A method for model selection using reinforcement learning when viewing design as a sequential decision process

Chhabra, Jaskanwal P. S.; Warn, Gordon P.

doi:10.1007/s00158-018-2145-6

Cited by 16 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, one major challenge in SBD methodologies is identifying the sets or subspaces out of all the possible combinations of discretised inputs that satisfy the requirements and discarding those that do not. Previous approaches can be divided into three main categories: [55] and Reinforcement Learning [56].…”

Section: Introductionmentioning

confidence: 99%

Application of Probabilistic Set-Based Design Exploration on the Energy Management of a Hybrid-Electric Aircraft

et al. 2022

View full text Add to dashboard Cite

The energy management strategy of a hybrid-electric aircraft is coupled with the design of the propulsion system itself. A new design space exploration methodology based on Set-Based Design is introduced to analyse the effects of different strategies on the fuel consumption, NOx and take-off mass. Probabilities are used to evaluate and discard areas of the design space not capable of satisfying the constraints and requirements, saving computational time corresponding to an average of 75%. The study is carried on a 50-seater regional turboprop with a parallel hybrid-electric architecture. The strategies are modelled as piecewise linear functions of the degree of hybridisation and are applied to different mission phases to explore how the strategy complexity and the number of hybridised segments can influence the behaviour of the system. The results indicate that the complexity of the parametrisation does not affect the trade-off between fuel consumption and NOx emissions. On the contrary, a significant trade-off is identified on which phases are hybridised. That is, the least fuel consumption is obtained only by hybridising the longest mission phase, while less NOx emissions are generated if more phases are hybridised. Finally, the maximum take-off mass was investigated as a parameter, and the impact to the trade-off between the objectives was analysed. Three energy management strategies were suggested from these findings, which achieved a reduction to the fuel consumption of up to 10% and a reduction to NOx emissions of up to 15%.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Probabilistic Set-Based Design Exploration on the Energy Management of a Hybrid-Electric Aircraft

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In 2019, Chhabra and Warn 187 expanded upon Miller et al 184 . work by selecting an approximate optimal modeling policy using the MDP with RL.…”

Section: Quantitative Methodsmentioning

confidence: 99%

“…Chhabra and Warn 187 and Miller et al 184 used MDP to determine the optimal modeling policy which sequentially increased the fidelity of the model to further reduce the design space. The cost model and discriminatory power model used in analysis were limited to FEA applications.…”

Section: 2mentioning

confidence: 99%

“…Chhabra and Warn 187 and Miller et al 184 . used MDP to determine the optimal modeling policy which sequentially increased the fidelity of the model to further reduce the design space.…”

Section: Synthesis Of the Literaturementioning

confidence: 99%

“…Based on this literature review Chhabra and Warn 187 and Miller et al 184 . provided the best examples of improving the level of analysis and using it to narrow the design space.…”

Section: Synthesis Of the Literaturementioning

confidence: 99%

See 2 more Smart Citations

Survey on set‐based design (SBD) quantitative methods

Dullen

Verma

Blackburn

et al. 2021

Systems Engineering

View full text Add to dashboard Cite

Product development efforts now more than ever are in need of methodologies that can address the challenges of increased system complexities, shortening time to market, increased demands in mass customization, market instabilities, geographical barriers, improved innovation, and adaptability to emerging technologies. To address these challenges most companies will need to make key decisions early in the product development life-cycle. In this early phase there are high levels of information uncertainty and information ambiguity. Under these circumstances many companies will converge too early to a point design (Point Based Design-PBD) which will lead to increased cost and schedule delays due to reworking the design later in the product development life cycle. To overcome these challenges many researchers have proposed the Set-Based Design (SBD) methodology. However, there has been limited guidance on how to define, reason, and narrow sets while improving the level of abstraction of the design.To address such concerns, a literature review was conducted. The contributions of this research include: (1) aggregated literature from over 100 sources on quantitative methods (QM) that has not been considered SBD but does support set-based thinking,(2) consolidated body of knowledge on QM to help industrial practitioners implement SBD, (3) defined gaps and opportunities for future research, and (4) defined strengths and limitations of QM and techniques to define, reason and narrow sets.

show abstract

A method to efficiently localize non-dominated regions using surrogate modeling with multi-fidelity data from a sequential decision process

Chhabra

Warn

2019

Struct Multidisc Optim

View full text Add to dashboard Cite

A method for model selection using reinforcement learning when viewing design as a sequential decision process

Cited by 16 publications

References 27 publications

Application of Probabilistic Set-Based Design Exploration on the Energy Management of a Hybrid-Electric Aircraft

Application of Probabilistic Set-Based Design Exploration on the Energy Management of a Hybrid-Electric Aircraft

Survey on set‐based design (SBD) quantitative methods

A method to efficiently localize non-dominated regions using surrogate modeling with multi-fidelity data from a sequential decision process

Contact Info

Product

Resources

About