Search

The paper reports the results of a comparative assessment concerned with the effectiveness of identifying the basic forms of partial discharges (PD) measured by the acoustic emission technique (AE), carried out by application of selected machine learning methods. As part of the re-search, the identification involved AE signals registered in laboratory conditions for eight basic classes of PDs that occur in paper-oil insulation systems of high-voltage power equipment. On the basis of acoustic signals emitted by PDs and by application of the frequency descriptor that took the form of a signal power density spectrum (PSD), the assessment involved the possibility of identifying individual types of PD by the analyzed classification algorithms. As part of the research, the results obtained with the use of five independent classification mechanisms were analyzed, namely: k-Nearest Neighbors method (kNN), Naive Bayes Classification, Support Vector Machine (SVM), Random Forests and Probabilistic Neural Network (PNN). The best results were achieved using the SVM classification tuned with polynomial core, which obtained 100% accuracy. Similar results were achieved with the kNN classifier. Random Forests and Naïve Bayes obtained high accuracy over 97%. Throughout the study, identification algorithms with the highest effectiveness in identifying specific forms of PD were established. [ABSTRACT FROM AUTHOR]

The prognosis of wind turbine failures in real operating conditions is a significant gap in the academic literature and is essential for achieving viable performance parameters for the operation and maintenance of these machines, especially those located offshore. This paper presents a framework for estimating the remaining useful life (RUL) of the main bearing using regression models fed operational data (temperature, wind speed, and the active power of the network) collected by a supervisory control and data acquisition (SCADA) system. The framework begins with a careful data filtering process, followed by creating a degradation profile based on identifying the behavior of temperature time series. It also uses a cross-validation strategy to mitigate data scarcity and increase model robustness by combining subsets of data from different available turbines. Support vector, gradient boosting, random forest, and extra trees models were created, which, in the tests, showed an average of 20 days in estimating the remaining useful life and presented mean absolute error (MAE) values of 0.047 and mean squared errors (MSE) of 0.012. As its main contributions, this work proposes (i) a robust and effective regression modeling method for estimating RUL based on temperature and (ii) an approach for dealing with a lack of data, a common problem in wind turbine operation. The results demonstrate the potential of using these forecasts to support the decision making of the teams responsible for operating and maintaining wind farms. [ABSTRACT FROM AUTHOR]

This study aims to forecast New York and Los Angeles gasoline spot prices on a daily frequency. The dataset includes gasoline prices and a big set of 128 other relevant variables spanning the period from 17 February 2004 to 26 March 2022. These variables were fed to three tree-based machine learning algorithms: decision trees, random forest, and XGBoost. Furthermore, a variable importance measure (VIM) technique was applied to identify and rank the most important explanatory variables. The optimal model, a trained random forest, achieves a mean absolute percent error (MAPE) in the out-of-sample of 3.23% for the New York and 3.78% for the Los Angeles gasoline spot prices. The first lag, AR (1), of gasoline is the most important variable in both markets; the top five variables are all energy-related. This paper can strengthen the understanding of price determinants and has the potential to inform strategic decisions and policy directions within the energy sector, making it a valuable asset for both industry practitioners and policymakers. [ABSTRACT FROM AUTHOR]

Complex oil and gas two-phase flow exists within an aero-engines bearing cavity scavenge pipe, prone to lubricated self-ignition and coking. Lubricant system designers must be able to accurately identify and understand the flow state of the scavenge pipe. The prediction accuracy of previous models is insufficient to meet the more demanding needs. This paper establishes a visualized flow pattern identification test system for the scavenge pipe, with a test temperature of up to 370 k, using a high-speed camera to photograph four flow patterns, decomposing the pressure signals obtained from high-frequency dynamic pressure sensors using the ensemble empirical mode decomposition (EEMD) method, and then performing Hilbert transform, using the Hilbert spectrum to quantify the changes of amplitude and frequency with time, and establishing the energy and flow pattern correspondence analysis. Then the energy percentage of IMFs is used as the input of feature values, and the random forest algorithm machine learning is used for predictive classification. The experimental results show that the flow pattern recognition rate established in this paper can reach 98%, which can identify the two-phase flow pattern in the scavenge pipe more objectively and accurately. [ABSTRACT FROM AUTHOR]

