E. Fornaro, Massimo Cardone, M. Terzo, S. Strano, C. Tordela
In the aeronautical field, aircraft reliability is strictly dependent on propulsion systems. Indeed, a reliable propulsion system ensures the safety of pilots and passengers and the possibility of making comfortable flights. Typically, on aircraft equipped with spark ignition (SI) engines, one of the principal requirements to make them reliable is the correct balancing between the intake air mass and fuel flows. Advances in the implementation of sophisticated control and estimation strategies on SI engines allow realizing engines with improved features in terms of performance, reducing pollution emissions, and fuel consumption. Approaches based on sensor redundancy are applied to improve the reliability in measurements of the manifold air pressure (MAP) and flow (MAF) to avoid issues related to possible faults of sensors vital for the correct functioning of SI engines. Model-based estimation techniques, based on the speed–density and alpha-speed methods for determining the MAF in engine control units, are employed to obtain sensor-less redundancy. The prediction of MAP and MAF, for sensors redundancy purposes, can be made through neural networks, allowing the avoidance of effects due to unmodeled dynamical behaviors. A sensor redundancy approach based on feedforward neural networks (FNNs) is proposed in this work for MAP and MAF prediction of a SI engine. The present work focuses on the possibility of estimating the physical quantities related to SI engines, such as the MAP and the MAF, fundamental for their monitoring using neural networks trained by means of a model-based approach avoiding expensive experimental tests for producing training data. A well-known intake manifold dynamical model (IMDM), parametrized based on the CMD 22 aeronautical engine, is employed for generating synthetic training data in steady-state conditions functional for making the chosen FNNs able to predict both MAP and MAF even in transient behavior. The MAP and MAF are predicted through two virtual sensors based on two independent FNNs, having the same inputs, constituted by the engine speed and the throttle angle. An experimental investigation based on an aircraft endurance test of two hours proposed by the European Aviation Safety Agency (EASA) has been made on a controlled and monitored CMD 22 engine for comparing the experimentally measured MAP and MAF with the predicted ones by the FNNs. The results demonstrate the suitability of the proposed approach for sensor redundancy purposes in SI engines to increase their reliability.
{"title":"Experimentally Validated Neural Networks for Sensors Redundancy\u0000 Purposes in Spark Ignition Engines","authors":"E. Fornaro, Massimo Cardone, M. Terzo, S. Strano, C. Tordela","doi":"10.4271/03-17-02-0012","DOIUrl":"https://doi.org/10.4271/03-17-02-0012","url":null,"abstract":"In the aeronautical field, aircraft reliability is strictly dependent on\u0000 propulsion systems. Indeed, a reliable propulsion system ensures the safety of\u0000 pilots and passengers and the possibility of making comfortable flights.\u0000 Typically, on aircraft equipped with spark ignition (SI) engines, one of the\u0000 principal requirements to make them reliable is the correct balancing between\u0000 the intake air mass and fuel flows. Advances in the implementation of\u0000 sophisticated control and estimation strategies on SI engines allow realizing\u0000 engines with improved features in terms of performance, reducing pollution\u0000 emissions, and fuel consumption. Approaches based on sensor redundancy are\u0000 applied to improve the reliability in measurements of the manifold air pressure\u0000 (MAP) and flow (MAF) to avoid issues related to possible faults of sensors vital\u0000 for the correct functioning of SI engines. Model-based estimation techniques,\u0000 based on the speed–density and alpha-speed methods for determining the MAF in\u0000 engine control units, are employed to obtain sensor-less redundancy. The\u0000 prediction of MAP and MAF, for sensors redundancy purposes, can be made through\u0000 neural networks, allowing the avoidance of effects due to unmodeled dynamical\u0000 behaviors. A sensor redundancy approach based on feedforward neural networks\u0000 (FNNs) is proposed in this work for MAP and MAF prediction of a SI engine. The\u0000 present work focuses on the possibility of estimating the physical quantities\u0000 related to SI engines, such as the MAP and the MAF, fundamental for their\u0000 monitoring using neural networks trained by means of a model-based approach\u0000 avoiding expensive experimental tests for producing training data. A well-known\u0000 intake manifold dynamical model (IMDM), parametrized based on the CMD 22\u0000 aeronautical engine, is employed for generating synthetic training data in\u0000 steady-state conditions functional for making the chosen FNNs able to predict\u0000 both MAP and MAF even in transient behavior.\u0000\u0000 \u0000The MAP and MAF are predicted through two virtual sensors based on two\u0000 independent FNNs, having the same inputs, constituted by the engine speed and\u0000 the throttle angle. An experimental investigation based on an aircraft endurance\u0000 test of two hours proposed by the European Aviation Safety Agency (EASA) has\u0000 been made on a controlled and monitored CMD 22 engine for comparing the\u0000 experimentally measured MAP and MAF with the predicted ones by the FNNs. The\u0000 results demonstrate the suitability of the proposed approach for sensor\u0000 redundancy purposes in SI engines to increase their reliability.","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89526010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}