scholarly journals Applying ensemble neural networks to analyze industrial maintenance: Influence of Saharan dust transport on gas turbine axial compressor fouling

2021 ◽  
Vol 24 (68) ◽  
pp. 53-71
Author(s):  
D. Gonzalez-Calvo ◽  
R.M. Aguilar ◽  
C. Criado-Hernandez ◽  
L.A. Gonzalez-Mendoza
Keyword(s):  
Neural Networks ◽  
Gas Turbine ◽  
Axial Compressor ◽  
Computational Procedure ◽  
Operating Regime ◽  
Economic Resources ◽  
Saharan Dust ◽  
Dust Transport ◽  
Industrial Maintenance ◽  
The Relationship

The planning of industrial maintenance associated with the production of electricity is vital, as it yields a current and future snapshot of an industrial component in order to optimize the human, technical and economic resources of the installation. This study focuses on the degradation due to fouling of a gas turbine in the Canary Islands, and analyzes fouling levels over time based on the operating regime and local meteorological variables. In particular, we study the relationship between degradation and the suspended dust that originates in the Sahara Desert. To this end, we use a computational procedure that relies on a set of artificial neural networks to build an ensemble, using a cross-validated committees approach, to yield the compressor efficiency. The use of trained models makes it possible to know in advance how the local fouling of an industrial rotating component will evolve, which is useful for maintenance planning and for calculating the relative importance of the variables that make up the system

scholarly journals Trends of Dust Transport Episodes in Cyprus Using a Classification of Synoptic Types Established with Artificial Neural Networks

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
S. Michaelides ◽  
F. Tymvios ◽  
S. Athanasatos ◽  
M. Papadakis
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Point Of View ◽  
Synoptic Scale ◽  
Dust Transport ◽  
Synoptic Patterns ◽  
Artificial Neural ◽  
Dust Events ◽  
The Relationship

The relationship between dust episodes over Cyprus and specific synoptic patterns has long been considered but also further supported in recent studies by the authors. Having defined a dust episode as a day when the average PM10 measurement exceeds the threshold of 50 mg/(m3 day), the authors have utilized Artificial Neural Networks and synoptic charts, together with satellite and ground measurements, in order to establish a scheme which links specific synoptic patterns with the appearance of dust transport over Cyprus. In an effort to understand better these complicated synoptic-scale phenomena and their associations with dust transport episodes, the authors attempt in the present paper a followup of the previous tasks with the objective to further investigate dust episodes from the point of view of their time trends. The results have shown a tendency for the synoptic situations favoring dust events to increase in the last decades, whereas, the synoptic situations not favoring such events tend to decrease with time.

Using Neural Networks in Controlling Low- and Medium-Capacity Gas-Turbine Plants

2019 ◽  
Vol 90 (11) ◽  
pp. 737-740 ◽  
Author(s):  
B. V. Kavalerov ◽  
I. V. Bakhirev ◽  
G. A. Kilin
Keyword(s):  
Neural Networks ◽  
Gas Turbine

Ozone Concentration Prediction using Artificial Neural Networks

2017 ◽  
Vol 68 (10) ◽  
pp. 2224-2227 ◽  
Author(s):  
Camelia Gavrila
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Ozone Concentration ◽  
Meteorological Data ◽  
Global Solar Radiation ◽  
Time Data ◽  
Marquardt Algorithm ◽  
Sensitivity Tests ◽  
Artificial Neural ◽  
The Relationship

The aim of this paper is to determine a mathematical model which establishes the relationship between ozone levels together with other meteorological data and air quality. The model is valid for any season and for any area and is based on real-time data measured in Bucharest and its surroundings. This study is based on research using artificial neural networks to model nonlinear relationships between the concentration of immission of ozone and the meteorological factors: relative humidity (RH), global solar radiation (SR), air temperature (TEMP). The ozone concentration depends on following primary pollutants: nitrogen oxides (NO, NO2), carbon monoxide (CO). To achieve this, the Levenberg-Marquardt algorithm was implemented in Scilab, a numerical computation software. Performed sensitivity tests proved the robustness of the model and its applicability in predicting the ozone on short-term.

scholarly journals Scene Complexity: A New Perspective on Understanding the Scene Semantics of Remote Sensing and Designing Image-Adaptive Convolutional Neural Networks

2021 ◽  
Vol 13 (4) ◽  
pp. 742
Author(s):  
Jian Peng ◽  
Xiaoming Mei ◽  
Wenbo Li ◽  
Liang Hong ◽  
Bingyu Sun ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Fundamental Problem ◽  
Semantic Representation ◽  
Feature Learning ◽  
Essential Elements ◽  
Complex Scene ◽  
Feature Representations ◽  
The Right ◽  
The Relationship

