Combustion of high carbon (C7-C8) alcohol fuels in a reactivity controlled compression ignition (RCCI) engine as low reactivity fuels and ANN approach to predict RCCI emissions

Okcu, Mutlu; Fırat, Müjdat; Varol, Yasin; Altun, Şehmus; Kamışlı, Fethi; Atila, Orhan

doi:10.1016/j.fuel.2022.123735

Cited by 22 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine Learning (ML)-based surrogate modeling of internal combustion engines (ICE) has been widely used for a broad range of applications. 25–29 Data-driven ML approaches, in particular, are popular for building ICE surrogate models; such approaches include neural networks (NN), 30–45 Support Vector Machines (SVM), 46–49 Gaussian Processes (GPs, 50–60 also known as kriging 61 ), and other learning models. 62–68 In surrogate modeling applications with limited training runs from expensive simulators, GPs (and its recent non-stationary extensions) have several key advantages over alternate deep learning models.…”

Section: Introductionmentioning

confidence: 99%

A misfire-integrated Gaussian process (MInt-GP) emulator for energy-assisted compression ignition (EACI) engines with varying cetane number jet fuels

Narayanan,

Ji,

Sapra

et al. 2024

International Journal of Engine Research

View full text Add to dashboard Cite

For energy-assisted compression ignition (EACI) engine propulsion at high-altitude operating conditions using sustainable jet fuels with varying cetane numbers, it is essential to develop an efficient engine control system for robust and optimal operation. Control systems are typically trained using experimental data, which can be costly and time consuming to generate due to setup time of experiments, unforeseen delays/issues with manufacturing, mishaps/engine failures and the consequent repairs (which can take weeks), and errors in measurements. Computational fluid dynamics (CFD) simulations can overcome such burdens by complementing experiments with simulated data for control system training. Such simulations, however, can be computationally expensive. Existing data-driven machine learning (ML) models have shown promise for emulating the expensive CFD simulator, but encounter key limitations here due to the expensive nature of the training data and the range of differing combustion behaviors (e.g. misfires and partial/delayed ignition) observed at such broad operating conditions. We thus develop a novel physics-integrated emulator, called the Misfire-Integrated GP (MInt-GP), which integrates important auxiliary information on engine misfires within a Gaussian process surrogate model. With limited CFD training data, we show the MInt-GP model can yield reliable predictions of in-cylinder pressure evolution profiles and subsequent heat release profiles and engine CA50 predictions at a broad range of input conditions. We further demonstrate much better prediction capabilities of the MInt-GP at different combustion behaviors compared to existing data-driven ML models such as kriging and neural networks, while also observing up to 80 times computational speed-up over CFD, thus establishing its effectiveness as a tool to assist CFD for fast data generation in control system training.

show abstract

Section: Introductionmentioning

confidence: 99%

A misfire-integrated Gaussian process (MInt-GP) emulator for energy-assisted compression ignition (EACI) engines with varying cetane number jet fuels

Narayanan,

Ji,

Sapra

et al. 2024

International Journal of Engine Research

View full text Add to dashboard Cite

show abstract

“…11 According to widely acknowledged observations, 12 traditional diesel engines have faced many ongoing difficulties, such as the development of localized rich zones inside the combustion chamber, lack of adequate mixing, and problems with autoignition. Numerous lowtemperature combustion strategies [13][14][15][16][17] have been developed in response to these difficulties, utilizing modern combustion technologies, like, Homogeneous Charge Compression Ignition (HCCI), Partially Premixed Compression Ignition, Reactivity Controlled Compression Ignition (RCCI), and Intelligent Charge Control Compression Ignition engines. Significant reductions in NO x emissions, very few exhaust soot production, increased thermal efficiency, improved fuel adaptability, and precise control over the rate of heat release are just a few of the advantages these novel approaches have shown.…”

Section: Introductionmentioning

confidence: 99%

A comparative study of the impact on combustion and emission characteristics of nanoparticle‐based fuel additives in the internal combustion engine

