Precise and efficient calculations are necessary to accurately assess the effects of thermal protection system (TPS) uncertainties on aerospacecrafts. This paper presents a probabilistic design methodology for TPSs based on physics-informed neural networks (PINNs) with parametric uncertainty. A typical thermal coating system is used to investigate the impact of uncertainty on the thermal properties of insulation materials and to evaluate the resulting temperature distribution. A sensitivity analysis is conducted to identify the influence of the parameters on the thermal response. The results show that PINNs can produce quick and accurate predictions of the temperature of insulation materials. The accuracy of the PINN model is comparable to that of a response surface surrogate model. Still, the computational time required by the PINN model is only a fraction of the latter. Considering both computational efficiency and accuracy, the PINN model can be used as a high-precision surrogate mo... [more]

Nowadays, wind power generation has become vital thanks to its advantages in cost, ecological friendliness, enormousness, and sustainability. However, the erratic and intermittent nature of this energy poses significant operational and management difficulties for power systems. Currently, the methods of wind power forecasting (WPF) are various and numerous. An accurate forecasting method of WPF can help system dispatchers plan unit commitment and reduce the risk of the unreliability of electricity supply. In order to improve the accuracy of short-term prediction for wind power and address the multi-step ahead forecasting, this research presents a Stacked Temporal Convolutional Network (S-TCN) model. By using dilated causal convolutions and residual connections, the suggested solution addresses the issue of long-term dependencies and performance degradation of deep convolutional models in sequence prediction. The simulation outcomes demonstrate that the S-TCN model’s training procedure... [more]

Predicting multiphase flow in complex fractured reservoirs is essential for developing unconventional resources, such as shale gas and oil. Traditional numerical methods are computationally expensive, and deep learning methods, as an alternative approach, have become an increasingly popular topic. Fourier neural operator (FNO) networks have been shown to be a hundred times faster than convolutional neural networks (CNNs) in predicting multiphase flow in conventional reservoirs. However, there are few relevant studies on applying FNO to predict multiphase flow in reservoirs with complex fractures. In the present study, FNO-net and U-net (CNN-based) were successfully applied to predict pressure and gas saturation fields for the 2D heterogeneous fractured reservoirs. The tested results show that FNO can accurately depict the influence of fine fractures, while the CNN-based method has relatively poor performance in the treatment of fracture systems, both in terms of accuracy and computatio... [more]

Injecting power plant flue gas into a goaf stores CO2 in the flue gas and effectively prevents the spontaneous combustion of the coal remaining in the goaf. Here, we investigated the adsorption behavior of three types of coal at normal temperature and pressure using a self-developed adsorption experimental device. We used a specific surface area and porosity analyzer to study the effects of pore structure, mineral content, and moisture content on CO2 adsorption in coal. Based on the experimental data, we designed a multifactor CO2 adsorption prediction model based on a backpropagation (BP) neural network. The results indicated that the pore size of most micropores in coal was in the range of 0.5−0.7 and 0.8−0.9 nm. The specific surface area and pore volume were positively correlated with the CO2-saturated adsorption capacity, whereas the mean pore diameter, mineral content, and moisture content were inversely associated with the CO2-saturated adsorption amount. The accuracy of the mult... [more]

This article presents the results of an analysis of heat enhancement intensification using twisted tapes in linear absorbers for low-concentration parabolic trough collectors, a technology frequently considered as a supplementary energy source for industrial heat production. This contribution proposes a segmented application of different twisted tapes to intensify heat absorption. A 33.7 mm tubular absorber placed in the collector focal point with an aperture of 1.8 m was selected. The temperature range of the heat transfer fluid was chosen at 60−250 °C. The impact of inserts with twisted ratios of 1, 2 and 4 on system operation was analysed using the Ansys Fluent and mathematical model. The models used were validated based on experimental results from a parabolic trough collector with solar simulator test bench. The results indicated that for the range of mass flow between 0.15−0.3 kg/s, the most optimal is applying twisted ratio 1, except for the highest-temperature section. In this... [more]

To improve the viability of nuclear power plants, there is a need to reduce their operational costs. Operational costs account for a significant portion of a plant’s yearly budget, due to their scheduled-based maintenance approach. In order to reduce these costs, proactive methods are required that estimate and forecast the state of a machine in real time to optimize maintenance schedules. In this research, we use Bayesian networks to develop a framework that can forecast the remaining useful life of a centrifugal pump. To do so, we integrate survival analysis with Bayesian statistics to forecast the health of the pump conditional to its current state. We complete our research by successfully using the Bayesian network on a case study. This solution provides an informed probabilistic viewpoint of the pumping system for the purpose of predictive maintenance.

