Identificação não linear usando uma rede fuzzy wavelet neural network modificada

In last decades, neural networks have been established as a major tool for the identification of nonlinear systems. Among the various types of networks used in identification, one that can be highlighted is the wavelet neural network (WNN). This network combines the characteristics of wavelet multiresolution theory with learning ability and generalization of neural networks usually, providing more accurate models than those ones obtained by traditional networks. An extension of WNN networks is to combine the neuro-fuzzy ANFIS (Adaptive Network Based Fuzzy Inference System) structure with wavelets, leading to generate the Fuzzy Wavelet Neural Network - FWNN structure. This network is very similar to ANFIS networks, with the difference that traditional polynomials present in consequent of this network are replaced by WNN networks. This paper proposes the identification of nonlinear dynamical systems from a network FWNN modified. In the proposed structure, functions only wavelets are used in the consequent. Thus, it is possible to obtain a simplification of the structure, reducing the number of adjustable parameters of the network. To evaluate the performance of network FWNN with this modification, an analysis of network performance is made, verifying advantages, disadvantages and cost effectiveness when compared to other existing FWNN structures in literature. The evaluations are carried out via the identification of two simulated systems traditionally found in the literature and a real nonlinear system, consisting of a nonlinear multi section tank. Finally, the network is used to infer values of temperature and humidity inside of a neonatal incubator. The execution of such analyzes is based on various criteria, like: mean squared error, number of training epochs, number of adjustable parameters, the variation of the mean square error, among others. The results found show the generalization ability of the modified structure, despite the simplification performed

Simulação do sistema de esgotamento sanitário de Ponta Negra- Natal: mitigação dos riscos ambientais e estratégia de manutenção preditiva

The simulation of SES-Natal Ponta Negra: mitigation of environmental risks and predictive maintenance strategy was developed in the context of several operational irregularities in the pumping stations and sewage systems in the system Ponta Negra. Thus, the environmental risks and complaints against the company due to overflows of sewage into the public thoroughfare became common. This neighborhood has shown in recent years an increase of resident higher than the initial expectation of growth. In this sense presumed the large population growth and generation of sewers higher than expected, associated to the use of corrective maintenance and misuse of the system may be the main causes of operational failures occurring in the SES. This study aimed at analyzing the hydraulic behavior of SES Ponta Negrathrough numerical simulation of its operation associated to future scenarios of occupation. The SES Ponta Negra has a long lengthof collection networks and 6 pumping stations interconnected, being EE 1, 2, 4 coastal way, and beach Shopping interconnected EE3 to receives all sewers pumped from the rest pumping station and pumped to the sewage treatment station of neighborhood which consists of a facultative pond followed by three maturation ponds with disposal of treated effluent into infiltration ditches. Oncethey are connected with each other, the study was conducted considering the days and times of higher inflow for all lifts. Furthermore, with the aim of measuring the gatherer network failures were conducted data survey of on the networks. Thephysical and operational survey data was conducted between January/2011 and janeiro/2012. The simulation of the SES was developed with the aim ofdemonstrating its functioning, eithercurrently and in the coming years, based in population estimates and sewage flow. The collected data represents the current framework of the pumping stations of the SES Ponta Negra and served as input to the model developed in MS Excel ® spreadsheet which allowed simulating the behavior of SES in future scenarios. The results of this study show thatBeach Shopping Pumping Station is actually undersized and presents serious functioning problemsthatmay compromise the environmental quality of surrounding area. The other pumping stations of the system will reach itsmaximum capacity between 2013 and 2015, although the EE1 and EE3 demonstrateoperation capacity, even precariously, until 2017. Moreover, it was observed that the misuse of the network system, due to the input of both garbage and stormwater, are major factors of failures that occur in the SES. Finally, it was found that the corrective maintenance appliance, rather than predictive,has proven to beinefficient because of the serious failuresin the system, causing damage to the environment and health risks to users