A fuel cell is an energy conversion device that utilizes hydrogen energy through an electrochemical reaction. Despite their many advantages, such as high efficiency, zero emissions, and fast startup, fuel cells have not yet been fully commercialized due to deficiencies in service life, cost, and performance. Efficient evaluation methods for performance and service life are critical for the design and optimization of fuel cells. The purpose of this paper was to review the application of common machine learning algorithms in fuel cells. The significance and status of machine learning applications in fuel cells are briefly described. Common machine learning algorithms, such as artificial neural networks, support vector machines, and random forests are introduced, and their applications in fuel cell performance prediction and optimization are comprehensively elaborated. The review revealed that machine learning algorithms can be successfully used for performance prediction, service life prediction, and fault diagnosis in fuel cells, with good accuracy in solving nonlinear problems. Combined with optimization algorithms, machine learning models can further carry out the optimization of design and operating parameters to achieve multiple optimization goals with good accuracy and efficiency. It is expected that this review paper could help the reader comprehend the state of the art of machine learning applications in fuel fuels and shed light on further development directions in fuel cell research. [ABSTRACT FROM AUTHOR]

Due to the transition toward the Internet of Everything (IOE), the prediction of energy consumed by household appliances has become a progressively more difficult topic to model. Even with advancements in data analytics and machine learning, several challenges remain to be addressed. Therefore, providing highly accurate and optimized models has become the primary research goal of many studies. This paper analyzes appliance energy consumption through a variety of machine learning-based strategies. Utilizing data recorded from a single-family home, input variables comprised internal temperatures and humidities, lighting consumption, and outdoor conditions including wind speed, visibility, and pressure. Various models were trained and evaluated: (a) multiple linear regression, (b) support vector regression, (c) random forest, (d) gradient boosting, (e) xgboost, and (f) the extra trees regressor. Both feature engineering and hyperparameter tuning methodologies were applied to not only extend existing features but also create new ones that provided improved model performance across all metrics: root mean square error (RMSE), coefficient of determination (R2), mean absolute error (MAE), and mean absolute percentage error (MAPE). The best model (extra trees) was able to explain 99% of the variance in the training set and 66% in the testing set when using all the predictors. The results were compared with those obtained using a similar methodology. The objective of performing these actions was to show a unique perspective in simulating building performance through data-driven models, identifying how to maximize predictive performance through the use of machine learning-based strategies, as well as understanding the potential benefits of utilizing different models. [ABSTRACT FROM AUTHOR]

Kicks can lead to well control risks during petroleum drilling, and even more serious kicks may lead to serious casualties, which is the biggest threat factor affecting the safety in the process of petroleum drilling. Therefore, how to detect kicks early and efficiently has become a focus practical problem. Traditional machine learning models require a large amount of labeled data, such kicked sample, and it is difficult to label data, which requires a lot of labor and time. To address the above issues, the deep forest is extended to a transfer learning model to improve the generalization ability. In this paper, a transfer learning model is built to detect kicks early. The source domain model adopts the deep forest model. Deep forest is an ensemble learning model with a hierarchical structure similar to deep learning. Each layer contains a variety of random forests. It is an integration of the model in depth and breadth. In the case of a small sample size (20–60 min), kick can be identified 10 min in advance. The deep forest model is established as the source domaining model, and a cascade forest is added at the last layer according to the transfer learning algorithm to form the classification model of this paper. The experimental results show that the kick prediction accuracy of the model is 80.13% by a confusion matrix. In the target domain, the proposed model performs better than other ensemble learning algorithms, and the accuracy is 5% lower than other SOTA transfer learning algorithms. [ABSTRACT FROM AUTHOR]

