Search Results (750)

This article aimed to incorporate the coordinated construction of classifiers to develop a model for predicting the pyrolysis of loose biomass. For the purposes of application, the ground form of pine cone was used to perform the thermogravimetric analysis at heating rates of 5, 10, and 15 °C∙min⁻¹. The supervised machine learning technique was considered to estimate the kinetic parameters associated with the thermal decomposition of the material. Here, the integral as well as differential form of the isoconversional method was used along with the Kissinger method for the maximum reaction rate determination. Python (version 3.13.2), along with PyCharm (2024.3.3) as an integrated development environment (IDE), was used to develop code for the given problem. The TG model obtained through the boosting technique provided the best fitting for the experimental dataset of raw pine cone, with the root squared error varying from ±1.82 × 10⁻³ to ±1.84 × 10⁻³, whereas it was in the range of ±1.78 × 10⁻³ to ±1.83 × 10⁻³ for processed pine cone. Similarly, the activation energies derived through the trained models of Friedman, OFW, and KAS were 176 kJ-mol⁻¹, 151.60 kJ-mol⁻¹, and 142.04 kJ-mol⁻¹, respectively, for raw pine cone. It was seen that the boosting technique did not provide a reasonable fit if the number of features was increased in the kinetic models. This happened owing to an inability to maintain a tradeoff between variance and bias. Moreover, the multiclassification in pyrolysis kinetics through the proposed scheme was not able to capture the distribution pattern of target values of the differential method. With the increase in the heating rates, the noise level in the predicted model was also relatively increased. Full article

In recent years, there has been increasing interest in new materials such as ceramic matrix composites (CMCs) for power generation and aerospace propulsion applications through hydrogen combustion. This study employed a deep artificial neural network (DANN) model to predict the ablation performance of CMCs in the hydrogen torch test (HTT). The study was conducted in three phases to increase the accuracy of the model’s predictions. Initially, to predict the thermal behavior of ceramic composites, two linear machine learning models were used known as Lasso and Ridge regression. In the second step, four decision tree-based ensemble machine learning models, namely random forest, gradient boosting regression, extreme gradient boosting regression, and extra tree regression, were used to improve the prediction accuracy metrics, including root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R² score), and mean absolute percentage error (MAPE), relative to the previously introduced linear models. Finally, to forecast the thermal stability of CMCs with time, an optimized DANN model with two hidden layers having rectified linear unit activation function was developed. The data collection procedure involved preparing CMCs with continuous Yttria-Stabilized Zirconia (YSZ) fibers and silicon carbide (SiC) matrix using a polymer infiltration and pyrolysis (PIP) technique. The samples were exposed to a hydrogen flame at a high heat flux of 183 W/cm² for a duration of 10 min. A good agreement between the DANN model’s predictions and experimental data with an R² score of 0.9671, RMSE of 16.45, an MAE of 14.07, and an MAPE of 3.92% confirmed the acceptability of the developed neural network model in this study. Full article

As the core process of the thermal treatment of municipal solid waste (MSW), incineration process optimization has become a frontier topic in the field of environmental engineering. This study took a 500 t/d incinerator for engineering application as the research object. Based on a two-fluid model, a three-dimensional transient model of a proportional incinerator was established. The effects of primary air proportion and moisture content on the combustion state in the incinerator were verified and discussed using field test data, and the dynamic changes in flue gas temperature were predicted by a BPNN (Backpropagation Neural Network). The results show that the increase in air volume in the drying section promotes water evaporation but inhibits the devolatilization and combustion of fixed carbon. The position where complete devolatilization and fixed carbon combustion begins was delayed by 1.5 m~3 m. The moisture content (M) is negatively correlated with the devolatilization and combustion of fixed carbon. From M = 25% to M = 40%, the flue gas outlet temperature decreased by 140 K. In addition, a dynamic combustion BP neural network model with the movement of the grate under rated conditions was constructed, with the MSE (Mean Squared Error) being 1.629%. The model can learn data characteristics well and has a good prediction effect. This study provides a scientific basis for optimizing the operating parameters of municipal solid waste incinerators, helps to optimize the incineration process, and is of great significance to the thermal treatment of MSW. Full article

