Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion 2020
DOI: 10.1145/3377929.3389963
|View full text |Cite
|
Sign up to set email alerts
|

Towards a Pittsburgh-style LCS for learning manufacturing machinery parametrizations

Abstract: We present a first evaluation of a new accuracy-based Pittsburghstyle learning classifier system (LCS) for supervised learning of multi-dimensional continuous decision problems: The SupRB-1 (Supervised Rule-Based) learning system. Designed primarily for finding parametrizations for industrial machinery, SupRB-1 learns an approximation of a continuous quality function from examples (consisting of situations, choices and associated qualities-all continous, the first two possibly multi-dimensional) and is then ab… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
9

Relationship

3
6

Authors

Journals

citations
Cited by 9 publications
(5 citation statements)
references
References 0 publications
0
5
0
Order By: Relevance
“…CAROL is developed in the context of a research project with the aim to optimize the parameterization process of fused deposition modelling by studying environmental influences on the process (Nordsieck et al, 2019). To this end, we extract rules based on operator interactions (Nordsieck et al, 2021) and combine them with learning systems (Heider et al, 2020) which requires an accurate dataset. To build this dataset, we perform extensive series of test prints of different objects.…”
Section: Case Studymentioning
confidence: 99%
“…CAROL is developed in the context of a research project with the aim to optimize the parameterization process of fused deposition modelling by studying environmental influences on the process (Nordsieck et al, 2019). To this end, we extract rules based on operator interactions (Nordsieck et al, 2021) and combine them with learning systems (Heider et al, 2020) which requires an accurate dataset. To build this dataset, we perform extensive series of test prints of different objects.…”
Section: Case Studymentioning
confidence: 99%
“…A current trend in manufacturing is to move from a fixed set of parameters to adaptive ones (Heider et al, 2020). The most promising parameters are chosen according to the system's state and this enables the configuration to be more specialised.…”
Section: Future Workmentioning
confidence: 99%
“…From a machine learning point of view our work is deeply linked to LCS research. Applications range from traffic control (Tomforde et al, 2008), over distributed camera control (Stein et al, 2017) to manufacturing (Heider et al, 2020a). We are also not the first to apply XCSF to a real-world problem.…”
Section: Related Workmentioning
confidence: 99%