Marley M. B. R. Vellasco

VLSI architectures for neural networks

An introduction to neural networks and neural information processing is provided. Neurocomputers are discussed, focusing on how their design exploits the architectural properties of VLSI circuits. General-purpose and special-purpose neurocomputer developments throughout the world are examined. As illustration, and to put European developments in perspective, some of the important projects in the United States and Japan are described. European research is then discussed in greater detail.<<ETX>>

Well Placement Optimization Using a Genetic Algorithm With Nonlinear Constraints

Well placement optimization is a very challenging problem due to the large number of decision variables involved and the nonlinearity of the reservoir response as well as of the well placement constraints. Over the years, a lot of research has been done on this problem, most of which using optimization routines coupled to reservoir simulation models. Despite all this research, there is still a lack of robust computer-aided optimization tools ready to be applied by asset teams in real field development projects. This paper describes the implementation of a tool, based on a Genetic Algorithm, for the simultaneous optimization of number, location and trajectory of producer and injector wells. The developed software is the result of a two-year project focused on a robust implementation of a computer-aided optimization tool to deal with realistic well placement problems with arbitrary well trajectories, complex model grids and linear and nonlinear constraints. The developed optimization tool uses a commercial reservoir simulator as the evaluation function without using proxies to substitute the full numerical model. Due to the large size of the problem, in some cases involving more than 100 decision variables, the optimization process may require thousands of reservoir simulations. Such a task has become feasible through a distributed computing environment running multiple simulations at the same time. The implementation uses a technique called Genocop III – Genetic Algorithm for Numerical Optimization of Constrained Problems – to deal with well placement constraints. Such constraints include grid size, maximum length of wells, minimum distance between wells, inactive grid cells and user-defined regions of the model, with non-uniform shape, where the optimization routine is not supposed to place wells. The optimization process was applied to three full-field reservoir models based on real cases. It increased the net present values and the oil recovery factors obtained by well placement scenarios previously proposed by reservoir engineers. The process was also applied to a synthetic case, based on outcrop data, to analyze the impact of using reservoir quality maps to generate an initial well placement scenario for the optimization routine without using an engineer-defined configuration. Introduction The definition of a well placement is a key aspect with major impact in a field development project. In this sense, the use of reservoir simulation allows the engineer to evaluate different placement scenarios. However, the current industry practice is still, in most cases, a manual procedure of trial and error that requires a lot of experience and knowledge from the engineers involved in the project. Considering that, the development of well placement optimization tools which can automate this process is a high desirable goal. Well placement optimization is a very challenging problem due to the large number of decision variables involved and the nonlinearity of the reservoir response as well as of the well placement constraints. Over the years, a lot of research has been done on this problem, most of which using optimization routines coupled to reservoir simulation and economical models. In 1995, Beckner and Song applied a Simulated Annealing algorithm to optimize the location and scheduling of 12 wells with fixed orientation and length. In 1997, Bittencourt and Horner applied a Genetic Algorithm (GA) hybridized with Polytope and Tabu Search methods to optimize the location of 33 vertical and horizontal wells, including wells, producers and injectors. In 1998, Pan and Horner investigated the use of multivariate interpolation algorithms, Least Squares and Kriging, as proxies to reservoir simulations for optimization problems including well placement. In 1999, Cruz et al. introduced the

Comparison of different evolutionary methodologies applied to electronic filter design

We present in this work the application of a set of different evolutionary methodologies in the problem of electronic filter design. The main objectives are to find out which constraints in the filter topologies, if any, must be observed along the evolutionary process and to study the problem of convergence to parsimonious circuits. The new area of evolutionary electronics is introduced, an evolutionary methodology based on variable length representation is presented and the results on the evolution of low-pass and band-pass filters are described.

Artificial evolution of active filters: a case study

This article focuses on the application of artificial avolution to the synthesis of analog active filters. The main objective of this research is the achievement of a new class of systems, with advantageous features compared to conventional ones, such as lower power consumption, higher speed and more robustness to noise. The particular problem of designing the amplifier of an AM receiver is examined in this work. Genetic algorithms are employed as our evolutionary tool and two sets of experiments are described. The first set has been carried out using a single objective, the desired frequency response of the circuit. In a second set of experiments, three other objectives have been included in the system. A new multi-objective evaluation methodology was conceived for this second set of experiments. A second approach for evolving active filters, using programmable chips, is also discussed in this paper.

