Novelty Detection Using Auto-Associative Neural Network

Condition monitoring of gear-based mechanical systems in non-stationary operation conditions is in general very challenging. This issue is particularly important for wind energy technology because most of the modern wind turbines are geared and gearbox damages account for at least the 20% of their unavailability time. In this work, a new method for the diagnosis of drive-train bearings damages is proposed: the general idea is that vibrations are measured at the tower instead of at the gearbox. This implies that measurements can be performed without impacting the wind turbine operation. The test case considered in this work is a wind farm owned by the Renvico company, featuring six wind turbines with 2 MW of rated power each. A measurement campaign has been conducted in winter 2019 and vibration measurements have been acquired at five wind turbines in the farm. The rationale for this choice is that, when the measurements have been acquired, three wind turbines were healthy, one wind turbine had recently recovered from a planetary bearing fault, and one wind turbine was undergoing a high speed shaft bearing fault. The healthy wind turbines are selected as references and the damaged and recovered are selected as targets: vibration measurements are processed through a multivariate Novelty Detection algorithm in the feature space, with the objective of distinguishing the target wind turbines with respect to the reference ones. The application of this algorithm is justified by univariate statistical tests on the selected time-domain features and by a visual inspection of the data set via Principal Component Analysis. Finally, a novelty index based on the Mahalanobis distance is used to detect the anomalous conditions at the damaged wind turbine. The main result of the study is that the statistical novelty of the damaged wind turbine data set arises clearly, and this supports that the proposed measurement and processing methods are promising for wind turbine condition monitoring.

Download Full-text

Numerical Assessment of SCAP: A Passive System for Preventing Thermoacoustic Oscillations in Gas Turbine Annular Combustors

Volume 2: Turbo Expo 2007 ◽

10.1115/gt2007-28063 ◽

2007 ◽

Cited By ~ 1

Author(s):

Stefano Tiribuzi

Keyword(s):

Gas Turbine ◽

Gas Turbines ◽

Research Unit ◽

Combined Cycle ◽

Computational Time ◽

Computational Domain ◽

Ambient Conditions ◽

Pressure Oscillations ◽

Operation Conditions ◽

Thermoacoustic Oscillations

ENEL operates a dozen combined cycle units whose V94.3A gas turbines are equipped with annular combustors. In such lean premixed gas turbines, particular operation conditions could trigger large pressure oscillations due to thermoacoustic instabilities. The ENEL Research unit is studying this phenomenon in order to find out methods which could avoid or mitigate such events. The use of effective numerical analysis techniques allowed us to investigate the realistic time evolution and behaviour of the acoustic fields associated with this phenomenon. KIEN, an in-house low diffusive URANS code capable of simulating 3D reactive flows, has been used in the Very Rough Grid approach. This approach permits the simulation, with a reasonable computational time, of quite long real transients with a computational domain extended over all the resonant volumes involved in the acoustic phenomenon. The V94.3A gas turbine model was set up with a full combustor 3D grid, going from the compressor outlet up to the turbine inlet, including both the annular plenum and the annular combustion chamber. The grid extends over the entire circular angle, including all the 24 premixed burners. Numerical runs were performed with the normal V94.3A combustor configuration, with input parameters set so as no oscillations develop in the standard ambient conditions. Wide pressure oscillations on the contrary are associated with the circumferential acoustic modes of the combustor, which have their onset and grow when winter ambient conditions are assumed. These results also confirmed that the sustaining mechanism is based on the equivalence ratio fluctuation of premix mixture and that plenum plays an important role in such mechanism. Based on these findings, a system for controlling the thermoacoustic oscillation has been conceived (Patent Pending), which acts on the plenum side of the combustor. This system, called SCAP (Segmentation of Combustor Annular Plenum), is based on the subdivision of the plenum annular volume by means of a few meridionally oriented walls. Repetition of KIEN runs with a SCAP configuration, in which a suitable number of segmentation walls were properly arranged in the annular plenum, demonstrated the effectiveness of this solution in preventing the development of wide thermoacoustic oscillations in the combustor.

Download Full-text

Synthesis of bio-functionalized three-dimensional titania nanofibrous 3 using femtosecond laser ablation

10.32920/14638530.v1 ◽

2021 ◽

Author(s):

Amirhossein Tavangar ◽

Bo Tan ◽

Krishnan Venkatakrishnan

Keyword(s):

