Estimating the Relative Crystallinity of Biodegradable Polylactic Acid and Polyglycolide Polymer Composites by Machine Learning Methodologies

The Effects of Nucleating Agents and Processing on the Crystallization and Mechanical Properties of Polylactic Acid: A Review

Polylactic acid (PLA) is a biobased, biodegradable, non-toxic polymer widely considered for replacing traditional petroleum-based polymer materials. Being a semi-crystalline material, PLA has great potential in many fields, such as medical implants, drug delivery systems, etc. However, the slow crystallization rate of PLA limited the application and efficient fabrication of highly crystallized PLA products. This review paper investigated and summarized the influence of formulation, compounding, and processing on PLA's crystallization behaviors and mechanical performances. The paper reviewed the literature from different studies regarding the impact of these factors on critical crystallization parameters, such as the degree of crystallinity, crystallization rate, crystalline morphology, and mechanical properties, such as tensile strength, modulus, elongation, and impact resistance. Understanding the impact of the factors on crystallization and mechanical properties is critical for PLA processing technology innovations to meet the requirements of various applications of PLA.

A novel neural-evolutionary framework for predicting weight on the bit in drilling operations

This study compares the performance of artificial neural networks (ANN) trained by grey wolf optimization (GWO), biogeography-based optimization (BBO), and Levenberg-Marquardt (LM) to estimate the weight on bit (WOB). To this end, a dataset consisting of drilling depth, drill string rotational speed, rate of penetration, and volumetric flow rate as input variables and the WOB as a response is used to develop and validate the intelligent tools. The relevance test is applied to sort the strength of WOB dependency on the considered features. It was observed that the WOB has the highest linear correlation with the drilling depth and drill string rotational speed. After dividing the databank into the training and testing (4:1) parts, the proposed LM-ANN, GWO-ANN, and BBO-ANN ensembles are constructed. A sensitivity analysis is then carried out to find the most powerful structure of the models. Each model performs to reveal the relationship between the WOB and the mentioned independent factors. The performance of the models is finally evaluated by mean square error (MSE) and mean absolute error criteria. The results showed that both GWO and BBO algorithms effectively help the ANN to achieve a more accurate prediction of the WOB. Accordingly, the training MSEs decreased by 14.62% and 24.90%, respectively, by applying the GWO and BBO evolutionary algorithms. Meanwhile, these values were obtained as around 9.86% and 9.41% for the prediction error of the ANN in the testing phase. It was also deduced that the BBO performs more efficiently than the other technique. The effect of input variables dimension on the accuracy and training time of the BBO-ANN clarified that the most accurate WOB predictions are achieved when the model constructs with all four input variables instead of utilizing either three or two of them with the highest linear correlation. It was also observed that the training stage of the BBO-ANN model with four input variables needs a little more computational time than its training with either two or three variables. Finally, the accuracy of the BBO-ANN model for the WOB prediction has been compared with the multiple linear regression, support vector regression, adaptive neuro-fuzzy inference systems, and group method of data handling. The statistical accuracy analysis confirmed that the BBO-ANN is more accurate than the other checked techniques.

Biodegradable chitosan-graphene oxide as an affective green filler for improving of properties in epoxy nanocomposites

In this work, we investigated the effect of biodegradable Chitosan-encapsulated Graphene Oxide (CGO) on the morphology and properties of epoxy composites prepared using solution mixing with different filler loadings. The microstructures and properties of chitosan-GO and composites were studied using FTIR, XRD, SEM, TEM, tensile, impact, bending analysis, DMTA and TG tests. Microstructural observations confirmed that the CGO composition and its content in the matrix affected the distribution of fillers in the epoxy matrix. Mechanical and thermal tests indicated that the loading level of CGO and the ratio of chitosan to GO were the main factors that changed the strength of epoxy/CGOs composites. The tensile analysis confirmed that nanocomposites containing CGO exhibited a 65 % increase in elastic modulus due to the improved load transfer as a result of interfacial interactions between CGO and the matrix. DMTA analysis showed that the presence of CGO in the epoxy matrix increased T_g of the composite by ~30 °C. In the TGA test, although the introduction of CGO caused higher decomposition temperature of the CGO filled resins. CGO enhanced the final properties of epoxy-based nanocomposites as a result of the synergistic effect of chitosan and GO and the formation of 3-D CGO structures in the epoxy matrix.

Prediction of nanofluid flows’ optimum velocity in finned tube-in-tube heat exchangers using artificial neural network

The average flow velocity in heat exchangers is considered less often and thus needs further and detailed investigation because of its crucial influence on the overall thermal performance of the application. The use of nanofluids has similar influences to finned tube designs. Considering the rise in heat transfer and pressure drop, uncertainties in cost analyses with the uses of fins and nanoparticles, evaluation of optimum operating velocity of the fluids is necessary. On the contrary, there aren’t enough experimental, parametric, or numerical investigations present on this subject. The use of machine learning techniques to heat transfer applications to make optimization becomes popular recently. In this work, important factors of the process as tube number, cleanliness factor, and overall cost as output factors have been estimated by an artificial intelligence method using 339 data points. The influence of input factors of Reynolds number, thermal conductivity, specific heat, viscosity, and total fin surface efficiency on the outputs have been studied. Total tube number, cleanliness factor, and total cost analysis have been determined with deviations of −0.66%, 0.001%, and 0.12% as a result of the solution with 6 inputs, correspondingly.

