MACHINE VISION FOR AUTOMATICVISUAL INSPECTION OF WOODENRAILWAY SLEEPERS USING UNSUPERVISED NEURAL NETWORKS

The motivation for this thesis work is the need for improving reliability of equipment and quality of service to railway passengers as well as a requirement for cost-effective and efficient condition maintenance management for rail transportation. This thesis work develops a fusion of various machine vision analysis methods to achieve high performance in automation of wooden rail track inspection.The condition monitoring in rail transport is done manually by a human operator where people rely on inference systems and assumptions to develop conclusions. The use of conditional monitoring allows maintenance to be scheduled, or other actions to be taken to avoid the consequences of failure, before the failure occurs. Manual or automated condition monitoring of materials in fields of public transportation like railway, aerial navigation, traffic safety, etc, where safety is of prior importance needs non-destructive testing (NDT).In general, wooden railway sleeper inspection is done manually by a human operator, by moving along the rail sleeper and gathering information by visual and sound analysis for examining the presence of cracks. Human inspectors working on lines visually inspect wooden rails to judge the quality of rail sleeper. In this project work the machine vision system is developed based on the manual visual analysis system, which uses digital cameras and image processing software to perform similar manual inspections. As the manual inspection requires much effort and is expected to be error prone sometimes and also appears difficult to discriminate even for a human operator by the frequent changes in inspected material. The machine vision system developed classifies the condition of material by examining individual pixels of images, processing them and attempting to develop conclusions with the assistance of knowledge bases and features.A pattern recognition approach is developed based on the methodological knowledge from manual procedure. The pattern recognition approach for this thesis work was developed and achieved by a non destructive testing method to identify the flaws in manually done condition monitoring of sleepers.In this method, a test vehicle is designed to capture sleeper images similar to visual inspection by human operator and the raw data for pattern recognition approach is provided from the captured images of the wooden sleepers. The data from the NDT method were further processed and appropriate features were extracted.The collection of data by the NDT method is to achieve high accuracy in reliable classification results. A key idea is to use the non supervised classifier based on the features extracted from the method to discriminate the condition of wooden sleepers in to either good or bad. Self organising map is used as classifier for the wooden sleeper classification.In order to achieve greater integration, the data collected by the machine vision system was made to interface with one another by a strategy called fusion. Data fusion was looked in at two different levels namely sensor-level fusion, feature- level fusion. As the goal was to reduce the accuracy of the human error on the rail sleeper classification as good or bad the results obtained by the feature-level fusion compared to that of the results of actual classification were satisfactory.

ANALYSIS & STUDY OF AI TECHNIQUES FORAUTOMATIC CONDITION MONITORING OFRAILWAY TRACK INFRASTRUCTURE : Artificial Intelligence Techniques

