Performance comparison of data-driven reduced models for a single-injector combustion process

2021 ◽  
Author(s):  
Parikshit Jain ◽  
Shane McQuarrie ◽  
Boris Kramer
Keyword(s):  
Combustion Process ◽  
Performance Comparison ◽  
Data Driven ◽  
Reduced Models

Study on Fuel and Injection Influence on a Spark Ignition Aeropiston Engine

2020 ◽  
Vol 142 (7) ◽  
Author(s):  
Wang Xiaogang ◽  
Liu Bolan ◽  
Yu Xiyang ◽  
Yan Chao ◽  
Yu Fei ◽  
...  
Keyword(s):  
Performance Test ◽  
Fuel Injection ◽  
Combustion Process ◽  
Weight Ratio ◽  
Engine Performance ◽  
Spark Ignition ◽  
Performance Comparison ◽  
Power Performance ◽  
Test Rig ◽  
Injection Methods

Abstract Spark ignition aeropiston engines have good prospects due to light weight and high power to weight ratio. Both gasoline and kerosene can be utilized on these engines by using either traditional port fuel injection (PFI) or the novel air-assisted fuel injection (A2FI). In this article, the effects of different fuels and injection methods on the performance of a four-cylinder opposed aeropiston engine were studied. The spray performance test rig and the engine performance test rig were established. First, the influence of different injection methods on engine performance were compared, which indicated that A2FI is superior to PFI in engine power and starting performance. Furthermore, the fuel performance comparison by using A2FI was conducted, which demonstrates that kerosene is inferior to gasoline in terms of spray characteristics and power performance. Finally, detailed working characteristics of A2FI system using kerosene were studied, which indicated that the stable and reliable operation of the spark-ignition operation can be realized and the kerosene's spark-ignition combustion process can be optimized similar to that of gasoline. Results shows that the use of kerosene combined with A2FI is the best technical way to achieve ideal working process of the spark ignition aeropiston engine.

iTrade

2015 ◽  
Vol 11 (1) ◽  
pp. 66-83 ◽  
Author(s):  
Yong Hu ◽  
Xiangzhou Zhang ◽  
Bin Feng ◽  
Kang Xie ◽  
Mei Liu
Keyword(s):  
Stock Market ◽  
Large Scale ◽  
Concept Drift ◽  
Composite Index ◽  
Performance Comparison ◽  
Mobile App ◽  
Data Driven ◽  
Support Vector ◽  
Individual Investors ◽  
Chinese Stock Market

Among all investors in the Chinese stock market, more than 95% are non-professional individual investors. These individual investors are in great need of mobile apps that can provide professional and handy trading analysis and decision support everywhere. However, financial data is challenging to analyze because of its large-scale, non-linear and noisy characteristics in a varying stock environment. This paper develops a Mobile Data-Driven Stock Trading System (iTrade), which is a mobile app system based on Client-Server architecture and various data mining techniques. The iTrade is characterized by 1) a data-driven intelligent learning model, which can provide further insight compared to empirical technical analysis, 2) a concept drift adaptation process, which facilitates the model adaptation to market structure changes, and 3) a rigorous benchmark analysis, including the Buy-and-Hold strategy and the strategies of three world-famous master investors (e.g., Warren E. Buffett). Technologies used in iTrade include the Least Absolute Shrinkage and Selection Operator (Lasso) algorithm, Support Vector Machine (SVM) and risk-adjusted portfolio optimization. An application case of iTrade is presented, which is based on a seven-year (2005-2011) back-testing. Evaluation results indicated that iTrade could gain much higher cumulative return compared to the benchmark (Shanghai Composite Index). To the best of our knowledge, this is the first study and mobile app system that emphasizes and investigates the concept drift phenomenon in stock market, as well as the performance comparison between data-driven intelligent model and strategies of master investors.

iTrade

2018 ◽  
pp. 995-1014
Author(s):  
Yong Hu ◽  
Xiangzhou Zhang ◽  
Bin Feng ◽  
Kang Xie ◽  
Mei Liu
Keyword(s):  
Stock Market ◽  
Concept Drift ◽  
Performance Comparison ◽  
Mobile App ◽  
Data Driven ◽  
Individual Investors ◽  
Chinese Stock Market ◽  
Back Testing ◽  
Structure Changes ◽  
Selection Operator

