Classification machine learning models require high-quality labeled datasets for training. Among the most useful datasets for photovoltaic array fault detection and diagnosis are module or string current-voltage (IV) curves. Unfortunately, such datasets are rarely collected due to the cost of high fidelity monitoring, and the data that is available is generally not ideal, often consisting of unbalanced classes, noisy data due to environmental conditions, and few samples. In this paper, we propose an alternate approach that utilizes physics-based simulations of string-level IV curves as a fully synthetic training corpus that is independent of the test dataset. In our example, the training corpus consists of baseline (no fault), partial soiling, and cell crack system modes. The training corpus is used to train a 1D convolutional neural network (CNN) for failure classification. The approach is validated by comparing the model’s ability to classify failures detected on a real, measured IV... [more]

Optimizing the heating, ventilation, and air conditioning (HVAC) system to minimize district heating usage in large groups of managed buildings is of the utmost important, and it requires a machine learning (ML) model to predict the energy consumption. An industrial use case to reach large building groups is restricted to using normal operational data in the modeling, and this is one reason for the low utilization of ML in HVAC optimization. We present a methodology to select the best-fitting ML model on the basis of both Bayesian optimization of black-box models for defining hyperparameters and a fivefold cross-validation for the assessment of each model’s predictive performance. The methodology was tested in one case study using normal operational data, and the model was applied to analyze the energy savings in two different practical scenarios. The software for the modeling is published on GitHub. The results were promising in terms of predicting the energy consumption, and one of t... [more]

During the building design phase, a lot of attention is paid to the thermal properties of the external envelopes. New regulations are introduced to improve energy efficiency of a building and impose a reduction of the overall heat transfer coefficient; meanwhile, this efficiency is more influenced by the efficiency of the heating system and the type of fuels used. This article presents a complex analysis including the impact of: heat transfer coefficient of the envelope, efficiency of building service systems, the type of energy source, and the fuel. The analysis was based on the results of simulation tests obtained for an exemplary multi-family residential building located in Poland that is not equipped with a cooling system. The conducted calculations gave quantitative evaluation of the influence of particular parameters on building energy performance and showed that the decrease of heat transfer coefficient of building boundaries, in accordance to the Polish regulation for 2017 and... [more]

To accurately and reliably predict the occurrence of rockburst disasters, a rockburst intensity level prediction model based on FA-SSA-PNN is proposed. Crding to the internal and external factors of rockburst occurrence, six rockburst influencing factors (σθ, σt, σc, σc/σt, σθ/σc, Wet) were selected to build a rockburst intensity level prediction index system. Seventy-five sets of typical rockburst case data at home and abroad were collected, the original data were preprocessed based on factor analysis (FA), and the comprehensive rockburst prediction indexes, CPI1, CPI2, and CPI3, obtained after dimensionality reduction, were used as the input features of the SSA-PNN model. Sixty sets of rockburst case data were extracted as the training set, and the remaining 15 sets of rockburst case data were used as the test set. After the model training was completed, the model prediction results were analysed and evaluated. The research results show that the proposed rockburst intensity level pre... [more]

The imbalance market is very volatile and often exhibits extreme price spikes. This makes it very hard to model; however, if predicted correctly, one could make significant gains by participating on the right side of the market. In this manuscript, we conduct a very short-term probabilistic forecasting of imbalance prices, contributing to the scarce literature in this novel subject. The forecasting is performed 30 min before the delivery, so that the trader might still choose the trading place. The distribution of the imbalance prices is modelled and forecasted using methods well-known in the electricity price forecasting literature: lasso with bootstrap, gamlss, and probabilistic neural networks. The methods are compared with a naive benchmark in a meaningful rolling window study. The results provide evidence of the efficiency between the intraday and balancing markets as the sophisticated methods do not substantially overperform the intraday continuous price index. On the other hand,... [more]

The goal of reaching the peak of carbon in the construction industry is urgent. However, the research on the feasibility of realizing this goal and the implementation of relevant policies in China is relatively superficial. In view of the historical data of energy consumption and building CO2 emission from 1995 to 2019, this paper establishes a BP neural network model for predicting building CO2 emissions. Moreover, the influencing factors, such as population, GDP, and total construction output, are introduced as the parameters in the model. Through the scenario analysis method explores the practical path to accomplish the peak of building CO2 emissions. When using traditional prediction methods to predict building carbon emissions, the long prediction cycle will increase the possibility of significant errors. Therefore, this paper constructs the calculation model of building carbon emission and forecasts the future carbon emission value through the BP neural network to avoid the error... [more]

