This paper aims to provide researchers and engineers with evidence that sensorless machine variable monitoring can achieve tool wear in broaching real production environments, reducing errors, enhancing product quality, facilitating zero-defect manufacturing. Additionally, plays a crucial role improving the quality of manufacturing products processes. These aspects are especially pertinent aeronautical manufacturing, which serves as experimental case this study. The research presents...

The high performance computing landscape is shifting from collections of homogeneous nodes towards heterogeneous systems, in which consist a combination traditional out-of-order execution cores and accelerator devices. Accelerators, built around GPUs, many-core chips, FPGAs or DSPs, are used to offload compute-intensive tasks. advent this type systems has brought about wide diverse ecosystem development platforms, optimization tools analysis frameworks. This review the state-of-the-art for...

Industrial communication protocols are used to interconnect systems, interfaces, and machines in industrial environments. With the advent of hyper-connected factories, role these is gaining relevance, as they enable real-time acquisition machine monitoring data, which can fuel data analysis platforms that conduct tasks such predictive maintenance. However, effectiveness largely unknown there a lack empirical evaluation compares their performance. In this work, we evaluate OPC-UA, Modbus,...

Eulerian-Lagrangian approaches capable of accurately reproducing complex fluid flows are becoming more and popular due to the increasing availability capacity High Performance Computing facilities. However, parallelisation Lagrangian part such methods is challenging when a large number markers employed. In this study, hybrid MPI/OpenMP strategy presented implemented in finite difference based large-eddy simulation code featuring immersed boundary method which generally employs markers. A...

In the new hyper connected factories, data gathering, and prediction models are key to keeping both productivity piece quality. This paper presents a software platform that monitors detects outliers in an industrial manufacturing process using scalable tools. The collects from machine, processes it, displays visualizations dashboard along with results. A statistical method is used detect process. performance of assessed two ways: firstly by monitoring five-axis milling machine secondly,...

Abstract The integration of new Internet Things (IoT) applications and services heavily relies on task offloading to external devices due the constrained computing battery resources IoT devices. Up now, Cloud Computing (CC) paradigm has been a good approach for tasks where latency is not critical, but it useful when matters, so Multi-access Edge (MEC) can be use. In this work, we propose distributed Deep Reinforcement Learning (DRL) tool optimize binary decision, is, independent decision...

Kernel density estimation (KDE) is a statistical technique used to estimate the probability function of sample set with unknown function. It considered fundamental data-smoothing problem for use large datasets, and widely applied in areas such as climatology biometry. Due volumes data that these problems usually process, KDE computationally challenging problem. Current HPC platforms built-in accelerators have an enormous computing power, but they be programmed efficiently order take...

The aeronautical manufacturing sector is currently involved in the 4th industrial revolution, namely Industry 4.0, improving processes with support of ICT. One objectives this revolution to be able predict defects that can have economic and operational impacts. In work, we present a software platform monitors detects outliers an process, close real time, using scalable tools. Our collects data from machine, it plots visualizations dashboard results. IQR method used detect process. We...

Data sharing is a key factor for ensuring reproducibility and transparency of scientific experiments, neuroimaging no exception. The vast heterogeneity data formats imaging modalities utilised in the field makes it very challenging problem. In this context, Brain Imaging Structure (BIDS) appears as solution organising describing datasets. Since its publication 2015, BIDS has gained widespread attention field, provides common way to arrange share multimodal brain images. Although evident...

In the new hyper connected factories, data gathering, and prediction models are key to keeping both productivity piece quality. This paper presents a software platform that monitors detects outliers in an industrial manufacturing process using scalable tools. The collects from machine, processes it, displays visualizations dashboard along with results. A statistical method is used detect process. performance of assessed two ways: firstly by monitoring five-axis milling machine secondly,...

Energy efficiency is a relevant research topic in High Performance Computing, strongly motivated by the increasing power consumption figures of modern compute devices. Recent processors introduce significant architectural differences compared to their predecessors and it can be challenging use them efficiently, both terms performance energy usage. In this work we conduct assessment 5 benchmarks 3 dual-socket machines with Intel CPUs different generations: 6-core Sandy Bridge, 18-core...

The increase in the number of large scale events held indoors (i.e. conferences, business events) opens new opportunities for crowd monitoring, access controlling as a way to prevent risks, provide further information about event's development. In addition, availability already connectable devices among attendees allows perform non-intrusive positioning during event, without need specific tracking devices. We present platform that integrates control management, monitoring based on passive...

The combination of Multi-access Edge Computing (MEC) and task offloading paradigms will enable next-generation IoT applications that are currently hampered due to the computational battery limitations devices. Moreover, requirements such apps can be so variable guaranteeing a certain Quality-of-Experience (QoE) level when performing decisions means enhancing user experience services. To address this problem, in paper, QoE-based algorithm is proposed. Considering an unpredictable time-varying...