In order to better release the heat generated by the electronic components, a novel heat dissipation system is proposed, which combines a microchannel heat pipe (MHP) with a high thermal conductivity and a radiative plate with a high emissivity at nighttime. First, a simple testing rig was made with an MHP and a radiative plate, where the radiative plate was made of acrylic resin, a curing agent, thinner, and aluminum plate, and had strong radiative cooling at nighttime. Second, the mathematical model was initially established and verified using experiments, where it was shown that the agreement between numerical and experimental data was well within experimental uncertainties. Comprehensive simulation investigations were conducted by varying wind speed, relative humidity, the cloudiness coefficient, dimension of the radiative plate, and tilted angle. The results show that: (1) the emissivity of the radiative plate was about 0.311 in the daytime and about 0.908 in the nighttime; (2) th... [more]

Details about a fault’s progression, including the remaining-useful-lifetime (RUL), are key features in monitoring, industrial operation and maintenance (O&M) planning. In order to avoid increases in O&M costs through subjective human involvement and over-conservative control strategies, this work presents models to estimate the RUL for wind turbine main bearing failures. The prediction of the RUL is estimated from a likelihood function based on concepts from prognostics and health management, and survival analysis. The RUL is estimated by training the model on run-to-failure wind turbines, extracting a parametrization of a probability density function. In order to ensure analytical moments, a Weibull distribution is assumed. Alongside the RUL model, the fault’s progression is abstracted as discrete states following the bearing stages from damage detection, through overtemperature warnings, to over overtemperature alarms and failure, and are integrated in a separate assessment model. A... [more]

In view of the fact that the statistical feature quantity of traditional partial discharge (PD) pattern recognition relies on expert experience and lacks certain generalization, this paper develops PD pattern recognition based on the convolutional neural network (cnn) and long-term short-term memory network (lstm). Firstly, we constructed the cnn-lstm PD pattern recognition model, which combines the advantages of cnn in mining local spatial information of the PD spectrum and the advantages of lstm in mining the PD spectrum time series feature information. Then, the transformer PD UHF (Ultra High Frequency) experiment was carried out. The performance of the constructed cnn-lstm pattern recognition network was tested by using different types of typical PD spectrums. Experimental results show that: (1) for the floating potential defects, the recognition rates of cnn-lstm and cnn are both 100%; (2) cnn-lstm has better recognition ability than cnn for metal protrusion defects, oil paper voi... [more]

Frequency response analysis (FRA) is a popular method for assessing a transformer’s mechanical condition. The paper proposes a new method for interpreting the frequency response measurement results. The currently used numerical indices only give one value, which may be misleading in the analysis, while the proposed frequency response quality index (FRQI) tool analyses three separate features in the whole frequency range. The applied numerical calculations technique allows for estimations of not only the values of the average quality indices, but also locally for given frequency ranges of the analysed spectrum. It allows for determination of the problems that can be found in the active part of a transformer. The presented results come from three transformers, representing cases of typical faults. Two of them are from industry, while one was used for deformational tests in laboratory conditions. The proposed FRQI method showed its usefulness in FRA test results analysis and may be introd... [more]

Artificial Neural Networks (ANNs) have proven to be a powerful tool in many fields of knowledge. At the same time, evolutionary algorithms show a very efficient technique in optimization tasks. Historically, ANNs are used in the training process of supervising networks by decreasing the error between the output and the target. However, we propose another approach in order to improve these two techniques together. The ANN is trained with the points obtained during an optimization process by a genetic algorithm and a flower pollination algorithm. The performance of this ANN is used as a stop criterion for the optimization process. This new configuration aims to reduce the number of iterations executed by the genetic optimizer when learning the cost function by an ANN. As a first step, this approach is tested with eight benchmark functions. As a second step, the authors apply it to an air jet impingement design process, optimizing the surface temperature and the fan efficiency. Finally, a... [more]

Building Energy and Comfort Management (BECM) systems have the potential to considerably reduce costs related to energy consumption and improve the efficiency of resource exploitation, by implementing strategies for resource management and control and policies for Demand-Side Management (DSM). One of the main requirements for such systems is to be able to adapt their management decisions to the users’ specific habits and preferences, even when they change over time. This feature is fundamental to prevent users’ disaffection and the gradual abandonment of the system. In this paper, a sensor-based system for analysis of user habits and early detection and prediction of user activities is presented. To improve the resulting accuracy, the system incorporates statistics related to other relevant external conditions that have been observed to be correlated (e.g., time of the day). Performance evaluation on a real use case proves that the proposed system enables early recognition of activitie... [more]

