Heavy Duty Diesel Engine Modeling with Layered Artificial Neural Network Structures
Bibliographic record
Abstract
In order to meet emissions and power requirements, modern engine design has evolved in complexity and control. The cost and time restraints of calibration and testing of various control strategies have made virtual testing environments increasingly popular. Using Hardware-in-the-Loop (HiL), Volvo Penta has built a virtual test rig named VIRTEC for efficient engine testing, using a model simulating a fully instrumented engine. This paper presents an innovative Artificial Neural Network (ANN) based model for engine simulations in HiL environment. The engine model, herein called Artificial Neural Network Engine (ANN-E), was built for D8-600 hp Volvo Penta engine, and directly implemented in the VIRTEC system. ANN-E uses a combination of feedforward and recursive ANNs, processing 7 actuator signals from the engine management system (EMS) to provide 30 output signals. To improve the accuracy in predicting exhaust emissions, the ANNs were arranged into two layers, such that engine temperature and pressure output signals and their average rate of change act as extra inputs for exhaust emission signals. The simulation results show that the ANN-E model accurately predicts engine performance, engine temperatures and pressures along the flow path, as well as exhaust emissions. In addition, the modular nature of ANN-E makes it possible for fast rebuild of the model if engine components are changed. Therefore, the layered modular ANN modeling approach represents a powerful tool for virtual engine testing and calibration optimization.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".