Application of AI in Tablet Development: An Integrated Machine Learning Framework for Pre-Formulation Property Prediction.

The intricacies and instability of introducing cryogenic propellants into the combustion system have piqued the curiosity of scientists studying the procedure. The latest innovation is utilizing data-driven machine learning and deep learning approaches to gain deeper insights into the related difficulties. However, the current work serves as a baseline for future research because relatively few studies have used data-driven methodologies to assess the temperature of liquid fuel injections in combustion systems. The performance of Linear Regression (LR), Random Forest (RF), Extra Trees Regressor (ETR), Polynomial Regression (PR), Support Vector Regressor (SVR), Decision Tree Regressor (DTR), Gradient Boost Regressor (GBR), XGB Regressor (XGBoost), AdaBoost Regressor (ABR), K-Neighbors Regressor (KNR), Long-Short Term Memory (LSTM), Bi-LSTM (Bi-directional Long-Short Term Memory) has all been investigated in this study. The study also suggested a Fully Connected Neural Network (FCNN) to examine its performance and paired it with an Extra Tree Regressor (ETR). The coupled FCNN and Extra Tree Regressor outperform the other algorithms with a Mean Square Error (MSE) of 0.0000005062, Root Mean Square Error (RMSE) of 0.00071148, Mean Absolute Error (MAE) of 0.00020672, and R-squared (R2) value of 0.99998689. Linear Regression, Polynomial Regression, and Support Vector Regressor are found to be the least-performing algorithms. The current work uses machine learning and deep learning methods to make data-driven decisions for liquid fuel injection in the combustion system.

An accurate energy consumption prediction becomes crucial with increasing electric vehicle usage for effective power grid management. This research examined the performance of eleven machine learning models for this purpose: Ridge Regression, Lasso Regression, K-Nearest Neighbors, Gradient Boosting, Support Vector Regression, Multi-Layer Perceptron, XGBoost, CatBoost, LightGBM, Gaussian Processes for Regression(GPR) and Extra Trees Regressor, considering real historical data from Colorado. The models were evaluated using different metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), R², Root Mean Squared Error(RMSE) and Normalized Root Mean Squared Error(NRMSE), with visual analyses through scatter plots and time series plots. The best model observed was the Extra Trees Regressor, which had an MAE of 0.5888, an MSE of 3.2683, R² value of 0.9592, RMSE of 1.8078 and NRMSE of 0.020. Gradient Boosting and KNN also returned good results, although they were slightly more dispersed. Nevertheless, while non-linear models like MLP, XGBoost, CatBoost, LightGBM and linear models such as Ridge and Lasso Regression offer valuable insights, they exhibit shortcomings in estimating energy, especially at extreme levels, highlighting limitations in capturing complex non-linear interactions. This study focuses on their applicability to energy projections to demonstrate how well ensemble and non-linear models may capture intricate patterns in time series. These cutting-edge machine learning techniques might greatly enhance energy demand predictions.

Accurate leaf area index estimation in sorghum using high-resolution UAV data and machine learning models

The constant dynamic changes in salt pond make it difficult to achieve accurate prediction of ion concentration. It is of great significance to get the accurate prediction of potassium ion concentration in salt pools for the actual production of potash fertilizer. In this paper, some machine learning methods, such as support vector regression (SVR), AdaBoost regressor, K neighbor regressor, gradient boosting regressor, extra trees regressor and neural network regressor, have been used to build the prediction models. In the experiment, the MSE and R2 of the K+ concentration by using SVR in test data set reach 0.26385 and 0.9414, which are better than other models. Therefore, the SVR model has high research value in the field of salt pool ion concentration prediction.

