Khashayar Ebrahimi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Khashayar Ebrahimi has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Charles Robert Koch
Department of Mechanical Engineering, University of Alberta, Edmonton, AB, Canada
4 shared publications Charles Robert Koch
2 shared publicationsSeyed Ali Jazayeri
K.N.Toosi University of Technology, Mechanical Engineering Department, Tehran, Iran
2 shared publicationsAlex Schramm
1 shared publicationAlexander Schramm
Department of Mechanical Engineering, University of Alberta, Edmonton, T6G 2G8, Canada
1 shared publicationArmin Norouzi
1 shared publication
Latest Publications
- 20 October 2024
- Published by ASME International
Soot Particle Number Prediction in GDI Engines: A Comprehensive Grey-Box Machine Learning Approach
Particulate matter (PM) emissions, including soot, pose a significant environmental concern. Traditional emission control approaches, such as engine calibration, often struggle to maintain consistent performance across varying driving conditions, engine speeds, and loads. This inconsistency leads to variations in pollutant output, making it challenging for internal combustion engines to comply with stringent emission standards under real-world driving conditions. Physics-based soot models, grounded in complex mathematical equations, have been developed to capture the mechanisms of soot formation. However, these models often face accuracy limitations and require substantial computational resources, rendering them impractical for real-time emission control. In contrast, Machine Learning (ML) techniques offer a more versatile and efficient approach to soot prediction. This paper introduces a machine learning methodology for predicting Soot Particle Numbers (PN). The approach integrates both physics-based and black-box strategies to create a grey-box model for predicting soot emissions from a 1600 cc Gasoline Direct Injection (GDI) engine across diverse load and speed conditions. The physical model is based on a validated 1D engine model in GT-SUITE, while the black-box model is formulated using multiple ML approaches exclusively on measured data. Ultimately, the grey-box model is developed through ML techniques based on measured data and combustion-related parameters obtained from the 1D engine physical model in GT-SUITE. The grey-box model’s results are compared with those of the black-box model. The ML techniques employed in this study include Gaussian Process Regression (GPR), Support Vector Machine (SVM), Artificial Neural Network (ANN), and an Ensemble of Regression Trees (ERT). The Minimum Redundancy Maximum Relevance (MRMR) and RreliefF feature selection methods are used to identify the most crucial features in soot PN prediction. The results indicate that the grey-box GPR exhibits superior performance for both single and multi-pulse injection strategies, achieving a coefficient of determination (R2) of 0.99.
- 20 October 2024
- Published by ASME International
Soot Particle Number Prediction in GDI Engines: A Comprehensive Grey-Box Machine Learning Approach
Particulate matter (PM) emissions, including soot, pose a significant environmental concern. Traditional emission control approaches, such as engine calibration, often struggle to maintain consistent performance across varying driving conditions, engine speeds, and loads. This inconsistency leads to variations in pollutant output, making it challenging for internal combustion engines to comply with stringent emission standards under real-world driving conditions. Physics-based soot models, grounded in complex mathematical equations, have been developed to capture the mechanisms of soot formation. However, these models often face accuracy limitations and require substantial computational resources, rendering them impractical for real-time emission control. In contrast, Machine Learning (ML) techniques offer a more versatile and efficient approach to soot prediction. This paper introduces a machine learning methodology for predicting Soot Particle Numbers (PN). The approach integrates both physics-based and black-box strategies to create a grey-box model for predicting soot emissions from a 1600 cc Gasoline Direct Injection (GDI) engine across diverse load and speed conditions. The physical model is based on a validated 1D engine model in GT-SUITE, while the black-box model is formulated using multiple ML approaches exclusively on measured data. Ultimately, the grey-box model is developed through ML techniques based on measured data and combustion-related parameters obtained from the 1D engine physical model in GT-SUITE. The grey-box model’s results are compared with those of the black-box model. The ML techniques employed in this study include Gaussian Process Regression (GPR), Support Vector Machine (SVM), Artificial Neural Network (ANN), and an Ensemble of Regression Trees (ERT). The Minimum Redundancy Maximum Relevance (MRMR) and RreliefF feature selection methods are used to identify the most crucial features in soot PN prediction. The results indicate that the grey-box GPR exhibits superior performance for both single and multi-pulse injection strategies, achieving a coefficient of determination (R2) of 0.99.
