Engine tests are both costly and time consuming in developing a new internal combustion engine.Therefore,it is of great importance to predict engine characteristics with high accuracy using artificial intelligence.Thu...Engine tests are both costly and time consuming in developing a new internal combustion engine.Therefore,it is of great importance to predict engine characteristics with high accuracy using artificial intelligence.Thus,it is possible to reduce engine testing costs and speed up the engine development process.Deep Learning is an effective artificial intelligence method that shows high performance in many research areas through its ability to learn high-level hidden features in data samples.The present paper describes a method to predict the cylinder pressure of a Homogeneous Charge Compression Ignition(HCCI)engine for various excess air coefficients by using Deep Neural Network,which is one of the Deep Learning methods and is based on the Artificial Neural Network(ANN).The Deep Learning results were compared with the ANN and experimental results.The results show that the difference between experimental and the Deep Neural Network(DNN)results were less than 1%.The best results were obtained by Deep Learning method.The cylinder pressure was predicted with a maximum accuracy of 97.83%of the experimental value by using ANN.On the other hand,the accuracy value was increased up to 99.84%using DNN.These results show that the DNN method can be used effectively to predict cylinder pressures of internal combustion engines.展开更多
For homogeneous charge compression ignition (HCCI) combustion, the auto-ignition process is very sensitive to in-cylinder conditions, including in-cylinder temperature, in-cylinder components and concentrations. The...For homogeneous charge compression ignition (HCCI) combustion, the auto-ignition process is very sensitive to in-cylinder conditions, including in-cylinder temperature, in-cylinder components and concentrations. Therefore, accurate control is required for reliable and efficient HCCI combustion. This paper outlines a simplified gasoline-fueled HCCI engine model implemented in Simulink environment. The model is able to run in real-time and with fixed simulation steps with the aim of cycle-to-cycle control and hardware- in-the-loop simulation. With the aim of controlling the desired amount of the trapped exhaust gas recirculation (EGR) from the previous cycle, the phase of the intake and exhaust valves and the respective profiles are designed to vary in this model. The model is able to anticipate the auto-ignition timing and the in-cylinder pressure and temperature. The validation has been conducted using a comparison of the experimental results on Ricardo Hydro engine published in a research by Tianjin University and a JAGUAR V6 HCCI test engine at the University of Birmingham. The comparison shows the typical HCCI combustion and a fair agreement between the simulation and experimental results.展开更多
The major advantages of homogeneous charge compression ignition (HCCI) are high efficiency in combination with low NOx-emissions. However, one of the major challenges with HCCI is the control of higher peak pressure...The major advantages of homogeneous charge compression ignition (HCCI) are high efficiency in combination with low NOx-emissions. However, one of the major challenges with HCCI is the control of higher peak pressures which may damage the engine, limiting the HCCI engine life period. In this paper, an attempt is made to analyze computationally the effect of induction swirl in controlling the peak pressures of an HCCI engine under various operating parameters. A single cylinder 1.6 L reentrant piston bowl diesel engine is chosen. For computational analysis, the ECFM-3Z model of STAR - CD is considered because it is suitable for analyzing the combustion processes in SI and CI engines. As an HCCI engine is a hybrid version of SI and CI engines, the ECFM- 3Z model with necessary modifications is used to analyze the peak pressures inside the combustion chamber. The ECFM-3Z model for HCCI mode of combustion is validated with the existing literature to make sure that the results obtained are accurate. Numerical experiments are performed to study the effect of varying properties like speed of the engine, piston bowl geometry, exhaust gas recirculation (EGR) and equivalence ratio under different swirl ratios in controlling the peak pressures inside the combustion chamber. The results show that the swirl ratio has a considerable impact on controlling the peak pressures of HCCI engine. A reduction in peak pressures are observed with a swirl ratio of 4 because of reduced in cylinder temperatures. The combined effect of four operating parameters, i.e., the speed of the engine, piston bowl geometry, EGR, and equivalence ratio with swirl ratios suggest that lower intake temperatures, reentrant piston bowl, higher engine speeds and higher swirl ratios are favorable in controlling the peak pressures.展开更多
文摘Engine tests are both costly and time consuming in developing a new internal combustion engine.Therefore,it is of great importance to predict engine characteristics with high accuracy using artificial intelligence.Thus,it is possible to reduce engine testing costs and speed up the engine development process.Deep Learning is an effective artificial intelligence method that shows high performance in many research areas through its ability to learn high-level hidden features in data samples.The present paper describes a method to predict the cylinder pressure of a Homogeneous Charge Compression Ignition(HCCI)engine for various excess air coefficients by using Deep Neural Network,which is one of the Deep Learning methods and is based on the Artificial Neural Network(ANN).The Deep Learning results were compared with the ANN and experimental results.The results show that the difference between experimental and the Deep Neural Network(DNN)results were less than 1%.The best results were obtained by Deep Learning method.The cylinder pressure was predicted with a maximum accuracy of 97.83%of the experimental value by using ANN.On the other hand,the accuracy value was increased up to 99.84%using DNN.These results show that the DNN method can be used effectively to predict cylinder pressures of internal combustion engines.
文摘For homogeneous charge compression ignition (HCCI) combustion, the auto-ignition process is very sensitive to in-cylinder conditions, including in-cylinder temperature, in-cylinder components and concentrations. Therefore, accurate control is required for reliable and efficient HCCI combustion. This paper outlines a simplified gasoline-fueled HCCI engine model implemented in Simulink environment. The model is able to run in real-time and with fixed simulation steps with the aim of cycle-to-cycle control and hardware- in-the-loop simulation. With the aim of controlling the desired amount of the trapped exhaust gas recirculation (EGR) from the previous cycle, the phase of the intake and exhaust valves and the respective profiles are designed to vary in this model. The model is able to anticipate the auto-ignition timing and the in-cylinder pressure and temperature. The validation has been conducted using a comparison of the experimental results on Ricardo Hydro engine published in a research by Tianjin University and a JAGUAR V6 HCCI test engine at the University of Birmingham. The comparison shows the typical HCCI combustion and a fair agreement between the simulation and experimental results.
文摘The major advantages of homogeneous charge compression ignition (HCCI) are high efficiency in combination with low NOx-emissions. However, one of the major challenges with HCCI is the control of higher peak pressures which may damage the engine, limiting the HCCI engine life period. In this paper, an attempt is made to analyze computationally the effect of induction swirl in controlling the peak pressures of an HCCI engine under various operating parameters. A single cylinder 1.6 L reentrant piston bowl diesel engine is chosen. For computational analysis, the ECFM-3Z model of STAR - CD is considered because it is suitable for analyzing the combustion processes in SI and CI engines. As an HCCI engine is a hybrid version of SI and CI engines, the ECFM- 3Z model with necessary modifications is used to analyze the peak pressures inside the combustion chamber. The ECFM-3Z model for HCCI mode of combustion is validated with the existing literature to make sure that the results obtained are accurate. Numerical experiments are performed to study the effect of varying properties like speed of the engine, piston bowl geometry, exhaust gas recirculation (EGR) and equivalence ratio under different swirl ratios in controlling the peak pressures inside the combustion chamber. The results show that the swirl ratio has a considerable impact on controlling the peak pressures of HCCI engine. A reduction in peak pressures are observed with a swirl ratio of 4 because of reduced in cylinder temperatures. The combined effect of four operating parameters, i.e., the speed of the engine, piston bowl geometry, EGR, and equivalence ratio with swirl ratios suggest that lower intake temperatures, reentrant piston bowl, higher engine speeds and higher swirl ratios are favorable in controlling the peak pressures.