This study presents the first application of Machine Learning (ML) models to optimise Powder Bed Fusion using Laser Beam (PBF-LB) process parameters for H13 steel fabricated on a 350 °C preheated building platform. A total of 189 cylindrical specimens were produced for training and testing machine learning (ML) models using variable process parameters: laser power (250-350 W), scanning speed (1050-1300 mm/s), and hatch spacing (65-90 μm). Eight ML models were investigated: 1. Support Vector Regression (SVR), 2. Kernel Ridge Regression (KRR), 3. Stochastic Gradient Descent Regressor, 4. Random Forest Regressor (RFR), 5. Extreme Gradient Boosting (XGBoost), 6. Extreme Gradient Boosting with limited depth (XGBoost LD), 7. Extra Trees Regressor (ETR) and 8. Light Gradient Boosting Machine (LightGBM). All models were trained using the Fast Library for Automated Machine Learning & Tuning (FLAML) framework to predict the relative density of the fabricated samples. Among these, the XGBoost model achieved the highest predictive accuracy, with a coefficient of determination R2=0.977, mean absolute percentage error MAPE = 0.002, and mean absolute error MAE = 0.017. Experimental validation was conducted on 27 newly fabricated samples using ML predicted process parameters. Relative densities exceeding 99.6% of the theoretical value (7.76 g/cm3) for all models except XGBoost LD and KRR. The lowest MAE = 0.004 and the smallest difference between the ML-predicted and PBF-LB validated density were obtained for samples made with LightGBM-predicted parameters. Those samples exhibited a hardness of 604 ± 13 HV0.5, which increased to approximately 630 HV0.5 after tempering at 550 °C. The LightGBM optimised parameters were further applied to fabricate a part of a forging die incorporating internal through-cooling channels, demonstrating the efficacy of machine learning-guided optimisation in achieving dense, defect-free H13 components suitable for industrial applications.

The speed of sound is of particular importance in determining the physical and chemical properties of gas mixtures. Given the importance of this parameter in hydrogen transport and the high speed and accuracy of machine learning methods compared to traditional methods such as equations of state, this study estimates the speed of sound in hydrogen/cushion gas mixtures. For this purpose, 665 data sets of sound speed in hydrogen/cushion gas mixtures were collected from previous studies, and then 4 machine learning methods were used, including Linear Regression (LR), Extra Trees Regressor (ETR), Extreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), and K-Nearest Neighbor (KNN). The hyperparameters of these models were optimized using the Bayesian algorithm, and fivefold cross-validation was used to prevent overfitting. The ETR method had the best performance with R2 = 0.9996 and RMSE = 6.2775 m/s, followed by the KNN method with R2 = 0.9996 and RMSE = 7.0540 m/s. Also, the weakest performance belonged to the Linear method with R2 = 0.8104. Also, the ETR method was able to estimate 64.81% of the data with an error of less than 0.0001%. Also, sensitivity analysis was performed using SHapley Additive exPlanations (SHAP) method, and based on its results, the hydrogen mole fraction had the greatest effect on the speed of sound, and at low values, this effect was inverse, and at high values, this effect was direct. After the hydrogen mole fraction, pressure was the second most effective parameter, which showed a behavior similar to the hydrogen mole fraction (inverse relationship at low values and direct at high values). Also, the methane mole fraction had the least effect on the speed of sound in the gas mixture. The developed machine learning models not only demonstrate outstanding predictive performance for sound speed in hydrogen-based mixtures but also offer valuable insight into the acoustic behavior of multicomponent gas systems. These findings can support the design and control of hydrogen energy infrastructures, where real-time monitoring and compositional analysis are critical.

TPLS as predictive platform for twin-screw wet granulation process and formulation development

The application of the informational theory to the analysis of the grinding process under action of transverse rotating magnetic field

Tablets which were prepared from separate formulations of Emcompress StandardR, a commercially available directly compressible granulation, with ascorbic acid, folic acid, and thiamine hydrochloride were subjected to accelerated aging conditions and studied for chemical stability and such physical parameters as hardness, friability, and disintegration time. Other physical factors which could affect the interpretation of the data, such as moisture content, particle size distribution, angle of repose, weight variation, and hardness were also studied using fresh samples.Accelerated aging showed that the ascorbic acid formulation was chemically unstable; the tablets became soft, the frability increased markedly, and the disintegration time decreased. The folic acid formulation was chemically stable, but the tablets became soft, the friability increased, and disintegration time increased. The thiamine hydrochloride formulation was also chemically stable—the tablets became soft, the disintegration time decreased, and the friability increased.