- 1 July 2024
- Published by Springer Nature
- p. 241-255
Simulation Study on Laminar Flame Speed of Ammonia-Hydrogen Blends Using Artificial Neural Networks
- 1 July 2024
- Published by Springer Nature
- p. 241-255
Simulation Study on Laminar Flame Speed of Ammonia-Hydrogen Blends Using Artificial Neural Networks
- 28 December 2023
- Published by SAE International in SAE International Journal of Engines
- Vol. 17 (4) , 477-492
Machine Learning Tabulation Scheme for Fast Chemical Kinetics Computation
- 28 December 2023
- Published by SAE International in SAE International Journal of Engines
- Vol. 17 (4) , 477-492
Machine Learning Tabulation Scheme for Fast Chemical Kinetics Computation
- Open Access
- 8 April 2021
- Published by SAGE Publications in International Journal of Engine Research
- Vol. 23 (7) , 1159-1179
Evaluation of ASTM D6424 standard for knock analysis using unleaded fuel candidates on a six cylinder aircraft engine
The ASTM D6424 standard is used for general aviation piston engine knock detection and is tested for unleaded fuel candidates. Issues are discussed regarding the identification of knocking cycles, filtering frequency bands, and the effects of down-sampling for this knock detection technique. The knock tests were performed on the Continental TSIO-520-VB engine at 12,000 ft for take-off and cruise conditions using three different fuels, the standard leaded 100LL avgas and two unleaded fuel candidates. The ASTM D6424 knock detection method has its own particular disadvantages, which are detailed and compared to other knock detection methods including the third derivative of pressure signal and discrete wavelet transform. Updates to the standard include a minimum sampling rate of 0.2 CAD. Additionally, the current standard does not contain recommendations for filtering the cylinder pressure which results in over detection of knocking cycles with the two new aviation fuel candidates tested. Recommendations are provided regarding the pressure signal processing prior to ASTM D6424 knock-characterization.
- 8 April 2021
- Published by SAGE Publications in International Journal of Engine Research
- Vol. 23 (7) , 1159-1179
Open AccessEvaluation of ASTM D6424 standard for knock analysis using unleaded fuel candidates on a six cylinder aircraft engine
The ASTM D6424 standard is used for general aviation piston engine knock detection and is tested for unleaded fuel candidates. Issues are discussed regarding the identification of knocking cycles, filtering frequency bands, and the effects of down-sampling for this knock detection technique. The knock tests were performed on the Continental TSIO-520-VB engine at 12,000 ft for take-off and cruise conditions using three different fuels, the standard leaded 100LL avgas and two unleaded fuel candidates. The ASTM D6424 knock detection method has its own particular disadvantages, which are detailed and compared to other knock detection methods including the third derivative of pressure signal and discrete wavelet transform. Updates to the standard include a minimum sampling rate of 0.2 CAD. Additionally, the current standard does not contain recommendations for filtering the cylinder pressure which results in over detection of knocking cycles with the two new aviation fuel candidates tested. Recommendations are provided regarding the pressure signal processing prior to ASTM D6424 knock-characterization.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 357-365
Fractal Pattern Effects on Natural Convection Heat Transfer and Flow Characteristics
Thermal management is necessary to dissipate heat from semiconductors while keeping system efficiency high. There is a clear need for compact, effective, reliable, high-capacity, and quiet, passive cooling systems in the power electronics industry. A novel Smith-Volterra-Cantor (SVC) set fractal heat-sink is introduced and numerically investigated for natural convection. The SVC fractal pattern increases the heat transfer area and interrupts the thermal and aerodynamic boundary layers. The heat-sink mass and size are reduced with the SVC fractal design compared to the classical ones that make compact passive cooling system design feasible. The thermal performance of the fractal heat-sink is detailed, considering the fin scale and surface heat flux. The analysis indicates mass normalized fin effectiveness is improved, and the temperature is more uniformly distributed for fractal design. These results are applicable for the development of compact power-electronics passive thermal management design for telecommunication and aviation applications with reduced parasitic powers, noise, and vibration.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 357-365
