Control of a Robotic Manipulator Using Artificial Neural Networks with On-line Adaptation

An adaptive neural system for positioning control of a PUMA 560 manipulator is presented". The computed torque method was implemented with a Multi-Layer Perceptron with on-line learning. The control scheme is implemented into two phases. The first one is the off-line phase in which the neural network is trained with previously known control actions. The second one is the on-line phase in which the neural network parameters are adapted while controlling the manipulator. The control system is able to respond to changes in the manipulator model and to load disturbances. As will be shown, control system performance is improved with the on-line learning strategy presented in this paper.     

Numerical Modeling of Inclusion Removal in Electromagnetic Stirred Steel Billets

To investigate the inclusion removal in billets cast under electromagnetic stirring (EMS) influence, a numerical model has been developed to compute the magnetic field, the Lorentz force, the steel flow velocities, and the particle transport within the liquid pool. The electromagnetic field was described by the Maxwell equations and the finite element method was applied using a commercial package. The turbulent fluid flow was described by the Navier‐Stokes equation and by the Reynolds Stress model and the finite volume method was applied using another numerical package. The time average of the Lorentz force was calculated in each element center and this value was applied as a body force in the Navier‐Stokes equation. The magnetic flux density profile was compared with the data obtained in the stirrer of the steel plant. The particle transport model includes the drag force, the buoyancy force and the random walk model, to include the turbulence effects on the particle trajectory. The inclusion removal was calculated and analysed in function of casting speed and stirring current for one size section of mold. The inclusions considered in the calculations have a fixed density and four values of diameter. The numerical results of the electromagnetic model are in agreement with the experimental measurements. A good relationship between the electromagnetic model and the fluid flow model could be shown. An interesting effect is the break of the rotation motion due to the EMS by the jet from the nozzle. The fraction of inclusions removed by the top surface of the mold was improved due to the EMS.     

Flow Intensity Parameter in Pier Scour Experiments

Technical note discusses a detailed approach to dimensional analysis for the bridge pier scour phenomenon and the introduction of flow intensity. It demonstrates the dependence of critical upstream velocity on the rest of the parameters describing the process and its implications on dimensional analysis. Assuming that the viscous effects are negligible in the local scour phenomenon, it is concluded that the flow intensity of the approaching undisturbed flow is not an adequate parameter to describe the process in usual laboratory conditions. A new proposal is established.     

Solution for the Closed-Loop Problem in Pressurized Multipipe Systems

The fundamental background of the solution for the steady-state flow in pressurized water closed-loop pipe systems, without any reservoirs in-between, is presented in this paper. The use of the steady-state mass balance and energy equations to calculate discharges and heads in this type of hydraulic system leads to an undetermined problem. The way to solve this indeterminacy is to consider an additional continuity equation associated with the difference between initial and final conditions, taking into account fluid compressibility and pipe-wall deformability. A complete formulation is derived considering pressure and temperature changes in the hydraulic system. Simplified formulae are presented for isothermal flows in simple systems and multiple closed-loops with pipes in series and in parallel. This problem can also be solved by a pseudotransient analysis technique applied to steady-state conditions. Proposed solutions for this problem are applied to steady-state flows and tested for different system configurations.     

How you move reveals who you are: understanding human behavior by analyzing trajectory data

The widespread use of mobile devices is producing a huge amount of trajectory data, making the discovery of movement patterns possible, which are crucial for understanding human behavior. Significant advances have been made with regard to knowledge discovery, but the process now needs to be extended bearing in mind the emerging field of behavior informatics. This paper describes the formalization of a semantic-enriched KDD process for supporting meaningful pattern interpretations of human behavior. Our approach is based on the integration of inductive reasoning (movement pattern discovery) and deductive reasoning (human behavior inference). We describe the implemented Athena system, which supports such a process, along with the experimental results on two different application domains related to traffic and recreation management.     

Applying a GA kernel on optimizing technical analysis rules for stock picking and portfolio composition

The management of financial portfolios or funds constitutes a widely known problematic in financial markets which normally requires a rigorous analysis in order to select the most profitable assets. The presented paper proposes a new approach, based on Intelligent Computation, in particular genetic algorithms, which aims to manage a financial portfolio by using technical analysis indicators (EMA, HMA, ROC, RSI, MACD, TSI, OBV). In order to validate the developed solution an extensive evaluation was performed, comparing the designed strategy against the market itself and several other investment methodologies, such as Buy and Hold and a purely random strategy. The time span (2003–2009) employed to test the approach allowed the performance evaluation under distinct market conditions, culminating with the most recent financial crash. The results are promising since the approach clearly beats the remaining approaches during the recent market crash.     

NETmix®, a new type of static mixer: Modeling,simulation, macromixing,and micromixing characterization

NETmix® is a new technology for static mixing based on a network of chambers connected by channels. The NETmix® model is the basis of a flow simulator coupled with chemical reaction used to characterize macro and micromixing in structured porous media. The chambers are modeled as perfectly mixing zones and the channels as plug flow perfect segregation zones. A segregation parameter is introduced as the ratio between the channels volume and the whole network volume. Different kinetics and reactants injection schemes can be implemented. Results show that the number of rows in the flow direction and the segregation parameter control both macro and micromixing, but the degree of micromixing is also controlled by the reactants injection scheme. The NETmix® model enables the systematic study of micromixing and macromixing for different network structures and reaction schemes, enabling the design of network structures to ensure the desired yield and selectivity. © 2009 American Institute of Chemical Engineers AIChE J, 2009     

Control of Microbial Adhesion as a Strategy for Food and Bioprocess Technology

Bacteria and other microorganisms have a natural tendency to adhere to surfaces as a survival mechanism. This can occur in many environments, including the living host, industrial systems, and natural waters. The general outcome of bacterial colonization of a surface is biofilm formation, which consists of microorganisms immobilized in a variety of polymeric compounds generally referred to as extracellular polymeric substances. Bacterial adhesion to a solid surface is a crucial step in the biofilm process. This step is dependent upon van der Waals, electrostatic, and acid–base interactions. These interactions are influenced by physicochemical properties of the substratum and the bacterial surface, such as hydrophobicity, surface charge, and electron donor–electron acceptor properties. In addition, the roughness of the substratum and the microbiological characteristics of the cell surface, such as cellular appendages and production of exopolysaccharides, can affect the adherence process. To date, many strategies have been developed to decrease the adherence of bacteria to surfaces. Surface modification with the addition of the suitable compounds makes surfaces less attractive for microorganisms and therefore prevents bacterial adherence and biofilm formation.     

Business-Driven Design of Infrastructures for IT Services

A methodology for designing data center infrastructure for Information Technology (IT) services is developed. The main departure from existing methodologies is that it evaluates and compares alternative designs using business metrics rather than purely technical metrics. Specifically, the methodology evaluates the business impact (financial loss) imposed by imperfect infrastructure. The methodology provides the optimal infrastructure that minimizes the sum of provisioning costs and business losses incurred during failures and performance degradations. Several full numerical example scenarios are provided and results are analyzed. The use of the method for dynamically provisioning an adaptive infrastructure is briefly discussed.