In this analysis, we considered a comparative study of micropolar Casson nanofluid flow on a vertical nonlinear Riga stretching sheet. Effects of thermal and velocity slip are considered under thermophoresis and Brownian motions. Select nonlinear PDEs transformed into nonlinear coupled ODEs using the set of suitable transformations. The nonlinear coupled ODEs are solved through a numerical technique along with the Runge−Kutta 4th-order scheme. The impacts of pertinent flow parameters on skin friction, Nusselt number, temperature, and velocity distributions are depicted through tabular and graphical form. Brownian motion and the magnitude of the Sherwood number have opposite performances; likewise, the Nusselt number and Brownian motion also have opposite performances. The Sherwood number and Nusselt number succeeded with higher values. The increment of the Casson fluid parameter declined with fluid velocity, which shows that thickness is reduced due to the increment of the Casson fluid... [more]

The P-S-N curve is a vital tool for dealing with fatigue life analysis, and its fitting under the condition of small samples is always concerned. In the view that the three parameters of the P-S-N curve equation can better describe the relationship between stress and fatigue life in the middle- and long-life range, this paper proposes an improved maximum likelihood method (IMLM). The backward statistical inference method (BSIM) recently proposed has been proven to be a good solution to the two-parameter P-S-N curve fitting problem under the condition of small samples. Because of the addition of an unknown parameter, the problem exists in the search for the optimal solution to the three-parameter P-S-N curve fitting. Considering that the maximum likelihood estimation is a commonly used P-S-N curve fitting method, and the rationality of its search for the optimal solution is better than that of BSIM, a new method combining BSIM and the maximum likelihood estimation is proposed. In additi... [more]

In recent years machine learning algorithms have been gaining momentum in resolving subsurface flow issues related to hydrocarbon flows, Carbon capture utilization and storage, hydrogen storage, geothermal flows, and enhanced oil recovery. This paper presents and attempts to solve subsurface flow problem using neural upscaling method. The neural upscaling method, described in the present work, is a machine learning approach to calculate effective properties in each grid block for subsurface flow modeling. This method is intended to be more accurate than traditional analytical upscaling methods (which are only accurate for layered or homogeneous media) and numerical upscaling methods (which are more accurate for heterogeneous media but involve higher computational cost and are dependent on boundary conditions). The neural upscaling method is based on learning from a large number of geological realizations, which allows it to account for uncertainty in geology. It is also computationally... [more]

At present, most salvage schemes are designed based on the calculation results of ship statics, which is still an empirical method. However, many projects are always affected by the wind and waves, and there is a significant difference between the force situation of ships with wind area and the calculation results of ship statistics. This paper analyzes the methods and tools of righting a capsized ship, establishes the righting force model of a capsized ship in wind and waves in accordance with floatation, stability, righting force, waves and wind, and then derives the method of longitudinal strength calculation. The floating state and stability of a capsized ship in four different sea conditions are calculated by GHS software, and three uprighting schemes are designed based on the number and position of the righting force. According to the size of the wind and waves, this paper simulates the uprighting process of the capsized hull in four cases. According to the results, it found that... [more]

To overcome the shortage of traditional temperature sensors, this paper adopts infrared thermal imaging technology for temperature measurement. To avoid the spatial information loss issue during the image data vectorization process, this paper adopted the spatial relationship between pixels in principal component analysis (PCA) model training, which is called spatial information-based PCA (SIPCA). Then, spatial information is also used in the fault localization method to enhance the fault location performance. Tested by an experimental tank system, the proposed method achieves better performance than the traditional PCA approach, and it can detect heat leakage faults on the surface of the equipment.

The procedure of FEM calculations was presented in the paper. The numerical calculations concerned a simulation of crack distribution and propagation in concrete beams reinforced longitudinally without shear reinforcement. The analysis of the obtained FEM results showed different modes of failure in the beams when shear span-to-depth ratio was a/d = 2.5 and a/d = 1.8. In the analyzed beams, the ratio of longitudinal reinforcement and the mechanical properties of the steel bars were also changing parameters. The FEM results have showed that the shear failure of reinforced concrete beams without transverse reinforcement significantly depends on the ratio and yield strength of longitudinal steel bars. Furthermore, the results of numerical calculation for the beams of a/d = 2.5 were also juxtaposed with experiments performed by the author on two longitudinally reinforced concrete beams.