Solar power forecasting is of high interest in managing any power system based on solar energy. In the case of photovoltaic (PV) systems, and building integrated PV (BIPV) in particular, it may help to better operate the power grid and to manage the power load and storage. Power forecasting directly based on PV time series has some advantages over solar irradiance forecasting first and PV power modeling afterwards. In this paper, the power forecasting for BIPV systems in a vertical façade is studied using machine learning algorithms based on decision trees. The forecasting scheme employs the skforecast library from the Python environment, which facilitates the implementation of different schemes for both deterministic and probabilistic forecasting applications. Firstly, deterministic forecasting of hourly BIPV power was performed with XGBoost and Random Forest algorithms for different cases, showing an improvement in forecasting accuracy when some exogenous variables were used. Secondly, probabilistic forecasting was performed with XGBoost combined with the Bootstrap method. The results of this paper show the capabilities of Random Forest and gradient boosting algorithms, such as XGBoost, to work as regressors in time series forecasting of BIPV power. Mean absolute error in the deterministic forecast, using the most influencing exogenous variables, were around 40% and close below 30% for the south and east array, respectively. [ABSTRACT FROM AUTHOR]

It is indisputable that power systems are being transformed around the world to increase the use of RES and reduce the use of fossil fuels in overall electricity production. This year, the EU Parliament adopted the Fit for 55 package, which should significantly reduce the use of fossil fuels in the energy balance of EU countries while increasing the use of RES. At the end of 2022, the total number of prosumer installations in Poland amounted to about one million two hundred thousand. Such a high saturation of prosumer micro-installations in the power system causes many threats resulting from their operation. These threats result, among others, from the fact that photovoltaics are classified as unstable sources and the expected production of electricity from such installations is primarily associated with highly variable weather conditions and is only dependent on people to a minor extent. Currently, there is a rapid development of topics related to forecasting the volume of energy production from unstable sources such as wind and photovoltaic power plants. This issue is being actively developed by research units around the world. Scientists use a whole range of tools and models related to forecasting techniques, from physical models to artificial intelligence. According to our findings, the use of machine learning models has the greatest chance of obtaining positive prognostic effects for small, widely distributed prosumer installations. The present paper presents the research results of two energy balance prediction algorithms based on machine learning models. For forecasting, we proposed two regression models, i.e., regularized LASSO regression and random forests. The work analyzed scenarios taking into account both endogenous and exogenous variables as well as direct multi-step forecasting and recursive multi-step forecasting. The training was carried out on real data obtained from a prosumer micro-installation. Finally, it was found that the best forecasting results are obtained with the use of a random forest model trained using a recursive multi-step method and an exogenous scenario. [ABSTRACT FROM AUTHOR]

At present, the condition assessment of transformer winding based on frequency response analysis (FRA) measurements demands skilled personnel. Despite many research efforts in the last decade, there is still no definitive methodology for the interpretation and condition assessment of transformer winding based on FRA results, and this is a major challenge for the industrial application of the FRA method. To overcome this challenge, this paper proposes a transformer condition assessment (TCA) algorithm, which is based on numerical indices, and a supervised machine learning technique to develop a method for the automatic interpretation of FRA results. For this purpose, random forest (RF) classifiers were developed for the first time to identify the condition of transformer winding and classify different faults in the transformer windings. Mainly, six common states of the transformer were classified in this research, i.e., healthy transformer, healthy transformer with saturated core, mechanically damaged winding, short-circuited winding, open-circuited winding, and repeatability issues. In this research, the data from 139 FRA measurements performed in more than 80 power transformers were used. The database belongs to the transformers having different ratings, sizes, designs, and manufacturers. The results reveal that the proposed TCA algorithm can effectively assess the transformer winding condition with up to 93% accuracy without much human intervention. [ABSTRACT FROM AUTHOR]

