Fault diagnosis in railway track circuits using Dempster–Shafer classifier fusion

This paper addresses the problem of fault detection and isolation in railway track circuits. A track circuit can be considered as a large-scale system composed of a series of trimming capacitors located between a transmitter and a receiver. A defective capacitor affects not only its own inspection data (short circuit current) but also the measurements related to all capacitors located downstream (between the defective capacitor and the receiver). Here, the global fault detection and isolation problem is broken down into several local pattern recognition problems, each dedicated to one capacitor. The outputs from local neural network or decision tree classifiers are expressed using the Dempster–Shafer theory and combined to make a final decision on the detection and localization of a fault in the system. Experiments with simulated data show that correct detection rates over 99% and correct localization rates over 92% can be achieved using this approach, which represents a major improvement over the state of the art reference method.     

Enzymatic synthesis of oligoesculin: structure and biological activities characterizations

The oligomerization of esculin, catalyzed by the laccase from Trametes versicolor, was realized in an attempt to improve the properties of this glycosidic coumarin. MALDI-TOF analyses showed a degree of oligomerization up to 9, whereas NMR spectra revealed the formation of C–C and C–O bridges, which involve both the phenolic and the glucosidic part of the coumarin. The solubility of oligomers is 189-fold higher than esculin’s solubility. Moreover, antioxidant properties of oligomers were correlated with their mass; the more the mass, the more the xanthine oxidase inhibitory activity and the radical scavenging activity are important. These experimental results were completed by in silico structural investigations, which suggested the preferential formation of C8–C8 linkages between esculin units during the oligomerization reaction.     

A quantitative assessment of security risks based on a multifaceted classification approach

Information systems and cloud computing infrastructures are frequently exposed to various types of threats. Without detection and prevention mechanisms, the threats can materialize and cause different types of damages that usually lead to significant financial losses. The threats arise from a complex and multifaceted environment. Currently, organizations are struggling to identify the threats to their information assets and assess the overall damage they might inflict to their systems. In order to empower mangers to better plan for shielding their information systems, the paper presents two main contributions. First, a new approach to threat classification that leads to a security assessment model that is systematic, extendable, and modular. Second, a quantitative analysis of information systems based on the model.

     

Fault diagnosis of a railway device using semi-supervised independent factor analysis with mixing constraints

Independent factor analysis (IFA) defines a generative model for observed data that are assumed to be linear mixtures of some unknown non-Gaussian, mutually independent latent variables (also called sources or independent components). The probability density function of each individual latent variable is modelled by a mixture of Gaussians. Learning in the context of this model is usually performed within an unsupervised framework in which only unlabelled samples are used. Both the mixing matrix and the parameters of latent variable densities are learned from the observed data. This paper investigates the possibility of estimating an IFA model in a noiseless setting when two kinds of prior information are incorporated, namely constraints on the mixing process and partial knowledge on the cluster membership of some training samples. Semi-supervised or partially supervised learning frameworks can thus be handled. The investigation of these two kinds of prior information was motivated by a real-world application concerning the fault diagnosis of railway track circuits. Simulated data, resulting from both these applications, are provided to demonstrate the capacity of our approach to enhance estimation accuracy and remove the indeterminacy commonly encountered in unsupervised IFA, such as source permutations.     

Partially supervised Independent Factor Analysis using soft labels elicited from multiple experts: application to railway track circuit diagnosis

Using a statistical model in a diagnosis task generally requires a large amount of labeled data. When ground truth information is not available, too expensive or difficult to collect, one has to rely on expert knowledge. In this paper, it is proposed to use partial information from domain experts expressed as belief functions. Expert opinions are combined in this framework and used with measurement data to estimate the parameters of a statistical model using a variant of the EM algorithm. The particular application investigated here concerns the diagnosis of railway track circuits. A noiseless Independent Factor Analysis model is postulated, assuming the observed variables extracted from railway track inspection signals to be generated by a linear mixture of independent latent variables linked to the system component states. Usually, learning with this statistical model is performed in an unsupervised way using unlabeled examples only. In this paper, it is proposed to handle this learning process in a soft-supervised way using imperfect information on the system component states. Fusing partially reliable information about cluster membership is shown to significantly improve classification results.     

Improvement in corrosion resistance of magnesium coating with cerium treatment

Corrosion protection afforded by a magnesium coating treated in cerium salt solution on steel substrate was investigated using open circuit potential, polarization curves, and electrochemical impedance spectroscopy (EIS) in 0.005 M sodium chloride solution (NaCl). The morphology of the surface was characterized by scanning electron microscopy (SEM), energy dispersive spectroscopy (EDS), and X-ray diffraction (XRD). The cerium treated coating was obtained by immersion in CeCl3 solution. The results showed that the corrosion resistance of the treated magnesium coating was improved. The corrosion potential of the treated coating was found to be nobler than that of the untreated magnesium coating and the corrosion current decreased significantly. Impedance results showed that the cerium treatment increased corrosion protection. The improvement of anti-corrosion properties was ataibuted to the formation of cerium oxides and hydroxides that gave to a physical barrier effect.     

The use of amino acids as corrosion inhibitors for metals: A review

The aim of this review is to present and discuss the research work reported in the literature on the use of glutamic acid and its derivatives as corrosion inhibitors for metals in different aggressive solutions. Mass loss and electrochemical techniques were among the most often used techniques to evaluate the corrosion inhibition efficiency of the used inhibitor. Glutamic acid can act as an efficient corrosion inhibitor, but it can in other cases show an opposite effect, which accelerates the corrosion process; all depend on the experimental conditions. Highest values of inhibition efficiency were obtained in the presence of ions as Zn²⁺ and ions halides. Glutamic acid derivatives have shown a good ability to use it as an effective corrosion inhibitor for metal in an acidic solution. The development of computational modeling helps to design new glutamic acid derivatives and to understand the inhibition mechanism of those compounds.     

Corrosion behavior of carbon steel coated with magnesium electrodeposited from methyl magnesium chloride solution

Magnesium coating was electroplated on carbon steel to improve its corrosion protection. The analytical characterization of the magnesium coating was performed by scanning electron spectroscopy and energy dispersive X-ray spectroscopy. The electrochemical behavior of Mg-coated carbon steel was assessed by electrochemical impedance spectroscopy, open-circuit potential measurements and potentiodynamic polarization curves in 0.03% sodium chloride solution. The electrochemical results showed that the self-corrosion current density (i _corr) of magnesium-coated steel was 0.32 mA cm^?2 (about 1.8% of that of uncoated steel). Impedance results showed an increase of the total impedance when magnesium coating was applied on steel substrate. The corrosion protection was ensured by a two-step mechanism. The first step was cathodic polarization; the second step was the formation of a barrier due to magnesium oxides composed of MgO, Mg(OH₂) and Mg(OH₃)Cl.