Nonintrusive load monitoring (NILM) is a process that disaggregates individual energy consumption based on the total energy consumption. In this study, an energy disaggregation model was developed and verified using an algorithm based on a recurrent neural network (RNN). It also aimed to evaluate the utility of the occupant location information, which is nonelectrical information. This study developed energy disaggregation models with RNN-based long short-term memory (LSTM) and gated recurrent unit (GRU). The performance of the suggested models was evaluated with a conventional method that uses the factorial hidden Markov model. As a result, when developing the GRU disaggregation model based on an RNN, the energy disaggregation performance improved in accuracy, F1-score, mean absolute error (MAE), and root mean square error (RMSE). In addition, when the location information of the occupants was used, the suggested model showed improved performance and good agreement with the real power... [more]

South Africa’s energy network is under severe pressure due to low supply and overwhelming demand. With an increase in renewable energy providers, specifically wind energy, knowing how the supply can satisfy the electricity demand may relieve apprehensions. This research aims to provide insight into the wind energy supply of South Africa and question how well this supply meets the demand of South Africa. The methodology used in this work highlights the importance of access to public datasets to dispel misconceptions in the energy industry. Additionally, the work supports network planning and the arguments for increasing wind energy penetration on the South African grid. Wind profiles and the typical energy production of South African wind farms are compared to electricity demand. The geographical spacing of the operational wind farms is considered. It is observed that wind energy supply assists in the peak electricity hourly demand as well as seasonal peaks. Furthermore, South Africa’s... [more]

In light of energy and climate targets, free cooling unlocks a major resource-saving potential compared to refrigeration. To fill the knowledge gap in quantifying this saving potential, we aim to specify the physical and technical limits of cooling tower applications and provide comprehensive data on electricity and water consumption. For this purpose, we distinguish six types of package-type cooling towers: dry, closed wet, open wet, and three types of hybrid systems; defining one generalized system for all types enables comparability. Subsequently, we collect data from 6730 system models of 27 manufacturers, using technical information from data sheets and additional material. The analysis reveals, for example, specific ranges of electricity demand from 0.01 to 0.06 kW/kW and highlights influencing factors, including type and operating point. Refrigeration systems would consume approximately ten times more electricity per cooling capacity. Furthermore, the evaluation demonstrates the... [more]

The eddy current brake (ECB) is an electromechanical energy conversion device that can be used as a load emulator to load a motor according to the intended load scenario. However, conducting an analysis in the time domain is difficult due to its complex behavior involving mechanical, electrical, and magnetic phenomena. The challenges with the time domain analysis of the ECB require new modeling approaches that provide reliability, robustness, and controllability over a wide speed interval. If the ECB can be modeled with high accuracy, it can be controlled like a load emulator that can simulate nonlinear industrial loads. This paper describes a neuromodeling approach taken to develop an ECB. The nonlinear characteristic of the brake system was modeled with a high performance by using an artificial neural network (ANN), which is a potent nonlinear system identification tool. Several characteristics of a designed and optimized brake system undergoing various excitation currents in whole s... [more]

In order to accurately calculate the geometric characteristics of the twin-screw compressor and obtain the optimal profile parameters, a calculation method for the geometric characteristics of twin-screw compressors was proposed to simplify the profile parameter design in this paper. In this method, the database of geometric characteristics is established by back-propagation (BP) neural network, and the genetic algorithm is used to find the optimal profile design parameters. The effects of training methods and hidden layers on the calculation accuracy of neural network are discussed. The effects of profile parameters, including inner radius of the male rotor, protection angle, radius of the elliptic arc, outer radius of the female rotor on the comprehensive evaluation value composed of length of the contact line, blow hole area and area utilization rate, are analyzed. The results show that the time consumed for the database established by BP neural network is 92.8% shorter than that of... [more]

The need for and interest in very-short-term load forecasting (VSTLF) is increasing and important for goals such as energy pricing markets. There is greater challenge in predicting load consumption for residential-load-type data, which is highly variable in nature and does not form visible patterns present in aggregated nodal-type load data. Previous works have used methods such as LSTM and CNN for VSTLF; however, the use of DNN has yet to be investigated. Furthermore, DNNs have been effectively used in STLF but have not been applied to very-short-term time frames. In this work, a deep network architecture is proposed and applied to very-short-term forecasting of residential load patterns that exhibit high variability and abrupt changes. The method extends previous work by including delayed load demand as an input, as well as working for 1 min data resolution. The deep model is trained on the load demand data of selected days—one, two, and a week—prior to the targeted day. Test results... [more]

