SAE International Journal of Engines最新文献

{"title":"AI-Based Virtual Sensing of Gaseous Pollutant Emissions at the\u0000 Tailpipe of a High-Performance Vehicle","authors":"Emanuele Giovannardi, A. Brusa, Boris Petrone, N. Cavina, Roberto Tonelli, Ioannis Kitsopanidis","doi":"10.4271/03-17-04-0029","DOIUrl":"https://doi.org/10.4271/03-17-04-0029","url":null,"abstract":"This scientific publication presents the application of artificial intelligence\u0000 (AI) techniques as a virtual sensor for tailpipe emissions of CO, NOx, and HC in\u0000 a high-performance vehicle. The study aims to address critical challenges faced\u0000 in real industrial applications, including signal alignment and signal dynamics\u0000 management. A comprehensive pre-processing pipeline is proposed to tackle these\u0000 issues, and a light gradient-boosting machine (LightGBM) model is employed to\u0000 estimate emissions during real driving cycles. The research compares two\u0000 modeling approaches: one involving a unique “direct model” and another using a\u0000 “two-stage model” which leverages distinct models for the engine and the\u0000 aftertreatment. The findings suggest that the direct model strikes the best\u0000 balance between simplicity and accuracy. Furthermore, the study investigates two\u0000 sensor setups: a standard configuration and an optimized one, which incorporates\u0000 an additional lambda probe in the exhaust line after the main catalyst. The\u0000 results indicate a significant enhancement in performance for NOx and CO\u0000 estimations with the introduction of the third lambda probe, while HC results\u0000 remain relatively unchanged. Additionally, the AI model is tested on two\u0000 different electronic control unit (ECU) software calibrations, yielding\u0000 excellent results in both cases. This suggests that machine learning models are\u0000 robust to control software variation and can be used to optimize software\u0000 calibrations in a virtual environment, reducing the reliance on extensive\u0000 experimental testing. Moreover, the AI model’s performance demonstrates\u0000 compatibility with real-time implementation. In conclusion, this work\u0000 establishes the viability and efficiency of AI techniques in accurately\u0000 estimating tailpipe emissions from an engine in an industrial context. The study\u0000 showcases the potential for AI to contribute to emission estimation and\u0000 optimization processes, offering a promising pathway for an innovative\u0000 industrial practice.","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":"18 2","pages":""},"PeriodicalIF":1.2,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139441541","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}

{"title":"Influence of Passive Pre-Chamber Nozzle Diameter on Jet Ignition in a\u0000 Constant-Volume Optical Engine under Varying Load and Dilution\u0000 Conditions","authors":"Dong Eun Lee, Tianxiao Yu, Afaque Alam, Claudia Iyer, Steven Wooldridge, Li Qiao, J. Yi","doi":"10.4271/03-17-04-0028","DOIUrl":"https://doi.org/10.4271/03-17-04-0028","url":null,"abstract":"Despite the growing prominence of electrified vehicles, internal combustion\u0000 engines remain essential in future transportation. This study delves into\u0000 passive pre-chamber jet ignition, a leading-edge combustion technology, offering\u0000 a comprehensive visualization of its operation under varying load and dilution\u0000 conditions in light-duty GDI engines. Our primary objectives are to gain\u0000 fundamental insights into passive pre-chamber jet ignition and subsequent main\u0000 combustion processes and evaluate their response to different load and dilution\u0000 conditions. We conducted experimental investigations using a light-duty,\u0000 optical, single-cylinder engine equipped with three passive pre-chamber designs\u0000 featuring varying nozzle diameters. Optical diagnostic imaging and heat release\u0000 analysis provided critical insights. Findings reveal that as load decreases,\u0000 fuel availability and flow conditions deteriorate, leading to delayed and\u0000 suboptimal jet characteristics impacting main chamber ignition and combustion.\u0000 Notably, at high and medium loads without dilution, the 1.2 mm-PC (smallest\u0000 nozzle diameter) excels, exhibiting superior jet ignition and main combustion.\u0000 This is attributed to earlier jet ejection, improved penetration, and\u0000 intensified jets, all enabled by the smaller nozzle diameter. Conversely, under\u0000 low load conditions, the 1.6 mm-PC (largest nozzle diameter) performs better due\u0000 to enhanced scavenging and reduced pre-chamber residuals, resulting in more\u0000 balanced pre-chamber combustion and jet characteristics. Furthermore, nozzle\u0000 diameter significantly influences cycle-to-cycle variations, with smaller\u0000 diameters enhancing jet ignition but intensifying variability. The impact of\u0000 external residuals (dilution) on jet ignition performance varies with nozzle\u0000 diameter, with the 1.6 mm-PC displaying less degradation and demonstrating\u0000 earlier jet ejection and CA50 timing under higher dilution conditions. In\u0000 summary, this research underscores the importance of scavenging and residual\u0000 levels in pre-chamber design, influencing dilution tolerance, and extending\u0000 possibilities for high-efficiency engines. It contributes essential insights\u0000 into the behavior of passive pre-chamber jet ignition systems, facilitating\u0000 their optimization for future internal combustion engines.","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":"70 12","pages":""},"PeriodicalIF":1.2,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138954700","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}

