Filters








1,419 Hits in 3.8 sec

On the Behaviour of Scalarization Methods for the Engagement of a Wet Clutch

Tim Brys, Kristof Van Moffaert, Kevin Van Vaerenbergh, Ann Nowe
2013 2013 12th International Conference on Machine Learning and Applications  
In this paper, we explore various of these scalarization techniques in the context of an industrial application, namely the engagement of a wet clutch using reinforcement learning.  ...  Recently, a reinforcement learning approach was proposed for the engagement of a wet clutch, and was validated in both simulation and on a real clutch, showing great improvements over the state-of-the-art  ...  This is the scalarization function used in the original work on wet clutch engagement [1] , with γ = 0.9.  ... 
doi:10.1109/icmla.2013.52 dblp:conf/icmla/BrysMVN13 fatcat:jtlue4oiwng7bmxsao5tvboknm

Model-based and model-free learning strategies for wet clutch control

Abhishek Dutta, Yu Zhong, Bruno Depraetere, Kevin Van Vaerenbergh, Clara Ionescu, Bart Wyns, Gregory Pinte, Ann Nowe, Jan Swevers, Robin De Keyser
2014 Mechatronics (Oxford)  
Learning) learning strategies for the control of wet-clutches.  ...  This paper presents an overview of model-based (Nonlinear Model Predictive Control, Iterative Learning Control and Iterative Optimization) and model-free (Genetic-based Machine Learning and Reinforcement  ...  (GA) and Reinforcement Learning (RL)) learning strategies are analyzed for the control of a wet clutch engagement.  ... 
doi:10.1016/j.mechatronics.2014.03.006 fatcat:uzg6nfb5f5c4dcr2lsmp6duf7a

A reference free iterative learning strategy for wet clutch control

Bruno Depraetere, Gregory Pinte, Jan Swevers
2011 Proceedings of the 2011 American Control Conference  
This paper presents a new iterative learning strategy to control wet clutches.  ...  The learning process is shown to converge towards the desired engagement quality, and a demonstration is given of the robustness with respect to changes in the operating conditions.  ...  CONCLUSION This paper proposes an iterative learning strategy for wet clutch control aimed at fast and smooth engagements.  ... 
doi:10.1109/acc.2011.5990938 fatcat:7tftarfz6zgndjzdqskcopfhhy

Iterative learning control for the filling of wet clutches

G. Pinte, B. Depraetere, W. Symens, J. Swevers, P. Sas
2010 Mechanical systems and signal processing  
This paper discusses the development of an advanced Iterative Learning Control (ILC) scheme for the filling of wet clutches.  ...  In the presented scheme, the appropriate actuator signal for a new clutch engagement is learned automatically based on the quality of previous engagements, such that time-consuming and cumbersome calibrations  ...  Reinforcement Learning) learning techniques for control after the filling phase.  ... 
doi:10.1016/j.ymssp.2010.05.016 fatcat:ru5rohdb2ndgndrgwgyfzopmdq

Position and Velocity Predictions of the Piston in a Wet Clutch System during Engagement by Using a Neural Network Modeling [chapter]

Yu Zhong, Bart Wyns, Abhishek Dutta, Clara-Mihaela Ionescu, Gregory Pinte, Wim Symens, Julian Stoev, Robin De Keyser
2012 IFIP Advances in Information and Communication Technology  
In a wet clutch system, a piston is used to compress the friction disks to close the clutch.  ...  The position and the velocity of the piston are the key effectors for achieving a good engagement performance. In a real setup, it is impossible to measure these variables.  ...  Recently, some advanced learning control methods are used to control and optimize the engagement performance of the wet clutch system. Zhong, et al.  ... 
doi:10.1007/978-3-642-33409-2_49 fatcat:v3lyicdh5rfp5irnx7i56e2vcu

Titelei/Inhaltsverzeichnis [chapter]

VDI Wissensforum GmbH
2019 Dritev – Drivetrain For Vehicles 2019  
f Simulation Artificial intelligence in transmission control -Clutch engagement with reinforcement learning� � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � � �  ...  description of a triple wet clutch unit and the related active and passive clutch and shift actuation system � � � � � � � � � � � � � � � � 471 O.  ... 
doi:10.51202/9783181023549-i-i fatcat:4gqhwsduizdhbbrgbuutpjhzxi

Modeling Simulation and Validation of a Tractor Wet Clutch Controlled by Proportional Valve

Ali YEL, Haydar LİVATYALI
2021 International Journal of Automotive Science and Technology  
The objective is to design an electro-hydraulic system for optimum engagement of the PTO output using a wet clutch and to develop a practical and effective method for the design and analysis of future  ...  Design of Wet Clutches Wet clutch systems are mostly laminated and multi-plate. The total area of the friction surface is increased by increasing the number of  ...  Machine Learning (GA) and Reinforcement Learning (RL).  ... 
doi:10.30939/ijastech..797276 fatcat:btj4xltsnvcfpksw2c34ttes54