Scene understanding of remote sensing images is of great significance in various applications. Its fundamental problem is how to construct representative features. Various convolutional neural network architectures have been proposed for automatically learning features from images. However, is the current way of configuring the same architecture to learn all the data while ignoring the differences between images the right one? It seems to be contrary to our intuition: it is clear that some images are easier to recognize, and some are harder to recognize. This problem is the gap between the characteristics of the images and the learning features corresponding to specific network structures. Unfortunately, the literature so far lacks an analysis of the two. In this paper, we explore this problem from three aspects: we first build a visual-based evaluation pipeline of scene complexity to characterize the intrinsic differences between images; then, we analyze the relationship between semantic concepts and feature representations, i.e., the scalability and hierarchy of features which the essential elements in CNNs of different architectures, for remote sensing scenes of different complexity; thirdly, we introduce CAM, a visualization method that explains feature learning within neural networks, to analyze the relationship between scenes with different complexity and semantic feature representations. The experimental results show that a complex scene would need deeper and multi-scale features, whereas a simpler scene would need lower and single-scale features. Besides, the complex scene concept is more dependent on the joint semantic representation of multiple objects. Furthermore, we propose the framework of scene complexity prediction for an image and utilize it to design a depth and scale-adaptive model. It achieves higher performance but with fewer parameters than the original model, demonstrating the potential significance of scene complexity.

scholarly journals Saharan dust and giant quartz particle transport towards Iceland

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
György Varga ◽  
Pavla Dagsson-Walhauserová ◽  
Fruzsina Gresina ◽  
Agusta Helgadottir
Keyword(s):  
Numerical Models ◽  
Saharan Dust ◽  
Atmospheric Environment ◽  
The Arctic ◽  
Dust Particles ◽  
Atmospheric Flow ◽  
Dust Transport ◽  
Strong Winds ◽  
Dust Events ◽  
Local Dust

AbstractMineral dust emissions from Saharan sources have an impact on the atmospheric environment and sedimentary units in distant regions. Here, we present the first systematic observations of long-range Saharan dust transport towards Iceland. Fifteen Saharan dust episodes were identified to have occurred between 2008 and 2020 based on aerosol optical depth data, backward trajectories and numerical models. Icelandic samples from the local dust sources were compared with deposited dust from two severe Saharan dust events in terms of their granulometric and mineralogical characteristics. The episodes were associated with enhanced meridional atmospheric flow patterns driven by unusual meandering jets. Strong winds were able to carry large Saharan quartz particles (> 100 µm) towards Iceland. Our results confirm the atmospheric pathways of Saharan dust towards the Arctic, and identify new northward meridional long-ranged transport of giant dust particles from the Sahara, including the first evidence of their deposition in Iceland as previously predicted by models.

Dream Bizarreness as the Cognitive Correlate of Altered Neuronal Behavior in REM Sleep

1989 ◽  
Vol 1 (3) ◽  
pp. 201-222 ◽  
Author(s):  
Adam N. Mamelak ◽  
J. Allan Hobson
Keyword(s):  
Neural Networks ◽  
Cerebral Cortex ◽  
Rem Sleep ◽  
Neuronal Dynamics ◽  
Neurophysiological Model ◽  
The Relationship ◽  
Cognitive Feature ◽  
The Brain ◽  
Cognitive Correlate ◽  
Raphe Neurons

Bizarreness is a cognitive feature common to REM sleep dreams, which can be easily measured. Because bizarreness is highly specific to dreaming, we propose that it is most likely brought about by changes in neuronal activity that are specific to REM sleep. At the level of the dream plot, bizarreness can be defined as either discontinuity or incongruity. In addition, the dreamer's thoughts about the plot may be logically deficient. We propose that dream bizarreness is the cognitive concomitant of two kinds of changes in neuronal dynamics during REM sleep. One is the disinhibition of forebrain networks caused by the withdrawal of the modulatory influences of norepinephrine (NE) and serotonin (5HT) in REM sleep, secondary to cessation of firing of locus coeruleus and dorsal raphe neurons. This aminergic demodulation can be mathematically modeled as a shift toward increased error at the outputs from neural networks, and these errors might be represented cognitively as incongruities and/or discontinuities. We also consider the possibility that discontinuities are the cognitive concomitant of sudden bifurcations or “jumps” in the responses of forebrain neuronal networks. These bifurcations are caused by phasic discharge of pontogeniculooccipital (PGO) neurons during REM sleep, providing a source of cholinergic modulation to the forebrain which could evoke unpredictable network responses. When phasic PGO activity stops, the resultant activity in the brain may be wholly unrelated to patterns of activity dominant before such phasic stimulation began. Mathematically such sudden shifts from one pattern of activity to a second, unrelated one is called a bifurcation. We propose that the neuronal bifurcations brought about by PGO activity might be represented cognitively as bizarre discontinuities of dream plot. We regard these proposals as preliminary attempts to model the relationship between dream cognition and REM sleep neurophysiology. This neurophysiological model of dream bizarreness may also prove useful in understanding the contributions of REM sleep to the developmental and experiential plasticity of the cerebral cortex.

