Open Access
Machine intelligence for adaptable closed loop and open loop production engineering systems
Reads0
Chats0
TLDR
This thesis investigates the application of machine learning algorithms for industrial production processes by improving the PID controller as an already existing closed loop control approach, and introducing a new architecture, consisting of several machineLearning algorithms, for industrial laser welding.Abstract:
This thesis investigates the application of machine learning algorithms for industrial production processes. First, the PID controller as an already existing closed loop control approach is improved. For this purpose, a neural network tunes the PID parameters, while the process is running. Second, a new architecture, consisting of several machine learning algorithms, is introduced for industrial laser welding. Following this approach, the control can be changed from open to closed loop.read more
Citations
More filters
Journal ArticleDOI
Interpretable PID parameter tuning for control engineering using general dynamic neural networks: An extensive comparison.
TL;DR: In this paper, the authors examine the utility of extending PID controllers with recurrent neural networks and highlight how they can be a scalable and interpretable option for modern control systems and provide an extensive study using four benchmark systems that represent the most common control engineering benchmarks.
Journal ArticleDOI
Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge Architectures.
TL;DR: TIDBD is shown to be a practical alternative for classic Temporal-Difference learning via an extensive parameter search, and the sensitivity of classic TD and TIDBD with respect to the initial step-size values on the robotic data set is investigated.
Proceedings ArticleDOI
Machine Learning in Electric Motor Production - Potentials, Challenges and Exemplary Applications
Andreas Mayr,Jörg Franke,Johannes Seefried,Marco Ziegler,Michael Masuch,Alexander Mahr,Johannes von Lindenfels,Moritz Meiners,Dominik Kisskalt,Maximilian Metzner +9 more
TL;DR: An overview of different ML approaches helps practitioners to better assess the possibilities and limitations of ML and encourages the identification and exploitation of further ML use cases in electric motor production.
Posted Content
Affordance as general value function: A computational model
TL;DR: Through a comprehensive review of existing literature on recent successes of GVF applications in robotics, rehabilitation, industrial automation, and autonomous driving, it is demonstrated that GVFs provide the right framework for learning affordances in real-world applications.
Journal ArticleDOI
Affordance as general value function: a computational model:
TL;DR: General value functions (GVFs) as discussed by the authors are long-term predictive summaries of the outcomes of agents following specific policies in the environment and are used in reinforcement learning (RL) literature.
Related Papers (5)
Computer aided design of control algorithms based on identified process models
E. Dymschiz,R. Isermann +1 more