Detecção e isolamento de falhas em sistemas dinâmicos baseados em redes neurais

This master dissertation presents the development of a fault detection and isolation system based in neural network. The system is composed of two parts: an identification subsystem and a classification subsystem. Both of the subsystems use neural network techniques with multilayer perceptron training algorithm. Two approaches for identifica-tion stage were analyzed. The fault classifier uses only residue signals from the identification subsystem. To validate the proposal we have done simulation and real experiments in a level system with two water reservoirs. Several faults were generated above this plant and the proposed fault detection system presented very acceptable behavior. In the end of this work we highlight the main difficulties found in real tests that do not exist when it works only with simulation environments

Utilização de redes neurais artificiais para detecção e diagnóstico de falhas

In a real process, all used resources, whether physical or developed in software, are subject to interruptions or operational commitments. However, in situations in which operate critical systems, any kind of problem may bring big consequences. Knowing this, this paper aims to develop a system capable to detect the presence and indicate the types of failures that may occur in a process. For implementing and testing the proposed methodology, a coupled tank system was used as a study model case. The system should be developed to generate a set of signals that notify the process operator and that may be post-processed, enabling changes in control strategy or control parameters. Due to the damage risks involved with sensors, actuators and amplifiers of the real plant, the data set of the faults will be computationally generated and the results collected from numerical simulations of the process model. The system will be composed by structures with Artificial Neural Networks, trained in offline mode using Matlab®

Desenvolvimento de um secador spray para obtenção de pós finos de precursores de nióbio

This work presents a spray-dryer designed to oxalate-niobate precursors and suitable for the production of Niobium Carbide. The dryer was intended to produce powders of controlled particle size. First, the precursor is dissolved in water to produce a solution of known concentration and then it is atomized on the spray-dryer to produce the powder. This equipment consists of a 304 stainless steel chamber, 0.48 m x 1.9 m (diameter x length), with a conical shape at the lower portion, which is assembled on a vertical platform. The chamber is heated by three 4 kW electrical resistances. In this process, drying air is heated as it flows inside a serpentine surrounding the chamber, in contrary to more traditional processes in which the hot drying air is used to heat the component. The air enters the chamber at the same temperature of the chamber, thus avoiding adherence of particles on the internal surface. The low speed flow is concurrent, directed from the top to the bottom portion of the chamber. Powders are deposited on a 0.4 m diameter tray, which separates the cylindrical portion from the conical portion of the chamber. The humid air is discharged though a plug placed underneath the collecting tray. A factorial experimental planning was prepared to study the influence of five parameters (concentration, input flow, operation temperature, drying air flow and spray air flow) on the characteristics of the powders produced. Particle size distribution and shape were measured by laser granulometry and scanning electronic microscopy. Then, the powders are submitted to reaction in a CH4 / H2 atmosphere to compare the characteristics of spray-dried powders with powders synthetizided by conventional methods

Detecção e diagnóstico de falhas não-supervisionados baseados em estimativa de densidade recursiva e classificador fuzzy auto-evolutivo

In this work, we propose a two-stage algorithm for real-time fault detection and identification of industrial plants. Our proposal is based on the analysis of selected features using recursive density estimation and a new evolving classifier algorithm. More specifically, the proposed approach for the detection stage is based on the concept of density in the data space, which is not the same as probability density function, but is a very useful measure for abnormality/outliers detection. This density can be expressed by a Cauchy function and can be calculated recursively, which makes it memory and computational power efficient and, therefore, suitable for on-line applications. The identification/diagnosis stage is based on a self-developing (evolving) fuzzy rule-based classifier system proposed in this work, called AutoClass. An important property of AutoClass is that it can start learning from scratch". Not only do the fuzzy rules not need to be prespecified, but neither do the number of classes for AutoClass (the number may grow, with new class labels being added by the on-line learning process), in a fully unsupervised manner. In the event that an initial rule base exists, AutoClass can evolve/develop it further based on the newly arrived faulty state data. In order to validate our proposal, we present experimental results from a level control didactic process, where control and error signals are used as features for the fault detection and identification systems, but the approach is generic and the number of features can be significant due to the computationally lean methodology, since covariance or more complex calculations, as well as storage of old data, are not required. The obtained results are significantly better than the traditional approaches used for comparison