Pipeline corrosion is one of the leading causes of failures in the transmission of gas and hazardous liquids in the oil and gas industry. In-line inspection is a non-destructive inspection for detecting corrosion defects in pipelines. Defects are measured in terms of their width, length and depth. Consecutive in-line inspection data are used to determine the pipeline's corrosion growth rate and its remnant life, which set the operational and maintenance activities of the pipeline. The traditional approach of manually processing in-line inspection data has various weaknesses, including being time consuming due to huge data volume and complexity, prone to error, subject to biased judgement by experts and challenging for matching of in-line inspection datasets. This paper aimed to contribute to the adoption of machine learning approaches in classifying pipeline defects as per Pipeline Operator Forum requirements and matching in-line inspection data for determining the corrosion growth rate and remnant life of pipelines. Machine learning techniques, namely, decision tree, random forest, support vector machines and logistic regression, were applied in the classification of pipeline defects using Phyton programming. The performance of each technique in terms of the accuracy of results was compared. The results showed that the decision tree classifier model was the most accurate (99.9%) compared with the other classifiers. [ABSTRACT FROM AUTHOR]

In this paper, a methodology based on data-driven models is developed to predict the NOx emissions of an internal combustion engine using, as inputs, a set of ECU channels representing the main engine actuations. Several regressors derived from the machine learning and deep learning algorithms are tested and compared in terms of prediction accuracy and computational efficiency to assess the most suitable for the aim of this work. Six Real Driving Emission (RDE) cycles performed at the roll bench were used for the model training, while another two RDE cycles and a steady-state map of NOx emissions were used to test the model under dynamic and stationary conditions, respectively. The models considered include Polynomial Regressor (PR), Support Vector Regressor (SVR), Random Forest Regressor (RF), Light Gradient Boosting Regressor (LightGBR) and Feed-Forward Neural Network (ANN). Ensemble methods such as Random Forest and LightGBR proved to have similar performances in terms of prediction accuracy, with LightGBR requiring a much lower training time. Afterwards, LightGBR predictions are compared with experimental NOx measurements in steady-state conditions and during two RDE cycles. Coefficient of determination (R2), normalized root mean squared error (nRMSE) and mean average percentage error (MAPE) are the main metrics used. The NOx emissions predicted by the LightGBR show good coherence with the experimental test set, both with the steady-state NOx map (R2 = 0.91 and MAPE = 6.42%) and with the RDE cycles (R2 = 0.95 and nRMSE = 0.04). [ABSTRACT FROM AUTHOR]

Accurate solar radiation forecasting is essential to operate power systems safely under high shares of photovoltaic generation. This paper compares the performance of several machine learning algorithms for solar radiation forecasting using endogenous and exogenous inputs and proposes an ensemble feature selection method to choose not only the most related input parameters but also their past observations values. The machine learning algorithms used are: Support Vector Regression (SVR), Extreme Gradient Boosting (XGBT), Categorical Boosting (CatBoost) and Voting-Average (VOA), which integrates SVR, XGBT and CatBoost. The proposed ensemble feature selection is based on Pearson coefficient, random forest, mutual information and relief. Prediction accuracy is evaluated based on several metrics using a real database from Salvador, Brazil. Different prediction time-horizons are considered: 1 h, 2 h and 3 h ahead. Numerical results demonstrate that the proposed ensemble feature selection approach improves forecasting accuracy and that VOA performs better than the other algorithms in all prediction time horizons. [ABSTRACT FROM AUTHOR]

In predicting energy consumption, classic econometric and statistical models are used to forecast energy consumption. These models may have limitations in an increasingly fast-changing energy market, which requires big data analysis of energy consumption patterns and relevant variables using complex mathematical tools. In current literature, there are minimal comparison studies reviewing machine learning algorithms to predict energy consumption in Korea. To bridge this gap, this paper compared three different machine learning algorithms, namely the Random Forest (RF) model, XGBoost (XGB) model, and Long Short-Term Memory (LSTM) model. These algorithms were applied in Period 1 (prior to the onset of the COVID-19 pandemic) and Period 2 (after the onset of the COVID-19 pandemic). Period 1 was characterized by an upward trend in energy consumption, while Period 2 showed a reduction in energy consumption. LSTM performed best in its prediction power specifically in Period 1, and RF outperformed the other models in Period 2. Findings, therefore, suggested the applicability of machine learning to forecast energy consumption and also demonstrated that traditional econometric approaches may outperform machine learning when there is less unknown irregularity in the time series, but machine learning can work better with unexpected irregular time series data. [ABSTRACT FROM AUTHOR]

