The ability to precisely forecast power generation for large wind farms is very important, since such generation is highly unstable and creates problems for Distribution and Transmission System Operators to properly prepare the power system for operation. Forecasts for the next 24 h play an important role in this process. They are also used in energy market transactions. Even a small improvement in the quality of these forecasts translates into more security of the system and savings for the economy. Using two wind farms for statistical analyses and forecasting considerably increases credibility of newly created effective prediction methods and formulated conclusions. In the first part of our study, we have analysed the available data to identify potentially useful explanatory variables for forecasting models with additional development of new input data based on the basic data set. We demonstrate that it is better to use Numerical Weather Prediction (NWP) point forecasts for hourly la... [more]

This paper aims to study the applicability of machine-learning algorithms, specifically neural networks, for forecasting the effectiveness of Improved recovery methods. Radial jet drilling is the case operation in this study. Understanding changes in reservoir flow properties and their effect on liquid flow rate is essential to evaluate the radial jet drilling effectiveness. Therefore, liquid flow rate after radial jet drilling is the target variable, while geological and process parameters have been taken as features. The effect of various network parameters on learning quality has been assessed. As a result, conclusions on the applicability of neural networks to evaluate the radial jet drilling potential of wells in various geological conditions of carbonate reservoirs have been made.

The petrophysical properties of Miocene mudstones and gas bearing-heteroliths were the main scope of the work performed in one of the multihorizon gas fields in the Polish Carpathian Foredeep. Ten boreholes were the subject of petrophysical interpretation. The analyzed interval covered seven gas-bearing Miocene horizons belonging to Sarmatian and Badenian deposits. The water saturation in shaly sand and mudstone intervals was calculated using the Montaron connectivity theory approach and was compared with Simandoux water saturation. Additionally, the Kohonen neural network was used for qualitative interpretation of four PSUs (petrophysically similar units), which represent the deposits of comparable petrophysical parameters. This approach allowed us to identify the sediment group with the highest probability of hydrocarbon saturation. Then, the spatial distribution of PSUs and reservoir parameters was carried out in Petrel. The resolution of the model was selected to reflect the variab... [more]

For the construction of transport infrastructure (including pipeline bridges for oil and gas transportation) in the conditions of the Far North, it is necessary to improve modern regulatory and technological base for using the fiber-reinforcing polymers. It is necessary to conduct searching research to determine the conditions and shapes of application of the fiber-reinforced polymer (FRP) in the load-bearing structures of bridges and pipelines through barriers. One such searching research is the study of the use of a suspension hybrid bridge with a superstructure of FRP. For this purpose, the calculations of finite-element models of pedestrian suspension bridges were performed and their aerodynamic stability was investigated on the section models in a wind tunnel. The novelty of the study consists in the proposed additions to the structure of the bridge, and the permissible geometric of the cross-sections of the superstructure were established for ensuring aerodynamic stability. Final... [more]

Failure mode, effects and criticality analysis (FMECA) is a well-known reliability analysis tool for recognizing, evaluating and prioritizing the known or potential failures in system, design, and process. In conventional FMECA, the failure modes are evaluated by using three risk factors, severity (S), occurrence (O) and detectability (D), and their risk priorities are determined by multiplying the crisp values of risk factors to obtain their risk priority numbers (RPNs). However, the conventional RPN has been considerably criticized due to its various shortcomings. Although significant efforts have been made to enhance the performance of traditional FMECA, some drawbacks still exist and need to be addressed in the real application. In this paper, a new FMECA model for risk analysis is proposed by using an integrated approach, which introduces Z-number, Rough number, the Decision-making trial and evaluation laboratory (DEMATEL) method and the VIsekriterijumska optimizacija i KOmpromisn... [more]

Multistage hydraulic fracturing is one of the most prevalent approaches for shale reservoir development. Due to the complexity of constructing reservoir environments for experiments, numerical simulation is a vital method to study flow behavior under reservoir conditions. In this paper, we propose a numerical model that considers a multistage fractured horizontal well with a hilly-terrain trajectory in a shale reservoir with the presence of natural fractures. The model was constructed based on the MATLAB Reservoir Simulation Toolbox and used the Embedded Discrete Fractured Model (EDFM) to describe the interrelationship between the matrix, fractures, and wellbore. The model was then applied to an actual condensate gas well producing from a shale reservoir, and the effects of reservoir parameters on the simulation data were studied based on this well case. The simulation results were highly consistent with the actual production data, which validates the accuracy of this model and proves... [more]

