Benjamim Rodrigues de Menezes

Computational intelligence in reliability and maintainability engineering

In this paper the basics of reliability and maintainability modeling, prediction and optimization problems using stochastic models are briefly reviewed (for non-repairable and repairable systems). As an alternative to classical methods based on stochastic models, computational intelligence techniques such as neural networks and fuzzy systems as well as evolutionary computing, artificial immune systems and swarm intelligence are introduced. Classical methods, neural networks, evolutionary computing and immune algorithm are followed by examples demonstrating their applicability to reliability modeling, analysis and optimization. This is a fairly new research area and it has a great potential to support engineers on solving problems such as modeling, analysis and optimization of real-world industrial systems.

Soft computing approaches in reliability modeling and analysis of repairable systems

This paper reviews soft computing approaches for reliability modeling and analysis of repairable systems. Although soft computing techniques such as neural networks and fuzzy systems and even stochastic methods have been employed for solving many different engineering complex problems, when it comes to reliability area traditional approaches are still preferred by industry. Unfortunately with the increasing complexity of systems such techniques might not be able to capture the changes in system features in a precise way what could help to prevent failures and improve system performance. This is a fairly new research area and the literature available points to the new challenges reliability engineers will have to face and the new tools they might use for planning and improving system reliability. In this paper basics of soft computing techniques will be provided as well as examples on how to apply them on the modeling and analysis of repairable systems. It is emphasized that this is a broad open subject and this paper does not try to be conclusive by any means.

Discrete-time sliding mode control: a new design strategy applied to induction motor drives

In this paper, a robust discrete-time sliding mode speed controller for induction motor drives is proposed. A nonlinear sliding surface is used to achieve fast response with low overshoot. A very simple control law is proposed in order to avoid torque oscillations inherent to usual discrete-time sliding mode design techniques. With the proposed design methodology, discrete-time sliding mode existence conditions are ensured. Simulation and experimental results show the effectiveness of the proposed algorithm.

Sliding Mode Observer for Rotor Faults Diagnosis

Although induction motors are traditional thought to be reliable and robust, the possibility of faults is unavoidable once the machines can be exposed to different hostile environments, misoperations, and manufacturing defects. Therefore, motor monitoring incipient fault detection and diagnosis are important topics. This paper presents a method for on-line induction motor monitoring with the purpose of detecting and locating a single rotor broken bar. The method avoids any frequency analysis and observes instead the machine state with the help of the two models. The torque difference between the two models indicates a fault. The technique utilizes input signals from standard transducers. An experimental setup has been constructed to implement the new technique in on-line model

A Stator Flux Oriented Induction Motor Drive with Deadbeat Direct Torque and Flux Control

A stator field oriented control scheme for induction motor drives is proposed. As a deadbeat controller, the algorithm calculates the voltage vector to be supplied by the frequency converter in order to eliminate the flux and torque errors each switching period. The strategy is a DTC scheme in the sense that there are no current controllers with the advantage of a fixed switching frequency. Simulation and experimental results are presented to show the effectiveness of the proposed method and the quality of torque and flux transient responses.

A New Neurofuzzy Controller Based on NFN Networks

This work presents a new online learning controller, the ONFC (Online Neurofuzzy Controller), which has as base the Neo Fuzzy Neuron – NFN. Its principal difference from the most of the neurofuzzy structure used in control systems is the fact that the process error is not only used to correct the network parameters, but also as network input. Moreover, the ONFC has a very simple structure with only one input and one output, associated by two fuzzy rules. Other important characteristic presented by this controller is the reduced effort for the fixed parameters adjustment. The proposed controller development is presented for single and multi-loop control. This controller is applied for the control of two different plants. In a single loop control, simulations results are obtained for a generic plant with reverse characteristic. In a multi-loop control, the controller performance is evaluated through a practical implementation of an induction motor vector control with stator field orientation.

Aplicação Da Computação Evolucionária Na Otimização De Confiabilidade De Sistemas

In this paper stochastic methods for solving redundancy-reliability allocation problems are employed. In order to understand the major issues on solving those problems, three different designs are considered and redundancy allocation problems are formulated for each of them. The problems are solved in two stages, one stochastic and another deterministic. Genetic and the immune algorithms are implemented. Keywords— reliability engineering, system reliability,immune algorithm, genetic algorithm Resumo— No presente trabalho métodos de otimização estocástica são utilizados para resolver problemas de alocação de redundância-confiabilidade. A fim de exemplificar as questões principais acerca da solução de tais problemas, três arquiteturas de sistemas distintas têm suas formulações apresentadas. Os problemas formulados são resolvidos em dois estágios, um estocástico e um determińıstico. Os algoritmos imune e genético são implementados. Keywords— engenharia de confiabilidade, confiabilidade de sistemas, algoritmo imune, algoritmo genético

Building a Leakage Detection System Using Ensembles: A New Way

Pipeline leakage is a demand from governmental and environmental associations that petroleum companies need to comply. Recent accidents with Petrobras pipelines increase local demand for leakage detection system. Due the high accuracy on detecting leakage required from that system is necessary to set a procedure that once applied will achieve the best performance considering the quality of the installed instrumentation. This paper describes a procedure to set such system in order to accomplish with the legal requirement keeping high reliability during normal and failure operations. Nuisance alarms are kept at low value while minimum leakage detection is too small. To do that the described system uses a set of models acting as specialists each one observing and diagnosing pipeline leakage. This system also validates the operations according to the business rules. System uses a set of tools, fuzzy logic, neural network, genetic algorithm and statistic analysis, to execute its function. The usage of an optimization tool, genetic algorithm in this case, helps the designer to set a function alarm that uses a statistical approach to assure a reliable performance when detecting the leakage and keeping the nuisance alarm closes to zero. Both qualities make the system highly reliable since once it generates one alarm there is a likelihood of almost a 100% that the event is true. Instead of using the common two parameters alarm, threshold and timing, this system uses pattern recognition to verify the fault or leak condition. The detectable leakage value is function of the difference between the flow measurement at the inlet and the outlet of the pipeline. The minimum leakage detectable is constant and equal to 1.4 times the standard deviation of the error between this two meters for 0.2% of nuisance alarm. In the application it is able to alarm when a leakage of 2% of the total flow happens in a time bellow 5 minutes. If allowed a level of 5% of nuisance alarms the system is able to detect a leakage of one standard deviation of the error. That represents the mentioned amount of 1.4 times the standard deviation of the error. The system is in operation supervising pipeline in a Brazilian installation.© 2004 ASME