With heavy trucks being more widely used in the logistics industry, more and more lorry drivers are frequently exposed to the acoustic-thermal dynamically coupled cockpit environment for a long time. The comfort in the cockpit directly affects driving safety and occupational health. However, the existing research lacks a multi-parameter fusion prediction method for occupant annoyance in this scenario. In this paper, we studied the effect of an acoustic-thermal composite environment on the annoyance level of truck occupants and predicted the annoyance level of the human body by combining environmental parameters and physiological parameters. A total of 20 adult males participated in the subjective annoyance evaluation test, and 60 sets of sample data were obtained under four working conditions by collecting environmental parameters and monitoring physiological parameters, and the effect of acoustic-thermal composite environments was explored using statistical analysis in combination with the subjects’ annoyance polls. The results showed that the human physiological parameters were significantly correlated with the thermal environment, and the correlation coefficient between PMV value and skin temperature was r₁ = 0.99, with p < 0.05. The subjective annoyance level was more sensitive to the thermal environment than noise. The correlation coefficient between PMV and annoyance level was r₂ = 0.931, and the correlation coefficient between the noise parameter roughness R and annoyance level was r₃ = 0.545. The results of this study were based on the screened predictor variables, the annoyance prediction model using the random forest algorithm showed high accuracy on the test set (R² = 0.941, root mean square error RMSE = 0.259, mean absolute error MAE = 0.201). The study showed that the annoyance prediction model incorporating environmental and physiological parameters could estimate subjects’ annoyance more accurately. Full article

Facing the complex coupled process of thermal mass transfer and electrochemical reaction inside fuel cells, the development of a one-dimensional model is an efficient solution to study the influence of mass transfer property parameters on the transfer and reaction process, which can effectively balance the computational efficiency and accuracy. Firstly, a one-dimensional two-phase non-isothermal parametric model is established to capture the performance and state of fuel cell quickly. Then, a sensitivity analysis is performed on various mass transfer parameters of the membrane electrode assembly. Subsequently, a neural network surrogate model and genetic algorithm are combined to optimize the mass transfer property parameters globally. The impact of these parameters on the thermal and mass transfer within the fuel cell is analyzed. The results show that the maximum error between the calculation results of the developed numerical model and the experimental results is 3.87%, and the maximum error between the predicted values of the trained surrogate model and the true values is 0.15%. The mass transfer characteristics of the gas diffusion layer have the most significant impact on the performance of the fuel cell. After optimizing the mass transfer characteristic parameters, the net power density of the fuel cell increased by 5.51%. The combination of the one-dimensional model, the surrogate model, and the genetic algorithm can effectively improve the optimization efficiency. Full article

The thermal error of the high-power grinding motorized spindle, caused by heating, seriously affects machining accuracy. In this paper, an ensemble learning algorithm is used to predict the thermal error of a high-precision motorized spindle. The subsequent problem of thermal error compensation can be effectively solved by a suitable thermal error model, which is crucial for improving the machining accuracy of the actual machining process. Firstly, the steady-state temperature field of the grinding motorized spindle is analyzed and used to determine the position of the sensors. Then, a signal acquisition instrument is used to monitor real-time temperature data. After that, experimental results are obtained, followed by verification. Finally, based on experimental data and the optimization results of temperature measurement points, temperature data are used as the input variable, and thermal deformation data are used as the output variable. The ensemble learning model is composed of different weak learners, which include multiple linear regression, back-propagation, and radial basis function neural networks. Different weak learners are trained using datasets separately, and the output of the weak learners is used as input to the model. Through integrating strategies, an ensemble learning model is established and compared with a weak learner. The error residual set of the ensemble learning model remains within [−0.2, 0.2], and the prediction performance shows that the ensemble learning model has a better predictive effect and strong robustness. Full article