Evolvable hardware: on the automatic synthesis of analog control systems

The automatic design of analog control circuits is the focus of this work. Particularly, we apply Evolutionary Computation to carry out the process of circuit synthesis. Evolutionary Computation encompasses a set of search algorithms, called Evolutionary Algorithms (EAs), which borrow from biological evolution their main principles. This particular area of research, where EAs are applied to electronic circuit synthesis, receives the name of Evolvable Hardware (EHW). Our technique differs from conventional approaches in that it considers specific circuits implementation requirements, such as power dissipation, intrinsic noise and fault tolerance, in addition to standard specifications for control systems, such as rise time and over-signal. Our results compare well with conventionally designed controllers presented in the literature, exhibiting a lower degree of oscillation, using lesser components, and achieving better fault tolerance properties.

Synthesis of CMOS operational amplifiers through genetic algorithms

This work studies the problem of CMOS operational amplifiers (OpAmps) design optimisation. The synthesis of these amplifiers can be translated into a multiple-objective optimisation task, in which a large number of specifications have to be taken into account, i.e., GBW area, power consumption and others. We introduce and apply the genetic algorithm (GA) optimisation technique to the proposed problem. A novel multi-objective optimisation methodology is embedded in our genetic algorithm and we focus on the synthesis of a standard analog operational amplifier. The proposed methodology is very general, in the sense that it can be applied to digital and analog VLSI design with multiple-objective specifications.

Quantum-Inspired Evolutionary Algorithms and Its Application to Numerical Optimization Problems

This work proposes a new kind of evolutionary algorithm inspired in the principles of quantum computing. This algorithm is an extension of a proposed model for combinatorial optimization problems which uses a binary representation for the chromosome. This extension uses probability distributions for each free variable of the problem, in order to simulate the superposition of solutions, which is intrinsic in the quantum computing methodology. A set of mathematical operations is used as implicit genetic operators over those probability distributions. The efficiency and the applicability of the algorithm are demonstrated through experimental results using the F6 function.

Cultural operators for a quantum-inspired evolutionary algorithm applied to numerical optimization problems

This work presents the application of cultural algorithms operators to a new quantum-inspired evolutionary algorithm with numerical representation. These operators (fission, fusion, generalization and specialization) are used in order to provide better control over the quantum-inspired evolutionary algorithm. We also show that the quantum-inspired evolutionary algorithm with numerical representation behaves in a very similar manner to a pure cultural algorithm and we propose further investigations concerning this aspect.

Short Term Load Forecasting Using Neural Nets

Load forecasting is decisive in the operation of power systems, for economic and security reasons. Many techniques have been proposed in the last two decades [1]. This work presents a short-term load forecasting system (whose main objective is to maintain the generation-load balance) using Neural Networks. Neural Networks have demonstrated to be a very efficient technique to time series forecasting, particularly in load series [2]. In the application shown in this paper, a Neural Network is used to learn the daily load behaviour of a real electrical system (CEMIG, Brazil, 1993). The network inputs are: past load data, the forecasting hour and the type of day (weekday or weekend). The windowing technique [3] is used to identify the series characteristics. Many neural nets with different architectures were tested and the results evaluated in terms of forecasting errors. We achieved an average forecasting error close to 1.5%. The forecasting system was developed in C programming language and includes the pre-processing of the input data, the network training and the forecasting. This system offers to the user options such as: tuning of some network parameters (learning rate, momentum term, number of processors in any layer), usage or not of the forecasted values as network inputs, adjustment of the size of the training window etc.

GPFIS-CONTROL: A GENETIC FUZZY SYSTEM FOR CONTROL TASKS

Abstract This work presents a Genetic Fuzzy Controller (GFC), called Genetic Programming Fuzzy Inference System for Control tasks (GPFIS-Control). It is based on Multi-Gene Genetic Programming, a variant of canonical Genetic Programming. The main characteristics and concepts of this approach are described, as well as its distinctions from other GFCs. Two benchmarks application of GPFIS-Control are considered: the Cart-Centering Problem and the Inverted Pendulum. In both cases results demonstrate the superiority and potentialities of GPFIS-Control in relation to other GFCs found in the literature.