Integrated Mobility and QoS Control in Cellular Wireless ATM Networks

This paper presents a traversed pathtracking-based technique for integrated mobility andquality-of-service (QoS) management of connections incellular wireless ATM networks. Simulation andanalytical results for probabilities of connectionBlocking, Dropping, and Unsuccessful Connections aredetermined. A distributed operating system-basedarchitecture for implementation of integrated mobilityand QoS control is then proposed. The objective is totreat mobility as a network impairment triggeredactivity which is to be handled via QoS management.Depending on the speed of the mobile unit and thecategory of service being used, the QoS of a connectionmay or may not vary continuously during a session. Theresults presented here consider coexistence of constantbit-rate and nonreal-time variable bitrate ATM connections over a single session.     

Volume changes of binary mixtures during solid state sintering

Abstract

The influence of the mixture concentration on densification of Fe-Cr, Fe-Mo, and Ti-Cu compacts during solid state sintering were investigated. The hypothesis was put forward before that only S and V shaped curves for concentration dependencies of densification exist as a result of solid phase sintering of mixtures. It was shown, in this paper, that the above idea on the existence only two types of the plots was correct. These curve shapes can be explained on the basis of diffusion interaction of metals, applying the multiparticle model of a two component compact.     

Neural network model of heat and fluid flow in gas metal arc fillet welding based on genetic algorithm and conjugate gradient optimisation

Abstract

Although numerical calculations of heat transfer and fluid flow can provide detailed insights into welding processes and welded materials, these calculations are complex and unsuitable in situations where rapid calculations are needed. A recourse is to train and validate a neural network, using results from a well tested heat and fluid flow model to significantly expedite calculations and ensure that the computed results conform to the basic laws of conservation of mass, momentum and energy. Seven feedforward neural networks were developed for gas metal arc (GMA) fillet welding, one each for predicting penetration, leg length, throat, weld pool length, cooling time between 800°C and 500°C, maximum velocity and peak temperature in the weld pool. Each model considered 22 inputs that included all the welding variables, such as current, voltage, welding speed, wire radius, wire feed rate, arc efficiency, arc radius, power distribution, and material properties such as thermal conductivity, specific heat and temperature coefficient of surface tension. The weights in the neural network models were calculated using the conjugate gradient (CG) method and by a hybrid optimisation scheme involving the CG method and a genetic algorithm (GA). The neural network produced by the hybrid optimisation model produced better results than the networks based on the CG method with various sets of randomised initial weights. The CG method alone was unable to find the best optimal weights for achieving low errors. The hybrid optimisation scheme helped in finding optimal weights through a global search, as evidenced by good agreement between all the outputs from the neural networks and the corresponding results from the heat and fluid flow model.     

Adaptive dynamic walking of a quadruped robot using a neural system model

We are trying to induce a quadruped robot to walk dynamically on irregular terrain by using a neural system model. In this paper, we integrate several reflexes, such as a stretch reflex, a vestibulospinal reflex and extensor/flexor reflexes, into a central pattern generator (CPG). We try to realize adaptive walking up and down a slope of 12°, walking over an obstacle 3 cm in height, and walking on terrain undulation consisting of bumps 3 cm in height with fixed parameters of CPGs and reflexes. The success in walking on such irregular terrain in spite of stumbling and landing on obstacles shows that the control method using a neural system model proposed in this study has the ability for autonomous adaptation to unknown irregular terrain. In order to clarify the role of a CPG, we investigate the relation between parameters of a CPG and the mechanical system by simulations and experiments. CPGs can generate stable walking suitable for the mechanical system by receiving inhibitory input as sensory feedback and generate adaptive walking on irregular terrain by receiving excitatory input as sensory feedback. MPEG footage of these experiments can be seen at: http://www.kimura.is.uec.ac.jp.     

Adaptive Multiuser Detection Based on RBF Networks in Impulsive Noise CDMA Channels

With increasing need for capacity in mobilecellular communications, code division multiple accesshas been viewed as the technique to meet this goal.However, the conventional receiver suffers frommultiuser interference and the near-far effect. Toalleviate this problem, various multiuser receivers havebeen proposed. They have been shown to enhance theperformance of the conventional receiver with respect to capacity and interference rejection. Butthese receivers, intended for Gaussian noise channels,can fail in other environments such as impulsive noiseconditions. A possible solution is to exploit the advantages of neural networks. A neuralnetwork's ability to reject non-Gaussian noise can beutilized to implement multiuser receivers that rejectboth impulsive noise and multiuser interference.Following this logic, this paper considers nonadaptivemultiuser receiver and adaptive multiuser receiver basedon radial basis function neural networks. Simulations ofthese receivers show results that are superior to previously studied multiuser receivers, withrespect to practicality and performance.     