Femtosecond Laser ◽

Three Dimensional ◽

Titanium Substrate ◽

Chemical Properties ◽

Femtosecond Laser Ablation ◽

Cell Interaction ◽

Primary Objective ◽

Femtosecond Laser Irradiation ◽

Ambient Conditions

The primary objective of current tissue regeneration research is to synthesize nano-based platforms that 24 can induce guided, controlled, and rapid healing. Titanium nanotubes have been extensively considered 25 as a new biomaterial for biosensors, implants, cell growth, tissue engineering, and drug delivery systems. 26 However, cell adhesion to nanotubes is poor due to their chemical inertness, as well as the one-dimen- 27 sional structure, and surface modification is required to enhance nanotube–cell interaction. While there 28 have been a considerable number of studies on growing titanium nanotubes, synthesizing a three-dimen- 29 sional (3-D) nano-architecture which can act as a growth support platform for bone and stem cells has 30 not been reported so far. Therefore, we present a novel technique to synthesize and grow 3-D titania 31 interwoven nanofibrous structures on a titanium substrate using femtosecond laser irradiation under 32 ambient conditions. This surface architecture incorporate the functions of 3-D nano-scaled topography 33 and modified chemical properties to improve osseointegration while at the same time leaving space to 34 deliver other functional agents. The results indicate that laser pulse repetition can control the density 35 and pore size of engineered nanofibrous structures. In vitro experiments reveal that the titania nanofi- 36 brous architecture possesses excellent bioactivity and can induce rapid, uniform, and controllable 37 bone-like apatite precipitation once immersed in simulated body fluid (SBF). This approach to synthesiz- 38 ing 3-D titania nanofibrous structures suggests considerable promise for the promotion of Ti interfacial 39 properties to develop new functional biomaterials for various biomedical applications.

Download Full-text

Continuous Respiration Rate Measurement of Heat-Stressed Dairy Cows and Relation to Environment, Body Temperature, and Lying Time

Transactions of the ASABE ◽

10.13031/trans.12451 ◽

2018 ◽

Vol 61 (5) ◽

pp. 1475-1485 ◽

Cited By ~ 7

Author(s):

Ian K. Atkins ◽

Nigel B. Cook ◽

Mario R. Mondaca ◽

Christopher Y. Choi

Keyword(s):

Heat Stress ◽

Body Temperature ◽

Dairy Cows ◽

Respiration Rate ◽

Cooling System ◽

Visual Observation ◽

Time Of Day ◽

Primary Objective ◽

Ambient Conditions ◽

Lactating Dairy Cows

Abstract. This study uses a continuously sampling sensor to document the respiration rate dynamics of lactating dairy cows under conditions of heat stress. Previously available respiration rate data on lactating dairy cows had primarily been generated by manually counting flank movements at discrete points in time, typically several times per day. Continuous measurements provide much higher-resolution data over time. The primary objective of this study was to analyze these continuous respiration rate measurements in relation to ambient conditions, body temperature, lying time, and time of day. Better understanding continuous responses to heat stress may help synchronize cooling system operation to the cows’ need for heat stress relief. For 19 days during a summer season in Wisconsin, eight lactating Holstein cows were equipped with sensors designed to detect the abdominal expansion associated with breathing. An algorithm was developed to derive respiration rate from each sensor’s signal. To validate the accuracy of the sensor and algorithms, measurements from the sensor were compared to respiration rate measurements taken via visual observation. Overall, variation in continuously measured respiration rate corresponded to changes in temperature-humidity index (THI) and body temperature. However, respiration rate and body temperature also remained elevated at night despite decreasing THI. Keywords: Dairy cow, Heat stress, Physiological monitoring, Respiration rate, Telemetry, Wearable.

Download Full-text

Thermal and Electrical Characterization of Power Mosfet Module Using Coupled Field Analysis

Journal of Mechanics ◽

10.1017/jmech.2019.19 ◽

2019 ◽

Vol 35 (5) ◽

pp. 641-655 ◽

Cited By ~ 1

Author(s):

H.-C. Cheng ◽

C.-H. Wu ◽

S.-Y. Lin

Keyword(s):

Circuit Simulation ◽

Field Analysis ◽

Electrical Performance ◽

Switching Frequency ◽

Power Losses ◽

Ambient Conditions ◽

Power Module ◽

Power Mosfet ◽

Operation Conditions ◽

Coupled Field

ABSTRACTTemperature resulting from the joule heating power and the turn-on and turn-off dissipation of high-power, high-frequency applications is the root cause of their thermal instability, electrical performance degradation, and even thermal-fatigue failure. Thus, the study presents thermal and electrical characterizations of the power MOSFET module packaged in SOT-227 under natural convection and forced convection through three-dimensional (3D) thermal-electric (TE) coupled field analysis. In addition, the influences of some key parameters like electric loads, ambient conditions, thermal management considerations (heat sink, heat spreader) and operation conditions (duty cycle and switching frequency) on the power loss and thermal performance of the power module are addressed. The study starts from a suitable estimation of the power losses, where the conduction losses are calculated using the temperature- and gate-voltage-dependent on-state resistance and drain current through the device, and the switching losses are predicted based on the ideal switching waveforms of the power MOSFETs applied. The effectiveness of the theoretical predictions in terms of device’s power losses and temperatures is demonstrated through comparison with the results of circuit simulation and thermal experiment.