There is a lot of research on the neural models used for short-term load forecasting (STLF), which is crucial for improving the sustainable operation of energy systems with increasing technical, economic, and environmental requirements. Neural networks are computationally powerful; however, the lack of clear, readable and trustworthy justification of STLF obtained using such models is a serious problem that needs to be tackled. The article proposes an approach based on the local interpretable model-agnostic explanations (LIME) method that supports reliable premises justifying and explaining the forecasts. The use of the proposed approach makes it possible to improve the reliability of heuristic and experimental neural modeling processes, the results of which are difficult to interpret. Explaining the forecasting may facilitate the justification of the selection and the improvement of neural models for STLF, while contributing to a better understanding of the obtained results and broade... [more]

A comprehensive uncertainty analysis in the event of a severe accident in a two-loop pressurized water reactor is conducted using an uncertainty package integrated in the ASYST code. The plant model is based on the nuclear power plant (NPP) Krško, a Westinghouse-type power plant. The station blackout scenario with a small break loss of coolant accident is analyzed, and all processes of the in-vessel phase are covered. A best estimate plus uncertainty (BEPU) methodology with probabilistic propagation of input uncertainty is used. The uncertain parameters are selected based on their impact on the safety criteria, the operation of the NPP safety systems and to describe uncertainties in the initial and boundary conditions. The number of required calculations is determined by the Wilks formula from the desired percentile and confidence level, and the values of the uncertain parameters are randomly sampled according to appropriate distribution functions. Results showing the thermal hydraulic... [more]

A novel Artificial Neural Network (ANN) Based Optimal Feedforward Torque Control (OFTC) strategy is proposed which, after proper ANN design, training and validation, allows to analytically compute the optimal reference currents (minimizing copper and iron losses) for Interior Permanent Magnet Synchronous Machines (IPMSMs) with highly operating point dependent nonlinear electric and magnetic characteristics. In contrast to conventional OFTC, which either utilizes large look-up tables (LUTs; with more than three input parameters) or computes the optimal reference currents numerically or analytically but iteratively (due to the necessary online linearization), the proposed ANN-based OFTC strategy does not require iterations nor a decision tree to find the optimal operation strategy such as e.g., Maximum Torque per Losses (MTPL), Maximum Current (MC) or Field Weakening (FW). Therefore, it is (much) faster and easier to implement while (i) still machine nonlinearities and nonidealities such... [more]

Energy efficiency is one of the most important current challenges, and its impact at a global level is considerable. To solve current challenges, it is critical that consumers are able to control their energy consumption. In this paper, we propose using a time series of window-based entropy to detect anomalies in the electricity consumption of a household when the pattern of consumption behavior exhibits a change. We compare the accuracy of this approach with two machine learning approaches, random forest and neural networks, and with a statistical approach, the ARIMA model. We study whether these approaches detect the same anomalous periods. These different techniques have been evaluated using a real dataset obtained from different households with different consumption profiles from the Madrid Region. The entropy-based algorithm detects more days classified as anomalous according to context information compared to the other algorithms. This approach has the advantages that it does not... [more]

The cooling of PV models is an important process that enhances the generated electricity from these models, especially in hot areas. In this work, a new, active cooling algorithm is proposed based on active fan cooling and an artificial neural network, which is named the artificial dynamic neural network Fan cooling algorithm (DNNFC). The proposed system attaches five fans to the back of a PV model. Subsequently, only two fans work at any given time to circulate the air under the PV model in order to cool it down. Five different patterns of working fans have been experimented with in this work. To select the optimal pattern for any given time, a back propagation neural network model was trained. The algorithm is a dynamic algorithm since it re-trains the model with new recorded surface temperatures over time. In this way, the model automatically adapts to any weather and environmental conditions. The model was trained with an indoor dataset and tested with an outdoor dataset. An accura... [more]

Simulating the phase behavior of a reservoir fluid requires the determination of many parameters, such as gas−oil ratio and formation volume factor. The determination of such parameters requires knowledge of the critical properties and compressibility factor (Z factor). There are many techniques to determine the compressibility factor, such as experimental pressure, volume, and temperature (PVT) tests, empirical correlations, and artificial intelligence approaches. In this work, two different models based on statistical regression and multi-layer-feedforward neural network (MLFN) were developed to predict the Z factor of natural gas by utilizing the experimental data of 1079 samples with a wide range of pseudo-reduced pressure (0.12−25.8) and pseudo reduced temperature (1.3−2.4). The statistical regression model was proposed and trained in R using the “rjags” package and Markov chain Monte Carlo simulation, while the multi-layer-feedforward neural network model was postulated and train... [more]

