Search results for "Mach"
showing 10 items of 3360 documents
Signal Spectrum-Based Machine Learning Approach for Fault Prediction and Maintenance of Electrical Machines
2022
Industrial revolution 4.0 has enabled the advent of new technological advancements, including the introduction of information technology with physical devices. The implementation of information technology in industrial applications has helped streamline industrial processes and make them more cost-efficient. This combination of information technology and physical devices gave birth to smart devices, which opened up a new research area known as the Internet of Things (IoT). This has enabled researchers to help reduce downtime and maintenance costs by applying condition monitoring on electrical machines utilizing machine learning algorithms. Although the industry is trying to move from schedu…
Different Methods of Artificial Intelligence Used for Optimization the Turning Process
2015
In this paper, we realize a comparative study between some heuristics methods applied in turning operation in order to find optimal cutting parameters. We consider five different constraints aimed to achieve minimum total cost of machining. We have chosen the Simulated Annealing (SA) – a local search method, and Weighted-Sum Genetic Algorithm (WSGA) – a non-Pareto approach of a multi-objective optimization algorithm, based on a weighted aggregation of objectives. The aggregation may be with fixed weights or with random (variable) weights. The simulations showed that, even if it produces better results than the SA, WSGA with fixed weights, does not lead to optimum results, highlighting in th…
Distributed ASM - Pitfalls and solutions
2014
Published version of a chapter in the book: Abstract State Machines, Alloy, B, TLA, VDM, and Z. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-662-43652-3_18 While sequential Abstract State Machines (ASM) capture the essence of sequential computation, it is not clear that this is true of distributed ASM. This paper looks at two kinds of distributed process, one based on a global state and one based on variable access. Their commonalities are extracted and conclusions for the general understanding of distributed computation are drawn, providing integration between global state and variable access.
Quantifying Fundamental Vegetation Traits over Europe Using the Sentinel-3 OLCI Catalogue in Google Earth Engine
2022
Thanks to the emergence of cloud-computing platforms and the ability of machine learning methods to solve prediction problems efficiently, this work presents a workflow to automate spatiotemporal mapping of essential vegetation traits from Sentinel-3 (S3) imagery. The traits included leaf chlorophyll content (LCC), leaf area index (LAI), fraction of absorbed photosynthetically active radiation (FAPAR), and fractional vegetation cover (FVC), being fundamental for assessing photosynthetic activity on Earth. The workflow involved Gaussian process regression (GPR) algorithms trained on top-of-atmosphere (TOA) radiance simulations generated by the coupled canopy radiative transfer model (RTM) SC…
Lo stato veneziano attraverso Machiavelli (a proposito di "Machiavelli e la crisi dello Stato veneziano")
2019
Nel 1974 Innocenzi Cervelli pubblica a Napoli il suo primo libro, dedicato alla crisi che sconvolge Venezia e il suo dominio di Terraferma all’inizio del Cinquecento. Il giovane studioso scelse di integrare nella ricostruzione dell’ambiente politico e intellettuale della laguna un’analisi di tutti i testi machiavelliani pertinenti: non solo le opere maggiori che affrontano esplicitamente il grande problema costituzionale che la Serenissima rappresenta agli occhi dei contemporanei, e dei fiorentini in particolare, ma anche gli scritti «di servizio» che rivelano lo sguardo acuto del Machiavelli ambasciatore, capace di percepire aspetti di Venezia preclusi a altri osservatori. Cervelli, che, c…
Monitoring and Diagnosis of Failures in Squirrel-Cage Induction Motors Due to Cracked or Broken Bars
2011
In this paper three diagnostic procedures, based on on the vibration, current and instantaneous power monitoring for the detection and monitoring of incipient faults as cracks or bar breaks on squirrel cage motors are briefly reminded. The experimental investigations, carried out at the SDESLab (Sustainable Development Energy Savings Laboratory) of the University of Palermo in order to underline merits and drawbacks of the methods applied to the same die cast squirrel cage induction motor, are presented. The results of the investigations confirmed the effectiveness of the diagnostic procedures here considered.
Machine Learning approach towards real time assessment of hand-arm vibration risk
2021
Abstract In industry 4,0, the establishment of an interconnected environment where human operators cooperate with the machines offers the opportunity for substantially improving the ergonomics and safety conditions of the workplace. This topic is discussed in the paper referring to the vibration risk, which is a well-known cause of work-related pathologies. A wearable device has been developed to collect vibration data and to segment the signals obtained in time windows. A machine learning classifier is then proposed to recognize the worker’s activity and to evaluate the exposure to vibration risks. The experimental results demonstrate the feasibility and effectiveness of the methodology pr…
Cutting Vibrations
2008
Chapter 8 provides comprehensive engineering knowledge regarding cutting vibrations, their typical sources in machining operations, and methods of their elimination to prevent negative influence on the surface finish (chatter marks). The classification of cutting vibrations including free, forced, and self-excited vibrations is discussed, and all possible sources and mechanisms of all types of cutting vibrations are specified and characterized. The regeneration of surface waviness, which is the predominant mechanism of chatter, is outlined for turning and milling operations. The stability of machining operations based on the stability lobe diagrams is highlighted and their practical applica…
A Comparative Study of Nonlinear Machine Learning for the "In Silico" Depiction of Tyrosinase Inhibitory Activity from Molecular Structure.
2011
In the preset report, for the first time, support vector machine (SVM), artificial neural network (ANN), Baye- sian networks (BNs), k-nearest neighbor (k-NN) are applied and compared on two "in-house" datasets to describe the tyrosinase inhibitory activity from the molecular structure. The data set Data I is used for the identification of tyrosi- nase inhibitors (TIs) including 701 active and 728 inactive compounds. Data II consists of active chemicals for potency estimation of TIs. The 2D TOMOCOMD-CARDD atom-based quadratic indices are used as molecular descriptors. The de- rived models show rather encouraging results with the areas under the Receiver Operating Characteristic (AURC) curve …
Convolutional architectures for virtual screening
2020
Abstract Background A Virtual Screening algorithm has to adapt to the different stages of this process. Early screening needs to ensure that all bioactive compounds are ranked in the first positions despite of the number of false positives, while a second screening round is aimed at increasing the prediction accuracy. Results A novel CNN architecture is presented to this aim, which predicts bioactivity of candidate compounds on CDK1 using a combination of molecular fingerprints as their vector representation, and has been trained suitably to achieve good results as regards both enrichment factor and accuracy in different screening modes (98.55% accuracy in active-only selection, and 98.88% …