The solid oxide fuel cell (SOFC) system is complicated because the characteristics of gas, heat, and electricity are intricately coupled. During the operation of the system, problems such as frequent failures and a decrease in the stack’s performance have caused the SOFC system to work less well and greatly shortened the SOFC’s practical life. As such, it is essential to accurately forecast its remaining useful life (RUL) to make the system last longer and cut down on economic losses. In this study, both model-based and data-driven prediction methods are used to make predictions about the RUL of SOFC. First, the linear degradation model of the SOFC system is established by introducing degradation resistance as the index of health status. Using the Kalman filtering (KF) method, the health status of SOFC is evaluated online. The results of the health state estimation indicated that the KF algorithm is accurate enough to provide a good basis for the model-based RUL prediction. Then, a lon... [more]

The main objective of this paper is to propose two innovative monitoring methods for electrical disturbances in low-voltage networks. The two approaches present a focus on the classification of voltage signals in the frequency domain using machine learning techniques. The first technique proposed here uses the Fourier transform (FT) of the voltage waveform and classifies the corresponding complex coefficients through a multilayered neural network with multivalued neurons (MLMVN). In this case, the classifier structure has three layers and a small number of neurons in the hidden layer. This allows complex-valued inputs to be processed without the need for pre-coding, thus reducing computational cost and keeping training time short. The second technique involves the use of the short-time Fourier transform (STFT) and a convolutional neural network (CNN) with 2D convolutions in each layer for feature extraction and dimensionality reduction. The voltage waveform perturbations taken into con... [more]

In the toxicological testing of new small-molecule compounds, it is desirable to establish in silico test methods to predict toxicity instead of relying on animal testing. Since quantitative structure−activity relationships (QSARs) can predict the biological activity from structural information for small-molecule compounds, QSAR applications for in silico toxicity prediction have been studied for a long time. However, in recent years, the remarkable predictive performance of deep learning has attracted attention for practical applications. In this review, we summarize the application of deep learning to QSAR for constructing prediction models, including a discussion of parameter optimization for deep learning.

This study is part of the re-valorisation of the dairy waste industry through the use of membrane ultrafiltration (UF), in order to recover whey proteins and remove as much water as possible from the permeate. This study aimed to predict and control the permeate flux decline in cross-flow whey UF through a step procedure, and to compare different Artificial Neural Networks (ANNs), followed by a genetic algorithm (GA), as the optimization strategy. Models were developed in Matlab® Neural Network Toolbox. ANNs of one or two hidden layers were trained and simulated. A trial-and-error procedure identified the best network based on its performance values. The networks were trained through a selected set of experimental data obtained for lab-scale hollow-fibre membrane modules used to re-value scotta, the final waste of the dairy industry. The operating conditions considered as the input of the ANN were: operating time (top), sampling time (tsample), cross-flow velocity (CFV) and transmembra... [more]

With the arrival of Industry 4.0, interoperability has become a major subject for companies worldwide. It is a crucial asset that enables new technologies and possibilities (Industrial Internet of Things, predictive maintenance or traceability solutions). With the increasing importance of data in business use cases, companies are faced with a choice between two interoperability approaches to deal with the challenge of reconciling different domains: standardization and mediation. This paper presents an analysis of each approach and proposes a decision-making methodology based on the Analytic Hierarchy Process (AHP) that aims to help companies in choosing the most suitable solution to resolve interoperability challenges.

The detection of coal and gangue is an essential part of intelligent sorting. A lightweight coal and gangue detection algorithm based on You Only Look Once version 5s (Yolov5s) is proposed for the current coal and gangue target detection algorithm with the low accuracy of small target detection, high model complexity, and sizeable computational memory consumption. Firstly, we build a new convolutional block based on the Funnel Rectified Linear Unit (FReLU) activation function and apply it to the original Yolov5s network so that the model adaptively captures local contextual information of the image. Secondly, the neck of the original network is redesigned to improve the detection accuracy of small samples by adding a small target detection head to achieve multi-scale feature fusion. Next, some of the standard convolution modules in the original network are replaced with Depthwise Convolution (DWC) and Ghost Shuffle Convolution (GSC) modules to build a lightweight feature extraction net... [more]

Restrictions on competitive fishing activities due to the depletion of living marine resources and the monitoring of fish resources for the purpose of marine ecosystem research are supported by statistics on the protection of fish resources and ecosystem research, which are gathered through existing observer monitoring systems. However, in the case of deep-sea fishing vessels and special-purpose fishing vessels, some matters, such as collusive transactions with shipping companies and shipowners and threats toward the observer, are problematic, as observers are always active on board. Therefore, through the present study we would like to discuss the methodology and directions for research on the independent role of the observer and the methods for improving the reliability of data through systems that automate the monitoring of the acquisition of fish resources, which is expected to be a continuing problem. After an analysis of research trends for each issue related to the electronic mo... [more]

