Data-Driven Model Learning and Control of RCCI Engines based on Heat Release Rate
Bibliographic record
Abstract
Reactivity controlled compression ignition (RCCI) technology not only offers high thermal efficiency but also produces low nitrogen oxides (NOx) and soot emissions. However, it is imperative to control the combustion in RCCI engines to prevent high pressure rise rates and combustion instability. In this study, a model-based control framework is developed to optimize the RCCI operating mode. To this end, the effects of variations in the premixed ratio, start of injection timing and fuel equivalence ratio on the combustion dynamics are analyzed by examining the heat release rates. Three distinct heat release rate patterns are identified together with two transition zones. Heat release rate traces are grouped together as a function of fractions of early and late heat release rates. Based on a classification algorithm, the fractions of early and late heat release rate are identified as scheduling variables for the data-driven modeling of an RCCI engine. Linear regression is used to model the fractions of early and late heat release. These models are then used to train linear parameter varying (LPV) models using least-squares support vector machine (LS-SVM). Using the learned LPV model, a model predictive controller (MPC) scheme is then developed for a 2-liter 4-cylinder RCCI engine to control combustion phasing (CA50) and indicated mean effective pressure (IMEP) while limiting the maximum pressure rise rate (MPRR) to avoid engine knocking. The simulation results show that the designed controller is capable of limiting MPRR below 6 bar/CAD while tracking CA50 and IMEP with average errors of 1.2 CAD and 6.2 kPa, respectively.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".