FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206443485> ?p ?o ?g. }

• W4206443485 endingPage "158" @default.
• W4206443485 startingPage "125" @default.
• W4206443485 abstract "The optimization of internal combustion (IC) engine is a highly complex problem because of the high-dimensionality and nonlinear interactions among design parameters. Machine learning (ML) offers a pathway to transform complex physical processes that occur in a combustion engine into compact informational processes. A careful definition of the objective (merit) function for optimization is a critical step. Training data for these ML algorithms must be cleverly prepared to improve the prediction efficiency. Global optimum search optimization methods must be adopted to avoid local optimum designs with reduced merit value. Postprocessing of the optimization outputs is also needed to evaluate the recommended design by employing sensitivity and robustness analysis. In this chapter, a machine learning-genetic algorithm (ML-GA) framework is discussed to optimize the performance of IC engines. ML-GA is comprised of a robust Super Learner approach to build the surrogate model (based on simulation or experimental data), wherein multiple ML algorithms are pooled together instead of a single learner. This Super Learner surrogate is then used to replace expensive simulations or experiments during the course of a GA optimization to rapidly arrive at the optimal design parameters at significantly lower cost. The efficiency and robustness of ML-GA is further enhanced by way of automated hyperparameter selection coupled with an active learning approach. In particular, a Bayesian approach is employed to optimize the hyperparameters of the base learners that make up a Super Learner model to obtain better test performance. In addition to performing hyperparameter optimization (HPO), an active learning approach is leveraged, where the process of data generation, ML training, and surrogate optimization, is performed repeatedly to refine the solution in the vicinity of the predicted optimum. The ML-GA algorithm has been demonstrated for simulation-driven design optimization of advanced IC engines with significant savings in design time and cost compared to traditional optimization methods, as highlighted in this chapter." @default.
• W4206443485 created "2022-01-26" @default.
• W4206443485 creator A5017782131 @default.
• W4206443485 creator A5017998380 @default.
• W4206443485 creator A5029709349 @default.
• W4206443485 creator A5037919862 @default.
• W4206443485 date "2022-01-01" @default.
• W4206443485 modified "2023-09-25" @default.
• W4206443485 title "A machine learning-genetic algorithm approach for rapid optimization of internal combustion engines" @default.
• W4206443485 cites W1977923618 @default.
• W4206443485 cites W1993145896 @default.
• W4206443485 cites W2015002486 @default.
• W4206443485 cites W2029545900 @default.
• W4206443485 cites W2044755884 @default.
• W4206443485 cites W2052667812 @default.
• W4206443485 cites W2057242689 @default.
• W4206443485 cites W2100072843 @default.
• W4206443485 cites W2103873115 @default.
• W4206443485 cites W2132364490 @default.
• W4206443485 cites W2134318784 @default.
• W4206443485 cites W2155889930 @default.
• W4206443485 cites W2222173969 @default.
• W4206443485 cites W2253516033 @default.
• W4206443485 cites W2340835349 @default.
• W4206443485 cites W2591386748 @default.
• W4206443485 cites W2755256460 @default.
• W4206443485 cites W2795778498 @default.
• W4206443485 cites W2795990911 @default.
• W4206443485 cites W2802442158 @default.
• W4206443485 cites W3048313361 @default.
• W4206443485 cites W3110511296 @default.
• W4206443485 cites W3178631786 @default.
• W4206443485 cites W347304664 @default.
• W4206443485 cites W4233056867 @default.
• W4206443485 cites W96733437 @default.
• W4206443485 doi "https://doi.org/10.1016/b978-0-323-88457-0.00003-5" @default.
• W4206443485 hasPublicationYear "2022" @default.
• W4206443485 type Work @default.
• W4206443485 citedByCount "1" @default.
• W4206443485 countsByYear W42064434852022 @default.
• W4206443485 crossrefType "book-chapter" @default.
• W4206443485 hasAuthorship W4206443485A5017782131 @default.
• W4206443485 hasAuthorship W4206443485A5017998380 @default.
• W4206443485 hasAuthorship W4206443485A5029709349 @default.
• W4206443485 hasAuthorship W4206443485A5037919862 @default.
• W4206443485 hasConcept C105923489 @default.
• W4206443485 hasConcept C119857082 @default.
• W4206443485 hasConcept C154945302 @default.
• W4206443485 hasConcept C178790620 @default.
• W4206443485 hasConcept C185592680 @default.
• W4206443485 hasConcept C41008148 @default.
• W4206443485 hasConcept C8880873 @default.
• W4206443485 hasConceptScore W4206443485C105923489 @default.
• W4206443485 hasConceptScore W4206443485C119857082 @default.
• W4206443485 hasConceptScore W4206443485C154945302 @default.
• W4206443485 hasConceptScore W4206443485C178790620 @default.
• W4206443485 hasConceptScore W4206443485C185592680 @default.
• W4206443485 hasConceptScore W4206443485C41008148 @default.
• W4206443485 hasConceptScore W4206443485C8880873 @default.
• W4206443485 hasLocation W42064434851 @default.
• W4206443485 hasOpenAccess W4206443485 @default.
• W4206443485 hasPrimaryLocation W42064434851 @default.
• W4206443485 hasRelatedWork W1596801655 @default.
• W4206443485 hasRelatedWork W2130043461 @default.
• W4206443485 hasRelatedWork W2350741829 @default.
• W4206443485 hasRelatedWork W2358668433 @default.
• W4206443485 hasRelatedWork W2376932109 @default.
• W4206443485 hasRelatedWork W2382290278 @default.
• W4206443485 hasRelatedWork W2390279801 @default.
• W4206443485 hasRelatedWork W2748952813 @default.
• W4206443485 hasRelatedWork W2899084033 @default.
• W4206443485 hasRelatedWork W2530322880 @default.
• W4206443485 isParatext "false" @default.
• W4206443485 isRetracted "false" @default.
• W4206443485 workType "book-chapter" @default.