The accurate evaluation and fair comparison of wind farms power generation performance is of great significance to the technical transformation and operation and maintenance management of wind farms. However, problems exist in the evaluation indicator systems such as confusion, coupling and broadness, and the influence of wind energy resource differences not being able to be effectively eliminated, which makes it difficult to achieve the fair comparison of power generation performance among different wind farms. Thus, the evaluation indicator system and comprehensive evaluation method of wind farm power generation performance, including the influence of wind energy resource differences, are proposed in this paper to address the problems above, to which some new concepts such as resource conditions, ideal performance, reachable performance, actual performance, and performance loss are introduced in the proposed indicator system; the combination of statistical and comparative indicators... [more]

Sand production has caused many serious problems in weakly consolidated reservoirs. Therefore, it is very urgent to find out the mechanism for this process. This paper employs a coupled lattice Boltzmann method and discrete element method (LBM-DEM) to study the sand production process of the porous media. Simulation of the sand production process is conducted and the force chain network evolvement is analyzed. Absolute and relative permeability changes before and after the sand production process are studied. The effect of injection flow rate, cementation strength, and confining pressure are investigated. During the simulation, strong force chain rupture and force chain reorganization can be identified. The mean shortest-path distance of the porous media reduces gradually after an initial sharp decrease while the mean degree and clustering coefficient increase in the same way. Furthermore, the degree of preferential wettability for water increases after the sand production process. Mor... [more]

In this article, a cascade fuzzy neural network (FNN) control approach is proposed for position control of quadrotor unmanned aerial vehicle (UAV) system with high coupling and underactuated. For the attitude loop with limited range, the FNN controller parameters were trained offline using flight data, whereas for the position loop, the method based on FNN compensation proportional-integral-derivative (PID) was adopted to tune the system online adaptively. This method not only combined the advantages of fuzzy systems and neural networks but also reduced the amount of calculation for cascade neural network control. Simulations of fixed set point flight and spiral and square trajectory tracking flight were then conducted. The comparison of the results showed that our method had advantages in terms of minimizing overshoot and settling time. Finally, flight experiments were carried out on a DJI Tello quadrotor UAV. The experimental results showed that the proposed controller had good perfo... [more]

In this study, using response surface methodology and central composite design, regression models were developed relating 12 input factors to the supply air outlet humidity ratio and temperature of 4-fluid internally-cooled liquid desiccant dehumidifiers. The selected factors are supply air inlet temperature, supply air inlet humidity ratio, exhaust air inlet temperature, exhaust air inlet humidity ratio, liquid desiccant inlet temperature, liquid desiccant concentration, liquid desiccant flow rate, supply air mass flow rate, the ratio of exhaust to supply air mass flow rate, the thickness of the channel, the channel length, and the channel width of the dehumidifier. The designed experiments were performed using a numerical two-dimensional heat and mass transfer model of the liquid desiccant dehumidifier. The numerical model predicted the measured values of the supply air outlet humidity ratio within 6.7%. The regression model’s predictions of the supply air outlet humidity ratio match... [more]

Short-term building energy consumption forecasting is vital for energy conservation and emission reduction. However, it is challenging to achieve accurate short-term forecasting of building energy consumption due to its nonlinear and non-stationary characteristics. This paper proposes a novel hybrid short-term building energy consumption forecasting model, SSA-CNNBiGRU, which is the integration of SSA (singular spectrum analysis), a CNN (convolutional neural network), and a BiGRU (bidirectional gated recurrent unit) neural network. In the proposed SSA-CNNBiGRU model, SSA is used to decompose trend and periodic components from the original building energy consumption data to reconstruct subsequences, the CNN is used to extract deep characteristic information from each subsequence, and the BiGRU network is used to model the dynamic features extracted by the CNN for time series forecasting. The subsequence forecasting results are superimposed to obtain the predicted building energy consum... [more]

Wax deposition and gelation of waxy crude oil in production pipelines are detrimental to crude oil transportation from offshore fields. A waxy crude oil forms intra-gel voids in pipelines under cooling mode, particularly below the pour point temperature. Consequently, intrusion of non-reacting gas into production pipelines has become a promising method to lessen the restart pressure required and clear the clogged gel. A trial-and-error method is currently employed to determine the required restart pressure and restart time in response to injected gas volume. However, this method is not always accurate and requires expert knowledge. In this study, predictive models based on an Artificial Neural Network (ANN) and multilinear regression are developed to predict restart pressure and time as a function of seabed temperature and non-reacting gas injected volume. The models’ outcomes are compared against experimental results available from the literature. The empirical models predicted the re... [more]