Método híbrido para detecção e diagnóstico de falhas baseado em resíduos

The detection and diagnosis of faults, ie., find out how , where and why failures occur is an important area of study since man came to be replaced by machines. However, no technique studied to date can solve definitively the problem. Differences in dynamic systems, whether linear, nonlinear, variant or invariant in time, with physical or analytical redundancy, hamper research in order to obtain a unique solution . In this paper, a technique for fault detection and diagnosis (FDD) will be presented in dynamic systems using state observers in conjunction with other tools in order to create a hybrid FDD. A modified state observer is used to create a residue that allows also the detection and diagnosis of faults. A bank of faults signatures will be created using statistical tools and finally an approach using mean squared error ( MSE ) will assist in the study of the behavior of fault diagnosis even in the presence of noise . This methodology is then applied to an educational plant with coupled tanks and other with industrial instrumentation to validate the system.

Protótipo de rastreador solar de um eixo baseado em microcontrolador

The increase in the efficiency of photo-voltaic systems has been the object of various studies the past few years. One possible way to increase the power extracted by a photovoltaic panel is the solar tracking, performing its movement in order to follow the sun’s path. One way to activate the tracking system is using an electric induction motor, which should have sufficient torque and low speed, ensuring tracking accuracy. With the use of voltage source inverters and logic devices that generate the appropriate switching is possible to obtain the torque and speed required for the system to operate. This paper proposes the implementation of a angular position sensor and a driver to be applied in solar tracker built at a Power Electronics and Renewable Energies Laboratory, located in UFRN. The speed variation of the motor is performed via a voltage source inverter whose PWM command to actuate their keys will be implemented in an FPGA (Field Programmable Gate Array) device and a TM4C microcontroller. A platform test with an AC induction machine of 1.5 CV was assembled for the comparative testing. The angular position sensor of the panel is implemented in a ATMega328 microcontroller coupled to an accelerometer, commanded by an Arduino prototyping board. The solar position is also calculated by the microcontroller from the geographic coordinates of the site where it was placed, and the local time and date obtained from an RTC (Real-Time Clock) device. A prototype of a solar tracker polar axis moved by a DC motor was assembled to certify the operation of the sensor and to check the tracking efficiency.

Computational Tracking of Mental Health in Youth: Latin American Contributions to a Low-Cost and Effective Solution for Early Psychiatric Diagnosis

The early onset of mental disorders can lead to serious cognitive damage, and timely interventions are needed in order to prevent them. In patients of low socioeconomic status, as is common in Latin America, it can be hard to identify children at risk. Here, we briefly introduce the problem by reviewing the scarce epidemiological data from Latin America regarding the onset of mental disorders, and discussing the difficulties associated with early diagnosis. Then we present computational psychiatry, a new field to which we and other Latin American researchers have contributed methods particularly relevant for the quantitative investigation of psychopathologies manifested during childhood. We focus on new technologies that help to identify mental disease and provide prodromal evaluation, so as to promote early differential diagnosis and intervention. To conclude, we discuss the application of these methods to clinical and educational practice. A comprehensive and quantitative characterization of verbal behavior in children, from hospitals and laboratories to homes and schools, may lead to more effective pedagogical and medical intervention

Sistema híbrido para detecção e diagnóstico de falhas em sistemas dinâmicos

The industries are getting more and more rigorous, when security is in question, no matter is to avoid financial damages due to accidents and low productivity, or when it s related to the environment protection. It was thinking about great world accidents around the world involving aircrafts and industrial process (nuclear, petrochemical and so on) that we decided to invest in systems that could detect fault and diagnosis (FDD) them. The FDD systems can avoid eventual fault helping man on the maintenance and exchange of defective equipments. Nowadays, the issues that involve detection, isolation, diagnose and the controlling of tolerance fault are gathering strength in the academic and industrial environment. It is based on this fact, in this work, we discuss the importance of techniques that can assist in the development of systems for Fault Detection and Diagnosis (FDD) and propose a hybrid method for FDD in dynamic systems. We present a brief history to contextualize the techniques used in working environments. The detection of fault in the proposed system is based on state observers in conjunction with other statistical techniques. The principal idea is to use the observer himself, in addition to serving as an analytical redundancy, in allowing the creation of a residue. This residue is used in FDD. A signature database assists in the identification of system faults, which based on the signatures derived from trend analysis of the residue signal and its difference, performs the classification of the faults based purely on a decision tree. This FDD system is tested and validated in two plants: a simulated plant with coupled tanks and didactic plant with industrial instrumentation. All collected results of those tests will be discussed

