Vibration Signature Analysis Using Artificial Neural Networks

Damage detection by measuring and analyzing vibration signals in a machine component is an established procedure in mechanical and aerospace engineering. This paper presents vibration signature analysis of steel bridge structures in a nonconventional way using artificial neural networks (ANN). Multilayer perceptrons have been adopted using the back-propagation algorithm for network training. The training patterns in terms of vibration signature are generated analytically for a moving load traveling on a trussed bridge structure at a constant speed to simulate the inspection vehicle. Using the finite-element technique, the moving forces are converted into stationary time-dependent force functions in order to generate vibration signals in the structure and the same is used to train the network. The performance of the trained networks is examined for their capability to detect damage from unknown signatures taken independently at one, three, and five nodes. It has been observed that the prediction using the trained network with single-node signature measurement at a suitability chosen location is even better than that of three-node and five-node measurement data.

Hierarchical artificial immune system for crop stage classification

This paper presents a new hierarchical clustering algorithm for crop stage classification using hyperspectral satellite image. Amongst the multiple benefits and uses of remote sensing, one of the important application is to solve the problem of crop stage classification. Modern commercial imaging satellites, owing to their large volume of satellite imagery, offer greater opportunities for automated image analysis. Hence, we propose a unsupervised algorithm namely Hierarchical Artificial Immune System (HAIS) of two steps: splitting the cluster centers and merging them. The high dimensionality of the data has been reduced with the help of Principal Component Analysis (PCA). The classification results have been compared with K-means and Artificial Immune System algorithms. From the results obtained, we conclude that the proposed hierarchical clustering algorithm is accurate.

Formation flying of small satellites using suboptimal MPSP guidance

Using the recently developed model predictive static programming (MPSP), a suboptimal guidance logic is presented in this paper for formation flying of small satellites. Due to the inherent nature of the problem formulation, MPSP does not require the system dynamics to be linearized. The proposed guidance scheme is valid both for high eccentricity chief satellite orbits as well as large separation distance between chief and deputy satellites. Moreover, since MPSP poses the desired conditions as a set of `hard constraints', the final accuracy level achieved is very high. The proposed guidance scheme has been tested successfully for a variety of initial conditions and for a variety of formation commands as well. Comparison with standard Linear Quadratic Regulator (LQR) solution (which serves as a guess solution for MPSP) and another nonlinear controller, State Dependent Riccati Equation (SDRE) reveals that MPSP guidance achieves the objective with higher accuracy and with lesser amount of control usage as well.

Artificial fertilization of the eggs, and rearing and identification of the larvae of the anchoveta, Cetengraulis mysticetus

ENGLISH: The anchoveta, Cetengraulis mysticetus (Günther), is an important bait fish used to capture tunas in the Eastern Tropical Pacific Ocean. Contributions to the early life history of this species in the Gulf of Panama were made by Simpson (1959), who was able to identify deductively the planktonic egg of the anchoveta from 10 other anchovy eggs concurrently present. He also reared these planktonic eggs in the laboratory and described the resultant larvae to the age of 48 hours after hatching. Because of the lack of differences among the anchovy larvae, this description does not permit the identification of anchoveta larvae from those of other engraulid species. Furthermore, while adult specimens are easily recognized, up to the present it has not been possible to extend the identification of the juvenile anchoveta to specimens smaller than about 25 mm. The purpose of this study, therefore, was to identify anchoveta from the time of hatching to about 25 mm. SPANISH: La anchoveta, Cetengraulis mysticetus (Günther), es un importante pez de carnada que se emplea en la captura de los atunes en el Océano Pacífico Oriental Tropical. Simpson (1959) logró identificar deductivamente el huevo planctónico de la anchoveta al separarlo de otros diez huevos de anchoas que se encuentran al mismo tiempo, contribuyendo de esta manera a conocer los primeros estados de la historia natural de esta especie en el Golfo de Panamá. El también estableció un criadero en el laboratorio con estos huevos planctónicos y describió las larvas resultantes hasta la edad de 48 horas después de la eclosión. Debido a que no hay diferencias entre las larvas de las anchoas, esta descripción no permite identificar las larvas de la anchoveta de las otras especies de engráulidos. Más aun, a pesar de que los especímenes adultos son fácilmente reconocibles, hasta ahora no ha sido posible identificar la anchoveta juvenil de menos de unos 25 mm. Consecuentemente, el propósito del presente estudio ha sido el de identificar al anchoveta desde el momento de la eclosión hasta que tiene unos 25 mm.

