Trauma

Trauma and trauma-related disorders are characterized by altered learning styles. Two learning processes that have been delineated using computational modeling are model-free and model-based reinforcement learning (RL), characterized by trial and error and goal-driven, rule-based learning, respectively. Prior research suggests that model-free RL is disrupted among individuals with a history of assaultive trauma and may contribute to altered fear responding. Currently, it is unclear whether model-based RL, which involves building abstract and nuanced representations of stimulus-outcome relationships to prospectively predict action-related outcomes, is also impaired among individuals who have experienced trauma. The present study sought to test the hypothesis of impaired model-based RL among adolescent females exposed to assaultive trauma. Participants (n=60) completed a three-arm bandit RL task during fMRI acquisition. Two computational models compared the degree to which each participant’s task behavior fit the use of a model-free versus model-based RL strategy. Overall, a greater portion of participants’ behavior was better captured by the model-based than model-free RL model. Although assaultive trauma did not predict learning strategy use, greater sexual abuse severity predicted less use of model-based compared to model-free RL. Additionally, severe sexual abuse predicted less left frontoparietal network encoding of model-based RL updates, which was not accounted for by PTSD. Given the significant impact that sexual trauma has on mental health and other aspects of functioning, it is plausible that altered model-based RL is an important route through which clinical impairment emerges.

Sign in / Sign up

Export Citation Format

Share Document