Synergies between Evolutionary Algorithms and Reinforcement Learning

Madalina M. Drugan
2015 Proceedings of the Companion Publication of the 2015 on Genetic and Evolutionary Computation Conference - GECCO Companion '15  
the clutch • the engagement time.  ...  problems are inherently multi-objective • Traffic light control --> linear scalarized multi-objective Q-learning • Control problems (like wet clutch) with two or more objectives --> adaptive linear  ...  learning for evolutionary computation • Most EC algorithms use model free RL or multi-armed bandits techniques for parameter tuning • Schemata theorem as initially used in association with multi-armed  ... 
doi:10.1145/2739482.2756582 dblp:conf/gecco/Drugan15 fatcat:5jedfs4jmfgclcpppzcjvz6yvu

Pareto Upper Confidence Bounds algorithms: An empirical study

Madalina M Drugan, Ann Nowe, Bernard Manderick
2014 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)  
control applications, i.e. the engagement of wet clutches.  ...  In this paper, we propose the improved Pareto Upper Confidence Bound (iPUCB) algorithm that straightforwardly extends the single objective improved UCB algorithm to reward vectors by deleting the suboptimal  ...  The goal is to learn by minimising simultaneously: i) the optimal current profile to the electrohydraulic valve, which controls the pressure of the oil to wet clutch, and ii) the engagement time.  ... 
doi:10.1109/adprl.2014.7010620 dblp:conf/adprl/DruganNM14 fatcat:4km4qmz4kzdnzdlvehpkwtfa7m

Progress in Automotive Transmission Technology

Xiangyang Xu, Peng Dong, Yanfang Liu, Hui Zhang
2018 Automotive Innovation  
., an increased speed number, expanded ratio spread and improved efficiency and shift quality.  ...  We then discuss the progress in the transmission technology of a conventional internal combustion engine vehicle in terms of new layouts; improved efficiency; noise, vibration and harshness technology;  ...  ., genetic-based machine learning and reinforcement learning) learning strategies have been analyzed for the control of wet clutches [99] .  ... 
doi:10.1007/s42154-018-0031-y fatcat:yehbzc2f3zchhfz2d6qk5j3uuu

Control Strategy of Mode Transition with Engine Start in a Plug-in Hybrid Electric Bus

Yang, Zhang, Zhang, Tian, Hu
2019 Energies  
Simulation and experimental results show that the proposed control strategy can effectively suppress torque fluctuation, avoid longitudinal acceleration impact, and improve driving performance.  ...  K.V.Vaerenbergh [25] used the reinforcement learning algorithm to control the engagement process of the wet clutch and obtained better simulation results.  ...  In this phase, the engine torque is gradually coupled with the downstream driveline along with the clutch engagement, while the driving motor torque is gradually reduced to ensure a relatively stable power  ... 
doi:10.3390/en12152989 fatcat:qhkyx7xatfaifgqbwaw4dr7imy

Assessment of the training program for Versius, a new innovative robotic system for use in minimal access surgery

Jessica Butterworth, Margaux Sadry, Danielle Julian, Fiona Haig
2021 BMJ Surgery, Interventions, & Health Technologies  
Greatest improvements were observed in the depth perception and robotic control domains.  ...  Participants were assessed during the technical training using the Global Evaluative Assessment of Robotic Skills (GEARS).SettingDry box exercises were conducted in classrooms, and wet lab sessions simulated  ...  for 'clutching' instead of using foot controls.  ... 
doi:10.1136/bmjsit-2020-000057 pmid:35051252 pmcid:PMC8647592 fatcat:zh2xeqnphrailknvvrfcrdbzpe

Review of the Methods to Optimize Power Flow in Electric Vehicle Powertrains for Efficiency and Driving Performance

Izhari Izmi Mazali, Zul Hilmi Che Daud, Mohd Kameil Abdul Hamid, Victor Tan, Pakharuddin Mohd Samin, Abdullah Jubair, Khairul Amilin Ibrahim, Mohd Salman Che Kob, Wang Xinrui, Mat Hussin Ab Talib
2022 Applied Sciences  
Besides, the sticking characteristics of the wet clutch, due to its hydraulic system, caused difficulty to optimize the clutch control for minimum jerking and engagement time.  ...  However, because of the usage of the wet clutch, some power was lost due to the clutch actuation.  ... 
doi:10.3390/app12031735 doaj:7917f265bf7e45d6a9d6ccb327c8d3ef fatcat:r3paq4y4evgznpnnnjxvhak3xu

Approaching Reading Development through Children's Literature: Insights from A Case Study of the University Student with Low English Proficiency

Cheng-Fang Huang
2017 Journal of Arts and Humanities  
Focusing on one university EFL learner with low English proficiency, the report provides in-depth description of her reading obstacles and progress while engaging in reading English children's literature  ...  Findings of the reading sessions showed that the learner (1) improved the oral reading fluency, (2) acquired better awareness of pronunciation rules, and (3) developed better reading comprehension.  ...  One area that deserves further investigation is what types of explicit instruction do the L2 learners need that complement their incidental language learning while engaged in free reading.  ... 
doi:10.18533/journal.v6i3.1129 fatcat:c7rvisovdbbupdzacfhcfuros4

Reinforcement and the organization of behavior in golden hamsters: Sunflower seed and nest paper reinforcers

Sara J. Shettleworth
1978 Animal Learning and Behavior  
motor and clutch system.  ...  Raising the operant level of face washing by spraying the animals with water did not improve instrumental performance.  ... 
doi:10.3758/bf03209626 fatcat:izm2gcklp5gylaroyryukru4fi
« Previous Showing results 1 — 15 out of 1,419 results