The Problem Sensitization Robotic Complex Drilling and Milling of Sandwich Shells of Polymer Composites

In clause is given robotic a complex for drilling and milling sandwich shells from polymeric composites. The machining of polymeric composite materials has technological problems. At drilling sandwich shells there is a probability of destruction of a drill from hit of the tool in a partition. The system sensibilization robotic complex for increase of reliability of work of the cutting tool of the small size is offered.

Polyethylene multiwalled carbon nanotube composites

Polyethylene (PE) multiwalled carbon nanotubes (MWCNTs) with weight fractions ranging from 0.1 to 10 wt% were prepared by melt blending using a mini-twin screw extruder. The morphology and degree of dispersion of the MWCNTs in the PE matrix at different length scales was investigated using scanning electron microscopy (SEM), transmission electron microscopy (TEM), atomic force microscopy (AFM) and wide-angle X-ray diffraction (WAXD). Both individual and agglomerations of MWCNTs were evident. An up-shift of 17 cm(-1) for the G band and the evolution of a shoulder to this peak were obtained in the Raman spectra of the nanocomposites, probably due to compressive forces exerted on the MWCNTs by PE chains and indicating intercalation of PE into the MWCNT bundles. The electrical conductivity and linear viscoelastic behaviour of these nanocomposites were investigated. A percolation threshold of about 7.5 wt% was obtained and the electrical conductivity of PE was increased significantly, by 16 orders of magnitude, from 10(-20) to 10(-4) S/cm. The storage modulus (G') versus frequency curves approached a plateau above the percolation threshold with the formation of an interconnected nanotube structure, indicative of 'pseudo-solid-like' behaviour. The ultimate tensile strength and elongation at break of the nanocomposites decreased with addition of MWCNTs. The diminution of mechanical proper-ties of the nanocomposites, though concomitant with a significant increase in electrical conductivity, implies the mechanism for mechanical reinforcement for PE/MWCNT composites is filler-matrix interfacial interactions and not filler percolation. The temperature of crystallisation (T.) and fraction of PE that was crystalline (F-c) were modified by incorporating MWCNTs. The thermal decomposition temperature of PE was enhanced by 20 K on addition of 10 wt% MWCNT. (c) 2005 Elsevier Ltd. All rights reserved.

Fatigue crack propagation in a sintered 2xxx series aluminium alloy

Many potential applications for sintered aluminium are limited by the poor fatigue properties of the material. In order to increase understanding of the fatigue mechanisms in sintered aluminium, fatigue tests were carried out on a sintered 2xxx series aluminium alloy, AMB-2712. The alloy has a fatigue endurance strength of approximately 145 MPa (R = 0.1). Three regions were identified on the fatigue fracture surfaces. Region I contains the initiation site and transgranular crack propagation. When the size of the cyclic plastic zone ahead of the crack becomes comparable to the grain size, microstructural damage at the crack tip results in a transition to intergranular propagation. Region 2 mainly contains intergranularly fractured material, whilst the final fracture area makes up Region 3, in the form of dimple coalescence and intergranular failure. Transgranular fractographic features observed on fatigued specimens include fissure-type striations, cross-hatched grains, furrowed grains and grains containing step-like features. (c) 2006 Elsevier B.V. All rights reserved.

A scatterometer neural network sensor model with input noise

The ERS-1 satellite carries a scatterometer which measures the amount of radiation scattered back toward the satellite by the ocean's surface. These measurements can be used to infer wind vectors. The implementation of a neural network based forward model which maps wind vectors to radar backscatter is addressed. Input noise cannot be neglected. To account for this noise, a Bayesian framework is adopted. However, Markov Chain Monte Carlo sampling is too computationally expensive. Instead, gradient information is used with a non-linear optimisation algorithm to find the maximum em a posteriori probability values of the unknown variables. The resulting models are shown to compare well with the current operational model when visualised in the target space.

Structured neural network modelling of multi-valued functions for wind retrieval from scatterometer measurements

A conventional neural network approach to regression problems approximates the conditional mean of the output vector. For mappings which are multi-valued this approach breaks down, since the average of two solutions is not necessarily a valid solution. In this article mixture density networks, a principled method to model conditional probability density functions, are applied to retrieving Cartesian wind vector components from satellite scatterometer data. A hybrid mixture density network is implemented to incorporate prior knowledge of the predominantly bimodal function branches. An advantage of a fully probabilistic model is that more sophisticated and principled methods can be used to resolve ambiguities.

