Search

In this article, a stochastic gradient based online learning algorithm for Extreme Learning Machines (ELM) is developed (SG-ELM). A stability criterion based on Lyapunov approach is used to prove both asymptotic stability of estimation error and stability in the estimated parameters suitable for identification of nonlinear dynamic systems. The developed algorithm not only guarantees stability, but also reduces the computational demand compared to the OS-ELM approach based on recursive least squares. In order to demonstrate the effectiveness of the algorithm on a real-world scenario, an advanced combustion engine identification problem is considered. The algorithm is applied to two case studies: An online regression learning for system identification of a Homogeneous Charge Compression Ignition (HCCI) Engine and an online classification learning (with class imbalance) for identifying the dynamic operating envelope of the HCCI Engine. The results indicate that the accuracy of the proposed SG-ELM is comparable to that of the state-of-the-art but adds stability and a reduction in computational effort., Comment: This paper was written as an extract from my PhD thesis (July 2013) and so references may not be to date as of this submission (Jan 2015). The article is in review and contains 10 figures, 35 references

Homogeneous charge compression ignition (HCCI) is a futuristic combustion technology that operates with a high fuel efficiency and reduced emissions. HCCI combustion is characterized by complex nonlinear dynamics which necessitates a model based control approach for automotive application. HCCI engine control is a nonlinear, multi-input multi-output problem with state and actuator constraints which makes controller design a challenging task. Typical HCCI controllers make use of a first principles based model which involves a long development time and cost associated with expert labor and calibration. In this paper, an alternative approach based on machine learning is presented using extreme learning machines (ELM) and nonlinear model predictive control (MPC). A recurrent ELM is used to learn the nonlinear dynamics of HCCI engine using experimental data and is shown to accurately predict the engine behavior several steps ahead in time, suitable for predictive control. Using the ELM engine models, an MPC based control algorithm with a simplified quadratic program update is derived for real time implementation. The working and effectiveness of the MPC approach has been analyzed on a nonlinear HCCI engine model for tracking multiple reference quantities along with constraints defined by HCCI states, actuators and operational limits., Comment: This paper was written as an extract from my PhD thesis (July 2013) and so references may not be to date as of this submission (Jan 2015). The article is in review and contains 10 figures, 35 references

Advanced combustion technologies such as homogeneous charge compression ignition (HCCI) engines have a narrow stable operating region defined by complex control strategies such as exhaust gas recirculation (EGR) and variable valve timing among others. For such systems, it is important to identify the operating envelope or the boundary of stable operation for diagnostics and control purposes. Obtaining a good model of the operating envelope using physics becomes intractable owing to engine transient effects. In this paper, a machine learning based approach is employed to identify the stable operating boundary of HCCI combustion directly from experimental data. Owing to imbalance in class proportions in the data, two approaches are considered. A re-sampling (under-sampling, over-sampling) based approach is used to develop models using existing algorithms while a cost-sensitive approach is used to modify the learning algorithm without modifying the data set. Support vector machines and recently developed extreme learning machines are used for model development and results compared against linear classification methods show that cost-sensitive versions of ELM and SVM algorithms are well suited to model the HCCI operating envelope. The prediction results indicate that the models have the potential to be used for predicting HCCI instability based on sensor measurement history., Comment: In a Journal review

Extreme Learning Machine (ELM) is an emerging learning paradigm for nonlinear regression problems and has shown its effectiveness in the machine learning community. An important feature of ELM is that the learning speed is extremely fast thanks to its random projection preprocessing step. This feature is taken advantage of in designing an online parameter estimation algorithm for nonlinear dynamic systems in this paper. The ELM type random projection and a nonlinear transformation in the hidden layer and a linear output layer is considered as a generalized model structure for a given nonlinear system and a parameter update law is constructed based on Lyapunov principles. Simulation results on a DC motor and Lorentz oscillator show that the proposed algorithm is stable and has improved performance over the online-learning ELM algorithm., Comment: 6 pages, 13 figures and in review

Low-sulfur "clean" diesel fuel has been mandated in the US and Europe. However, quality of diesel fuel, particularly the sulfur content, varies significantly in other parts of the world. Due to logistical issues in various theaters of operation, the Army is often forced to rely on local fuel supplies, which exposes vehicles to diesel fuel or jet fuel (JP-8) with elevated levels of sulfur. Modern engines typically use cooled Exhaust Gas Recirculation (EGR) to meet emissions regulations. Using high-sulfur fuels and cooled EGR elevates problems associated with cooler fouling and corrosion of engine components. Hence, an experimental study has been carried out in a heavy-duty diesel engine running on standard JP-8 fuel and fuel doped with 2870 ppm of sulfur. Gas was sampled from the EGR cooler and analyzed using a condensate collection device developed according to a modified ASTM 3226-73T standard. Engine-out emissions were analyzed in parallel. Analysis of results indicates significantly increased levels of sulfur-dioxide and particulate mass with high-sulfur fuel, but negligible amounts of condensed sulfuric acid under normal operating temperatures., Presented at SAE 2008 World Congress held in Detroit, MI on 14-17 April 2008. Published in the Proceedings of the SAE World Congress, 2008. The original document contains color images.