Since the last decade the problem of surface inspection has been receiving great attention from the scientific community, the quality control and the maintenance of products are key points in several industrial applications.The railway associations spent much money to check the railway infrastructure. The railway infrastructure is a particular field in which the periodical surface inspection can help the operator to prevent critical situations. The maintenance and monitoring of this infrastructure is an important aspect for railway association.That is why the surface inspection of railway also makes importance to the railroad authority to investigate track components, identify problems and finding out the way that how to solve these problems. In railway industry, usually the problems find in railway sleepers, overhead, fastener, rail head, switching and crossing and in ballast section as well. In this thesis work, I have reviewed some research papers based on AI techniques together with NDT techniques which are able to collect data from the test object without making any damage. The research works which I have reviewed and demonstrated that by adopting the AI based system, it is almost possible to solve all the problems and this system is very much reliable and efficient for diagnose problems of this transportation domain. I have reviewed solutions provided by different companies based on AI techniques, their products and reviewed some white papers provided by some of those companies. AI based techniques likemachine vision, stereo vision, laser based techniques and neural network are used in most cases to solve the problems which are performed by the railway engineers.The problems in railway handled by the AI based techniques performed by NDT approach which is a very broad, interdisciplinary field that plays a critical role in assuring that structural components and systems perform their function in a reliable and cost effective fashion. The NDT approach ensures the uniformity, quality and serviceability of materials without causing any damage of that materials is being tested. This testing methods use some way to test product like, Visual and Optical testing, Radiography, Magnetic particle testing, Ultrasonic testing, Penetrate testing, electro mechanic testing and acoustic emission testing etc. The inspection procedure has done periodically because of better maintenance. This inspection procedure done by the railway engineers manually with the aid of AI based techniques.The main idea of thesis work is to demonstrate how the problems can be reduced of thistransportation area based on the works done by different researchers and companies. And I have also provided some ideas and comments according to those works and trying to provide some proposal to use better inspection method where it is needed.The scope of this thesis work is automatic interpretation of data from NDT, with the goal of detecting flaws accurately and efficiently. AI techniques such as neural networks, machine vision, knowledge-based systems and fuzzy logic were applied to a wide spectrum of problems in this area. Another scope is to provide an insight into possible research methods concerning railway sleeper, fastener, ballast and overhead inspection by automatic interpretation of data.In this thesis work, I have discussed about problems which are arise in railway sleepers,fastener, and overhead and ballasted track. For this reason I have reviewed some research papers related with these areas and demonstrated how their systems works and the results of those systems. After all the demonstrations were taking place of the advantages of using AI techniques in contrast with those manual systems exist previously.This work aims to summarize the findings of a large number of research papers deploying artificial intelligence (AI) techniques for the automatic interpretation of data from nondestructive testing (NDT). Problems in rail transport domain are mainly discussed in this work. The overall work of this paper goes to the inspection of railway sleepers, fastener, ballast and overhead.

Periodic inspection on crop sprayers: Results according to age of sprayers

The objectives of the IPP Project-Periodic Inspection on Crop Sprayers-are to develop methods for sprayer certification, analyze quality on spray operation, propose an inspection system for crop sprayers in Brazil, improve environmental quality on spray operation, and reduce costs on chemical control for plant protection systems. Periodic inspections on crop sprayers are performed in several countries and are compulsory in most of them, and it is becoming an important tool for improvement and optimization of use of chemicals. The IPP Project in Brazil is funded by FAPESP-Fundação de Amparo a Pesquisa do Estado de São Paulo. The results so far showed that all the sprayers presented failures. However, most of them could be approved with minor services. As an example, 56.6% of the sprayers with more than 2 years of use presented leaks, 47% of them had damaged hoses and 80.5% presented bad tips (nozzles). These results indicate the need for better procedures of use and maintenance of sprayers, justifying the periodic inspection system.

Study of the interaction between cardiolipin bilayers and methylene blue in polymer-based Layer-by-Layer and Langmuir films applied as membrane mimetic systems

An increase of the reports involving mimetic systems has been observed. Briefly, these systems use biological phospholipids to exploit specific interactions between membrane-models and drugs. Here, the Layer-by-Layer (LbL) and Langmuir techniques were used to investigate the interaction between cardiolipin (CLP-negative phospholipid) and a cationic-like drug methylene blue (MB). Supported by a cationic polyelectrolyte (PAH), LbL films containing PAH/(CLP + MB) and PAH/(CLP + MB + AgNP) were grown up to 14 bilayers. The optical microscopy analysis revealed a decrease of the CLP vesicle sizes in the presence of MB as a possible consequence of the MB action onto the mechanical properties of the CLP membrane. From FTIR spectra, changes mainly related to peak position and band intensity and shape were observed in the spectra from PAH/CLP when in the presence of MB. The latter supports that the interactions between the phosphate and amine charged groups from CLP and PAH, respectively, established during the LbL film fabrication, besides the CLP hydrocarbon environment, are influenced by the presence of MB. Using the micro-Raman technique, a chemical mapping was build based on MB spectrum by resonance Raman scattering (RRS) and surface-enhanced resonance Raman scattering (SERRS). The later phenomenon was activated by Ag nanoparticles (AgNPs) trapped within the LbL film allowing collecting spectra for a single bilayer of PAH/(CLP + MB + AgNP). A rough estimation showed a SERRS amplification of 10(3) in comparison to RRS spectra. As a complementary approach, Langmuir films of CLP in the presence of co-spread MB were investigated through surface pressure vs mean molecular area (pi-A) isotherms. The results showed that for concentrations of MB below 100 mol%, the drug is expelled to water subphase for high values of surface pressure (condensed phase). For concentration at 100% and higher, the MB keeps bound to CLP floating monolayer. (C) 2010 Elsevier B.V. All rights reserved.

