Machinability assessment and surface integrity characteristics of Austempered Ductile Iron (ADI) using ultra-hard cutting tools

The application of austempered ductile iron (ADI) is gaining an ever greater share of the worldwide ferrous product market, specifically centering on the aerospace, automotive and shipping industries. ADI is a heat treated cast iron, which exhibits remarkable mechanical properties and provides an attractive material for designers and engineers to displace conventional materials. Previous attempts, however, to machine ADI using carbide or ceramic cutting tools produced poor tool life characteristics due to the relatively poor machinability of the workpiece. This paper presents a research study that has applied the advanced technology of modern ultrahard cutting tools, in an attempt to achieve enhanced machinability performance. This performance was evaluated through the analysis of cutting forces, tool wear, surface finish and roundness.

Fast one-class support vector machine for novelty detection

Novelty detection arises as an important learning task in several applications. Kernel-based approach to novelty detection has been widely used due to its theoretical rigor and elegance of geometric interpretation. However, computational complexity is a major obstacle in this approach. In this paper, leveraging on the cutting-plane framework with the well-known One-Class Support Vector Machine, we present a new solution that can scale up seamlessly with data. The first solution is exact and linear when viewed through the cutting-plane; the second employed a sampling strategy that remarkably has a constant computational complexity defined relatively to the probability of approximation accuracy. Several datasets are benchmarked to demonstrate the credibility of our framework.

Real time cyber attack analysis on Hadoop ecosystem using machine learning algorithms

Big Data technologies are exciting cutting-edge technologies that generate, collect, store and analyse tremendous amount of data. Like any other IT revolution, Big Data technologies also have big challenges that are obstructing it to be adopted by wider community or perhaps impeding to extract value from Big Data with pace and accuracy it is promising. In this paper we first offer an alternative view of «Big Data Cloud» with the main aim to make this complex technology easy to understand for new researchers and identify gaps efficiently. In our lab experiment, we have successfully implemented cyber-attacks on Apache Hadoop's management interface «Ambari». On our thought about «attackers only need one way in», we have attacked the Apache Hadoop's management interface, successfully turned down all communication between Ambari and Hadoop's ecosystem and collected performance data from Ambari Virtual Machine (VM) and Big Data Cloud hypervisor. We have also detected these cyber-attacks with 94.0187% accurateness using modern machine learning algorithms. From the existing researchs, no one has ever attempted similar experimentation in detection of cyber-attacks on Hadoop using performance data.

Machine learning for user modeling

At first blush, user modeling appears to be a prime candidate for straightforward application of standard machine learning techniques. Observations of the user's behavior can provide training examples that a machine learning system can use to form a model designed to predict future actions. However, user modeling poses a number of challenges for machine learning that have hindered its application in user modeling, including: the need for large data sets; the need for labeled data; concept drift; and computational complexity. This paper examines each of these issues and reviews approaches to resolving them.

Fast algorithm for the cutting angle method of global optimization

The cutting angle method for global optimization was proposed in 1999 by Andramonov et al. (Appl. Math. Lett. 12 (1999) 95). Computer implementation of the resulting algorithm indicates that running time could be improved with appropriate modifications to the underlying mathematical description. In this article, we describe the initial algorithm and introduce a new one which we prove is significantly faster at each stage. Results of numerical experiments performed on a Pentium III 750 Mhz processor are presented.

Predicting molecular structures: an application of the cutting angle method

The ability to predict molecular geometries has important applications in chemistry. Specific examples include the areas of protein space structure elucidation, the investigation of host–guest interactions, the understanding of properties of superconductors and of zeolites. This prediction of molecular geometries often depends on finding the global minimum or maximum of a function such as the potential energy. In this paper, we consider several well-known molecular conformation problems to which we apply a new method of deterministic global optimization called the cutting angle method. We demonstrate that this method is competitive with other global optimization techniques for these molecular conformation problems.

Geometry and combinatorics of the cutting angle method

Lower approximation of Lipschitz functions plays an important role in deterministic global optimization. This article examines in detail the lower piecewise linear approximation which arises in the cutting angle method. All its local minima can be explicitly enumerated, and a special data structure was designed to process them very efficiently, improving previous results by several orders of magnitude. Further, some geometrical properties of the lower approximation have been studied, and regions on which this function is linear have been identified explicitly. Connection to a special distance function and Voronoi diagrams was established. An application of these results is a black-box multivariate random number generator, based on acceptance-rejection approach.

Cutting angle method - a tool for constrained global optimization

Cutting angle method (CAM) is a deterministic global optimization technique applicable to Lipschitz functions f: Rn → R. The method builds a sequence of piecewise linear lower approximations to the objective function f. The sequence of solutions to these relaxed problems converges to the global minimum of f. This article adapts CAM to the case of linear constraints on the feasible domain. We show how the relaxed problems are modified, and how the numerical efficiency of solving these problems can be preserved. A number of numerical experiments confirms the improved numerical efficiency.

On the production of randomly-oriented recrystallization nuclei for selective growth experiments

The ideal starting condition for selective growth experiments is one having a layer of randomly-oriented nuclei adjacent to a matrix with negligible orientational variation but sufficient stored energy to promote growth. In practice, cutting or deformation processes are used in an attempt to approximate these ideal conditions, but the degree to which this is achieved has not been rigorously quantified. In this work, Fe-3wt%Si single crystals were cut or deformed using six different processes. The variation in texture with distance from the cut or deformed surface was measured using electron backscatter diffraction (EBSD) in a field emission gun scanning electron microscope (FEG-SEM) in order to assess the ability of each process to create conditions suitable for selective growth experiments. While grooving with a machine tool produced the best spread of orientations at the cut surface, the suitability of this process is diminished by the presence of a differently-textured deformed layer between the cut surface and the single crystal matrix. Grinding produced a less ideal distribution of orientations at the cut surface, but the presence of these orientations in a very thin layer adjacent to the matrix makes this process preferable for preparing crystals for selective growth experiments, provided the results are corrected for the deviation in the distribution of nuclei orientations from a random distribution.

Towards extended machine translation model for next generation world wide web

In this paper, we proposed a Data Translation model which potentially is a major promising web service of the next generation world wide web. This technique is somehow analogy to the technique of traditional machine translation but it is far beyond what we understand about machine translation in the past and nowadays in terms of the scope and the contents. To illustrate the new concept of web services based data translation, a multilingual machine translation electronic dictionary system and its web services based model including generic services, multilingual translation services are presented. This proposed data translation model aims at achieving better web services in easiness, convenience, efficiency, and higher accuracy, scalability, self-learning, self-adapting.

Machine vision system for automatic inspection of surface defects in aluminum die casting

A camera based machine vision system for the automatic inspection of surface defects in aluminum die casting is presented. The system uses a hybrid image processing algorithm based on mathematic morphology to detect defects with different sizes and shapes. The defect inspection algorithm consists of two parts. One is a parameter learning algorithm, in which a genetic algorithm is used to extract optimal structuring element parameters, and segmentation and noise removal thresholds. The second part is a defect detection algorithm, in which the parameters obtained by a genetic algorithm are used for morphological operations. The machine vision system has been applied in an industrial setting to detect two types of casting defects: parts mix-up and any defects on the surface of castings. The system performs with a 99% or higher accuracy for both part mix-up and defect detection and is currently used in industry as part of normal production.