The US army single fuel forward policy mandates that deployed vehicles must refuel with aviation fuel JP-8, and when that is not available, are permitted to use diesel. The US army is expected to use JP-8 till year 2025. There is a known torque and fuel economy penalty associated with the operation of a diesel engine with JP-8 fuel due to its lower density and viscosity, but few experimental studies suggest that kerosene-based fuels have the potential for lowering exhaust emissions (especially particulate matter) compared to typical distillate fuels such as diesel #2. However, studies so far were typically focused on quantifying effects of simply replacing the regular diesel fuel with JP-8, rather than fully investigating the reasons behind the observed differences. This research evaluates the effect of using JP-8 fuel in a heavy duty diesel engine on fuel injection, combustion, performance and emissions, and subsequently utilizes the obtained insight to propose engine calibration capable of minimizing the possible penalties. Test experiments were carried out on a Detroit Diesel Corporation (DDC) S60 engine outfitted with EGR. The results indicate that torque and fuel economy of diesel fuel can be matched without smoke or NOx penalty by increasing the duration of injection to compensate for lower density. The lower cetane number of JP-8 led to higher ignition delay and increased premixed combustion, but adjusting of injection timing to keep the ignition timing unchanged had a minor effect. Under almost all conditions, JP-8 led to lower NOx and PM emissions and shifted the NOx-PM tradeoff favorably., Prepared in collaboration with University of Michigan, Automotive Research Center, Ann Arbor, MI.

Medium trucks constitute a large market segment of the commercial transportation sector, and are also used widely for military tactical operations. Recent technological advances in hybrid powertrains and fuel cell auxiliary power units have enabled design alternatives that can improve fuel economy and reduce emissions dramatically. However, deterministic design optimization of these configurations may yield designs that are optimal with respect to performance but raise concerns regarding the reliability of achieving that performance over lifetime. In this article we identify and quantify uncertainties due to modeling approximations or incomplete information. We then model their propagation using Monte Carlo simulation and perform sensitivity analysis to isolate statistically significant uncertainties. Finally, we formulate and solve a series of reliability-based optimization problems and quantify tradeoffs between optimality and reliability. The most relevant design parameters of the diesel engine, fuel cell, driveline and vehicle are considered. The results demonstrate the necessity for addressing uncertainty to make valid assessments and design decisions, Upprättat; 2011; 20110822 (andbra)

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Ocean Engineering, 1986., MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING., Bibliography: leaves 135-140., by Dionissios Nikolaou Assanis., Ph.D.

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Ocean Engineering, 1986., MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING., Bibliography: leaves 135-140., by Dionissios Nikolaou Assanis., Ph.D.

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Ocean Engineering, 1986., MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING., Bibliography: leaves 135-140., by Dionissios Nikolaou Assanis., Ph.D.

Medium trucks constitute a large market segment of the commercial transportation sector, and are also used widely for military tactical operations. Recent technological advances in hybrid powertrains and fuel cell auxiliary power units have enabled design alternatives that can improve fuel economy and reduce emissions dramatically. However, deterministic design optimization of these configurations may yield designs that are optimal with respect to performance but raise concerns regarding the reliability of achieving that performance over lifetime. In this article we identify and quantify uncertainties due to modeling approximations or incomplete information. We then model their propagation using Monte Carlo simulation and perform sensitivity analysis to isolate statistically significant uncertainties. Finally, we formulate and solve a series of reliability-based optimization problems and quantify tradeoffs between optimality and reliability. The most relevant design parameters of the diesel engine, fuel cell, driveline and vehicle are considered. The results demonstrate the necessity for addressing uncertainty to make valid assessments and design decisions, Upprättat; 2011; 20110822 (andbra)

This paper discusses the compression ratio influence on maximum load of a Natural Gas HCCI engine. A modified Volvo TD100 truck engine is controlled in a closed-loop fashion by enriching the Natural Gas mixture with Hydrogen. The first section of the paper illustrates and discusses the potential of using hydrogen enrichment of natural gas to control combustion timing. Cylinder pressure is used as the feedback and the 50 percent burn angle is the controlled parameter. Full-cycle simulation is compared to some of the experimental data and then used to enhance some of the experimental observations dealing with ignition timing, thermal boundary conditions, emissions and how they affect engine stability and performance. High load issues common to HCCI are discussed in light of the inherent performance and emissions tradeoff and the disappearance of feasible operating space at high engine loads. The problems of tighter limits for combustion timing, unstable operational points and physical constraints at high loads are discussed and illustrated by experimental results. Finally, the influence on operational limits, i.e., emissions peak pressure rise and peak cylinder pressure, from compression ratio at high load are discussed.

The target cascading methodology is applied to the conceptual design of an advanced heavy tactical truck. Two levels are defined: an integrated truck model is represented at the top (vehicle ) level and four independent suspension arms are represented at the lower (system ) level. Necessary analysis models are developed, and design problems are formulated and solved iteratively at both levels. Hence, vehicle design variables and system specifications are determined in a consistent manner. Two different target sets and two different propulsion systems are considered. Trade-offs between conflicting targets are identified. It is demonstrated that target cascading can be useful in avoiding costly design iterations late in the product development process., Upprättat; 2011; 20110823 (andbra)

The target cascading methodology is applied to the conceptual design of an advanced heavy tactical truck. Two levels are defined: an integrated truck model is represented at the top (vehicle ) level and four independent suspension arms are represented at the lower (system ) level. Necessary analysis models are developed, and design problems are formulated and solved iteratively at both levels. Hence, vehicle design variables and system specifications are determined in a consistent manner. Two different target sets and two different propulsion systems are considered. Trade-offs between conflicting targets are identified. It is demonstrated that target cascading can be useful in avoiding costly design iterations late in the product development process., Upprättat; 2011; 20110823 (andbra)