Coherent properties and Rabi oscillations in two-level donor systems

Coherent properties and Rabi oscillations in two-level donor systems, under terahertz excitation, are theoretically investigated. Here we are concerned with donor states in bulk GaAs and GaAs-(Ga,Al)As quantum dots. We study confinement effects, in the presence of an applied magnetic field, on the electronic and on-center donor states in GaAs- (Ga,Al)As dots, as compared to the situation in bulk GaAs, and estimate some of the associated decay rate parameters. Using the optical Bloch equations with damping, we study the time evolution of the Is and 2p(+) states in the presence of an applied magnetic field and of a terahertz laser. We also discuss the role played by the distinct dephasing rates on the photocurrent and calculate the electric dipole transition moment. Results indicate that the Rabi oscillations are more robust as the total dephasing rate diminishes, corresponding to a favorable coherence time.

Synthesis, optical and ferroelectric properties of PZT thin films: experimental and theoretical investigation

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Bond strength durability of a resin composite on a reinforced ceramic using various repair systems

Objectives. This study compared the durability of repair bond strength of a resin composite to a reinforced ceramic after three repair systems.Methods. Alumina-reinforced feldspathic ceramic blocks (Vitadur-alpha(R)) (N=30) were randomly divided into three groups according to the repair method: PR-Porcelain Repair Kit (Bisco) [etching with 9.5% hydrofluoric acid + silanization + adhesive]; CJ-CoJet Repair Kit (3M ESPE) [(chairside silica coating with 30 mu m SiO2 + silanization (ESPE(R)-Sil) + adhesive (Visio(TM)-Bond)]; CL-Clearfil Repair Kit [diamond surface roughening, etching with 40% H3PO4 + Clearfil Porcelain Bond Activator + Clearfil SE Bond)]. Resin composite was photo-polymerized on each conditioned ceramic block. Non-trimmed beam specimens were produced for the microtensile bond strength (mu TBS) tests. In order to study the hydrolytic durability of the repair methods, the beam specimens obtained from each block were randomly assigned to two conditions. Half of the specimens were tested either immediately after beam production (Dry) or after long-term water storage (37 degrees C, 150 days) followed by thermocyling (12,000 cycles, 5-55 degrees C) in a universal testing machine (1 mm/min). Failure types were analyzed under an optical microscope and SEM.Results. mu TBS results were significantly affected by the repair method (p=0.0001) and the aging conditions (p=0.0001) (two-way ANOVA, Tukey's test). In dry testing conditions, PR method showed significantly higher (p < 0.001) repair bond strength (19.8 +/- 3.8 MPa) than those of CJ and CL (12.4 +/- 4.7 and 9.9 +/- 2.9, respectively). After long-term water storage and thermocycling, CJ revealed significantly higher results (14.5 +/- 3.1 MPa) than those of PR (12.1 +/- 2.6 MPa) (p < 0.01) and CL (4.2 +/- 2.1 MPa) (p < 0.001). In all groups when tested in dry conditions, cohesive failure in the composite accompanied with adhesive failure at the interface (mixed failures), was frequently observed (76%, 80%, 65% for PR, CJ and CL, respectively). After aging conditions, while the specimens treated with PR and CJ presented primarily mixed failure types (52% and 87%, respectively), CL group presented mainly complete adhesive failures at the interface (70%).Significance. Hydrolytic stability of the repair method based on silica coating and silanization was superior to the other repair strategies for the ceramic tested. (C) 2009 Academy of Dental Materials. Published by Elsevier Ltd. All rights reserved.