Aplicação de sistemas multi-classificadores no diagnóstico de falhas em motores de indução trifásicos

Equipment maintenance is the major cost factor in industrial plants, it is very important the development of fault predict techniques. Three-phase induction motors are key electrical equipments used in industrial applications mainly because presents low cost and large robustness, however, it isn t protected from other fault types such as shorted winding and broken bars. Several acquisition ways, processing and signal analysis are applied to improve its diagnosis. More efficient techniques use current sensors and its signature analysis. In this dissertation, starting of these sensors, it is to make signal analysis through Park s vector that provides a good visualization capability. Faults data acquisition is an arduous task; in this way, it is developed a methodology for data base construction. Park s transformer is applied into stationary reference for machine modeling of the machine s differential equations solution. Faults detection needs a detailed analysis of variables and its influences that becomes the diagnosis more complex. The tasks of pattern recognition allow that systems are automatically generated, based in patterns and data concepts, in the majority cases undetectable for specialists, helping decision tasks. Classifiers algorithms with diverse learning paradigms: k-Neighborhood, Neural Networks, Decision Trees and Naïves Bayes are used to patterns recognition of machines faults. Multi-classifier systems are used to improve classification errors. It inspected the algorithms homogeneous: Bagging and Boosting and heterogeneous: Vote, Stacking and Stacking C. Results present the effectiveness of constructed model to faults modeling, such as the possibility of using multi-classifiers algorithm on faults classification

Litoestratigrafia e deformação cenzóica na região de Icapuí, Ceará, e implicações para a estruturação de campos de petróleo na borda ocidental da bacia Potiguar(NE do Brasil)