Biology and Management of the American Shad and Status of the Fisheries, Atlantic Coast of the United States, 1960

This paper summarizes current information on the American shad, Alosa sapidissima, and describes the species and its fishery. Emphasis is placed on (1) life history of the fish, (2) condition of the fishery by State and water areas in 1960 compared to 1896 when the last comprehensive description was made, (3) factors responsible for decline in abundance, and (4) management measures. The shad fishery has changed little over the past three-quarters of a century, except in magnitude of yield. Types of shad-fishing gear have remained relatively unchanged, but many improvements have been made in fishing techniques, mostly to achieve economy. In 1896 the estimated catch was more than 50 million pounds. New Jersey ranked first in production with about 14 million pounds, and Virginia second with 11 million pounds. In 1960 the estimated catch was slightly more than 8 million pounds. Maryland ranked first in production with slightly more than 1.5 million pounds, Virginia second with slightly less than 1.4 million pounds, and North Carolina third with about 1.3 million pounds. Biological and economic factors blamed for the decline in shad abundance, such as physical changes in the environment, construction of dams, pollution, over-fishing, and natural cycles of abundance, are discussed. Also discussed are methods used for the rehabilitation and management of the fishery, such as artificial propagation, installation of fish-passage facilities at impoundments, and fishing regulations. With our present knowledge, we can manage individual shad populations; but, we probably cannot restore the shad to its former peak of abundance.

Swimming dynamics of bidirectional artificial flagella

We study magnetic artificial flagella whose swimming speed and direction can be controlled using light and magnetic field as external triggers. The dependence of the swimming velocity on the system parameters (e.g., length, stiffness, fluid viscosity, and magnetic field) is explored using a computational framework in which the magnetostatic, fluid dynamic, and solid mechanics equations are solved simultaneously. A dimensionless analysis is carried out to obtain an optimal combination of system parameters for which the swimming velocity is maximal. The swimming direction reversal is addressed by incorporating photoresponsive materials, which in the photoactuated state can mimic natural mastigonemes. © 2013 American Physical Society.

Preliminary model development for predicting strength and stiffness of cement-stabilized soils using artificial neural networks

This paper presents ongoing work on data collection and collation from a large number of laboratory cement-stabilization projects worldwide. The aim is to employ Artificial Neural Networks (ANN) to establish relationships between variables, which define the properties of cement-stabilized soils, and the two parameters determined by the Unconfined Compression Test, the Unconfined Compressive Strength (UCS), and stiffness, using E50 calculated from UCS results. Bayesian predictive neural network models are developed to predict the UCS values of cement-stabilized inorganic clays/silts, as well as sands as a function of selected soil mix variables, such as grain size distribution, water content, cement content and curing time. A model which can predict the stiffness values of cement-stabilized clays/silts is also developed and compared to the UCS model. The UCS model results emulate known trends better and provide more accurate estimates than the results from the E50 stiffness model. © 2013 American Society of Civil Engineers.

Integer filling facfor phases and isospin in vertical diatomic artificial molecules

Integer filling factor phases of many-electron vertically coupled diatomic artificial quantum dot molecules are investigated for different values of the interdot coupling. The experimental results are analyzed within local-spin density functional theory for which we have determined a simple lateral confining potential law that can be scaled for the different coupling regimes, and Hartree-Fock theory. Maximum density droplets composed of electrons in both bonding and antibonding or just bonding states are revealed, and interesting isospin-flip physics appears for weak interdot coupling when the systematic depopulation of antibonding states leads to changes in isospin.

Magnetoresistance at artificial interfaces in the itinerant SrRuO3 ferromagnet

The magnetoresistance across interfaces in the itinerant ferromagnetic oxide SrRuO3 have been studied. To define appropriately the interfaces, epitaxial thin films have been grown on bicrystalline and laser-patterned SrTiO3 substrates. Comparison is made with results obtained on similar experiments using the double-exchange ferromagnetic oxide La2/3Sr1/3MnO3. It is found that in SrRuO3, interfaces induce a substantial negative magnetoresistance, although no traces of the low-field spin tunneling magnetoresistance are found. We discuss these results on the basis of the distinct degree of spin polarization in ruthenates and manganites and the different nature of the surface magnetic layer formed at interfaces.