Maintenance is a key factor to ensure the production efficiency, since the occurrence of unexpected failures leads to a degradation of the system performance, causing the loss of productivity and business opportunitie...
详细信息
Maintenance is a key factor to ensure the production efficiency, since the occurrence of unexpected failures leads to a degradation of the system performance, causing the loss of productivity and business opportunities, which are crucial roles to achieve competitiveness. The article aims to propose a reference architecture which will improve the way maintenance is considered in the current manufacturing world, by enabling an overall increase of production rates, while increasing the operational equipment effectiveness and decreasing the impact of maintenance needs. This objective would be accomplished by establishing an IoT infrastructure for the collection of the huge amount of available shop floor data, which can be analyzed, considering data analytics algorithms, predictive maintenance models and forecasting techniques, to perform the machine/system health assessment and prediction of maintenance needs, e.g. by detecting earlier the occurrence of possible failures and consequently the need to implement maintenance interventions. The scheduling of predictive maintenance needs will be integrated with the existing maintenance planning tools, and especially synchronized with the production planning tools to achieve a nondisruptive maintenance impact in the production system. A cloud-based collaborative maintenance services platform allows the secure collection, aggregation and analysis of a large amount of shared data from numerous manufacturers that use the same or similar machinery, and acts as an open market where companies can contract specialized maintenance services. This reference architecture aims to provide replicable architecture to be broadly applicable in a variety of industries, capable to improve the production efficiency through a real-time health monitoring and early detection of failures and outages, to speed up the maintenance delivery, and consequently mitigate their impact.
Innovations in Next-Generation Sequencing are enabling generation of DNA sequence data at ever faster rates and at very low cost. For example, the Illumina NovaSeq 6000 sequencer can generate 6 Terabases of data in le...
详细信息
Research software has become a central asset in academic research. It optimizes existing and enables new research methods, implements and embeds research knowledge, and constitutes an essential research product in its...
详细信息
Architecture, size, and shape of glands are most important patterns used by pathologists for assessment of cancer malignancy in prostate histopathological tissue slides. Varying structures of glands along with cumbers...
详细信息
distributed Complex Event Processing (DCEP) is a paradigm to infer the occurrence of complex situations in the surrounding world from basic events like sensor readings. In doing so, DCEP operators detect event pattern...
详细信息
We present a policy and process framework for secure environments for productive data science research projects at scale, by combining prevailing data security threat and risk profiles into five sensitivity tiers, and...
详细信息
This paper presents the summary of experience obtained with the modified clustering algorithm of Projective Adaptive Resonance Theory. The algorithm was proposed by authors, and was tested for text processing. Possibl...
详细信息
ISBN:
(纸本)9781509021628
This paper presents the summary of experience obtained with the modified clustering algorithm of Projective Adaptive Resonance Theory. The algorithm was proposed by authors, and was tested for text processing. Possible usage of the algorithm is exemplified by text document clustering, and generation of keyword dictionaries from text documents.
The wide adoption of smart devices has stimulated a fast shift of security-critical data from desktop to mobile devices. However, recurrent device theft and loss expose mobile devices to various security threats and e...
详细信息
During large-scale crisis situations there is an acute demand for relevant and accurate information. The availability of such information to incident commanders assists the ever continuing need to improve the effectiv...
详细信息
During large-scale crisis situations there is an acute demand for relevant and accurate information. The availability of such information to incident commanders assists the ever continuing need to improve the effectiveness of emergency response through the enhancement of agency preparedness and awareness; this also includes the potential offered by volunteers and the general public as well. To address the above mentioned challenges a distributed platform capable of seamlessly collect and aggregate information from engaged users providing information using the web or mobile devices is proposed. At the same time integration of information from sources such as sensors deployed on incident sites, publicly available open data, corporate legacy systems or documents stored on remote locations is enabled. As a result the platform end users can act based on the results of information aggregation and analysis. The work presented in this paper is motivated mainly by requirements identified by first responders during numerous crisis responses.
Large-scale graph-structured computation usually exhibits iterative and convergence-oriented computing nature, where input data is computed iteratively until a convergence condition is reached. Such features have led ...
详细信息
ISBN:
(纸本)9781450332057
Large-scale graph-structured computation usually exhibits iterative and convergence-oriented computing nature, where input data is computed iteratively until a convergence condition is reached. Such features have led to the development of two different computation modes for graph-structured programs, namely synchronous (Sync) and asynchronous (Async) modes. Unfortunately, there is currently no in-depth study on their execution properties and thus programmers have to manually choose a mode, either requiring a deep understanding of underlying graph engines, or suffering from suboptimal performance. This paper makes the first comprehensive characterization on the performance of the two modes on a set of typical graph-parallel applications. Our study shows that the performance of the two modes varies significantly with different graph algorithms, partitioning methods, execution stages, input graphs and cluster scales, and no single mode consistently outperforms the other. To this end, this paper proposes Hsync, a hybrid graph computation mode that adaptively switches a graph-parallel program between the two modes for optimal performance. Hsync constantly collects execution statistics on-the-fly and leverages a set of heuristics to predict future performance and determine when a mode switch could be profitable. We have built online sampling and offline profiling approaches combined with a set of heuristics to accurately predicting future performance in the two modes. A prototype called PowerSwitch has been built based on PowerGraph, a state-of-the-art distributed graph-parallel system, to support adaptive execution of graph algorithms. On a 48-node EC2-like cluster, PowerSwitch consistently outperforms the best of both modes, with a speedup ranging from 9% to 73% due to timely switch between two modes. Copyright 2015 ACM.
暂无评论