Neural network-based wind vector retrieval from satellite scatterometer data

Obtaining wind vectors over the ocean is important for weather forecasting and ocean modelling. Several satellite systems used operationally by meteorological agencies utilise scatterometers to infer wind vectors over the oceans. In this paper we present the results of using novel neural network based techniques to estimate wind vectors from such data. The problem is partitioned into estimating wind speed and wind direction. Wind speed is modelled using a multi-layer perceptron (MLP) and a sum of squares error function. Wind direction is a periodic variable and a multi-valued function for a given set of inputs; a conventional MLP fails at this task, and so we model the full periodic probability density of direction conditioned on the satellite derived inputs using a Mixture Density Network (MDN) with periodic kernel functions. A committee of the resulting MDNs is shown to improve the results.

Multi-valued control problems and mixture density network

We have proposed a novel robust inversion-based neurocontroller that searches for the optimal control law by sampling from the estimated Gaussian distribution of the inverse plant model. However, for problems involving the prediction of continuous variables, a Gaussian model approximation provides only a very limited description of the properties of the inverse model. This is usually the case for problems in which the mapping to be learned is multi-valued or involves hysteritic transfer characteristics. This often arises in the solution of inverse plant models. In order to obtain a complete description of the inverse model, a more general multicomponent distributions must be modeled. In this paper we test whether our proposed sampling approach can be used when considering an arbitrary conditional probability distributions. These arbitrary distributions will be modeled by a mixture density network. Importance sampling provides a structured and principled approach to constrain the complexity of the search space for the ideal control law. The effectiveness of the importance sampling from an arbitrary conditional probability distribution will be demonstrated using a simple single input single output static nonlinear system with hysteretic characteristics in the inverse plant model.

Probability distribution modelling to improve stability in nonlinear MIMO control

We consider the direct adaptive inverse control of nonlinear multivariable systems with different delays between every input-output pair. In direct adaptive inverse control, the inverse mapping is learned from examples of input-output pairs. This makes the obtained controller sub optimal, since the network may have to learn the response of the plant over a larger operational range than necessary. Moreover, in certain applications, the control problem can be redundant, implying that the inverse problem is ill posed. In this paper we propose a new algorithm which allows estimating and exploiting uncertainty in nonlinear multivariable control systems. This approach allows us to model strongly non-Gaussian distribution of control signals as well as processes with hysteresis. The proposed algorithm circumvents the dynamic programming problem by using the predicted neural network uncertainty to localise the possible control solutions to consider.

A scatterometer neural network sensor model with input noise

The ERS-1 satellite carries a scatterometer which measures the amount of radiation scattered back toward the satellite by the ocean's surface. These measurements can be used to infer wind vectors. The implementation of a neural network based forward model which maps wind vectors to radar backscatter is addressed. Input noise cannot be neglected. To account for this noise, a Bayesian framework is adopted. However, Markov Chain Monte Carlo sampling is too computationally expensive. Instead, gradient information is used with a non-linear optimisation algorithm to find the maximum em a posteriori probability values of the unknown variables. The resulting models are shown to compare well with the current operational model when visualised in the target space.

Structured neural network modelling of multi-valued functions for wind retrieval from scatterometer measurements

A conventional neural network approach to regression problems approximates the conditional mean of the output vector. For mappings which are multi-valued this approach breaks down, since the average of two solutions is not necessarily a valid solution. In this article mixture density networks, a principled method to model conditional probability density functions, are applied to retrieving Cartesian wind vector components from satellite scatterometer data. A hybrid mixture density network is implemented to incorporate prior knowledge of the predominantly bimodal function branches. An advantage of a fully probabilistic model is that more sophisticated and principled methods can be used to resolve ambiguities.

Neural network-based wind vector retrieval from satellite scatterometer data

Obtaining wind vectors over the ocean is important for weather forecasting and ocean modelling. Several satellite systems used operationally by meteorological agencies utilise scatterometers to infer wind vectors over the oceans. In this paper we present the results of using novel neural network based techniques to estimate wind vectors from such data. The problem is partitioned into estimating wind speed and wind direction. Wind speed is modelled using a multi-layer perceptron (MLP) and a sum of squares error function. Wind direction is a periodic variable and a multi-valued function for a given set of inputs; a conventional MLP fails at this task, and so we model the full periodic probability density of direction conditioned on the satellite derived inputs using a Mixture Density Network (MDN) with periodic kernel functions. A committee of the resulting MDNs is shown to improve the results.