The production of fused magnesia is a process in which raw materials are melted and recrystallized in the electric-fused magnesia furnace (EFMF). Temperature is the key factor that affects production, but it is difficult to be observed and monitored due to the high internal temperature. Thus, the working current is the standard for workers to judge whether the production process is normal. In order to master heat transfer characteristics in the furnace and accurately control the processes, a three-dimensional mathematical model of coupling the magnetic−fluid−thermal multifield has been established in a six-electrode EFMF. The model also considers the thermal decomposition of magnesium carbonate in the furnace. The phase change of materials is simulated by the solidification and melting model. The results show that the current density and Joule heat are concentrated in the region below the electrode. When the current size increases to 12,500 A, the molten pool begins to be connected. Th... [more]

Pipeline is one of the safest and most cost-effective means of transportation for hydrocarbons. However, hydrocarbon releases and the subsequent fires and explosions, are presented as persistent events. Quantitative Risk Assessment (QRA) enables one to address the risk and to prevent these events. In this regard, different approaches have been proposed for pipelines, but few studies are focused on oil transportation. This paper presents a methodology for performing QRA for onshore oil pipelines, which is based on the calculation of individual and societal risk indicators. This methodology is illustrated using an authentic case study of a segment of 17.53 km of the length of an onshore oil pipeline located in the southwest of Colombia, considering jet and pool fire scenarios. The results show that the Individual Risk Per Annum (IRPA) for operation (and maintenance) and administrative workers are 6.14 × 10−4 and 8.52 × 10−5 yr−1, respectively. The IRPA for people close to the pipeline is... [more]

Even in the context of smart mines, unsafe human acts are still an important cause of coal mine gas explosion accidents, but there are few models to analyze unsafe human acts in coal mine gas explosion accidents. This study tries to solve this problem through a risk assessment method of unsafe acts in coal mine gas explosion accidents based on Human Factor Analysis and Classification system (HFACS-GE) and Bayesian networks (BN). After verifying the reliability of HFACS-GE framework, a BN model of risk factors of unsafe acts was established with the Chi-square test and odds ratios analysis. After reasoning analysis, risk paths and key risk factors of unsafe acts were obtained, and preventive measures were granted. Based on the analysis of 100 coal mine gas explosion cases, the maximum probability of five kinds of unsafe acts of employees is 38%. Among the 22 risk factors, the mental state of employees has the greatest influence on the habitual violation of regulations, and the sensitivi... [more]

Once a chemical production accident occurs in a chemical plant, it often causes serious economic losses, casualties, and environmental damage. Statistics show that many major accidents in the production and storage of chemicals are mainly caused by human factors. This article considers the influence of the human factor and proposes a quantitative analysis model of a chemical plant based on a Bayesian network. The model takes into account the main human factors in seven aspects: organization, information, job design, human system interface, task environment, workplace design, and operator characteristics. The Bayesian network modeling method and simulation were used to predict the safety quantitative value and safety level of the chemical plant. Using this model, we can quickly calculate the safe quantitative ratio of each factor in the chemical plant. Through the safety quantitative value, safety level, and sensitivity analysis, the safety hazards of chemical companies can be discovere... [more]

Using the mixture of carbonized rice husk and shungite from the Kazakhstan Koksu deposit and the experimentally determined oil sorption capacity from contaminated soil with oil originating in the Karazhanbas oil field, a set of Artificial Neural Network (ANN) models were built for sorption predictions. The ANN architecture design, training, validation and testing methodology were performed, and the sorption capacity prediction was evaluated. The ANN models were successfully trained for capturing the sorption capacity dependence on time and on a carbonized rice husk and shungite mixture ratio for the 10% and 15% oil-contaminated soil. The best trained ANNs revealed a very good prediction capability for the testing data subset, demonstrated by the high coefficient of the determination values of R2 = 0.998 and R2 = 0.981 and the mean absolute percentage errors ranging from 1.60% to 3.16%. Furthermore, the ANN sorption models proved their interpolation ability and utility for predicting th... [more]

The topic of Industry 4.0 is more actual for various companies worldwide. Its impact is anywhere in company and government areas. Due to the individual parts of Industry 4.0, such as digitalization and robotization, we express changes impact on human resource management, where the most changes are defined. This contribution is focused on human resource management in the context of the application of Industry 4.0 in engineering companies operating in the Czech Republic and Germany. The main objective of the paper is to define potential connections between Industry 4.0 and its areas with the forfeiture of professions and preparedness for potential job changes. We employed a primary research approach with in-depth interviews and a questionnaire survey to reach a defined goal. The interviews were aimed at top managers and a questionnaire survey of ordinary employees and students/temporary workers. According to the gained results, there exist relevant statistical dependencies between Indust... [more]

The purpose of this article is to point out the need to use software simulation tools in industrial practice to optimize the production process and assess the economic effectiveness of investment, including risk. The goal of the research is to find an optimal investment variant to ensure an increase in the production volume of at least 50% and to achieve the maximum economic efficiency of the investment, even considering the risk. The article presents a comprehensive approach that enables the achievement of the set research goal. The selection of the optimal version of the investment is carried out in three steps. Firstly, the versions of the investment variants are assessed from the production point of view using the program Tecnomatix Plant Simulation. Subsequently, the versions of the investment variants are assessed from an economic point of view and from a risk point of view. Economic efficiency is assessed using the financial criteria net present value (NPV), profitability index... [more]