Morro de Seis Lagos, a region in the Brazilian Amazon, contains a small (less than 1%) formation of siderite carbonatites which is considered to be one of the world’s largest niobium reserves. This highly weathered geological and pedological occurrence makes the site ideal for studying the pedogenetic process of lateralization and the spatial variability of chemical elements. The aim of this study was to investigate the influences of various sampling combinations (scenarios) derived from three sampling designs on the spatial predictions associated with chemical compounds (Al₂O₃, Fe₂O₃, MnO, Nb₂O₅, TiO₂, and SiO₂), using multiple machine learning algorithms combined with remotely sensed imagery. The dataset comprised 341 samples from the Geological Survey of Brazil (CPRM). Covariates included remotely sensed data collected from Sentinel-2 MSI, Sentinel-1A, and the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), and topographic attributes were calculated from a 20 m digital elevation model derived from hydrologic data (HC-DEM). The machine learning algorithms (Generalized Linear Models with Elastic Net Regularization (GLMNET), Nearest Neighbors (KNN), Neural Network (NNET), Random Forest (RF) and Support Vector Machine (SVMRadial) were used in combination with covariates and measured elements at point locations to spatially map the concentrations of these chemical elements. The optimal covariates for modeling were selected using Recursive Feature Elimination (RFE), processing 10 runs for each chemical element. The RF, SVMRadial, and KNN models performed best, followed by the models from the Neural Network group (NNET). The sampling scenarios were not significantly different, based on root mean square error (F = 1.7; p-value = 0.15) and mean absolute error (F = 0.4; p-value = 0.79); however, significant differences were observed in the coefficient of determination (F = 41.2; p-value < 0.00) across all models. Overall, the models performed poorly for all elements, with R² ranging from 0.07 to 0.27, regardless of sampling scenario (F = 1.6; p-value = 0.08). Relatively, RF, GLMET, and KNN performed better, compared to other models. The terrain attributes were significantly more successful as to the spatial predictions of the elements contained in laterites than were the remote sensing spectral indices, likely due to the fact that the underlying spatial structures of the two formations (laterite and talus) occur at different elevations. Full article

Thermal printing is a prevalent method due to its advantages of rapid output, cost effectiveness, and ease of use. However, the quality of thermal printing is influenced by the printing speed, the temperature, and the concentration and characteristics of the materials. This research employs a BP neural network to forecast print quality, utilizing two activation functions. The findings indicate that a dual-layer hidden configuration utilizing the GeLU activation function yields a lower root-mean-square error (RMSE). The optimal configuration identified consists of six neurons in the first hidden layer and three neurons in the second hidden layer. To enhance the predictive performance, a PSO algorithm was integrated with the PSO-BP model to refine the parameter selection, which included ambient temperature, printing speed, and printing concentration, with iterative training and validation conducted via the gradient descent algorithm. The PSO-BP network achieved an MAE of 0.1108, an RMSE of 0.145, an MSE of 0.021, and an R² value of 0.9916 in predicting print quality. These results substantiate the stability and reliability of the neural network model developed with the PSO algorithm. Further validation with ten sets of test samples demonstrated that the model attained an average absolute error of 2.77% in print quality predictions, indicating robust generalization capabilities and precise forecasting. Full article

Tomato is a crop with high potential to be used in various food industry co-products, such as sauces. In addition to increasing the supply of differentiated products, processed foods have improved shelf life. However, as a consequence of thermal processing, there may be some important nutritional losses. In this context, the choice of suitable varieties for each type of processing based on the assessment of food losses is extremely important to both the processing industry and the consumer. Therefore, this work aimed to predict the percentage of concentration loss in tomatoes during cooking for sauce production using an artificial neural network (ANN). The prediction was made by analyzing the fresh fruit and comparing it to the cooked product. The study investigated bioactive compounds (vitamin C, ascorbic acid, phenolic compounds, flavonoids, carotenoids, anthocyanins, lycopene, and β-carotene), antioxidant activity (DPPH and FRAP), soluble solids, pH, titratable acidity, ratio, and total sugar. Nine commercial and non-commercial tomato varieties were evaluated. The artificial neural network used was the multilayer perceptron, and its results were compared with first-, second-, and third-degree polynomial regression techniques, evidencing its superiority. This superiority was confirmed by the higher correlation achieved using the ANN (R² = 0.9025), outperforming the first-, second-, and third-degree regressions (R² = 0.8817, 0.8819, and 0.8941, respectively). Furthermore, the ANN achieved a lower mean squared error (MSE = 0.000999) and strong validation performance, reinforcing its greater precision and reliability compared to traditional models. Full article