Gupta,

Kumar,

Maurya

et al. 2023

Energy Science & Engineering

View full text Add to dashboard Cite

The search for an effective solution to improve performance and emission characteristics of internal combustion (IC) engines used in the commercial sector is regarded as one of the most important and essential issues in recent years due to increasing levels of pollution. Nanoparticles with their additive ability to increase fuel reactivity and atomization, due to their large surface area and high heat transfer coefficient, can improve the performance and emission characteristics of a fuel. This review highlights the use of nanoparticles as fuel additives to enhance the emission and performance characteristics of IC engines. Detailed comparisons of performance, emission, and combustion characteristics of IC engines using fuels blended with nanoparticles have been done. Nanoparticles were observed to be an oxygen buffer for fuel combustion and boost fuel atomization, thus enhancing engine performance. While alumina exhibited a decrease in levels of HC and CO but a considerable increase in NOx, graphene nanoparticles and ceria were found to be particularly effective in enhancing engine performance. Detailed study has been done on other nanoparticles, including metal‐oxide, nonmetal‐oxide as well as carbon nanoparticles. Overall, the use of nanoparticles can enhance the thermophysical characteristics of fuels, improving the emission and performance characteristics of engines. The review suggests that selecting the right dosage and variety of nanoparticles is crucial for optimizing engine performance, and thus directly helps in tackling the ongoing pollution problem.

show abstract

“…Makine öğrenmesi yöntemleri tıp [8], inşaat [9], otomotiv [10], enerji [11], malzeme araştırma ve üretim endüstrisi [12][13][14][15] gibi farklı alanlarda başarıyla kullanılmaktadır. Karayel [16], çalışmasında St 50.2 çeliğini CNC torna tezgâhında farklı kesme derinlikleri, kesme hızları ve ilerleme hızlarında işlemiştir.…”

Section: Introductionunclassified

St37 Çeliğinin Tornalanmasında Yüzey Pürüzlülüğünün Destek Vektör Regresyonu Kullanılarak Tahmini

Altay

Gürgenç

2022

Fırat Üniversitesi Mühendislik Bilimleri Dergisi

View full text Add to dashboard Cite

St37 çeliği birçok yapısal elemanda sıklıkla tercih edilen bir malzemedir. Düşük yüzey pürüzlülük değerine sahip parçalar yorulma, aşınma ve korozyon açısından tercih sebebidir. Yüzey pürüzlülüklerinin deneysel olarak belirlenmesi zaman alıcı ve maliyetli olduğundan makine öğrenmesi yöntemleri ile yüzey pürüzlülükleri tahmin edilerek bu durumlar elemine edilebilir. Bu çalışmada, St37 çeliği CNC torna tezgâhında farklı parametrelerde işlenmiştir. Deneysel numunelerin yüzey pürüzlülükleri (Ra, µm) farklı işlem parametreleri için ayrı ayrı profilometre ile ölçülmüş ve 72 adet veri elde edilmiştir. Elde edilen deneysel değerler destek vektör regresyon (DVR) kullanılarak modellenmiştir. DVR iki farklı çekirdek fonksiyon kullanarak modellenmiştir. Bunlar lineer ve Gauss çekirdek fonksiyonlarıdır. Modellerde giriş parametreleri olarak iki farklı koşul (kuru ve ıslak durum), iş mili hızı (dev/dak) ve ilerleme hızı (mm/dev) kullanılmıştır. Çıkış parametresi ise yüzey pürüzlülüğüdür (Ra, µm) Tasarlanan modellerin sonucunda Gauss çekirdek fonksiyonunun kullanıldığı DVR’nin daha iyi performans gösterdiği görülmüştür. Bu modelde R-kare değeri 0.8876 olarak elde edilirken lineer fonksiyona sahip DVR’de 0.7231 olarak elde edilmiştir. Gauss çekirdek fonksiyonuna sahip DVR’nin tornalama ile St37 çeliğinden parçalar üreten endüstrilerde kullanılmasıyla zaman, malzeme ve maliyet kayıplarının azaltılabileceği beklenmektedir.

show abstract

Combustion of high carbon (C7-C8) alcohol fuels in a reactivity controlled compression ignition (RCCI) engine as low reactivity fuels and ANN approach to predict RCCI emissions

Cited by 22 publications

References 41 publications

A misfire-integrated Gaussian process (MInt-GP) emulator for energy-assisted compression ignition (EACI) engines with varying cetane number jet fuels

A misfire-integrated Gaussian process (MInt-GP) emulator for energy-assisted compression ignition (EACI) engines with varying cetane number jet fuels

A comparative study of the impact on combustion and emission characteristics of nanoparticle‐based fuel additives in the internal combustion engine

St37 Çeliğinin Tornalanmasında Yüzey Pürüzlülüğünün Destek Vektör Regresyonu Kullanılarak Tahmini

Contact Info

Product

Resources

About