Download Full-text

Synthesis of bio-functionalized three-dimensional titania nanofibrous 3 using femtosecond laser ablation

10.32920/14638530 ◽

2021 ◽

Author(s):

Amirhossein Tavangar ◽

Bo Tan ◽

Krishnan Venkatakrishnan

Keyword(s):

Femtosecond Laser ◽

Three Dimensional ◽

Titanium Substrate ◽

Chemical Properties ◽

Femtosecond Laser Ablation ◽

Cell Interaction ◽

Primary Objective ◽

Femtosecond Laser Irradiation ◽

Ambient Conditions

The primary objective of current tissue regeneration research is to synthesize nano-based platforms that 24 can induce guided, controlled, and rapid healing. Titanium nanotubes have been extensively considered 25 as a new biomaterial for biosensors, implants, cell growth, tissue engineering, and drug delivery systems. 26 However, cell adhesion to nanotubes is poor due to their chemical inertness, as well as the one-dimen- 27 sional structure, and surface modification is required to enhance nanotube–cell interaction. While there 28 have been a considerable number of studies on growing titanium nanotubes, synthesizing a three-dimen- 29 sional (3-D) nano-architecture which can act as a growth support platform for bone and stem cells has 30 not been reported so far. Therefore, we present a novel technique to synthesize and grow 3-D titania 31 interwoven nanofibrous structures on a titanium substrate using femtosecond laser irradiation under 32 ambient conditions. This surface architecture incorporate the functions of 3-D nano-scaled topography 33 and modified chemical properties to improve osseointegration while at the same time leaving space to 34 deliver other functional agents. The results indicate that laser pulse repetition can control the density 35 and pore size of engineered nanofibrous structures. In vitro experiments reveal that the titania nanofi- 36 brous architecture possesses excellent bioactivity and can induce rapid, uniform, and controllable 37 bone-like apatite precipitation once immersed in simulated body fluid (SBF). This approach to synthesiz- 38 ing 3-D titania nanofibrous structures suggests considerable promise for the promotion of Ti interfacial 39 properties to develop new functional biomaterials for various biomedical applications.

Download Full-text

PERFORMANCE ASSESSMENT OF A LARGE INTERNAL COMBUSTION ENGINE DUE TO INLET AIR COOLING AND DEHUMIDIFICATION: GT-POWER SOFTWARE SIMULATION

Revista de Engenharia Térmica ◽

10.5380/reterm.v20i2.81782 ◽

2021 ◽

Vol 20 (2) ◽

pp. 13

Author(s):

I. C. Campblell ◽

A. Chun ◽

B. M. F. Miotto ◽

J. L. M. Donatelli ◽

J. J. C. S. Santos ◽

...

Keyword(s):

Internal Combustion Engines ◽

Combustion Engine ◽

Ambient Air ◽

Internal Combustion ◽

Maximum Temperature ◽

Air Cooling ◽

Ambient Conditions ◽

Operation Conditions ◽

Brake Mean Effective Pressure ◽

Cooling Coil

Large internal combustion engines (ICEs) performance is limited by knocking phenomenon due to harsh ambient conditions such as hot temperature and excessive humidity. The performance of these engines can be enhanced by cooling and dehumidifying the inlet air on turbocharger upstream under safe operation conditions through a cooling coil heat exchanger, hence, increasing the power output as well as reducing the brake specific fuel consumption and pollutant specific emissions. Analysis have been performed in the GT-POWER software through a 1-D thermodynamic modelling of the Wärtsilä W20V34SG engine, making it possible to verify the influence of cooled and dehumidified ambient air, considering a temperature range from 9.5°C (282.7 K) to 15.5°C (288.7 K), while keeping 1 bar for pressure and relative humidity of 100%. Furthermore, the brake mean effective pressure (BMEP) has been set from 20 to 23.45 bar with a step of 1.15 bar. Such simulations are aimed to find the maximum air temperature at the cooling coil outlet in which the average of maximum cylinder pressures does not exceed the safety limit pressure of 186 bar while maintaining control on the wastegate valve. As a result, it was possible to evaluate that the maximum temperature to be chosen, under the conditions already mentioned, should be lower than 13.8°C (287 K).

