Topic
Spark (mathematics)
About: Spark (mathematics) is a research topic. Over the lifetime, 7304 publications have been published within this topic receiving 63322 citations.
Papers published on a yearly basis
Papers
More filters
••
01 Jan 2004-Precision Engineering-journal of The International Societies for Precision Engineering and Nanotechnology
TL;DR: In parallel spark EDM as discussed by the authors, a capacitor is inserted parallel to each discharge gap between each electrode and workpiece, and multiple discharges can dispersively be generated for each pulse.
Abstract: This paper describes the development of parallel spark EDM method. In the discharge circuit, the electrode is divided into multiple electrodes, each of which is electrically insulated and connected to the pulse generator through a diode. A capacitor is inserted parallel to each discharge gap between each electrode and workpiece (here workpiece is common for each electrode). Compared with conventional EDM in which only a singular discharge can be generated for each pulse, multiple discharges can dispersively be generated for each pulse in parallel spark EDM. Results of experiments on parallel spark EDM and conventional EDM show that not only is the machining process more stable, but the machining speed and surface roughness can also be improved with parallel spark EDM.
24 citations
••
TL;DR: This paper designs and implements the algorithms for solving the traveling salesman problem based on ant colony algorithm on MapReduce framework and Spark platform and combines it with genetic algorithm, and shows that with the increase of ant colony size, this solution reflects the superiority of parallel computation.
24 citations
••
TL;DR: In this article, the authors discuss some of the changes that have taken place in power systems and explore the inherent requirements for simulation technologies in order to keep up with this rapidly changing environment.
Abstract: ISSN 0895-0156/02/$17.00©2002 IEEE T he computer simulation of power systems has presented many challenges and opportunities over the years. Fortunately, the general nature of power systems remained relatively the same for a long period of time. This allowed power system engineers to improve modeling techniques progressively and to apply computer hardware and software technology to design study tools that met the analysis requirements. The models were based on fundamental frequency responses. However, with the wide-spread use of microprocessor-based controls and the associated advances in power electronic devices over the past 10 years, the nature of modern power systems has significantly changed. This article discusses some of the changes that have taken place in power systems and explores some of the inherent requirements for simulation technologies in order to keep up with this rapidly changing environment. Industrial examples of how power system simulation has been applied by end-users to meet the advancing requirements is provided.
24 citations
•
16 Oct 2006TL;DR: In this paper, a spray-guided, spark-ignition, direct fuel injection engine is described, and a preferred elapsed time between an end of the first fuel pulse and start of the spark ignition is determined based upon engine load.
Abstract: A method and article of manufacture are provided to operate a spray-guided, spark-ignition, direct fuel injection engine, including injecting a first fuel pulse during a combustion cycle, and initiating spark ignition by energizing a spark igniter. A second fuel pulse is injected during the combustion cycle effective to form an ignitable fuel-air mixture proximal to the spark igniter during a period in time whereat the spark igniter is energized. A preferred elapsed time between an end of the first fuel pulse and start of the spark ignition is determined based upon engine load.
24 citations
••
19 Mar 2017TL;DR: The purpose is to study the influence of accessing data stored in the Hadoop File System HDFS in each evaluation step of a metaheuristic and to provide a software tool to solve multi-objective Big Data Optimization problems.
Abstract: Big Data Optimization is the term used to refer to optimization problems which have to manage very large amounts of data. In this paper, we focus on the parallelization of metaheuristics with the Apache Spark cluster computing system for solving multi-objective Big Data Optimization problems. Our purpose is to study the influence of accessing data stored in the Hadoop File System HDFS in each evaluation step of a metaheuristic and to provide a software tool to solve these kinds of problems. This tool combines the jMetal multi-objective optimization framework with Apache Spark. We have carried out experiments to measure the performance of the proposed parallel infrastructure in an environment based on virtual machines in a local cluster comprising upi¾źto 100 cores. We obtained interesting results for computational effort and propose guidelines to face multi-objective Big Data Optimization problems.
24 citations