{"title":"Experimental Investigation on Noise and Vibration of an Internal\u0000 Combustion Engine with Oxyhydrogen Decarbonization","authors":"S. Raikar, Adil Ahmed Shaikh, Mohmmed Irfan Dukandar, Nilesh Kakatkar, Pratik Prakash Naik, Sahil Kumar Manjilkar","doi":"10.4271/03-17-04-0026","DOIUrl":"https://doi.org/10.4271/03-17-04-0026","url":null,"abstract":"Internal combustion engines are prone to get carbon deposits or residue which\u0000 accumulate due to incomplete fuel combustion. This can have adverse effects on\u0000 engine efficiency and performance. Engine decarbonization is one of the recent\u0000 technologies in automobile maintenance, which involves the removal of carbon\u0000 deposits or residue from various components within the internal combustion\u0000 engine, including valves, pistons, cylinder heads, and combustion chambers.\u0000 Decarbonization methods typically utilize specialized cleaning agents or\u0000 additives to dissolve and eliminate these carbon deposits claiming to enhance\u0000 engine performance and restoring optimal functionality. This article focuses to\u0000 study the effects of engine decarbonization on noise and vibration of an IC\u0000 engine. Oxyhydrogen (HHO) carbon cleaning machine has been used for\u0000 decarbonization of the engine. This research addresses a contemporary concern in\u0000 automotive maintenance by investigating the potential benefits of\u0000 decarbonization in reducing noise and vibration levels. The results obtained\u0000 from the data analysis provide insights into the effectiveness of the HHO carbon\u0000 cleaning in improving engine performance. After decarbonization, the average\u0000 noise levels have been observed to be decreased by an average of 3.28%, with a\u0000 maximum reduction of 8.42% at a specific location and RPM value. Additionally,\u0000 the vibration levels decreased by an average of 3.44%, with a maximum reduction\u0000 of 16.38% at a particular location and RPM value.","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":"46 8","pages":""},"PeriodicalIF":1.2,"publicationDate":"2023-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138588678","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}

{"title":"Combustion Optimization of a Premixed Ultra-Lean Blend of Natural Gas\u0000 and Hydrogen in a Dual Fuel Engine Running at Low Load","authors":"C. Rinaldini, F. Scrignoli, T. Savioli, E. Mattarelli","doi":"10.4271/03-17-04-0025","DOIUrl":"https://doi.org/10.4271/03-17-04-0025","url":null,"abstract":"The numerical study presented in this article is based on an automotive diesel\u0000 engine (2.8 L, 4-cylinder, turbocharged), considering a NG–H2 blend\u0000 with 30 vol% of H2, ignited by multiple diesel fuel injections. The\u0000 3D-CFD investigation aims at improving BTE, CO, and UHC emissions at low load,\u0000 by means of an optimization of the diesel fuel injection strategy and of the\u0000 in-cylinder turbulence (swirl ratio, SR). The operating condition is 3000 rpm –\u0000 BMEP = 2 bar, corresponding to about 25% of the maximum load of a gen-set\u0000 engine, able to deliver up to 83 kW at 3000 rpm (rated speed). The reference\u0000 diesel fuel injection strategy, adopted in all the previous numerical and\u0000 experimental studies, is a three-shot mode. The numerical optimization carried\u0000 out in this study consisted in finding the optimal number of injections per\u0000 cycle, as well as the best timing of each injection and the fuel mass split\u0000 among the injections. The analysis revealed that combustion can be improved by\u0000 increasing the local concentration of the more reactive fuel (diesel): in\u0000 detail, the best strategy is a two-shot mode, with SOI1 = −35°CA AFTDC and SOI2\u0000 = −20°CA AFTDC, injecting 70% of the total diesel fuel mass at the first shot.\u0000 As far as the SR is concerned, the best compromise between performance and\u0000 emissions was found for a relatively low SR = 1.4. The optimization permitted to\u0000 extract the full potential of the H2 enrichment in the DF\u0000 H2/NG–diesel combustion also at low loads: in comparison to the\u0000 DF NG case, combustion efficiency, and gross indicated thermal efficiency have\u0000 been improved by 45.7% and 61.0%, respectively; CO- and UHC-specific emissions\u0000 have been reduced by about 85.0%. Comparing CDC to the optimized DF 30 vol%\u0000 H2/NG–diesel case, soot emissions are completely canceled,\u0000 CO2-specific emissions have been reduced by approximately 42.0%,\u0000 NOx-specific emissions by 33.8%. However, further work has to be\u0000 done in order to reach comparable values of HC and CO, which are still higher\u0000 than in a standard diesel combustion.","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":" 38","pages":""},"PeriodicalIF":1.2,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138614312","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}

