1,720,960 research outputs found
Deep anomaly detection in horizontal axis wind turbines using Graph Convolutional Autoencoders for Multivariate Time series
Full text linkWind power is one of the fastest-growing renewable energy sectors instrumental in the ongoing decarbonization process. However, wind turbines are subjected to a wide range of dynamic loads which can cause more frequent failures and downtime periods, leading to ever-increasing attention to effective Condition Monitoring strategies. In this paper, we propose a novel unsupervised deep anomaly detection framework to detect anomalies in wind turbines based on SCADA data. We introduce a promising neural architecture, namely a Graph Convolutional Autoencoder for Multivariate Time series, to model the sensor network as a dynamical functional graph. This structure improves the unsupervised learning capabilities of Autoencoders by considering individual sensor measurements together with the nonlinear correlations existing among signals. On this basis, we developed a deep anomaly detection framework that was validated on 12 failure events occurred during 20 months of operation of four wind turbines. The results show that the proposed framework successfully detects anomalies and anticipates SCADA alarms by outperforming other two recent neural approaches
Time series clustering. A complex network-based approach for feature selection in multi-sensor data
Full text linkDistributed monitoring sensor networks are used in an ever increasing number of applications, particularly with the advent of IoT technologies. This has led to a growing demand for unconventional analytical tools to cope with a large amount of different signals. In this scenario, the modeling of time series in similar groups represents an interesting area especially for feature subset selection (FSS) purposes. Methods based on clustering algorithms are very promising for FSS, but in their original form they are unsuitable to manage the complexity of temporal dynamics in time series. In this paper we propose a clustering approach, based on complex network analysis, for the unsupervised FSS of time series in sensor networks. We used natural visibility graphs to map signal segments in the network domain, then extracted features in the form of node degree sequences of the graphs, and finally computed time series clustering through community detection algorithms. The approach was tested on multivariate signals monitored in a 1 MW cogeneration plant and the results show that it outperforms standard time series clustering in terms of both redundancy reduction and information gain. In addition, the proposed method demonstrated its merit in terms of retention of information content with respect to the original dataset in the analyzed condition monitoring system
Multivariate KPI for energy management of cooling system in food industry
Full text linkWithin EU, the food industry is currently ranked among the energy-intensive sectors, mainly as a consequence of the cooling
system shareover the total energy demand.
As such, the definition of appropriate key performance indicators (KPI) for ammonia chillers can play a strategic role for the
efficient monitoring of the energy performance of the cooling systems.
The goal of this paper is to develop an appropriate management approach, to account for energy inefficiency of the single
compressors, and to identify the specific variables driving the performance outliers.
To this end, a new KPI is proposed which correlates the energy consumption and the different process variables. The construction
of the new indicator was carried out by means of multivariate statistical analysis, in particular using Kernel Partial Least Square
(KPLS).This method is able to evaluate the maximum correlation between dataset and energy consumption employing nonlinear
regression techniques.
The validity of the new KPI is discussed on a case study relevant to the cooling system of a frozen ready meals industry. The
assessment of the proposed metric is one against Specific Energy Consumption (SEC) like indicator, typically used in the context
of the Energy Management Systems
Industrial energy management systems in Italy: state of the art and perspective
Full text linkDespite the economic crisis, the impact of industry sector Share on the total primary energy demand in Italy is still significant. The certification of companies according to the standard ISO 50001:2011 ("Energy management systems Requirements and guidelines for use"), can represent a key element in the achievement of objectives set in the 20-20-20 Climate-Energy Package.
This paper illustrates the state of implementation of ISO 50001 certifications in Italy, reporting on the results of a questionnaire carried out as a part of a master's thesis project at Sapienza, University of Rome in collaboration with FIRE (Italian Federation for the Rational Use of Energy) that included the major certification bodies, certified companies and consultants. The purpose is to outline the current situation, identify the perspectives and highlight the pros and cons related to the implementation of an Energy Management System (EnMS).
The big picture shows that Italy, one of the leading countries in energy efficiency policies, suffer from a significant delay in the implementation of the EnMS in industry with respect to Germany.
The results of the survey also show that the definition of energy performance indicators, as hell as the individuations of an energy baseline and a. monitoring plan constitute the requirements most critical to comply with for companies than for consultants. It also appears that more than 35% of companies already ISO 50001 certified have received benefits in terms of cumulative energy saving above 5%, and that the main reason why they have implemented an EnMS is related to the potential impact on increasing the competitiveness of the core business
Multivariate Key Performance Indicator of Baking Process
No full textAbstractEnergy efficiency is nowadays a subject deeply discussed in several fields, with a large potential in industry. Here proper process and energy management routines turns out to be essential to reduce the energy demand while keeping the control of the product quality. In this respect the bread baking, one of the pillar of food related industry, is an energy intensive process irrespective to the adopted oven technology or to the primary energy nature. Baking is the fundamental step of the bread production process and it entails a number of complex chemical and physical phenomena, critical to the final physical properties of bread, i.e. crust colour, crumb texture and taste. A careful balance throughout all the steps of the “manufacturing” cycle is vital to ensure the processes synchronization, in order to produce a consistent and satisfactory loaf of bread. A proper energy management of this process needs to consider such features to ensure a high quality product. As such process monitoring can not be conveniently described using customary specific energy metric (correlating the energy demand to the amount of processed material) or full three-dimensional (3D) physic-based modeling as in computational fluid dynamics (CFD).In this paper, the energy analysis of the system is carried out with a methodology rooted in the family of non parametric approaches. The aim of the study is to identify key performance indicators (KPIs) able to assess the effectiveness of the energy “use” along the baking process. Specifically, the identification of KPIs is carried out using Principal Component Analysis (PCA) of the available datasets
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