Fractal Pattern Effects on Natural Convection Heat Transfer and Flow Characteristics
Thermal management is necessary to dissipate heat from semiconductors while keeping system efficiency high. There is a clear need for compact, effective, reliable, high-capacity, and quiet, passive cooling systems in the power electronics industry. A novel Smith-Volterra-Cantor (SVC) set fractal heat-sink is introduced and numerically investigated for natural convection. The SVC fractal pattern increases the heat transfer area and interrupts the thermal and aerodynamic boundary layers. The heat-sink mass and size are reduced with the SVC fractal design compared to the classical ones that make compact passive cooling system design feasible. The thermal performance of the fractal heat-sink is detailed, considering the fin scale and surface heat flux. The analysis indicates mass normalized fin effectiveness is improved, and the temperature is more uniformly distributed for fractal design. These results are applicable for the development of compact power-electronics passive thermal management design for telecommunication and aviation applications with reduced parasitic powers, noise, and vibration.
- 1 January 2019
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 52 (5) , 153-158
Integral Discrete-time Sliding Mode Control of Homogeneous Charge Compression Ignition (HCCI) Engine Load and Combustion Timing
- 1 January 2019
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 52 (5) , 153-158
Integral Discrete-time Sliding Mode Control of Homogeneous Charge Compression Ignition (HCCI) Engine Load and Combustion Timing
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1622-1628
Real-time Control of HCCI Engine Using Model Predictive Control
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1622-1628
Real-time Control of HCCI Engine Using Model Predictive Control
- 14 April 2015
- Published by SAE International in SAE International Journal of Advances and Current Practices in Mobility
- Vol. 1
Model Predictive Control for Combustion Timing and Load Control in HCCI Engines
A Model Predictive Control (MPC) strategy for Homogeneous Charge Compression Ignition (HCCI) combustion timing and output work control that takes into account actuator constraints is designed. The MPC is based on the linearized version of a nonlinear Control Oriented Model (COM). The COM for the HCCI engine has combustion timing and engine load as outputs and valve timing and fueling rate as the inputs. The COM model is developed and validated and found to be accurate enough for control purposes and can be implemented in real-time. A Detailed Physical Model (DPM) is used to test the controller using the valve timing and fueling rate as constrained actuators. Constraints on combustion timing and output work are also considered to prevent ringing or misfire. The simulation results show that the developed controller works over a range of load conditions and can maintain HCCI combustion timing and load to their desired values.
- 14 April 2015
- Published by SAE International in SAE International Journal of Advances and Current Practices in Mobility
- Vol. 1
Model Predictive Control for Combustion Timing and Load Control in HCCI Engines
A Model Predictive Control (MPC) strategy for Homogeneous Charge Compression Ignition (HCCI) combustion timing and output work control that takes into account actuator constraints is designed. The MPC is based on the linearized version of a nonlinear Control Oriented Model (COM). The COM for the HCCI engine has combustion timing and engine load as outputs and valve timing and fueling rate as the inputs. The COM model is developed and validated and found to be accurate enough for control purposes and can be implemented in real-time. A Detailed Physical Model (DPM) is used to test the controller using the valve timing and fueling rate as constrained actuators. Constraints on combustion timing and output work are also considered to prevent ringing or misfire. The simulation results show that the developed controller works over a range of load conditions and can maintain HCCI combustion timing and load to their desired values.