Among all investors in the Chinese stock market, more than 95% are non-professional individual investors. These individual investors are in great need of mobile apps that can provide professional and handy trading analysis and decision support everywhere. However, financial data is challenging to analyze because of its large-scale, non-linear and noisy characteristics in a varying stock environment. This paper develops a Mobile Data-Driven Stock Trading System (iTrade), which is a mobile app system based on Client-Server architecture and various data mining techniques. The iTrade is characterized by 1) a data-driven intelligent learning model, which can provide further insight compared to empirical technical analysis, 2) a concept drift adaptation process, which facilitates the model adaptation to market structure changes, and 3) a rigorous benchmark analysis, including the Buy-and-Hold strategy and the strategies of three world-famous master investors (e.g., Warren E. Buffett). Technologies used in iTrade include the Least Absolute Shrinkage and Selection Operator (Lasso) algorithm, Support Vector Machine (SVM) and risk-adjusted portfolio optimization. An application case of iTrade is presented, which is based on a seven-year (2005-2011) back-testing. Evaluation results indicated that iTrade could gain much higher cumulative return compared to the benchmark (Shanghai Composite Index). To the best of our knowledge, this is the first study and mobile app system that emphasizes and investigates the concept drift phenomenon in stock market, as well as the performance comparison between data-driven intelligent model and strategies of master investors.

The Comparison between Empirical and Data-driven Computation in Predicting CO and NOx Emissions from Gas-Turbine-Based Power Plant

2021 ◽  
Author(s):  
T. Y. Wicaksono
Keyword(s):  
Gas Turbine ◽  
Monitoring System ◽  
Power Plants ◽  
Combustion Process ◽  
Open Data ◽  
Living Organism ◽  
Empirical Method ◽  
Data Driven ◽  
Gas Emissions ◽  
Data Driven Approach

The demand for the energy has been significantly increased over years led by the growth of global population. By the signing of the Paris Agreement in 2015, countries pledged to reduce the greenhouse gas effect including gas emissions to prevent and mitigate the global warming. The emissions control from power generation has then become a serious concern for countries to achieve their target in reducing gas emissions. Besides, the emitted gas such as Nitrogen oxides (NOx) or Carbon Monoxide (CO) that are resulted from the combustion process of fossil fuels in power plants is harmful pollutants to the living organism. The presence of those gas emissions can be predicted using Predictive Emissions Monitoring System (PEMS) or Continues Emissions Monitoring System (CEMS) methods. Continuous Emissions Monitoring System is a system that was designed to monitor the effluent gas streams resulted from the combustion processes. However, this empirical method still has several constraints in predicting the gas emissions where in some cases, it produces significant errors that caused by some uncontrollable aspects such as ambient temperature, pressure and humidity that can lead to miscalculation of operational risks and costs. Solving this problem, we conduct a PEMS with data-driven approach. In this study, we used the 2011-2015 open data from gas-turbine-based power plants in Turkey to train and test several supervised methods as a practical application to predict gas concentration. Predictive Emissions Monitoring System (PEMS) offers more advantages than Continuous Emissions Monitoring System (CEMS) especially in economic aspects. The system will monitor and predict the actual emissions from gas-turbine-based power plants operation. The results of this study indicate that the data-driven approach produces a good RMSE value. By having the gas emissions predicted, a mitigation plan can be set and the operational costs in the following years can be optimized by the company

Evaluation of control-oriented flame propagation models for production control of a spark-assisted compression ignition engine

2021 ◽  
pp. 095440702110208
Author(s):  
Dennis Robertson ◽  
Robert Prucka
Keyword(s):  
Flame Propagation ◽  
Internal Combustion Engines ◽  
Production Control ◽  
Combustion Process ◽  
Data Driven ◽  
Efficient Production ◽  
Compression Ignition ◽  
Compression Ignition Engine ◽  
Advanced Combustion ◽  
Crank Angle

The drive to improve internal combustion engines has led to efficiency objectives that exceed the capability of conventional combustion strategies. As a result, advanced combustion modes are more attractive for production. These advanced combustion strategies typically add sensors, actuators, and degrees of freedom to the combustion process. Spark-assisted compression ignition (SACI) is an efficient production-viable advanced combustion strategy characterized by spark-ignited flame propagation that triggers autoignition in the remaining unburned gas. Modeling this complex combustion process for control demands a careful selection of model structure to maximize predictive accuracy within computational constraints. This work comprehensively evaluates a physics-based and a data-driven model. The physics-based model produces a burn duration by computing laminar flame speed as a function of test point conditions. The crank-angle domain is intentionally excluded to reduce computational expense. The data-driven model is an artificial neural network (ANN). The candidate models are compared to a one-dimensional engine model validated to experimental SACI engine data. Though both models capture the trends in burn rates, the ANN model has a root-mean square error (RMSE) of 1.4 CAD, significantly lower than the 10.4 CAD RMSE of the physics-based model. The exclusion of the crank-angle domain results in insufficient detail for the physics-based model, while the ANN can tolerate this exclusion.

Sign in / Sign up

Export Citation Format

Share Document