Global Fault Detection in Adhesively Bonded Joints Using Artificial Intelligence

In general, non-destructive evaluation is applied to detect and localize structural faults using a signal with a wavelength smaller than the detected fault. But the method requires analyzing the object in numerous small sections to detect the damage. Non-invasive diagnosis methods for fault detection are used in different industrial sectors. In this work, the main focus is on global fault detection for structural mechanical components such as a bonded beam using artificial intelligence, i.e., neural nets. Therefore, the fault detection procedure requires only a global measurement in the structural component in operational conditions. An experimental setup using two aluminum beams bonded with an adhesive was used to simulate a bonded joint. Different sizes of adhesive surface simulate faults in the original adhesive joint. Thereafter, resonance frequency shifts in the Frequency Response Functions (FRFs) were used to detect structural faults. Damage in structures causes small changes in the structural resonances. Then, the FRFs were used as an input into an artificial supervised neural network. This work considers global non-destructive tests focused only on the soundness estimation of the system. The neural network involved is a supervised feed-forward network with Levenberg–Marquardt backpropagation algorithm, which classifies the beams in four clusters. The classification consists in beam damaged or not damaged. If the beam is damaged the intensity of the fault is established.     

Vision based seam tracking system for underwater flux cored arc welding

Abstract

Manual underwater welding is usually time consuming, expensive and hard to perform because of the rigorous underwater environment. Automatic underwater welding can be performed faster at less cost and with higher quality. An automatic seam tracking system for underwater flux cored arc welding has been developed. It consists of a vision sensing module, a seam recognition module, a fuzzy controller (FC) and an X–Y travel platform. The vision sensing module can capture clear seam images during welding, successfully resolving the problem of welding arc interference during underwater flux cored arc welding. The seam recognition module filters, enhances and thresholds the seam images and then recognises the seam deviation angle with a three layer back propagation neural network. The FC outputs the control parameters according to the seam deviation angle and then controls the X–Y platform to drive the torch to the centre of the seam. In this study, three different welds were considered: a straight line, a kinked straight line and an S curved line. These welds were tracked real timely during underwater flux cored arc welding. The results show that this seam tracking system can meet the requirements of the automatic underwater flux cored arc welding.     

Chelant enhanced passivation of carbon steel in deoxygenated alkaline aqueous solutions

Abstract

The passivation characteristics of carbon steel surfaces at 473 K in the presence of certain chelating agents such as NTA DTP A, and HEDTA are described. The relative impacts of these chelants on the passivation process are evaluated by using base metal loss, soluble and insoluble iron concentrations in the mediums SEM studies of the topography of the surface coatings, and electrochemical investigations of the protection afforded by the oxide coating. The results have been compared with the passivation behaviour obtained under simple alkaline pH (LiOH) treatment (without chelating agents) and that previously obtained in the presence of EDTA. It is found that at 473 K, the presence of these complexing agents greatly increases the base metal loss, although a lower base metal loss is observed with LiOH. but the oxide film formed is more protective than the one formed under LiOR or EDTA treatments. The morphology of the coatings formed under complexing conditions has revealed highly developed crystallite faces on the outer surface layer. It is concluded that at 473 K passivation by LiOR is preferred to that given by the chelants.     

Possibility of grain size prediction in AA5754 aluminium ingots using neural networks

Abstract

The approach to the grain size prediction in AA5754 Al alloy ingots based on artificial neural networks (ANN) has been used in the present study. The ANN has been trained on data that was measured in the real industrial conditions during the process of direct chill Al ingots casting. A very complex relation between the numerous casting parameters and the microstructure of the ingots justifies the application of neural networks, which are known for mapping complex and non-linear systems. A feed forward ANN model with the resilient back-propagation learning algorithm and weight decay regularisation has been developed to relate the grain size to casting rate, meniscus level, casting temperature, water flow for the metal mould cooling and speed of wire for master alloy addition. The results obtained from the ANN are found to be consistent with the theoretical researches and experience from the foundry.     

The Forcer Concept and Express Route Planning in Mesh-Survivable Networks

To date, mesh network design theory has beendeveloped for the case where working and protectioncapacity is terminated at every node. It is recognizedthat express routes, which bypass some nodes en-route, would decrease the total DCS port costs but ithas been unclear how to incorporate bypass planning inthe optimal spare capacity design for a mesh-restorablenetwork. An important issue is whether the introduction of nodal bypass will increase the total sparecapacity needed for restorability, due to a reduction ofrestoration re-routing flexibility. To address thesequestions, we introduce the forcer concept for analysis of the relationship between workingand spare capacity in a mesh-restorable network. Weapply the forcer concept to show theoretically whybypass in fact need never require an increase in sparing and may actually permit a decrease in somecases. In tests to validate and exploit these findings,an average reduction of 12% in total spare capacity and16% in DCS port count totals were obtainedsimultaneously with an Integer Programming optimization. Thesesavings are relative to an already optimized fullyterminated network design. The work thus contributes togreater theoretical understanding and designcost-effectiveness for mesh-based restorable networks.