State-of-energy (SOE) estimation helps to enhance the safety of battery operation and predict vehicle range. However, the voltage plateau of the LiFePO4 (LFP) battery presents a significant challenge for SOE estimation. Therefore, this paper introduces a significantly varying mechanical force feature to tackle the flat voltage curve in the mid-SOE region. A fusion model that integrates a bidirectional long short-term memory (BiLSTM) network, particle swarm optimization (PSO), and Kalman filter (KF) algorithm is proposed for SOE estimation. The BiLSTM is applied to fully capture the temporal dependencies from inputs to output over both local and long cycles. Subsequently, PSO is employed to optimize the parameters of KF, which is utilized to smooth the results of the BiLSTM network, thereby achieving highly accurate SOE estimation. Experimental results across different operating conditions and temperatures reveal that the introduction of mechanical force significantly improves SOE estimation accuracy. Compared to models using only traditional electrical and thermal features, the model with the introduction of mechanical force achieves average improvements of 67.06%, 66.38%, and 66.46% for the root mean square error (RMSE), maximum absolute error (MAXE), and mean absolute error (MAE), respectively. Moreover, the generalizability and robustness of the proposed method are further confirmed by the comparison of different models and preload forces. Full article

This work aims to explore the magnetohydrodynamic mixed convection boundary layer flow (MHD-MCBLF) on a slanted extending cylinder using Eyring–Powell fluid in combination with Levenberg–Marquardt algorithm–artificial neural networks (LMA-ANNs). The thermal properties include thermal stratification, which has a higher temperature surface on the cylinder than on the surrounding fluid. The mathematical model incorporates essential factors involving mixed conventions, thermal layers, heat absorption/generation, geometry curvature, fluid properties, magnetic field intensity, and Prandtl number. Partial differential equations govern the process and are transformed into coupled nonlinear ordinary differential equations with proper changes of variables. Datasets are generated for two cases: a flat plate (zero curving) and a cylinder (non-zero curving). The applicability of the LMA-ANN solver is presented by solving the MHD-MCBLF problem using regression analysis, mean squared error evaluation, histograms, and gradient analysis. It presents an affordable computational tool for predicting multicomponent reactive and non-reactive thermofluid phase interactions. This study introduces an application of Levenberg–Marquardt algorithm-based artificial neural networks (LMA-ANNs) to solve complex magnetohydrodynamic mixed convection boundary layer flows of Eyring–Powell fluids over inclined stretching cylinders. This approach efficiently approximates solutions to the transformed nonlinear differential equations, demonstrating high accuracy and reduced computational effort. Such advancements are particularly beneficial in industries like polymer processing, biomedical engineering, and thermal management systems, where modeling non-Newtonian fluid behaviors is crucial. Full article

Automated monitoring of the coolant temperature can enable autonomous operation of generation IV reactors (GenIV), thus reducing their operating and maintenance costs. Automation can be accomplished with machine learning (ML) models trained on historical sensor data. However, the performance of ML usually depends on the availability of large amount of training data, which is difficult to obtain for GenIV, as this technology is still under development. We propose the use of transfer learning (TL), which involves utilizing knowledge across different domains, to compensate for this lack of training data. TL can be used to create pre-trained ML models with data from small-scale research facilities, which can then be fine-tuned to monitor GenIV reactors. In this work, we develop pre-trained Transformer and long short-term memory (LSTM) networks by training them on temperature measurements from thermal hydraulic flow loops operating with water and Galinstan fluids at room temperature at Argonne National Laboratory. The pre-trained models are then fine-tuned and re-trained with minimal additional data to perform predictions of the time series of high temperature measurements obtained from the Engineering Test Unit (ETU) at Kairos Power. The performance of the LSTM and Transformer networks is investigated by varying the size of the lookback window and forecast horizon. The results of this study show that LSTM networks have lower prediction errors than Transformers, but LSTM errors increase more rapidly with increasing lookback window size and forecast horizon compared to the Transformer errors. Full article