Influence of Water Droplet Size and Temperature on Wet Compression

2007 ◽  
Author(s):  
M. Bianchi ◽  
F. Melino ◽  
A. Peretto ◽  
P. R. Spina ◽  
S. Ingistov
Keyword(s):  
Gas Turbine ◽  
Water Droplet ◽  
Droplet Diameter ◽  
Axial Compressor ◽  
Combined Cycle ◽  
Water Evaporation ◽  
Air Cooling ◽  
Compression Process ◽  
Two Phase ◽  
Wet Compression

In the last years, among all different gas turbine inlet air cooling techniques, an increasing attention to fogging approach is dedicated. The various fogging strategies seem to be a good solution to improve gas turbine or combined cycle produced power with low initial investment cost and less installation downtime. In particular, overspray fogging and interstage injection involve two-phase flow consideration and water evaporation during compression process (also known as wet compression). According to the Author’s knowledge, the field of wet compression is not completely studied and understood. In the present paper, all the principal aspects of wet compression and in particular the influence of injected water droplet diameter and surface temperature, and their effect on gas turbine performance and on the behavior of the axial compressor (change in axial compressor performance map due to the water injection, redistribution of stage load, etc.) are analyzed by using a calculation code, named IN.FO.G.T.E. (INterstage FOgging Gas Turbine Evaluation), developed and validated by the Authors.

Compressor Performance and Operability in Swirl Distortion

2010 ◽  
Author(s):  
Yogi Sheoran ◽  
Bruce Bouldin ◽  
P. Murali Krishnan
Keyword(s):  
Gas Turbine ◽  
Complex Geometry ◽  
Full Range ◽  
Axial Compressor ◽  
Cfd Model ◽  
Generator System ◽  
Sliding Mesh ◽  
Wide Range ◽  
Compressor Performance ◽  
The Impact

Inlet swirl distortion has become a major area of concern in the gas turbine engine community. Gas turbine engines are increasingly installed with more complicated and tortuous inlet systems, like those found on embedded installations on Unmanned Aerial Vehicles (UAVs). These inlet systems can produce complex swirl patterns in addition to total pressure distortion. The effect of swirl distortion on engine or compressor performance and operability must be evaluated. The gas turbine community is developing methodologies to measure and characterize swirl distortion. There is a strong need to develop a database containing the impact of a range of swirl distortion patterns on a compressor performance and operability. A recent paper presented by the authors described a versatile swirl distortion generator system that produced a wide range of swirl distortion patterns of a prescribed strength, including bulk swirl, twin swirl and offset swirl. The design of these swirl generators greatly improved the understanding of the formation of swirl. The next step of this process is to understand the effect of swirl on compressor performance. A previously published paper by the authors used parallel compressor analysis to map out different speed lines that resulted from different types of swirl distortion. For the study described in this paper, a computational fluid dynamics (CFD) model is used to couple upstream swirl generator geometry to a single stage of an axial compressor in order to generate a family of compressor speed lines. The complex geometry of the analyzed swirl generators requires that the full 360° compressor be included in the CFD model. A full compressor can be modeled several ways in a CFD analysis, including sliding mesh and frozen rotor techniques. For a single operating condition, a study was conducted using both of these techniques to determine the best method given the large size of the CFD model and the number of data points that needed to be run to generate speed lines. This study compared the CFD results for the undistorted compressor at 100% speed to comparable test data. Results of this study indicated that the frozen rotor approach provided just as accurate results as the sliding mesh but with a greatly reduced cycle time. Once the CFD approach was calibrated, the same techniques were used to determine compressor performance and operability when a full range of swirl distortion patterns were generated by upstream swirl generators. The compressor speed line shift due to co-rotating and counter-rotating bulk swirl resulted in a predictable performance and operability shift. Of particular importance is the compressor performance and operability resulting from an exposure to a set of paired swirl distortions. The CFD generated speed lines follow similar trends to those produced by parallel compressor analysis.

Sign in / Sign up

Export Citation Format

Share Document