Apart from electric vehicles, most internal combustion (IC) engines are powered while burning petroleum-based fossil or alternative fuels after mixing with inducted air. Thereby the operations of mixing and combustion evolve in a turbulent flow environment created during the intake phase and then intensified by the piston motion and influenced by the shape of combustion chamber. In particular, the swirl and turbulence levels existing immediately before and during combustion affect the evolution of these processes and determine engine performance, noise and pollutant emissions. Both the turbulence characteristics and the bulk flow pattern in the cylinder are strongly affected by the inlet port and valve design. In the present paper, large eddy simulation (LES) is appraised and applied to studying the turbulent fluid flow around the intake valve of a single cylinder IC-engine as represented by the so called magnetic resonance velocimetry (MRV) flow bench configuration with a relatively l... [more]

This paper presents a detailed description of data predictive control (DPC) applied to a demand-side energy management system. Different from traditional model-based predictive control (MPC) algorithms, this approach introduces two model-free algorithms of artificial neural network (ANN) and random forest (RF) to make control strategy predictions on system operation, while avoiding the huge cost and effort associated with learning a grey/white box model of the physical system. The operating characteristics of electrical appliances, system energy consumption, and users’ comfort zones are also considered in the selected energy management system based on a real-time electricity pricing system. Case studies consisting of two scenarios (0% and 15% electricity price fluctuation) are delivered to demonstrate the effectiveness of the proposed approach. Simulation results demonstrate that the DPC controller based on ANN pays only 0.18% additional bill cost to maintain users’ comfort zones and s... [more]

In this research work, bio-inspired computational heuristic algorithms (BCHAs) integrated with active-set algorithms (ASA) were designed to study integrated economics load dispatch problems with valve point effects involving stochastic wind power. These BCHAs are developed through variants of genetic algorithms based on a different set of routines for reproduction operators in order to make exploration and exploitation in the entire search space for finding the global optima, while the ASA is used for rapid local refinements of the results. The designed schemes are estimated on different load dispatch systems consisting of a combination of thermal generating units and wind power plants with and without valve point loading effects. The accuracy, convergence, robustness and complexity of the proposed schemes has been examined through comparative studies based on a sufficiently large number of independent trails and their statistical observations in terms of different performance indices.

This paper develops a neural network (NN) vector controller for an interior mounted permanent magnet (IPM) motor by using a Texas Instrument TMS320F28335 digital signal processor (DSP). The NN controller is developed based on the complete state-space equation of an IPM motor and it is trained to achieve optimal control according to approximate dynamic programming (ADP). A DSP-based NN control system is built for an IPM motor drives system, and a high efficient DSP program is developed to implement the NN control algorithm while considering the limited memory and computing capability of the TMS320F28335 DSP. The DSP-based NN controller is able to manage IPM motor control in linear, over, and six-step modulation regions to improve the efficiency of IPM drives and to allow for the full utilization of DC bus voltage with space-vector pulse-width modulation (SVPWM). The experiment results show that the proposed NN controller is able to operate with a sampling period of 0.1ms, even with limi... [more]

The intermittency of solar energy resources has brought a big challenge for the optimization and planning of a future smart grid. To reduce the intermittency, an accurate prediction of photovoltaic (PV) power generation is very important. Therefore, this paper proposes a new forecasting method based on the recurrent neural network (RNN). At first, the entire solar power time series data is divided into inter-day data and intra-day data. Then, we apply RNN to discover the nonlinear features and invariant structures exhibited in the adjacent days and intra-day data. After that, a new point prediction model is proposed, only by taking the previous PV power data as input without weather information. The forecasting horizons are set from 15 to 90 min. The proposed forecasting method is tested by using real solar power in Flanders, Belgium. The classical persistence method (Persistence), back propagation neural network (BPNN), radial basis function (RBF) neural network and support vector mac... [more]

Machine learning has been applied successfully for faulty wafer detection tasks in semiconductor manufacturing. For the tasks, prediction models are built with prior data to predict the quality of future wafers as a function of their precedent process parameters and measurements. In real-world problems, it is common for the data to have a portion of input variables that are irrelevant to the prediction of an output variable. The inclusion of many irrelevant variables negatively affects the performance of prediction models. Typically, prediction models learned by different learning algorithms exhibit different sensitivities with regard to irrelevant variables. Algorithms with low sensitivities are preferred as a first trial for building prediction models, whereas a variable selection procedure is necessarily considered for highly sensitive algorithms. In this study, we investigate the effect of irrelevant variables on three well-known representative learning algorithms that can be appli... [more]

This work presents a computational method for the simulation of wind speeds and for the calculation of the statistical distributions of wind farm (WF) power curves, where the wake effects and terrain features are taken into consideration. A three-parameter (3-P) logistic function is used to represent the wind turbine (WT) power curve. Wake effects are simulated by means of the Jensen’s wake model. Wind shear effect is used to simulate the influence of the terrain on the WTs located at different altitudes. An analytical method is employed for deriving the probability density function (PDF) of the WF power output, based on the Weibull distribution for describing the cumulative wind speed behavior. The WF power curves for four types of terrain slopes are analyzed. Finally, simulations applying the Monte Carlo method on different sample sizes are provided to validate the proposed model. The simulation results indicate that this approximated formulation is a possible substitute for WF outpu... [more]