{"title":"Research on the Secondary Motion of Engine Piston Considering the Transport of Lubricating Oil","authors":"Jihai Liu, Jun Sun","doi":"10.4271/03-17-03-0024","DOIUrl":"https://doi.org/10.4271/03-17-03-0024","url":null,"abstract":"At present, it is generally considered in the analysis of the secondary motion of engine piston that the piston skirt–cylinder liner friction pair is fully lubricated in an engine operating cycle. However, in practice, when the piston moves upward, the amount of lubricating oil at the inlet may not ensure that the friction pair is fully lubricated. In this article, the secondary motion of piston is studied when the transport of lubricating oil is considered to determine the lubrication condition of piston skirt–cylinder liner friction pair. The secondary motion of piston is solved based on the combined piston motion model, hydrodynamic lubrication model, asperity contact model, and lubricating oil flow model. The secondary motion equation of piston is solved by the Broyden method. The hydrodynamic lubrication equation is solved by the finite difference method. The asperity contact between piston skirt and cylinder liner is calculated by the Greenwood model. The flow of lubricating oil is analyzed based on the theory of fluid mechanics. The results indicate that, when the actual transport of lubricating oil is considered to determine the lubrication condition of piston skirt–cylinder liner friction pair, the secondary motion of piston is remarkably different from that in which the flooded lubrication is assumed in an engine operating cycle. Therefore, it is helpful to improve the accuracy and make the analysis closer to the actual engine operating situation that the transport of lubricating oil is considered in the analysis of the secondary motion of engine piston.","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":"3 3","pages":""},"PeriodicalIF":1.2,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139253802","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}

{"title":"The Neutronic Engine: A Platform for Operando Neutron Diffraction in Internal Combustion Engines","authors":"Martin Wissink, Christopher L. Wray, P.M. Lee, Matthew M. Hoffmeyer, Matthew J. Frost, Ke An, Yan Chen","doi":"10.4271/03-17-02-0016","DOIUrl":"https://doi.org/10.4271/03-17-02-0016","url":null,"abstract":"<div>Neutron diffraction is a powerful tool for noninvasive and nondestructive characterization of materials and can be applied even in large devices such as internal combustion engines thanks to neutrons’ exceptional ability to penetrate many materials. While proof-of-concept experiments have shown the ability to measure spatially and temporally resolved lattice strains in a small aluminum engine on a timescale of minutes over a limited spatial region, extending this capability to timescales on the order of a crank angle degree over the full volume of the combustion chamber requires careful design and optimization of the engine structure to minimize attenuation of the incident and diffracted neutrons to maximize count rates. We present the design of a “neutronic engine,” which is analogous to an optical engine in that the materials and external geometry of a typical automotive engine have been optimized to maximize access of the diagnostic while maintaining the internal combustion chamber geometry and operability of the engine. The high transparency of aluminum to neutrons makes it the ideal window material for neutron diagnostics, which allows the neutronic engine to be a truly all-metal engine with the same load and boundary condition capabilities of a modern downsized passenger car engine. The neutronic engine will enable 3D and time-resolved measurements of strain, stress, and temperature fields as well as phase transformation, texture, and microstructure throughout the metal components of the combustion chamber.</div>","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":" 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135291316","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}