The vibration signals for offshore wind-turbine high-speed bearings are often contaminated with noises due to complex environmental and structural loads, which increase the difficulty of fault detection and diagnosis. In view of this problem, we propose a fault-diagnosis strategy with good noise immunity in this paper by integrating the two-dimensional convolutional neural network (2DCNN) with random forest (RF), which is supposed to utilize both CNN's automatic feature-extraction capability and the robust discrimination performance of RF classifiers. More specifically, the raw 1D time-domain bearing-vibration signals are transformed into 2D grayscale images at first, which are then fed to the 2DCNN-RF model for fault diagnosis. At the same time, three procedures, including exponential linear unit (ELU), batch normalization (BN), and dropout, are introduced in the model to improve feature-extraction performance and the noise immune capability. In addition, when the 2DCNN feature extractor is trained, the obtained feature vectors are passed to the RF classifier to improve the classification accuracy and generalization ability of the model. The experimental results show that the diagnostic accuracy of the 2DCNN-RF model could achieve 99.548% on the CWRU high-speed bearing dataset, which outperforms the standard CNN and other standard machine-learning and deep-learning algorithms. Furthermore, when the vibration signals are polluted with noises, the 2DCNN-RF model, without retraining the model or any denoising process, still achieves satisfying performance with higher accuracy than the other methods. [ABSTRACT FROM AUTHOR]

This paper details the selection of machine learning models for predicting the effectiveness of a heat pipe system in a concentric tube exchanger. Heat exchanger experiments with methanol as the working fluid were conducted. The value of the angle varied from 0° to 90°, values of temperature varied from 50 °C to 70 °C, and the flow rate varied from 40 to 120 litres per min. Multiple experiments were conducted at different combinations of the input parameters and the effectiveness was measured for each trial. Multiple machine learning algorithms were taken into consideration for prediction. Experimental data were divided into subsets and the performance of the machine learning model was analysed for each of the subsets. For the overall analysis, which included all the three parameters, the random forest algorithm returned the best results with a mean average error of 1.176 and root-mean-square-error of 1.542. [ABSTRACT FROM AUTHOR]

The indicated mean effective pressure (IMEP) is a key parameter for measuring the power output of an internal combustion engine (ICE). This indicator can be used to locate the high efficiency regions of engines. Therefore, it makes sense to predict the IMEP based on the machine learning (ML) approaches. However, different ML models are applicable to different scenarios, so it is important to choose the right model for prediction. The objective of this paper was to compare three ML models' (ANN, SVR, RF) predictive performance in forecasting IMEP indicator with the input parameters spark timing (ST), speed and load. A validated one-dimensional (1D) computational fluid dynamics (CFD) model was employed to provide 756 sets of data for the training, validation, and testing of the model. The results indicated that the random forest (RF) model had the worst prediction performance, and support vector regression (SVR) had a slightly better prediction performance than the artificial neural network (ANN), at least for the investigations in this study. Overall, the ANN and SVR models showed good predictive performance for IMEP, as the coefficient of determination (R2) was close to unity, and the root mean squared error (RMSE) was close to zero. Whereas the overall prediction results of the RF model are acceptable, the RF model does not learn well for some internal engine laws. [ABSTRACT FROM AUTHOR]

Microgrids should be continuously monitored in order to maintain suitable voltages over time. Microgrids are mainly monitored remotely, and their measurement data transmitted through lossy communication networks are vulnerable to cyberattacks and packet loss. The current study leverages the idea of data fusion to address this problem. Hence, this paper investigates the effects of estimation fusion using various machine-learning (ML) regression methods as data fusion methods by aggregating the distributed Kalman filter (KF)-based state estimates of a linear smart microgrid in order to achieve more accurate and reliable state estimates. This unreliability in measurements is because they are received through a lossy communication network that incorporates packet loss and cyberattacks. In addition to ML regression methods, multi-layer perceptron (MLP) and dependent ordered weighted averaging (DOWA) operators are also employed for further comparisons. The results of simulation on the IEEE 4-bus model validate the effectiveness of the employed ML regression methods through the RMSE, MAE and R-squared indices under the condition of missing and manipulated measurements. In general, the results obtained by the Random Forest regression method were more accurate than those of other methods. [ABSTRACT FROM AUTHOR]

