Modelling the correlation between processing parameters and properties of maraging steels using artificial neural network

An artificial neural network (ANN) model is developed for the analysis and simulation of the correlation between the properties of maraging steels and composition, processing and working conditions. The input parameters of the model consist of alloy composition, processing parameters (including cold deformation degree, ageing temperature, and ageing time), and working temperature. The outputs of the ANN model include property parameters namely: ultimate tensile strength, yield strength, elongation, reduction in area, hardness, notched tensile strength, Charpy impact energy, fracture toughness, and martensitic transformation start temperature. Good performance of the ANN model is achieved. The model can be used to calculate properties of maraging steels as functions of alloy composition, processing parameters, and working condition. The combined influence of Co and Mo on the properties of maraging steels is simulated using the model. The results are in agreement with experimental data. Explanation of the calculated results from the metallurgical point of view is attempted. The model can be used as a guide for further alloy development.

Artificial Intelligence and Cognitive Science

Editorial for 17th AICS Conference

Uniplanar left-handed artificial metamaterials

Planar periodic arrays of metallic elements printed on grounded dielectric substrates are presented to exhibit left-handed properties for surface wave propagation. The proposed structures dispense with the need for grounding vias and ease the implementation of uniplanar left-handed metamaterials at higher frequencies. A transmission line description is used for the initial design and interpretation of the left-handed property. A thorough study based on full wave simulations is carried out with regards to the effect of the element geometrical characteristics and the array periodicity to the properties of the artificial material. Dispersion curves are presented and studied. The distribution of the modal fields in the unit cell is also studied in order to provide an explanation of the material properties. The scalability of the proposed structures to infrared frequencies is demonstrated.

Artificial magnetic conductor surfaces and their application to low-profile high-gain planar antennas

Planar periodic metallic arrays behave as artificial magnetic conductor (AMC) surfaces when placed on a grounded dielectric substrate and they introduce a zero degrees reflection phase shift to incident waves. In this paper the AMC operation of single-layer arrays without vias is studied using a resonant cavity model and a new application to high-gain printed antennas is presented. A ray analysis is employed in order to give physical insight into the performance of AMCs and derive design guidelines. The bandwidth and center frequency of AMC surfaces are investigated using full-wave analysis and the qualitative predictions of the ray model are validated. Planar AMC surfaces are used for the first time as the ground plane in a high-gain microstrip patch antenna with a partially reflective surface as superstrate. A significant reduction of the antenna profile is achieved. A ray theory approach is employed in order to describe the functioning of the antenna and to predict the existence of quarter wavelength resonant cavities.

Low-profile resonant cavity antenna with artificial magnetic conductor ground plane

A planar artificial magnetic conductor (AMC) ground plane is proposed as a means to reduce the profile of a highly directive resonant cavity antenna. The structure is formed by a printed microstrip patch antenna and a superimposed partially reflective surface. The antenna profile is reduced to approximately half by virtue of employing the AMC ground plane. A ray theory model is used to qualitatively describe the functioning of the antenna and theoretically predict the existence of quarter wavelength resonant cavities.

Artificial gravity reveals that economy of action determines the stability of sensorimotor coordination.

Background
When we move along in time with a piece of music, we synchronise the downward phase of our gesture with the beat. While it is easy to demonstrate this tendency, there is considerable debate as to its neural origins. It may have a structural basis, whereby the gravitational field acts as an orientation reference that biases the formulation of motor commands. Alternatively, it may be functional, and related to the economy with which motion assisted by gravity can be generated by the motor system.
Methodology/Principal Findings
We used a robotic system to generate a mathematical model of the gravitational forces acting upon the hand, and then to reverse the effect of gravity, and invert the weight of the limb. In these circumstances, patterns of coordination in which the upward phase of rhythmic hand movements coincided with the beat of a metronome were more stable than those in which downward movements were made on the beat. When a normal gravitational force was present, movements made down-on-the-beat were more stable than those made up-on-the-beat.
Conclusions/Significance
The ubiquitous tendency to make a downward movement on a musical beat arises not from the perception of gravity, but as a result of the economy of action that derives from its exploitation.

Artificial Intelligence Model for Flowable Concrete Mixtures Used in Underwater Construction and Repair

This study explores using artificial neural networks to predict the rheological and mechanical properties of underwater concrete (UWC) mixtures and to evaluate the sensitivity of such properties to variations in mixture ingredients. Artificial neural networks (ANN) mimic the structure and operation of biological neurons and have the unique ability of self-learning, mapping, and functional approximation. Details of the development of the proposed neural network model, its architecture, training, and validation are presented in this study. A database incorporating 175 UWC mixtures from nine different studies was developed to train and test the ANN model. The data are arranged in a patterned format. Each pattern contains an input vector that includes quantity values of the mixture variables influencing the behavior of UWC mixtures (that is, cement, silica fume, fly ash, slag, water, coarse and fine aggregates, and chemical admixtures) and a corresponding output vector that includes the rheological or mechanical property to be modeled. Results show that the ANN model thus developed is not only capable of accurately predicting the slump, slump-flow, washout resistance, and compressive strength of underwater concrete mixtures used in the training process, but it can also effectively predict the aforementioned properties for new mixtures designed within the practical range of the input parameters used in the training process with an absolute error of 4.6, 10.6, 10.6, and 4.4%, respectively.