Dissipative dynamics of matter-wave solitons in a nonlinear optical lattice

Dynamics and stability of solitons in two-dimensional (2D) Bose-Einstein condensates (BEC), with one-dimensional (1D) conservative plus dissipative nonlinear optical lattices, are investigated. In the case of focusing media (with attractive atomic systems), the collapse of the wave packet is arrested by the dissipative periodic nonlinearity. The adiabatic variation of the background scattering length leads to metastable matter-wave solitons. When the atom feeding mechanism is used, a dissipative soliton can exist in focusing 2D media with 1D periodic nonlinearity. In the defocusing media (repulsive BEC case) with harmonic trap in one direction and nonlinear optical lattice in the other direction, the stable soliton can exist. Variational approach simulations are confirmed by full numerical results for the 2D Gross-Pitaevskii equation.

Cold-atom systems and the scaling limit

With perspective to applications of cold-atom systems, some aspects of few-body physics at very low energies will be reviewed. By exploring the possibilities of varying the two-body interaction via the Feshbach resonance mechanism, some recent results are reported for condensed systems in optical lattices.

Well-conditioned robust observer for detection of family systems components

A new concept of fault detection and isolation using robust observation for systems with random noises is presented. The method selects the parameters from components that may fault during the process and constructs well conditioned robust observers, considering sensors faults. To isolate component failures via robust observation, a bank of detection observers is constructed, where each observer is only sensitive to one specified component failure while robust to all other component failures.

Optical properties of remotely doped parabolic quantum wells

This work is intended to report on optical measurements in a parabolic quantum well with a two dimensional-three dimensional electron gas. Photoluminescence results show broad spectra which are related to emission involving several subbands on conduction band with the fundamental level of the valence band. This assumption is based on the behavior of the PL peak position and the full width at half maximum in the function of the incident power intensity. (C) 2002 Elsevier B.V. B.V. All rights reserved.

Small-angle X-ray scattering study of the smart thermo-optical behavior of zirconyl aqueous colloids

The smart thermo-optical systems studied here are based on the unusual thermoreversible sol-gel transition of zirconyl chloride aqueous solution modified by sulfuric acid in the molar ratio Zr/SO4:3/1. The transparency to the visible light changes during heating due to light scattering. This feature is related to the aggregates growth that occurs during gelation. These reversible changes can be controlled by the amount of chloride ions in solution. The thermoreversible sol-gel transition temperature increases from 323 to 343 K by decreasing the molar ratio Cl/Zr from 7.0 to 1.3. In this work the effect of the concentration of chloride ions on the structural characteristics of the system has been analyzed by in situ SAXS measurements during the sol-gel transition carried out at 323 and 333 K. The experimental SAXS curves of sols exhibit three regions at small, medium and high scattering vectors characteristics of Guinier, fractal and Porod regimes, respectively. The radius of primary particles, obtained from the crossover between the fractal and Porod regimes, remains almost invariable with the chloride concentration, and the value (4 Angstrom) is consistent with the size of the molecular precursor. During the sol-gel transition the aggregates grow with a fractal structure and the fractal dimensionality decreases from 2.4 to 1.8. This last value is characteristic of a cluster-cluster aggregation controlled by a diffusion process. Furthermore, the time exponent of aggregate growth presents values of 0.33 and 1, typical of diffusional and hydrodynamic motions. A crossover between these two regimes is observed.

Effect of Different Solvent Ratios (Water/Ethylene Glycol) on the Growth Process of CaMoO4 Crystals and Their Optical Properties

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Unfolding of plasmon-polariton modes in one-dimensional layered systems containing anisotropic left-handed materials

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)