This paper presents the results of a research project which investigated permeability prediction for the Precipice Sandstone of the Surat Basin. Machine learning techniques were used for permeability estimation based on multiple wireline logs. This information improves the prediction of CO2 injectivity in this formation. Well logs and core data were collected from 5 boreholes in the Surat Basin, where extensive core data and complete sets of conventional well logs exist for the Precipice Sandstone. Four different machine learning (ML) techniques, including Random Forest (RF), Artificial neural network (ANN), Gradient Boosting Regressor (GBR), and Support Vector Regressor (SVR), were independently trained with a wide range of hyper-parameters to ensure that not only is the best model selected, but also the right combination of model parameters is selected. Cross-validation for 20 different combinations of the seven available input logs was used for this study. Based on the performances in the validation and blind testing phases, the ANN with all seven logs used as input was found to give the best performance in predicting permeability for the Precipice Sandstone with the coefficient of determination (R2) of about 0.93 and 0.87 for the training and blind data sets respectively. Multi-regression analysis also appears to be a successful approach to calculate reservoir permeability for the Precipice Sandstone. Models with a complete set of well logs can generate reservoir permeability with R2 of more than 90%. [ABSTRACT FROM AUTHOR]

Achieving relatively high-accuracy short-term wind speed forecasting estimates is a precondition for the construction and grid-connected operation of wind power forecasting systems for wind farms. Currently, most research is focused on the structure of forecasting models and does not consider the selection of input variables, which can have significant impacts on forecasting performance. This paper presents an input variable selection method for wind speed forecasting models. The candidate input variables for various leading periods are selected and random forests (RF) is employed to evaluate the importance of all variable as features. The feature subset with the best evaluation performance is selected as the optimal feature set. Then, kernel-based extreme learning machine is constructed to evaluate the performance of input variables selection based on RF. The results of the case study show that by removing the uncorrelated and redundant features, RF effectively extracts the most strongly correlated set of features from the candidate input variables. By finding the optimal feature combination to represent the original information, RF simplifies the structure of the wind speed forecasting model, shortens the training time required, and substantially improves the model's accuracy and generalization ability, demonstrating that the input variables selected by RF are effective. [ABSTRACT FROM AUTHOR]

Short-term Photovoltaic (PV) Power Forecasting (STPF) is considered a topic of utmost importance in smart grids. The deployment of STPF techniques provides fast dispatching in the case of sudden variations due to stochastic weather conditions. This paper presents an efficient data-driven method based on enhanced Random Forest (RF) model. The proposed method employs an ensemble of attribute selection techniques to manage bias/variance optimization for STPF application and enhance the forecasting quality results. The overall architecture strategy gathers the relevant information to constitute a voted feature-weighting vector of weather inputs. The main emphasis in this paper is laid on the knowledge expertise obtained from weather measurements. The feature selection techniques are based on local Interpretable Model-Agnostic Explanations, Extreme Boosting Model, and Elastic Net. A comparative performance investigation using an actual database, collected from the weather sensors, demonstrates the superiority of the proposed technique versus several data-driven machine learning models when applied to a typical distributed PV system. [ABSTRACT FROM AUTHOR]

Accurate prediction of building energy need plays a fundamental role in building design, despite the high computational cost to search for optimal energy saving solutions. An important advancement in the reduction of computational time could come from the application of machine learning models to circumvent energy simulations. With the goal of drastically limiting the number of simulations, in this paper we investigate the regression performance of different machine learning models, i.e., Support Vector Machine, Random Forest, and Extreme Gradient Boosting, trained on a small data-set of energy simulations performed on a case study building. Among the XX algorithms, the tree-based Extreme Gradient Boosting showed the best performance. Overall, we find that machine learning methods offer efficient and interpretable solutions, that could help academics and professionals in shaping better design strategies, informed by feature importance. [ABSTRACT FROM AUTHOR]