Download Full-text

Support for Operation Strategy in CHP Plants With Gas Turbines

Volume 4: Cycle Innovations; Electric Power; Industrial and Cogeneration; Manufacturing Materials and Metallurgy ◽

10.1115/gt2006-91153 ◽

2006 ◽

Author(s):

Gerard Kosman ◽

Tadeusz Chmielniak ◽

Wojciech Kosman

Keyword(s):

Gas Turbine ◽

Gas Turbines ◽

Extended Period ◽

Health State ◽

Ambient Conditions ◽

Operation Conditions ◽

Thermal Measurements ◽

Time Of Operation ◽

Diagnostic Module

This paper presents procedure, which supports planning a strategy of operation, repairs and modernizations. Reliability and effectiveness are assumed to form the criteria for appropriate operation with a special attention to working costs. The procedure involves diagnostic analysis. Information derived from diagnostic may be utilized in many ways. It allows to determine losses, which derive from components wear or improper operation, and track the wear rate of machines components. This in turn allows to assess the losses, which appear in case of extended period between routine repairs. The most important application of the diagnostic results is the determination of the working costs for a CHP plant. It establishes a relation between the working costs of a gas turbine and its future time of operation. In addition it analyses the influence of the parameters independent of the gas turbine user (such as ambient conditions) on the operation and costs. The calculations presented in this paper involve a diagnostic module designed for uncooled and cooled gas turbines. The health state is assessed through a set of performance indices. Thermal measurements are the input data for the module, which may utilize even a small number of available measurements. The working costs create the basis for the procedure, which supports planning the strategy of operation and repairs. The procedure consists of several diagnostic rules. It draws conclusions from given premises. A premise includes a set of data, which involve among others working costs calculated according to health state. A conclusion indicates whether a further operation is possible and under what circumstances. The circumstances specify any required adjustments of the operation conditions or suggest an exchange or repair of some turbine components, which might be damaged.

Download Full-text

Structural Damage Classification Using Extreme Value Statistics

Journal of Dynamic Systems Measurement and Control ◽

10.1115/1.1849240 ◽

2005 ◽

Vol 127 (1) ◽

pp. 125-132 ◽

Cited By ~ 54

Author(s):

Hoon Sohn ◽

David W. Allen ◽

Keith Worden ◽

Charles R. Farrar

Keyword(s):

Extreme Values ◽

Novelty Detection ◽

Extreme Value ◽

Extreme Value Statistics ◽

Series Data ◽

Identification Algorithm ◽

Damage Classification ◽

Mass System ◽

Damage Diagnosis ◽

Normality Assumption

The first and most important objective of any damage identification algorithm is to ascertain with confidence if damage is present or not. Many methods have been proposed for damage detection based on ideas of novelty detection founded in pattern recognition and multivariate statistics. The philosophy of novelty detection is simple. Features are first extracted from a baseline system to be monitored, and subsequent data are then compared to see if the new features are outliers, which significantly depart from the rest of population. In damage diagnosis problems, the assumption is that outliers are generated from a damaged condition of the monitored system. This damage classification necessitates the establishment of a decision boundary. Choosing this threshold value is often based on the assumption that the parent distribution of data is Gaussian in nature. While the problem of novelty detection focuses attention on the outlier or extreme values of the data, i.e., those points in the tails of the distribution, the threshold selection using the normality assumption weights the central population of data. Therefore, this normality assumption might impose potentially misleading behavior on damage classification, and is likely to lead the damage diagnosis astray. In this paper, extreme value statistics is integrated with the novelty detection to specifically model the tails of the distribution of interest. Finally, the proposed technique is demonstrated on simulated numerical data and time series data measured from an eight degree-of-freedom spring-mass system.

Download Full-text

Liquid Mass Sensing Using Resonating Microplates under Harsh Drop and Spray Conditions

Physics Research International ◽

10.1155/2014/320324 ◽

2014 ◽

Vol 2014 ◽

pp. 1-8 ◽

Cited By ~ 10

Author(s):

Said Mahajne ◽

Dafne Guetta ◽

Stella Lulinsky ◽

Slava Krylov ◽

Yoav Linzon

Keyword(s):

Resonant Frequency ◽

Resonant Mode ◽

Ambient Conditions ◽

Mass Sensing ◽

Operation Conditions ◽

Multiple Cycles ◽

Volatile Liquids ◽

Deposited Film ◽

Harsh Conditions

We have performed in situ real time mass sensing of deposited liquid volatile droplets and sprays using plate-like microstructures, with robust and reusable performance attained over harsh conditions and multiple cycles of operation. A home-built electrooptical sensing system in ambient conditions has been used. The bimorph effect on the resonant frequency of altered mass loading, elasticity, and strain had been carefully compared, and the latter were found to be negligible in the presence of nonviscous liquids deposited on top of our microplate devices. In resonant mode, the loaded mass has been estimated from measured resonant frequency shifts and interpreted from a simple, uniformly deposited film model. A minimum submicrogram detectable mass was estimated, suggesting the system’s potential for robust, fast, and reusable sensing capabilities, in the presence of volatile liquids under harsh operation conditions.

Download Full-text