Nonlinear identification of a gasoline HCCI engine using neural networks coupled with principal component analysis

Janakiraman, Vijay Manikandan; Nguyen, XuanLong; Assanis, Dennis N.

doi:10.1016/j.asoc.2013.01.006

Cited by 70 publications

(36 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Los esfuerzos para predecir estados futuros del motor también son de gran interés en el desarrollo tecnológico de los motores, así lo demuestra un estudio desarrollado por la Universidad de Michigan, en donde las RNA son usadas para predecir el comportamiento de la combustión de un motor de ignición por compresión de carga homogénea (HCCI), durante su funcionamiento transitorio [10].…”

Section: Introductionunclassified

Determinación de la presión máxima de compresión de un MEP basado en una RNAR

Urgilés¹,

Arichávala²,

Jérez³

2018

ings

View full text Add to dashboard Cite

En la presente investigación se realiza la explicación de la metodología aplicada a la determinación de la presión máxima de compresión de un motor de combustión interna alternativo de encendido provocado (MEP), el cual se basa en un estudio que parte de la caracterización de las curvas del consumo de amperaje del motor de arranque. Se aplica un protocolo de adquisición de datos y su posterior análisis estadístico. Los valores estadísticos de la señal como energía, promedio, desviación estándar, varianza, kurtosis, asimetría, máximo, mínimo y factor de cresta son seleccionados en función al mayor aporte de información para la caracterización del experimento; estos valores generan bases de datos las cuales son aplicadas para la creación y entrenamiento de una red neuronal artificial recurrente (RNAR) en la cual se obtiene un error absoluto menor al 2 \%. En una primera instancia se aplica la metodología de pruebas en un motor ensamblado en un banco didáctico y luego se procede a la aplicación del método en motores aplicados en vehículos.

show abstract

Section: Introductionunclassified

Determinación de la presión máxima de compresión de un MEP basado en una RNAR

Urgilés¹,

Arichávala²,

Jérez³

2018

ings

View full text Add to dashboard Cite

show abstract

“…If the persistent excitation condition is not met,Ŵ converges to some constant values. For general nonlinear systems where persistence of excitation may not be met [20], a multi-step signal varying between extreme values of the inputs are typically used [4], [5]. For any given step input, the update law in (19) asymptotically reduces the error e(k) to zero.…”

Section: Lyapunov Based Parameter Update Algorithmmentioning

confidence: 99%

“…Data mining on dynamic systems has been as significant as on static systems but often the time connection in a dynamic system is usually not utilized. For instance, neural networks [3], [4] and support vector machines [5] have been used in modeling dynamic systems but algorithms designed for static data with an i.i.d assumption (data sampled from an independent and identical distribution) are used. The temporal aspects of the data useful for parameter estimation and decision making for dynamical systems are typically not taken into account.…”

Section: Introductionmentioning

confidence: 99%

“…a significant area of research solving problems in modeling [3], [4], fault detection, optimization and control [6], [7]. In most cases, an online regression algorithm updates the parameters by minimizing a given cost function and decisions are made simultaneously based on the estimated model (as in case of adaptive control for instance [7]).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A lyapunov based stable online learning algorithm for nonlinear dynamical systems using extreme learning machines

Janakiraman

2013

The 2013 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Abstract-Extreme Learning Machine (ELM) is a promising learning scheme for nonlinear classification and regression problems and has shown its effectiveness in the machine learning literature. ELM represents a class of generalized single hidden layer feed-forward networks (SLFNs) whose hidden layer parameters are assigned randomly resulting in an extremely fast learning speed along with superior generalization performance. It is well known that the online sequential learning algorithm (OS-ELM) based on recursive least squares [1] might result in ill-conditioning of the Hessian matrix and hence instability in the parameter estimation. To address this issue, the stability theory of Lyapunov is utilized to develop an online learning algorithm for temporal data from dynamic systems and time series. The developed algorithm results in parameter estimation that is globally asymptotically stable. Simulations results of the developed algorithm compared against online sequential ELM (OS-ELM) and the offline batch learning ELM (O-ELM) show that the online Lyapunov ELM algorithm can perform online learning at reduced computation, comparable accuracy and with a guarantee on the boundedness of the estimated system.

show abstract

“…It is now well established that phenomenological models typically provide a more accurate description of the process, especially for extrapolation, and empirical models are easier to obtain and manipulate during online applications in real time, especially when obtaining experimental data is facilitated (Vieira et al, 2003;Cubillos et al, 2007;Janakiraman et al, 2013). For this reason, some applications require an optimization/adaptation of the model developed and eventually the use of hybrid structures, which take into account empirical knowledge plus phenomeno-logical knowledge, may be considered.…”

Section: Introductionmentioning

confidence: 99%

Predictive Control of a Batch Polymerization System Using a Feedforward Neural Network With Online Adaptation by Genetic Algorithm

Cancelier

Claumann

Bolzan

et al. 2016

Braz. J. Chem. Eng.

View full text Add to dashboard Cite

-This study used a predictive controller based on an empirical nonlinear model comprising a threelayer feedforward neural network for temperature control of the suspension polymerization process. In addition to the offline training technique, an algorithm was also analyzed for online adaptation of its parameters. For the offline training, the network was statically trained and the genetic algorithm technique was used in combination with the least squares method. For online training, the network was trained on a recurring basis and only the technique of genetic algorithms was used. In this case, only the weights and bias of the output layer neuron were modified, starting from the parameters obtained from the offline training. From the experimental results obtained in a pilot plant, a good performance was observed for the proposed control system, with superior performance for the control algorithm with online adaptation of the model, particularly with respect to the presence of off-set for the case of the fixed parameters model.

show abstract

Nonlinear identification of a gasoline HCCI engine using neural networks coupled with principal component analysis

Cited by 70 publications

References 42 publications

Determinación de la presión máxima de compresión de un MEP basado en una RNAR

Determinación de la presión máxima de compresión de un MEP basado en una RNAR

A lyapunov based stable online learning algorithm for nonlinear dynamical systems using extreme learning machines

Predictive Control of a Batch Polymerization System Using a Feedforward Neural Network With Online Adaptation by Genetic Algorithm

Contact Info

Product

Resources

About