This thesis deals with the sedimentological/stratigraphic and structural evolution of the sedimentary rocks that occur in the NW continental border of the Potiguar Basin. These rocks are well exposed along coastal cliffs between the localities of Lagoa do Mato and Icapuí, Ceará State (NE Brazil). The sedimentological/stratigraphic study involved, at the outcrop scale, detailed facies descriptions, profile mapping of the vertical succession of different beds, and columnar sections displaying inferred lateral relationships. The approach was complemented by granulometric and petrographic analyses, including the characterization of heavy mineral assemblages. The data set allowed to recognize two kinds of lithological units, a carbonate one of very restricted occurrence at the base of the cliffs, and three younger, distinct siliciclastic units, that predominate along the cliffs, in vertical and lateral extent. The carbonate rocks were correlated to the late Cretaceous Jandaíra Formation, which is covered by the siliciclastic Barreiras Formation. The Barreiras Formation occurs in two distinct structural settings, the usual one with nondeformed, subhorizontal strata, or as tilted beds, affected by strong deformation. Two lithofacies were recognized, vertically arranged or in fault contacts. The lower facies is characterized by silty-argillaceous sandstones with low-angle cross bedding; the upper facies comprises medium to coarse grained sandstones, with conglomeratic layers. The Tibau Formation (medium to coarse-grained sandstones with argillite intercalations) occurs at the NW side of the studied area, laterally interlayered with the Barreiras Formation. Eolic sediments correlated to the Potengi Formation overly the former units, either displaying an angular unconformity, or simply an erosional contact (stratigraphic unconformity). Outstanding structural features, identified in the Barreiras Formation, led to characterize a neocenozoic stress field, which generated faults and folds and/or reactivated older structures in the subjacent late cretaceous (to paleogene, in the offshore basin) section. The structures recognized in the Barreiras Formation comprise two distinct assemblages, namely a main extensional deformation between the localities of Ponta Grossa and Redonda, and a contractional style (succeeded by oblique extensional structures) at Vila Nova. In the first case, the structural assemblage is dominated by N-S (N±20°Az) steep to gently-dipping extensional faults, displaying a domino-style or listric geometry with associated roll-over structures. This deformation pattern is explained by an E-W/WNW extension, contemporaneous with deposition of the upper facies of the Barreiras Formation, during the time interval Miocene to Pleistocene. Strong rotation of blocks and faults generated low-angle distensional faults and, locally, subvertical bedding, allowing to estimate very high strain states, with extension estimates varying between 40% up to 200%. Numerous detachment zones, parallel to bedding, help to acommodate this intense deformation. The detachment surfaces and a large number of faults display mesoscopic features analoguous to the ones of ductile shear zones, with development of S-C fabrics, shear bands, sigmoidal clasts and others, pointing to a hydroplastic deformation regime in these cases. Local occurrences of the Jandaíra limestone are controled by extensional faults that exhume the pre-Barreiras section, including an earlier event with N-S extension. Finally, WNWtrending extensional shear zones and faults are compatible with the Holocene stress field along the present continental margin. In the Vila Nova region, close to Icapuí, gentle normal folds with fold hinges shallowly pluging to SSW affect the lower facies of the Barreiras Formation, displaying an incipient dissolution cleavage associated with an extension lineation at high rake (a S>L fabric). Deposition of the upper facies siliciclastics is controlled by pull-apart graben structures, bordered by N-NE-trending sinistral-normal shear zones and faults, characterizing an structural inversion. Microstructures are compatible with tectonic deformation of the sedimentary pile, burried at shallow depths. The observed features point to high pore fluid pressures during deformation of the sediments, producing hydroplastic structures through mechanisms of granular flow. Such structures are overprinted by microfractures and microfaults (an essentially brittle regime), tracking the change to microfracturing and frictional shear mechanisms accompanying progressive dewatering and sediment lithification. Correlation of the structures observed at the surface with those present at depth was tested through geophysical data (Ground Penetrating Radar, seismics and a magnetic map). EW and NE-trending lineaments are observed in the magnetic map. The seismic sections display several examples of positive flower structures which affect the base of the cretaceous sediments; at higher stratigraphic levels, normal components/slips are compatible with the negative structural inversion characterized at the surface. Such correlations assisted in proposing a structural model compatible with the regional tectonic framework. The strong neogenepleistocene deformation is necessarily propagated in the subsurface, affecting the late cretaceous section (Açu and Jandaíra formations), wich host the hydrocarbon reservoirs in this portion of the Potiguar Basin. The proposed structural model is related to the dextral transcurrent/transform deformation along the Equatorial Margin, associated with transpressive terminations of E-W fault zones, or at their intersections with NE-trending lineaments, such as the Ponta Grossa-Fazenda Belém one (the LPGFB, itself controlled by a Brasiliano-age strike-slip shear zone). In a first step (and possibly during the late Cretaceous to Paleogene), this lineament was activated under a sinistral transpressional regime (antithetic to the main dextral deformation in the E-W zones), giving way to the folds in the lower facies of the Barreiras Formation, as well as the positive flower structures mapped through the seismic sections, at depth. This stage was succeeded (or was penecontemporaneous) by the extensional structures related to a (also sinistral) transtensional movement stage, associated to volcanism (Macau, Messejana) and thermal doming processes during the Neogene-Pleistocene time interval. This structural model has direct implications to hydrocarbon exploration and exploitation activities at this sector of the Potiguar Basin and its offshore continuation. The structure of the reservoirs at depth (Açu Formation sandstones of the post-rift section) may be controlled (or at least, strongly influenced) by the deformation geometry and kinematics characterized at the surface. In addition, the deformation event recognized in the Barreiras Formation has an age close to the one postulated for the oil maturation and migration in the basin, between the Oligocene to the Miocene. In this way, the described structural cenario represents a valid model to understand the conditions of hydrocarbon transport and acummulation through space openings, trap formation and destruction. This model is potentially applicable to the NW region of the Potiguar Basin and other sectors with a similar structural setting, along the brazilian Equatorial Atlantic Margin