{"title":"Innovative Model-Free Onboard Diagnostics for Diesel Particulate Filter","authors":"Bilal Youssef","doi":"10.4271/03-17-03-0023","DOIUrl":"https://doi.org/10.4271/03-17-03-0023","url":null,"abstract":"<div>Recent legislations require very low soot emissions downstream of the particulate filter in diesel vehicles. It will be difficult to meet the new more stringent OBD requirements with standard diagnostic methods based on differential sensors. The use of inexpensive and reliable soot sensors has become the focus of several academic and industrial works over the past decade. In this context, several diagnostic strategies have been developed to detect DPF malfunction based on the soot sensor loading time. This work proposes an advanced online diagnostic method based on soot sensor signal projection. The proposed method is model-free and exclusively uses soot sensor signal without the need for subsystem models or to estimate engine-out soot emissions. It provides a comprehensive and efficient filter monitoring scheme with light calibration efforts. The proposed diagnostic algorithm has been tested on an experimentally validated simulation platform. 2D signatures are generated from soot sensor signal for nominal and faulty configurations. Gaussian dispersions on soot estimator (30%) and sensor model (15%) have been considered. Based on a statistical analysis, a relevant threshold is defined satisfying a compromise between non-detection and false alarm rates. The selected threshold is then used for online DPF diagnostic using NEDC cycle. The obtained results are promising and clearly show the performance of the proposed method in terms of non-detection and false alarm rates. The resulting diagnostic scheme can be easily integrated in the ECU for onboard DPF monitoring.</div>","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":" 16","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135291312","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}

{"title":"Methanol (M85) Port-Fuel-Injected Spark Ignition Motorcycle Engine Development—Part 2: Dynamic Performance, Transient Emissions, and Catalytic Converter Effectiveness","authors":"Avinash Agarwal, Omkar Yadav, Hardikk Valera","doi":"10.4271/03-17-03-0019","DOIUrl":"https://doi.org/10.4271/03-17-03-0019","url":null,"abstract":"<div>Methanol is emerging as an alternate internal combustion engine fuel. It is getting attention in countries such as China and India as an emerging transport fuel. Using methanol in spark ignition engines is easier and more economical than in compression ignition engines via the blending approach. M85 (85% v/v methanol and 15% v/v gasoline) is one of the preferred blends with the highest methanol concentration. However, its physicochemical properties significantly differ from gasoline, leading to challenges in operating existing vehicles. This experimental study addresses the challenges such as cold-start operation and poor throttle response of M85-fueled motorcycle using a port fuel injection engine. In this study, M85-fueled motorcycle prototype is developed with superior performance, similar/better drivability, and lower emissions than a gasoline-fueled port-fuel-injected motorcycle. An open electronic control unit was installed using suitable wiring harness/sensors and actuators to control the engine. Then the motorcycle electronic control unit was calibrated for transient operations on a chassis dynamometer. The motorcycle was tested under road load simulation and wide-open throttle conditions on the chassis dynamometer to compare its performance with a baseline gasoline-fueled motorcycle. Evaluation parameters included power at wheels, maximum vehicle speed, and time-based and speed-based acceleration characteristics. Transient emissions were evaluated following the Indian driving cycle protocols. The effectiveness of the catalytic converter for M85 fueling was assessed by comparing various emissions upstream and downstream of the catalytic converter. M85-fueled motorcycle generated higher power at wheels and similar maximum speeds as baseline gasoline-fueled motorcycle. Fine-tuned M85-fueled motorcycle exhibited superior acceleration characteristics over baseline gasoline-fueled motorcycle, indicating that an appropriate tuning strategy could tackle the issue of “drivability.” M85-fueled motorcycle emitted lower carbon monoxide and hydrocarbon during the warm-up cycles in the Indian driving cycle protocol. The inherent fuel oxygen of M85 enhanced the carbon monoxide–carbon dioxide conversion, reducing carbon monoxide emissions in the engine exhaust. The existing catalytic converter was also suitable for M85 fueling since the hydrocarbon, nitric oxide, and carbon monoxide emissions were effectively reduced downstream of the catalytic converter in all test conditions.</div>","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136312087","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}

