Search

A multilayered neural network is a multi-input, multi-output nonlinear system in which network weights can be trained by using parameter estimation algorithms. In this paper, a novel training method is proposed. This method is based on the relatively new smooth variable structure filter (SVSF) and is formulated for feed-forward multilayer perceptron training. The SVSF is a state and parameter estimation that is based on the sliding mode concept and works in a predictor-corrector fashion. The SVSF training performance is tested on three benchmark pattern classification problems. Furthermore, a study is presented comparing the popular back-propagation method, the extended Kalman filter, and the SVSF. [ABSTRACT FROM AUTHOR]

In this paper, an engine fault detection and classification technique using vibration data in the crank angle domain is presented. These data are used in conjunction with artificial neural networks (ANNs), which are applied to detect faults in a four-stroke gasoline engine built for experimentation. A comparative study is provided between the popular backpropagation (BP) method, the Levenberg–Marquardt (LM) method, the quasi-Newton (QN) method, the extended Kalman filter (EKF), and the smooth variable structure filter (SVSF). The SVSF is a relatively new estimation strategy, based on the sliding mode concept. It has been formulated to efficiently train ANNs and is consequently referred to as the SVSF-ANN. The accuracy of the proposed method is compared with the standard accuracy of the Kalman-based filters and the popular BP algorithms in an effort to validate the SVSF-ANN performance and application to engine fault detection and classification. The customizable fault diagnostic system is able to detect known engine faults with various degrees of severity, such as defective lash adjuster, piston chirp (PC), and chain tensioner (CT) problems. The technique can be used at any dealership or assembly plant to considerably reduce warranty costs for the company and manufacturer. [ABSTRACT FROM PUBLISHER]

The smooth variable structure filter (SVSF) is a recently proposed predictor-corrector filter for state and parameter estimation. The SVSF is based on the sliding mode control concept. It defines a hyperplane in terms of the state trajectory and then applies a discontinuous corrective action that forces the estimate to go back and forth across that hyperplane. The SVSF is robust and stable to modeling uncertainties making it suitable for fault detection application. The discontinuous action of the SVSF results in a chattering effect that can be used to correct modeling errors and uncertainties in conjunction with adaptive strategies. In this paper, the SVSF is complemented with a novel parameter estimation technique referred to as the iterative bi-section/shooting method (IBSS). This combined strategy is used for estimating model parameters and states for systems in which only the model structure is known. This combination improves the performance of the SVSF in terms of rate of convergence, robustness, and stability. The benefits of the proposed estimation method are demonstrated by its application to an electrohydrostatic actuator. [ABSTRACT FROM AUTHOR]

The article presents a proposal for a neural network-based control system for fine control of the intake air/fuel ratio in a bi-fuel engine. The control system is a module for an existing vehicle manufacturer's electronic control units (ECUs). Effectiveness of the neural control system is demonstrated by a simulation of a Dodge four-stroke bi-fuel engine.

Abstract Deep-Learning has become a leading strategy for artificial intelligence and is being applied in many fields due to its excellent performance that has surpassed human cognitive abilities in a number of classification and control problems (Ciregan, Meier, & Schmidhuber, 2012; Mnih et al., 2015). However, the training process of Deep-Learning is usually slow and requires high-performance computing, capable of handling large datasets. The optimization of the training method can improve the learning rate of the Deep-Learning networks and result in a higher performance while using the same number of training epochs (cycles). This paper considers the use of estimation theory for training of large neural networks and in particular Deep-Learning networks. Two estimation strategies namely the Extended Kalman Filter (EKF) and the Smooth Variable Structure Filter (SVSF) have been revised (subsequently referred to as RSVSF and REKF) and used for network training. They are applied to several benchmark datasets and comparatively evaluated. Highlights • Two Deep-Learning training algorithms are introduced, called REKF and RSVSF. • REKF and RSVSF allow Deep-Learning networks to learn fast. • REKF and RSVSF use less memory than current adaptive methods. [ABSTRACT FROM AUTHOR]

A method that is often used for parameter estimation is the extended Kalman filter (EKF). EKF is a model-based strategy that implicitly considers the effect of modeling uncertainties. This implicit consideration often leads to the tuning of the filter by trial and error. When formulated for parameter estimation, the "tuned" EKF becomes sensitive to uncertainties in its internal model. The EKF's robustness can be improved by combining it with the recently proposed variable structure filter (VSF) concept. In a combined form, the modeling uncertainties no longer affect stability, but impact the performance and the quality of the estimation process. Furthermore, the VSF concept provides a secondary set of indicators of performance that is in addition to the estimation error and that pertains to the range of parametric uncertainties. As such, the robustness of the combined method and its multiple indicators of performance allow the use of intelligent adaptation for improving the performance of the estimation process. For real-time applications, online neural network adaptation may be used to improve the performance by progressively reducing specific modeling uncertainties in the system. In this paper, a new parameter estimation method that uses concepts associated with the EKF, the VSF, and neural network adaptation is introduced. The performance of this method is considered and discussed for applications that involve parameter estimation such as fault detection. [ABSTRACT FROM AUTHOR]