Soil moisture (SM) profoundly influences crop growth, yield, soil temperature regulation, and ecological balance maintenance and plays a pivotal role in water resources management and regulation. The focal objective of this investigation is to identify feature parameters closely associated with soil moisture through the implementation of feature selection methods on multi-source remote sensing data. Specifically, three feature selection methods, namely SHApley Additive exPlanations (SHAP), information gain (Info-gain), and Info_gain ∩ SHAP were validated in this study. The multi-source remote sensing data collected from Sentinel-1, Landsat-8, and Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Digital Elevation Model (ASTGTM DEM) enabled the derivation of 25 characteristic parameters through sound computational approaches. Subsequently, a stacking algorithm integrating multiple machine-learning (ML) algorithms based on adaptive learning was engineered to accomplish soil moisture prediction. The attained prediction outcomes were then juxtaposed against those of single models, including Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost). Notably, the adoption of feature factors selected by the Info_gain algorithm in combination with the adaptive stacking (Ada-Stacking) algorithm yielded the most optimal soil moisture prediction results. Specifically, the Mean Absolute Error (MAE) was determined to be 1.86 Vol. %, the Root Mean Square Error (RMSE) amounted to 2.68 Vol. %, and the R-squared (R2) reached 0.95. The multifactor integrated model that harnessed optical remote sensing data, radar backscatter coefficients, and topographic data exhibited remarkable accuracy in soil surface moisture retrieval, thus providing valuable insights for soil moisture inversion studies in the designated study area. Furthermore, the Ada-Stacking algorithm demonstrated its potency in integrating multiple models, thereby elevating retrieval accuracy and overcoming the limitations inherent in a single ML model. Full article

Boiling heat transfer, utilizing latent heat during phase change, has widely been used due to its high thermal efficiency and plays an important role in existing and next-generation cooling technologies. The most critical parameter in boiling heat transfer is critical heat flux (CHF), which represents the maximum heat flux a heated surface can sustain during boiling. CHF is primarily influenced by the wicking performance, which governs liquid supply to the surface. This study experimentally and numerically analyzed the wicking performance of micropillar structures at various temperatures (20–95 °C) using distilled water as the working fluid to provide fundamental data for CHF prediction. Infrared (IR) visualization was used to extract the wicking coefficient, and the experimental data were compared with computational fluid dynamics (CFD) simulations for validation. At room temperature (20 °C), the wicking coefficient increased with larger pillar diameters (D) and smaller gaps (G). Specifically, the highest roughness factor sample (D04G10, r = 2.51) exhibited a 117% higher wicking coefficient than the lowest roughness factor sample (D04G20, r = 1.51), attributed to enhanced capillary pressure and improved liquid supply. Additionally, for the same surface roughness factor, the wicking coefficient increased with temperature, showing a 49% rise at 95 °C compared to 20 °C due to reduced viscous resistance. CFD simulations showed strong agreement with experiments, with error within ±10%. These results confirm that the proposed numerical methodology is a reliable tool for predicting wicking performance near boiling temperatures. Full article

This paper investigates how octanol, used as a renewable additive in Jet A fuel, influences the performance and emissions of aviation micro-turbo engines. Blends containing 10%, 20%, and 30% octanol, with an additional 5% n-heptane, were tested to closely replicate Jet A’s physical–chemical properties. Mathematical models validated using density and viscosity data achieved accurate predictions, with maximum absolute errors of 0.0018 g/cm³ for density and 0.4020 mm²/s for viscosity. Performance assessments showed that fuel consumption increased due to octanol’s lower calorific value, requiring higher fuel flow to sustain engine speed. Combustion temperature variations ranged from a decrease of 5.38% in Regime 1 (30% octanol) to increases of up to 1.47% and 1.13% in Regimes 2 and 3, respectively, without compromising engine stability. Thrust variations were minimal, with decreases up to 0.72% observed at 30% octanol concentration. Emission analysis indicated significant reductions in CO and NO_x levels with increased octanol content, attributed to enhanced combustion completeness and additional oxygen availability. SO₂ emissions also decreased slightly due to the lower sulfur content. Thermal efficiency marginally declined from 5.04% (Jet A) to approximately 4.92–4.97% for octanol blends. These findings support octanol as a viable sustainable additive, offering substantial emission benefits with only minor efficiency trade-offs. Full article