{"title":"Methanol (M85) Port Fuel-Injected Spark Ignition Motorcycle Engine Development—Part 1: Combustion Optimization for Efficiency Improvement and Emission Reduction","authors":"Avinash Agarwal, Omkar Yadav, Hardikk Valera","doi":"10.4271/03-17-03-0018","DOIUrl":"https://doi.org/10.4271/03-17-03-0018","url":null,"abstract":"<div>Limited fossil fuel resources and carbonaceous greenhouse gas emissions are two major problems the world faces today. Alternative fuels can effectively power internal combustion engines to address these issues. Methanol can be an alternative to conventional fuels, particularly to displace gasoline in spark ignition engines. The physicochemical properties of methanol are significantly different than baseline gasoline and fuel mixture-aim lambda; hence methanol-fueled engines require modifications in the fuel injection parameters. This study optimized the fuel injection quantity, spark timing, and air–fuel ratio for M85 (85% v/v methanol + 15% v/v gasoline) fueling of a port fuel-injected single-cylinder 500 cc motorcycle test engine. Comparative engine performance, combustion, and emissions analyses were performed for M85 and baseline gasoline. M85-fueled engine exhibited improved combustion characteristics such as higher peak in-cylinder pressure, heat release rate, and cumulative heat release due to higher flame speed and the effect of fuel oxygen. The brake thermal efficiency increased by up to 23% at lower loads and 8% at higher loads for M85 fueling. Carbon monoxide was reduced by 11.4–94% and 46.1–94.4% for M85 w.r.t. baseline gasoline at 2500 and 3500 rpm, respectively, at varying engine loads. Hydrocarbon emissions showed mixed trends for M85 w.r.t. baseline gasoline. Nitric oxide emissions were 4–90.2% higher for M85 w.r.t. baseline gasoline at 2500 rpm, at varying engine loads; however, mixed trends were observed at 1500 and 3500 rpm. Carbon monoxide, hydrocarbons, and nitric oxide emissions were 4.6, 38.9, and 84.3% lower for M85 than baseline gasoline during idling. Overall the M85-fueled motorcycle engine emitted fewer harmful pollutants, indicating its superior environmental sustainability, except for slightly higher NO emission.</div>","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136312088","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}

{"title":"Investigations on Multiple Injection Strategies in a Common Rail Diesel Engine Using Machine Learning and Image-Processing Techniques","authors":"Abhijeet Vaze, Pramod S. Mehta, Anand Krishnasamy","doi":"10.4271/03-17-03-0021","DOIUrl":"https://doi.org/10.4271/03-17-03-0021","url":null,"abstract":"<div>The present study examines the effect of the multiple injection strategies in a common rail diesel engine using machine learning, image processing, and object detection techniques. The study demonstrates a novel approach of utilizing image-processing tools to gain information from heat release rates and in-cylinder visualizations from experimental or computational studies. The 3D CFD combustion and emission predictions of a commercial code ANSYS FORTE© are validated with small-bore common rail diesel engine data with known injection strategies. The validated CFD tool is used as a virtual plant model to optimize the injection schedule for reducing oxides of nitrogen (NO_x) and soot emissions using an apparent heat release rate image-based machine learning tool. A methodology of the machine learning tool is quite helpful in predicting the NO–soot trade-off. This methodology shows a significant reduction in soot and NO emissions using a pilot–main–post-injection schedule of 25% pilot, 25% post-, and 50% main injection, compared to a baseline pilot–main injection schedule. In addition, this work attempts a robust and high-fidelity optimization of the fuel injection schedule using the random forest algorithm for predicting the NO and soot emissions using 73 simulations done with different pilot–main and pilot–main–post-injection strategies on a small-bore diesel engine. Further, the object detection algorithm is trained on simulation data from the small-bore engine for detecting the interaction between the developed combustion from the pilot or main with sprays of subsequent injections using in-cylinder 3D CFD simulation and experimental data. A small-bore engine dataset shows that the trained object detection algorithm successfully corroborates the simulation and experimental data interaction. This investigation, therefore, presents a novel application of object detection methodology by automating the process and providing a general-purpose object detection algorithm. This approach can be used on any new simulation or experimental data for automated detection of the spray–thermal zone interaction without human intervention.</div>","PeriodicalId":47948,"journal":{"name":"SAE International Journal of Engines","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134906715","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}