There are many challenges against an accurate gas turbine fault diagnostics, such as the nonlinearity of the engine health, the measurement uncertainty, and the occurrence of simultaneous faults. The conventional methods have limitations in effectively handling these challenges. In this paper, a hybrid intelligent technique is devised by integrating an autoassociative neural network (AANN), nested machine learning (ML) classifiers, and a multilayer perceptron (MLP). The AANN module is used as a data preprocessor to reduce measurement noise and extract the important features for visualisation and fault diagnostics. The features are extracted from the bottleneck layer output values based on the concept of the nonlinear principal component analysis (NLPCA). The nested classifier modules are then used in such a manner that fault and no-fault conditions, component and sensor faults, and different component faults are distinguished hierarchically. As part of the classification, evaluation of the fault classification performance of five widely used ML techniques aiming to identify alternative approaches is undertaken. In the end, the MLP approximator is utilised to estimate the magnitude of the isolated component faults in terms of flow capacity and isentropic efficiency indices. The developed system was implemented to diagnose up to three simultaneous faults in a two-shaft industrial gas turbine engine. Its robustness towards the measurement uncertainty was also evaluated based on Gaussian noise corrupted data. The test results show the derivable benefits of integrating two or more methods in engine diagnostics on the basis of offsetting the weakness of the one with the strength of another.
The performance of integrated solar collector / thermal energy storage with immersed heat exchanger was investigated experimentally at the Solar Research Site, University Technology PETRONAS, (4.4224oN, 100.9904oE), Malaysia. The experimental set up consisted of 150 liters storage tank capacity with immersed coil heat exchanger, single glazing 1.5m2 flat plate collector with 15o tilt to the horizontal. The circulation of the working fluid was by forced in closed loop with a mini solar pump. Aluminum cell foam was attached to the absorber as extended surface. The surface of the collector was coated with black ornament to improve its absorption. The system was tested under clear skys, for two cases; with and without water drawn-off for seven days per case studied. The performance evaluation data obtained for case1 at the mean maximum solar intensity was 503.98 W/m2 were: maximum daily water temperature 63°C, average daily water temperature 46°C, collector efficiency 63% and system efficiency 43%. Whilst for case 2, the mean maximum solar intensity was 473.11 W/m2, the maximum daily water temperature 54°C, average daily water temperature 39.36°C, collector efficiency 54% and system efficiency 39%. The system efficiency for case 2 showed that the heat exchanger performed slighlty better and the water drawn-off effect is minimal.
Thermal degradation of Poultry Processing Dewatered Sludge (PPDS) was studied using thermogravimetric analysis (TGA) method. The effect of particle size on PPDS samples and operational condition such as heating rates were investigated. The non-isothermal TGA was run under a constant flow of oxygen at a rate of 30 mL/min with temperature ranging from 30ºC to 800ºC. Four sample particle sizes ranging between 0.425 mm to 2 mm, and heating rate between 5 K/min to 20 K/min were used in this study. The TGA results showed that particle size does not have any significant effect on the thermogravimetry (TG) curves at the initial stage, but the TG curves started to separate explicitly at the second stage. Particle size may affect the reactivity of sample and combustion performance due to the heat transfer and temperature gradient. The TG and peak of derivative thermogravimetry (DTG) curves tend to alter at high temperature when heating rate is increased most likely due to the limitation of mass transfer and the delay of degradation process.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.