Numerical simulation of a dissolution process in a stirred tank reactor

On the influence of raw material attributes on process behaviour and product quality in a continuous WET granulation tableting line

Salts in the root zone have high spatial variability, change rapidly and adversely affect soil quality and crop productivity. In contrast to the time-intensive traditional methods for measuring electrical conductivity (EC), visible-near infrared (Vis-NIR) and mid-infrared (MIR) spectroscopy provide faster alternatives that can assist in creating strategies to reduce negative impacts on soil and plants. Soils were collected from the Indo-Gangetic Plains and analysed for EC1:2.5 using conventional method. There was a wide variation in EC measured by the conventional method. So Partial Least Squares Regression (PLSR) was used to predict soil EC from spectral data, with the data divided into calibration (70%) and validation (30%) datasets. The partial least square regression (PLSR), random forest (RF), support vector regression (SVR) and multivariate adaptive regression splines (MARS) both in Vis-NIR and MIR region during calibration. The predictive performance of PLSR, RF, SVR, and MARS models for EC1:2.5 in the Vis-NIR range showed PLSR as the best model (R2 = 0.84, RMSE = 0.21, RPD = 2.44). In the MIR range, RF was considered fairly good (R2 = 0.52, RMSE = 0.20, RPD = 1.43). Vis-NIR spectroscopy with PLSR algorithm predicted EC better than MIR spectroscopy and would be the method of choice for rapid estimation and prediction of EC in the study region.

A novel approach to investigate the processability of polyamide 12/dimethylacetamide (PA12/DMAc) microspheres for laser sintering through molecular interactions of the functional groups and the effects of DMAc on the morphology, particle size distribution, and thermal properties of the polymer composites was addressed in this study. The increase in DMAc concentrations enhanced polymer dissolution, minimized agglomeration, and improved the binding adhesive forces within the polymer matrix. It also enhanced the stretching vibrations in the primary amide (C=N), amine bond (C–N), and hydrogen bond (N–H) of the PA12. The melting enthalpy of the polymer powder increased with greater molecular interactions with the solvent. All the PA12 powder samples exhibited a consistent average crystallization point of 147.5°C, similar to that of virgin PA12 (149.3°C) due to identical exothermic properties. The SEM and particle size distribution analysis of PA12/DMAc samples indicated variability in molecular interspaces between powder particles due to differences in the interfacial mobility, which expanded with an increase in the solvent input ratios. However, the particle size distribution span reduced with an increase in the volume of DMAc. The optimal mean particle size distribution was 64.87 μm, accompanied by a bulk density of 0.38 g/cm3, which could facilitate the sinterability of the PA12 powder.Highlights Compatibility of PA12/DMAc microspheres Molecular interactions during TIPS Effects of DMAc on PA12 dissolution and precipitation time Dissolution and precipitation rate analysis Melting and crystallization behavior.

Among fundamental properties of ceramic raw materials, particle size distribution, hygroscopicity, colloid, content, etc. were measured directly; surface factor and total surface area were calculated from these data, and discussed the relations among them.The effects of treating methods of clays, e.g. water-washing hydrogen peroxide treatment, egeing in water, etc. upon dispersion of clays were also studied and discussed.

Sedimentation and drying are important physicochemical processes that play critical roles in the management of mining operations, directly impacting environmental safety and operational efficiency. This study develops a methodology of utilizing portable single-sided nuclear magnetic resonance (NMR) instruments to study free and induced sedimentation as well as drying processes of complex tailings materials from gold mine tailings storage facilities (TSFs) via the detection of 1H NMR water signals of the tailings. The results obtained are discussed considering the influence of the physical and mineralogical properties of tailings, such as particle-size distribution, mineral composition, and solid-content percentage. We observed various phases of sedimentation, including short-term and long-term sedimentations, which are characterized by significantly different timescales required for reaching the complete settling of the sludge layers. Moreover, we show that NMR allows the detection of an interesting effect of mechanically induced sedimentation, which is reported only scarcely in the literature. These findings demonstrate the complexity of the sedimentation process and support a clear relationship among the settling rate, particle size, and density of the minerals. In addition, by using a controlled aeration method on top of a single-sided NMR device, we could evaluate the dynamics of the drying process. The utilized NMR methodology is sensitive to slight changes in the water content and mobility via the measurements of both the 1H NMR signal amplitudes and the T2 relaxation times. It allows one to quantify the water content during the transition from slurry-like to sludge-like forms of the studied tailings. The findings can provide valuable tools to characterize tailings sedimentation and dewatering, highlighting the potential of portable NMR as an analytical tool for real-time monitoring and optimization of TSF management strategies.