Because of its slow rate of disintegration, plastic debris has steadily risen over time and contributed to a host of environmental issues. Recycling the world’s increasing debris has taken on critical importance. Pyrolysis is one of the most practical techniques for recycling plastic because of its intrinsic qualities and environmental friendliness. For scale-up and reactor design, an understanding of the degradation process is essential. Using one model-free kinetic approach (Friedman) and two model-fitting kinetic methods (Arrhenius and Coats-Redfern), the thermal degradation of Polyethylene Terephthalate (PET) microplastics at heating rates of 10, 20, and 30 °C/min was examined in this work. Additionally, a powerful artificial neural network (ANN) model was created to forecast the heat deterioration of PET MPs. At various heating rates, the TG and DTG thermograms from the PET MPs degradation revealed the same patterns and trends. This showed that the heating rates do not impact the... [more]

Multi-attribute decision-making (MADM) refers to making preference decisions via assessing a finite number of pre-specified alternatives under multiple and usually conflicting attributes. Many problems in the field of additive manufacturing (AM) are essentially MADM problems or can be converted into MADM problems. Recently, a variety of MADM methods have been applied to solve MADM problems in AM. This generates a series of interesting questions: What is the general trend of this research topic from the perspective of published articles every year? Which journals published the most articles on the research topic? Which articles on the research topic are the most cited? What MADM methods have been applied to the field of AM? What are the main strengths and weaknesses of each MADM method used? Which MADM method is the most used one in this field? What specific problems in AM have been tackled via using MADM methods? What are the main issues in existing MADM methods for AM that need to be... [more]

Flood disasters are a natural occurrence around the world, resulting in numerous casualties. It is vital to develop an accurate flood forecasting and prediction model in order to curb damages and limit the number of victims. Water resource allocation, management, planning, flood warning and forecasting, and flood damage mitigation all benefit from rain forecasting. Prior to recent decades’ worth of research, this domain demonstrated to be promising prospects in time series prediction tasks. Therefore, the main aim of this study is to build a forecasting model based on the exponential smoothing-long-short term memory (ES-LSTM) structure and recurrent neural networks (RNNs) for predicting hourly precipitation seasons; and classify the precipitation using an artificial neural network (ANN) model and decision tree (DT) algorithm. We employ the dataset from the Australian commonwealth office of meteorology named Historical Daily Weather dataset to test the effectiveness of the proposed mode... [more]

The accelerated advancement of industrialization, urbanization, and technology produces an enormous amount of waste materials that are channelled into the environment, contaminating the soil, water and air. This exceedingly large volume of waste in the planet’s environment has made it challenging and difficult to handle; thus, it is urgent to facilitate alternative methods of waste disposal. Moreover, the consumption of concrete raw materials increases as a consequence of a sudden increase in concrete usage. In this study, printed circuit boards (PCB), cutting waste (e-waste) (0%, 5%, 10%, 15%, 20%) and recycled concrete aggregate (construction and demolition waste) (0%, 20%, 40%, 60%, 80%, 100%) replace the fine and coarse aggregate; this is utilised in the making of self-compacting concrete (SCC). To mitigate the impact of shrinkage and micro-cracks produced during loading, synthetic fibres (polypropylene fibres) (0%, 0.25%, 0.5%, 0.75%, 1%) are incorporated into the dense matrix of... [more]

This research paper presents novel condensed CNN architecture for the recognition of multispectral images, which has been developed to address the lack of attention paid to neural network designs for multispectral and hyperspectral photography in comparison to RGB photographs. The proposed architecture is able to recognize 10-band multispectral images and has fewer parameters than popular deep designs, such as ResNet and DenseNet, thanks to recent advancements in more efficient smaller CNNs. The proposed architecture is trained from scratch, and it outperforms a comparable network that was trained on RGB images in terms of accuracy and efficiency. The study also demonstrates the use of a Bayesian variant of CNN architecture to show that a network able to process multispectral information greatly reduces the uncertainty associated with class predictions in comparison to standard RGB images. The results of the study are demonstrated by comparing the accuracy of the network’s predictions... [more]

Friction stir welding is a material processing technique used to combine dissimilar and similar materials. Ultimate tensile strength (UTS) is one of the most common objectives of welding, especially friction stir welding (FSW). Typically, destructive testing is utilized to measure the UTS of a welded seam. Testing for the UTS of a weld seam typically involves cutting the specimen and utilizing a machine capable of testing for UTS. In this study, an ensemble deep learning model was developed to classify the UTS of the FSW weld seam. Consequently, the model could classify the quality of the weld seam in relation to its UTS using only an image of the weld seam. Five distinct convolutional neural networks (CNNs) were employed to form the heterogeneous ensemble deep learning model in the proposed model. In addition, image segmentation, image augmentation, and an efficient decision fusion approach were implemented in the proposed model. To test the model, 1664 pictures of weld seams were cre... [more]