With increasingly prominent environmental problems, controlling automobile exhaust has become essential to the environment. The fuel consumption of transportation is the critical factor that determines exhaust gas. By analyzing the naturalistic driving data of heavy-duty diesel trucks (HDDTs), this paper explored the influence of engine technical state, road features, weather, and temperature conditions on fuel consumption during driving. The detailed process is as follows: Firstly, we collected 1153 naturalistic driving data from 34 HDDTs and made a specific analysis and summary description of the data; secondly, by establishing a binary Logistic regression model, we quantitatively explored the influence of significant factors on the fuel consumption; meanwhile, based on quantitative analysis of factor's effectiveness, this research used several machine learning algorithms (back-propagation neural network, decision tree, and random forest) to build fuel consumption predictors, and compared the prediction performance of different algorithms. The results showed that the prediction accuracy of the decision tree, back-propagation (BP) neural network, and random forest is 81.38%, 83.98%, and 86.58%, respectively. The random forest showed the best performance in predicting. The conclusions can assist transportation companies in formulating driving training strategies and contribute to reducing energy consumption and emissions. [ABSTRACT FROM AUTHOR]

The quality of feedstock used in base oil processing depends on the source of the crude oil. Moreover, the refinery is fed with various blends of crude oil to meet the demand of the refining products. These circumstances have caused changes of quality of the feedstock for the base oil production. Often the feedstock properties deviate from the original properties measured during the process design phase. To recalculate and remodel using first principal approaches requires significant costs due to the detailed material characterizations and several pilot-plant runs requirements. To perform all material characterization and pilot plant runs every time the refinery receives a different blend of crude oil will simply multiply the costs. Due to economic reasons, only selected lab characterizations are performed, and the base oil processing plant is operated reactively based on the feedback of the lab analysis of the base oil product. However, this reactive method leads to loss in production for several hours because of the residence time as well as time required to perform the lab analysis. Hence in this paper, an alternative method is studied to minimize the production loss by reacting proactively utilizing machine learning algorithms. Support Vector Regression (SVR), Decision Tree Regression (DTR), Random Forest Regression (RFR) and Extreme Gradient Boosting (XGBoost) models are developed and studied using historical data of the plant to predict the base oil product kinematic viscosity and viscosity index based on the feedstock qualities and the process operating conditions. The XGBoost model shows the most optimal and consistent performance during validation and a 6.5 months plant testing period. Subsequent deployment at our plant facility and product recovery analysis have shown that the prediction model has facilitated in reducing the production recovery period during product transition by 40%. [ABSTRACT FROM AUTHOR]

The traditional way to mitigate loss circulation in drilling operations is to use preventative and curative materials. However, it is difficult to quantify the amount of materials from every possible combination to produce customized rheological properties. In this study, machine learning (ML) is used to develop a framework to identify material composition for loss circulation applications based on the desired rheological characteristics. The relation between the rheological properties and the mud components for polyacrylamide/polyethyleneimine (PAM/PEI)-based mud is assessed experimentally. Four different ML algorithms were implemented to model the rheological data for various mud components at different concentrations and testing conditions. These four algorithms include (a) k-Nearest Neighbor, (b) Random Forest, (c) Gradient Boosting, and (d) AdaBoosting. The Gradient Boosting model showed the highest accuracy (91 and 74% for plastic and apparent viscosity, respectively), which can be further used for hydraulic calculations. Overall, the experimental study presented in this paper, together with the proposed ML-based framework, adds valuable information to the design of PAM/PEI-based mud. The ML models allowed a wide range of rheology assessments for various drilling fluid formulations with a mean accuracy of up to 91%. The case study has shown that with the appropriate combination of materials, reasonable rheological properties could be achieved to prevent loss circulation by managing the equivalent circulating density (ECD). [ABSTRACT FROM AUTHOR]