The maturity of tobacco leaves directly affects their curing quality. However, no effective method has been developed for determining their maturity during production. Assessment of tobacco maturity for flue curing has long depended on production experience, leading to considerable variation. In this study, hyperspectral imaging combined with a novel algorithm was used to develop a classification model that could accurately determine the maturity of tobacco leaves. First, tobacco leaves of different maturity levels (unripe, under-ripe, ripe, and over-ripe) were collected. ENVI software was used to remove the hyperspectral imaging (HSI) background, and 11 groups of filtered images were obtained using Python 3.7. Finally, a full-band-based partial least-squares discriminant analysis (PLS-DA) classification model was established to identify the maturity of the tobacco leaves. In the calibration set, the model accuracy of the original spectrum was 88.57%, and the accuracy of the de-trendin... [more]

In this paper, a multi-point flux mixed-finite-element decoupled method was considered for the compressible miscible displacement problem. For this compressible problem, a fully discrete backward Euler scheme was proposed, in which the velocity and pressure equations were decoupled by a multi-point flux MFE method using BDM1 elements combined with a trapezoidal quadrature rule. The concentration equation was handled by a standard FE method. The error analysis for velocity, pressure, and concentration were rigorously derived. Numerical experiments to verify the convergence rates and simulate the miscible displacement problem of a water−oil system were presented.

With the continuous enrichment of big data technology application scenarios, the clustering analysis of a data stream has become a research hotspot. However, the existing data stream clustering algorithms usually have some defects, such as inability to cluster arbitrary shapes, difficulty determining some important parameters, and “static” clustering. In this study, a novel algorithm MDDSDB-GC is innovated. It selected MDDB-GC as the original algorithm that cannot deal with a data stream. In MDDSDB-GC, the calculation methods of contribution, grid density, and migration factor are effectively improved, and other parts are adjusted accordingly. The experiments show that MDDSDB-GC retains the advantage of MDDB-GC and obtains the ability to cluster an analysis for a data stream. At the same time, it effectively overcomes the above conventional defects, and its overall performance is better.

Heat release rate (HRR) is the principal fire characteristic of materials. There are three known methods for the measurement of HRR (based on oxygen consumption, mass loss rate, and combustion products temperature rise). The method based on oxygen consumption is considered to be the reference. However, this method is expensive and for a large part of laboratories and universities unavailable. The simplest method is based on combustion products’ temperature rise. However, this method has a fundamental problem with the temperature dependence of the heat capacity of combustion products and the thermal inertia of the measurement system. This problem has been solved by training neural networks to predict molar heat capacity and the amount of substance (chemical amount) flow rate of combustion products in the cone calorimeter exhaust duct. Data were obtained for six different wood species: birch (Betula verrucosa Ehrh.), oak (Quercus robur L.) spruce (Picea abies (L.) H. Karst.), locust (Rob... [more]

This paper introduces and studies a new discrete distribution with one parameter that expands the Poisson model, discrete weighted Poisson Lerch transcendental (DWPLT) distribution. Its mathematical and statistical structure showed that some of the basic characteristics and features of the DWPLT model include probability mass function, the hazard rate function for single and double components, moments with auxiliary statistical measures (expectation, variance, index of dispersion, skewness, kurtosis, negative moments), conditional expectation, Lorenz function, and order statistics, which were derived as closed forms. DWPLT distribution can be used as a flexible statistical approach to analyze and discuss real asymmetric leptokurtic data. Moreover, it could be applied to a hyperdispersive data model. Two different estimation methods were derived, i.e., maximal likelihood and the moments technique for the DWPLT parameter, and some advanced numerical methods were utilized for the estimati... [more]

One of China’s ambitious hydrogen strategies over the past few years has been to promote fuel cells. A number of hydrogen refueling stations (HRSs) are currently being built in China to refuel hydrogen-powered automobiles. In this context, it is crucial to assess the dangers of hydrogen leaking in HRSs. The present work simulated the liquid hydrogen (LH2) leakage with the goal of undertaking an extensive consequence evaluation of the LH2 leakage on an LH2 refueling station (LHRS). Furthermore, the utilization of an air curtain to prevent the diffusion of the LH2 leakage is proposed and the defending effect is studied accordingly. The results reveal that the Richardson number effectively explained the variation of plume morphology. Furthermore, different facilities have great influence on the gas cloud diffusion trajectory with the consideration of different leakage directions. The air curtain shows satisfactory prevention of the diffusion of the hydrogen plume. Studies show that with t... [more]