Outlier detection in scatterometer data:Neural network approaches

Satellite-borne scatterometers are used to measure backscattered micro-wave radiation from the ocean surface. This data may be used to infer surface wind vectors where no direct measurements exist. Inherent in this data are outliers owing to aberrations on the water surface and measurement errors within the equipment. We present two techniques for identifying outliers using neural networks; the outliers may then be removed to improve models derived from the data. Firstly the generative topographic mapping (GTM) is used to create a probability density model; data with low probability under the model may be classed as outliers. In the second part of the paper, a sensor model with input-dependent noise is used and outliers are identified based on their probability under this model. GTM was successfully modified to incorporate prior knowledge of the shape of the observation manifold; however, GTM could not learn the double skinned nature of the observation manifold. To learn this double skinned manifold necessitated the use of a sensor model which imposes strong constraints on the mapping. The results using GTM with a fixed noise level suggested the noise level may vary as a function of wind speed. This was confirmed by experiments using a sensor model with input-dependent noise, where the variation in noise is most sensitive to the wind speed input. Both models successfully identified gross outliers with the largest differences between models occurring at low wind speeds. © 2003 Elsevier Science Ltd. All rights reserved.

The n-tuple network: coping with sub-optimality

The subject of this thesis is the n-tuple net.work (RAMnet). The major advantage of RAMnets is their speed and the simplicity with which they can be implemented in parallel hardware. On the other hand, this method is not a universal approximator and the training procedure does not involve the minimisation of a cost function. Hence RAMnets are potentially sub-optimal. It is important to understand the source of this sub-optimality and to develop the analytical tools that allow us to quantify the generalisation cost of using this model for any given data. We view RAMnets as classifiers and function approximators and try to determine how critical their lack of' universality and optimality is. In order to understand better the inherent. restrictions of the model, we review RAMnets showing their relationship to a number of well established general models such as: Associative Memories, Kamerva's Sparse Distributed Memory, Radial Basis Functions, General Regression Networks and Bayesian Classifiers. We then benchmark binary RAMnet. model against 23 other algorithms using real-world data from the StatLog Project. This large scale experimental study indicates that RAMnets are often capable of delivering results which are competitive with those obtained by more sophisticated, computationally expensive rnodels. The Frequency Weighted version is also benchmarked and shown to perform worse than the binary RAMnet for large values of the tuple size n. We demonstrate that the main issues in the Frequency Weighted RAMnets is adequate probability estimation and propose Good-Turing estimates in place of the more commonly used :Maximum Likelihood estimates. Having established the viability of the method numerically, we focus on providillg an analytical framework that allows us to quantify the generalisation cost of RAMnets for a given datasetL. For the classification network we provide a semi-quantitative argument which is based on the notion of Tuple distance. It gives a good indication of whether the network will fail for the given data. A rigorous Bayesian framework with Gaussian process prior assumptions is given for the regression n-tuple net. We show how to calculate the generalisation cost of this net and verify the results numerically for one dimensional noisy interpolation problems. We conclude that the n-tuple method of classification based on memorisation of random features can be a powerful alternative to slower cost driven models. The speed of the method is at the expense of its optimality. RAMnets will fail for certain datasets but the cases when they do so are relatively easy to determine with the analytical tools we provide.

The fatigue ageing of vulcanised rubbers

The cause of the respective rough and smooth fatigue failure surfaces of Neoprene GS : Neoprene W and Neoprene GS : natural rubber vulcanisates is investigated. The contrasting morphology of the vulcanisates is found to be the major factor determining the fatigue behaviour of the blends. Neoprene GS and Neoprene W appear to form homogeneous blends which exhibit physical properties and fatigue failure surfaces intermediate between those of the two horropolymers. Neoprene GS and natural rubber exhibit heterogeneity when blended together. The morphology of these blends is found to influence both the fatigue resistance and failure surface of the vulcanisates. Exceptional uncut and cut initiated fatigue lives are observed for blends having an interconnecting network morphology. The network structure and cross-link density of the elastomers in the blends and the addition of carbon black and antioxidant are all found to influence the fatigue resistance but not the failure mechanism of the vulcanisate.