Empirical-statistical downscaling (ESD) can be a computationally advantageous alternative to dynamical downscaling in representing a high-resolution regional climate. Two distinct strategies of ESD are employed here to reconstruct near-surface winds in a region of rugged terrain. ESD is used to reconstruct the innermost grid of a multiply nested mesoscale model framework for regional climate downscaling. An analog ensemble (AnEn) and a convolutional neural network (CNN) are compared in their ability to represent near-surface winds in the innermost grid in lieu of dynamical downscaling. Downscaling for a 30 year climatology of 10 m April winds is performed for southern MO, USA. Five years of training suffices for producing low mean absolute error and bias for both ESD techniques. However, root-mean-squared error is not significantly reduced by either scheme. In the case of the AnEn, this is due to a minority of cases not producing a satisfactory representation of high-resolution wind, a... [more]

In 2020, the World Bioenergy Association published an interesting report about the global development of using biomass and bioenergy along with statistics and trends [...]

This paper is an initial exploratory study that provides recommendations for the sustainable development of future automated and connected transport (ACT) systems in Romania. To achieve this, our paper investigates the different factors that influence mobility behaviour related to ACT systems through two different themes. The first part analyses (i) the strategic framework that is relevant to future ACT deployment and (ii) the spatial development patterns of large cities in Romania that might influence future mobility behaviour based on ACT systems. We presumed, and the study confirmed, that there is currently a poor focus on ACT systems in strategic documents and that the current spatial patterns show some premises for unsustainable mobility behaviour based on ACT systems. The second part describes the results of our analysis on the WISE-ACT survey deployed in Romania. We explored how informed Romanian citizens are about AVs; whether they are ready to use them; and what perceptions, c... [more]

With the development of intelligent manufacturing, automated data acquisition techniques are widely used. The autocorrelations between data that are collected from production processes have become more common. Residual charts are a good approach to monitoring the process with data autocorrelation. An improved hidden Markov model (IHMM) for the prediction of autocorrelated observations and a new expectation maximization (EM) algorithm is proposed. A residual chart based on IHMM is employed to monitor the autocorrelated process. The numerical experiment shows that, in general, IHMMs outperform both conventional hidden Markov models (HMMs) and autoregressive (AR) models in quality shift diagnosis, decreasing the cost of missing alarms. Moreover, the times taken by IHMMs for training and prediction are found to be much less than those of HMMs.

There is currently great general interest in reducing the use of fossil-based materials. Fossil-based tarps are still widely used as cover for wood chip storage piles, causing additional waste or requiring further waste treatment in the supply chain. This study aimed to investigate the performance of an innovative bio-based wood chip pile cover compared to conventional treatments (plastic-covered and uncovered) in eastern Finnish conditions. The experiment evaluated the drying process during the storage of stemwood chips during 5.9 months of storage. It included the developments of temperature, moisture content, heating value, energy content, basic density, particle size distribution, and the dry matter losses of a total of six piles. As a result, the forest stemwood chips dried by 11%, with dry-matter losses of 4.3%, when covered with the bio-pile cover. Using the plastic covering, the forest stemwood chips dried by 22%, with dry matter losses of 2.9%. At the end of the experiment, th... [more]

A small prototype of a 5-level single-phase full H-bridge inverter for ocean current applications is presented. The inverter was designed applying level-shift control in pulse-width modulation (LS-PWM), and experimental tests were conducted using a variety of modulation subschemes, including in-phase disposition (IPD), alternate-phase opposition−disposition (APOD), and phase opposition−disposition (POD). The test results were examined for harmonic content and voltage total harmonic distortion (THDV). The results suggest that the inverter presents a viable solution with significant potential for the development of a larger three-phase inverter model that can be used to connect ocean current power sources to the electrical grid.

For medium and high-powered applications, modular multilevel converters have become the most promising converter application. In this paper, a sliding mode controller based on an RBF neural network is proposed for a modular multilevel converter. The RBF neural network is designed to approximate the uncertainty mathematical model of a modular multilevel converter. The main innovation of the proposed method is that it does not require any model parameters and control parameters during the whole control process. This means that parameter changes caused by the external environment will not influence the controller performances. Finally, by comparing with a conventional PI controller, the simulation proves the feasibility and effectiveness of the proposed control method. In addition, the experimental results show that the grid-side current can become stable immediately while the active power is stabilized after 20 ms when the set value is changed.