This paper proposes and describes a model for evaluating the hydro-mechanical efficiency of external gear machines. The model is built considering and evaluating the main friction losses in the machines, including the viscous friction losses at the tooth tip gap, at the bearing blocks-gears gaps, at the journal bearings, and the meshing loss. To calculate the shear stress at each gap interface, the geometry of the gap has to be known. For this reason, the actual position of the gears inside the pump casing and consequent radial pressure distribution are numerically calculated to evaluate the gap height at the tooth tips. Moreover, the variation of the tilt and reference height of the lateral gaps between the gears and the pump bushings are considered. The shear stresses within the lateral gaps are estimated, for different lateral heights and tilt values. At the journal bearings gaps, the half Sommerfeld solution has been applied. The meshing loss has been calculated according to the su... [more]

Electricity load forecasting plays an essential role in improving the management efficiency of power generation systems. A large number of load forecasting models aiming at promoting the forecasting effectiveness have been put forward in the past. However, many traditional models have no consideration for the significance of data preprocessing and the constraints of individual forecasting models. Moreover, most of them only focus on the forecasting accuracy but ignore the forecasting stability, resulting in nonoptimal performance in practical applications. This paper presents a novel hybrid model that combines an advanced data preprocessing strategy, a deep neural network, and an avant-garde multi-objective optimization algorithm, overcoming the defects of traditional models and thus improving the forecasting performance effectively. In order to evaluate the validity of the proposed hybrid model, the electricity load data sampled in 30-min intervals from Queensland, Australia are used... [more]

In this paper, a fuzzy neural network controller for regulating demand-side thermostatically controlled loads (TCLs) is designed with the aim of stabilizing the frequency of the smart grid. Specifically, the balance between power supply and demand is achieved by tracking the automatic generation control (AGC) signal in an electric power system. The particle swarm optimization (PSO) and error back propagation (BP) algorithms are used to optimize the control parameters and consequently reduce the tracking errors. The fuzzy neural network can be applied to solve load control problems in power systems, since its self-learning and associative storage functions can deal with the highly nonlinear relationship between input and output. Simulation results show the advantage of the fuzzy neural network control scheme in terms of frequency regulation error and consumer comfort.

Accurate short-term electric load forecasting is significant for the smart grid. It can reduce electric power consumption and ensure the balance between power supply and demand. In this paper, the Stacked Denoising Auto-Encoder (SDAE) is adopted for short-term load forecasting using four factors: historical loads, somatosensory temperature, relative humidity, and daily average loads. The daily average loads act as the baseline in final forecasting tasks. Firstly, the Denoising Auto-Encoder (DAE) is pre-trained. In the symmetric DAE, there are three layers: the input layer, the hidden layer, and the output layer where the hidden layer is the symmetric axis. The input layer and the hidden layer construct the encoding part while the hidden layer and the output layer construct the decoding part. After that, all DAEs are stacked together for fine-tuning. In addition, in the encoding part of each DAE, the weight values and hidden layer values are combined with the original input layer values... [more]

Highly nonlinear and nonconvex power flow analysis plays a key role in the monitoring, control, and operation of power systems. There is no analytic solution to power flow problems, and therefore, finding a numerical solution is oftentimes an aim of modern computation in power system analysis. An iterative Newton-Raphson method is widely in use. While most times this method finds a solution in a reasonable time, it often involves numerical robustness issues, such as a limited convergence region and an ill-conditioned system. Sometimes, the truncation error may not be small enough to ignore, which can make the iterative process significantly expansive. We propose a new unified framework, based on the Kronecker product, that does not involve any truncation, and which is bilinear to make it possible to incorporate statistical analysis. The proposed method is tested for power flow, state estimation, probabilistic power flow, and optimal power flow studies on various IEEE model systems.

Solar energy predictive models designed to emulate the long-term (e.g., monthly) global solar radiation (GSR) trained with satellite-derived predictors can be employed as decision tenets in the exploration, installation and management of solar energy production systems in remote and inaccessible solar-powered sites. In spite of a plethora of models designed for GSR prediction, deep learning, representing a state-of-the-art intelligent tool, remains an attractive approach for renewable energy exploration, monitoring and forecasting. In this paper, algorithms based on deep belief networks and deep neural networks are designed to predict long-term GSR. Deep learning algorithms trained with publicly-accessible Moderate Resolution Imaging Spectroradiometer (MODIS) satellite data are tested in Australia’s solar cities to predict the monthly GSR: single hidden layer and ensemble models. The monthly-scale MODIS-derived predictors (2003−2018) are adopted, with 15 diverse feature selection appro... [more]

This paper presents a comparative study on the application of different neural network structures to early detection of electrical faults in induction motor drives. The diagnosis inference of the stator inter-turn short-circuits and broken rotor bars is based on the analysis of an axial flux of the induction motor. In order to automate the fault detection process, three different structures of neural networks were used: multi-layer perceptron, self-organizing Kohonen network and recursive Hopfield network. Tests were carried out for various levels of stator and rotor failures. In order to assess the sensitivity of the applied neural detectors, the tests were carried out for variable load conditions and for different values of the supply voltage frequency. Experimental results of the elaborated neural detectors are presented and discussed.