Owing to the ever-growing impetus towards the development of eco-friendly and low carbon footprint energy solutions, biodiesel production and usage have been the subject of tremendous research efforts. The biodiesel production process is driven by several process parameters, which must be maintained at optimum levels to ensure high productivity. Since biodiesel productivity and quality are also dependent on the various raw materials involved in transesterification, physical experiments are necessary to make any estimation regarding them. However, a brute force approach of carrying out physical experiments until the optimal process parameters have been achieved will not succeed, due to a large number of process parameters and the underlying non-linear relation between the process parameters and responses. In this regard, a machine learning-based prediction approach is used in this paper to quantify the response features of the biodiesel production process as a function of the process parameters. Three powerful machine learning algorithms—linear regression, random forest regression and AdaBoost regression are comprehensively studied in this work. Furthermore, two separate examples—one involving biodiesel yield, the other regarding biodiesel free fatty acid conversion percentage—are illustrated. It is seen that both random forest regression and AdaBoost regression can achieve high accuracy in predictive modelling of biodiesel yield and free fatty acid conversion percentage. However, AdaBoost may be a more suitable approach for biodiesel production modelling, as it achieves the best accuracy amongst the tested algorithms. Moreover, AdaBoost can be more quickly deployed, as it was seen to be insensitive to number of regressors used. [ABSTRACT FROM AUTHOR]

Dead oil viscosity is a critical parameter to solve numerous reservoir engineering problems and one of the most unreliable properties to predict with classical black oil correlations. Determination of dead oil viscosity by experiments is expensive and time-consuming, which means developing an accurate and quick prediction model is required. This paper implements six machine learning models: random forest (RF), lightgbm, XGBoost, multilayer perceptron (MLP) neural network, stochastic real-valued (SRV) and SuperLearner to predict dead oil viscosity. More than 2000 pressure–volume–temperature (PVT) data were used for developing and testing these models. A huge range of viscosity data were used, from light intermediate to heavy oil. In this study, we give insight into the performance of different functional forms that have been used in the literature to formulate dead oil viscosity. The results show that the functional form f (γ A P I , T) , has the best performance, and additional correlating parameters might be unnecessary. Furthermore, SuperLearner outperformed other machine learning (ML) algorithms as well as common correlations that are based on the metric analysis. The SuperLearner model can potentially replace the empirical models for viscosity predictions on a wide range of viscosities (any oil type). Ultimately, the proposed model is capable of simulating the true physical trend of the dead oil viscosity with variations of oil API gravity, temperature and shear rate. [ABSTRACT FROM AUTHOR]

The goal of the paper is to develop an online forecasting procedure to be adopted within the H2020 InteGRIDy project, where the main objective is to use the photovoltaic (PV) forecast for optimizing the configuration of a distribution network (DN). Real-time measurements are obtained and saved for nine photovoltaic plants in a database, together with numerical weather predictions supplied from a commercial weather forecasting service. Adopting several error metrics as a performance index, as well as a historical data set for one of the plants on the DN, a preliminary analysis is performed investigating multiple statistical methods, with the objective of finding the most suitable one in terms of accuracy and computational effort. Hourly forecasts are performed each 6 h, for a horizon of 72 h. Having found the random forest method as the most suitable one, further hyper-parameter tuning of the algorithm was performed to improve performance. Optimal results with respect to normalized root mean square error (NRMSE) were found when training the algorithm using solar irradiation and a time vector, with a dataset consisting of 21 days. It was concluded that adding more features does not improve the accuracy when adopting relatively small training sets. Furthermore, the error was not significantly affected by the horizon of the forecast, where the 72-h horizon forecast showed an error increment of slightly above 2% when compared to the 6-h forecast. Thanks to the InteGRIDy project, the proposed algorithms were tested in a large scale real-life pilot, allowing the validation of the mathematical approach, but taking also into account both, problems related to faults in the telecommunication grids, as well as errors in the data exchange and storage procedures. Such an approach is capable of providing a proper quantification of the performances in a real-life scenario. [ABSTRACT FROM AUTHOR]