A new Jacobian matrix for optimal learning of single-layer neural networks

This paper investigates the learning of a wide class of single-hidden-layer feedforward neural networks (SLFNs) with two sets of adjustable parameters, i.e., the nonlinear parameters in the hidden nodes and the linear output weights. The main objective is to both speed up the convergence of second-order learning algorithms such as Levenberg-Marquardt (LM), as well as to improve the network performance. This is achieved here by reducing the dimension of the solution space and by introducing a new Jacobian matrix. Unlike conventional supervised learning methods which optimize these two sets of parameters simultaneously, the linear output weights are first converted into dependent parameters, thereby removing the need for their explicit computation. Consequently, the neural network (NN) learning is performed over a solution space of reduced dimension. A new Jacobian matrix is then proposed for use with the popular second-order learning methods in order to achieve a more accurate approximation of the cost function. The efficacy of the proposed method is shown through an analysis of the computational complexity and by presenting simulation results from four different examples.

Genetic algorithms for local controller network construction

Local Controller Networks (LCNs) provide nonlinear control by interpolating between a set of locally valid, subcontrollers covering the operating range of the plant. Constructing such networks typically requires knowledge of valid local models. This paper describes a new genetic learning approach to the construction of LCNs directly from the dynamic equations of the plant, or from modelling data. The advantage is that a priori knowledge about valid local models is not needed. In addition to allowing simultaneous optimisation of both the controller and validation function parameters, the approach aids transparency by ensuring that each local controller acts independently of the rest at its operating point. It thus is valuable for simultaneous design of the LCNs and identification of the operating regimes of an unknown plant. Application results from a highly nonlinear pH neutralisation process and its associated neural network representation are utilised to illustrate these issues.

Neural modelling, control and optimisation of an industrial grinding process

This paper describes the development of neural model-based control strategies for the optimisation of an industrial aluminium substrate disk grinding process. The grindstone removal rate varies considerably over a stone life and is a highly nonlinear function of process variables. Using historical grindstone performance data, a NARX-based neural network model is developed. This model is then used to implement a direct inverse controller and an internal model controller based on the process settings and previous removal rates. Preliminary plant investigations show that thickness defects can be reduced by 50% or more, compared to other schemes employed. (c) 2004 Elsevier Ltd. All rights reserved.

System oriented neural networks - Problem formulation, methodology and application

A novel methodology is proposed for the development of neural network models for complex engineering systems exhibiting nonlinearity. This method performs neural network modeling by first establishing some fundamental nonlinear functions from a priori engineering knowledge, which are then constructed and coded into appropriate chromosome representations. Given a suitable fitness function, using evolutionary approaches such as genetic algorithms, a population of chromosomes evolves for a certain number of generations to finally produce a neural network model best fitting the system data. The objective is to improve the transparency of the neural networks, i.e. to produce physically meaningful

Estimation of ternary liquid-liquid equilibria for arene/alkane/ionic liquid mixtures using neural networks

Neural network models have been explored for the prediction of the liquid-liquid equilibrium data and aromatic/aliphatic selectivity values. Four ternary systems composed of toluene, heptane, and the ionic liquids 1-ethyl-3-methylimidazolium ethylsulfate, or 1,3-dimethylimidazolium methylsulfate were investigated at 313.2 and 348.2 K.

Application of auto-associative neural networks to transient fault detection in an IC engine

The tailpipe emissions from automotive engines have been subject to steadily reducing legislative limits. This reduction has been achieved through the addition of sub-systems to the basic four-stroke engine which thereby increases its complexity. To ensure the entire system functions correctly, each system and / or sub-systems needs to be continuously monitored for the presence of any faults or malfunctions. This is a requirement detailed within the On-Board Diagnostic (OBD) legislation. To date, a physical model approach has been adopted by me automotive industry for the monitoring requirement of OBD legislation. However, this approach has restrictions from the available knowledge base and computational load required. A neural network technique incorporating Multivariant Statistical Process Control (MSPC) has been proposed as an alternative method of building interrelationships between the measured variables and monitoring the correct operation of the engine. Building upon earlier work for steady state fault detection, this paper details the use of non-linear models based on an Auto-associate Neural Network (ANN) for fault detection under transient engine operation. The theory and use of the technique is shown in this paper with the application to the detection of air leaks within the inlet manifold system of a modern gasoline engine whilst operated on a pseudo-drive cycle. Copyright © 2007 by ASME.

Automated nonlinear system modelling with multiple neural networks

This article discusses the identification of nonlinear dynamic systems using multi-layer perceptrons (MLPs). It focuses on both structure uncertainty and parameter uncertainty, which have been widely explored in the literature of nonlinear system identification. The main contribution is that an integrated analytic framework is proposed for automated neural network structure selection, parameter identification and hysteresis network switching with guaranteed neural identification performance. First, an automated network structure selection procedure is proposed within a fixed time interval for a given network construction criterion. Then, the network parameter updating algorithm is proposed with guaranteed bounded identification error. To cope with structure uncertainty, a hysteresis strategy is proposed to enable neural identifier switching with guaranteed network performance along the switching process. Both theoretic analysis and a simulation example show the efficacy of the proposed method.

Improved structure optimization for fuzzy-neural networks

Fuzzy-neural-network-based inference systems are well-known universal approximators which can produce linguistically interpretable results. Unfortunately, their dimensionality can be extremely high due to an excessive number of inputs and rules, which raises the need for overall structure optimization. In the literature, various input selection methods are available, but they are applied separately from rule selection, often without considering the fuzzy structure. This paper proposes an integrated framework to optimize the number of inputs and the number of rules simultaneously. First, a method is developed to select the most significant rules, along with a refinement stage to remove unnecessary correlations. An improved information criterion is then proposed to find an appropriate number of inputs and rules to include in the model, leading to a balanced tradeoff between interpretability and accuracy. Simulation results confirm the efficacy of the proposed method.

Power-Capped DVFS and Thread Allocation with ANN Models on Modern NUMA Systems

Abstract—Power capping is an essential function for efficient power budgeting and cost management on modern server systems. Contemporary server processors operate under power caps by using dynamic voltage and frequency scaling (DVFS). However, these processors are often deployed in non-uniform memory
access (NUMA) architectures, where thread allocation between cores may significantly affect performance and power consumption. This paper proposes a method which maximizes performance under power caps on NUMA systems by dynamically optimizing two knobs: DVFS and thread allocation. The method selects the optimal combination of the two knobs with models based on artificial neural network (ANN) that captures the nonlinear effect of thread allocation on performance. We implement
the proposed method as a runtime system and evaluate it with twelve multithreaded benchmarks on a real AMD Opteron based NUMA system. The evaluation results show that our method outperforms a naive technique optimizing only DVFS by up to
67.1%, under a power cap.