The viscosity data of two heavy oil samples X and Y, with asphaltene contents 24.8% w/w and 18.5% w/w, respectively, were correlated with temperature and pressure using empirical models and the artificial neural network (ANN) approach. The viscosities of the samples were measured over a range of temperatures between 70 °C and 150 °C; and from atmospheric pressure to 7 MPa. It was found that the viscosity of sample X, at 85 °C and atmospheric pressure (0.1 MPa), was 1894 cP and that it increased to 2787 cP at 7 MPa. At 150 °C, the viscosity increased from 28 cP (at 0.1 MPa) to 33 cP at 7 MPa. For sample Y, the viscosity at 70 °C and 0.1 MPa increased from 2260 cP to 3022 cP at 7 MPa. At 120 °C, the viscosity increased from 65 cP (0.1 MPa) to 71 cP at 7 MPa. Notably, using the three-parameter empirical models (Mehrotra and Svrcek, 1986 and 1987), the correlation constants obtained in this study are very close to those that were previously obtained for the Canadian heavy oil samples. More... [more]

This paper presents the use of a fuzzy-based statistical feature extraction from the air gap disturbances for diagnosing broken rotor bars in large induction motors fed by line or an inverter. The method is based on the analysis of the magnetic flux density variation in a Hall Effect Sensor, installed between two stator slots of the motor. The proposed method combines a fuzzy inference system and a support vector machine technique for time-domain assessment of the magnetic flux density, in order to detect a single fault or multiple broken bars in the rotor. In this approach, it is possible to detect not only the existence of failures, but also its severity. Moreover, it is not necessary to estimate the slip of the motor, usually required by other methods and the damaged rotor detection was also evaluated for oscillating load conditions. Thus, the present approach can overcome some drawbacks of the traditional MCSA method, particularly in operational cases where false positive and false... [more]

This article studies the combustion of refined sunflower, virgin sunflower and virgin rapeseed oils in a low-pressure auxiliary air fluid pulverization burner in order to establish the optimal operating conditions. The influence of varying the type of vegetable oil, fuel flow rate and secondary airflow rate in the combustion process was analyzed. These three factors are independent in the combustion process, which means having to carry out numerous assays, combining the various factors with one another. Given the amount of variables to be optimized and the existence of three factors, a statistical approach is adopted to help interpret the results obtained and to evaluate how each factor influences the combustion results. Optimal combustion is determined based on three criteria, minimum pollutant emissions (CO, NOx and CxHy), maximum combustion performance, and minimum excess air. The result of this study showed that airflow was the principal factor affecting emissions, whereas for comb... [more]

The aim of this study was to develop a mathematical regression model for predicting end-use energy consumption in the residential sector. To this end, housing characteristics were collected through a field survey and in-depth interviews with residents of 71 households (15 apartment complexes) in Seoul, South Korea, and annual data on end-use energy consumption were collected from measurement systems installed within each apartment unit. Based on the data collected, correlativity between the field-survey data and end-use energy consumption was analyzed, and effective independent variables from the field-survey data were selected. Regression models were developed and validated for estimating six end uses of energy consumption: heating, cooling, domestic hot water (DHW), lighting, electric appliances, and cooking. Regression analysis for ventilation was not applied, and instead a calculation formula was derived, because the energy-consumption proportion was too low. The adj-R2 of the esti... [more]

Wind power, one of renewable energy resources, is a fluctuating source of energy that prevents its further participation in the power market. To improve the stability of the wind power injected into the power grid, a short-term wind speed predicting model is proposed in this work, named VMD-P-(ARIMA, BP)-PSOLSSVM. In this model, variational mode decomposition (VMD) is combined with phase space reconstruction (P) as data processing method to determine intrinsic mode function (IMF) and its input−output matrix in the prediction model. Then, the linear model autoregressive integrated moving average model (ARIMA) and typical nonlinear model back propagation neural network (BP) are adopted to forecast each IMF separately and get the prediction of short-term wind speed by adding up the IMFs. In the final stage, particle swarm optimization least squares support vector machine (PSOLSSVM) uses the prediction results of the two separate models from previous step for the secondary prediction. For... [more]