Constructing an Intelligent Model Based on Support Vector Regression to Simulate the Solubility of Drugs in Polymeric Media

This study constructs a machine learning method to simultaneously analyze the thermodynamic behavior of many polymer–drug systems. The solubility temperature of Acetaminophen, Celecoxib, Chloramphenicol, D-Mannitol, Felodipine, Ibuprofen, Ibuprofen Sodium, Indomethacin, Itraconazole, Naproxen, Nifedipine, Paracetamol, Sulfadiazine, Sulfadimidine, Sulfamerazine, and Sulfathiazole in 1,3-bis[2-pyrrolidone-1-yl] butane, Polyvinyl Acetate, Polyvinylpyrrolidone (PVP), PVP K12, PVP K15, PVP K17, PVP K25, PVP/VA, PVP/VA 335, PVP/VA 535, PVP/VA 635, PVP/VA 735, Soluplus analyzes from a modeling perspective. The least-squares support vector regression (LS-SVR) designs to approximate the solubility temperature of drugs in polymers from polymer and drug types and drug loading in polymers. The structure of this machine learning model is well-tuned by conducting trial and error on the kernel type (i.e., Gaussian, polynomial, and linear) and methods used for adjusting the LS-SVR coefficients (i.e., leave-one-out and 10-fold cross-validation scenarios). Results of the sensitivity analysis showed that the Gaussian kernel and 10-fold cross-validation is the best candidate for developing an LS-SVR for the given task. The built model yielded results consistent with 278 experimental samples reported in the literature. Indeed, the mean absolute relative deviation percent of 8.35 and 7.25 is achieved in the training and testing stages, respectively. The performance on the largest available dataset confirms its applicability. Such a reliable tool is essential for monitoring polymer–drug systems’ stability and deliverability, especially for poorly soluble drugs in polymers, which can be further validated by adopting it to an actual implementation in the future.

Biodegradable polymeric materials for flexible and degradable electronics

Biodegradable electronics have great potential to reduce the environmental footprint of electronic devices and to avoid secondary removal of implantable health monitors and therapeutic electronics. Benefiting from the intensive innovation on biodegradable nanomaterials, current transient electronics can realize full components’ degradability. However, design of materials with tissue-comparable flexibility, desired dielectric properties, suitable biocompatibility and programmable biodegradability will always be a challenge to explore the subtle trade-offs between these parameters. In this review, we firstly discuss the general chemical structure and degradation behavior of polymeric biodegradable materials that have been widely studied for various applications. Then, specific properties of different degradable polymer materials such as biocompatibility, biodegradability, and flexibility were compared and evaluated for real-life applications. Complex biodegradable electronics and related strategies with enhanced functionality aimed for different components including substrates, insulators, conductors and semiconductors in complex biodegradable electronics are further researched and discussed. Finally, typical applications of biodegradable electronics in sensing, therapeutic drug delivery, energy storage and integrated electronic systems are highlighted. This paper critically reviews the significant progress made in the field and highlights the future prospects.

Estimating the Dissolution of Anticancer Drugs in Supercritical Carbon Dioxide with a Stacked Machine Learning Model

Synthesizing micro-/nano-sized pharmaceutical compounds with an appropriate size distribution is a method often followed to enhance drug delivery and reduce side effects. Supercritical CO₂ (carbon dioxide) is a well-known solvent utilized in the pharmaceutical synthesis process. Reliable knowledge of a drug’s solubility in supercritical CO₂ is necessary for feasible study, modeling, design, optimization, and control of such a process. Therefore, the current study constructs a stacked/ensemble model by combining three up-to-date machine learning tools (i.e., extra tree, gradient boosting, and random forest) to predict the solubility of twelve anticancer drugs in supercritical CO₂. An experimental databank comprising 311 phase equilibrium samples was gathered from the literature and applied to design the proposed stacked model. This model estimates the solubility of anticancer drugs in supercritical CO₂ as a function of solute and solvent properties and operating conditions. Several statistical indices, including average absolute relative deviation (AARD = 8.62%), mean absolute error (MAE = 2.86 × 10⁻⁶), relative absolute error (RAE = 2.42%), mean squared error (MSE = 1.26 × 10⁻¹⁰), and regression coefficient (R² = 0.99809) were used to validate the performance of the constructed model. The statistical, sensitivity, and trend analyses confirmed that the suggested stacked model demonstrates excellent performance for correlating and predicting the solubility of anticancer drugs in supercritical CO₂.

Polymeric Nanotechnologies for the Treatment of Periodontitis: A Chronological Review

Periodontitis is a chronic infectious and inflammatory disease of periodontal tissues estimated to affect 70 - 80 % of all adults. At the same time, periodontium, the site of periodontal pathologies, is an extraordinarily complex plexus of soft and hard tissues, the regeneration of which using even the most advanced forms of tissue engineering continues to be a challenge. Nanotechnologies, meanwhile, have provided exquisite tools for producing biomaterials and pharmaceutical formulations capable of elevating the efficacies of standard pharmacotherapies and surgical approaches to whole new levels. A bibliographic analysis provided here demonstrates a continuously increasing research output of studies on the use of nanotechnologies in the management of periodontal disease, even when they are normalized to the total output of studies on periodontitis. The great majority of biomaterials used to tackle periodontitis, including those that pioneered this interesting field, have been polymeric. In this article, a chronological review of polymeric nanotechnologies for the treatment of periodontitis is provided, focusing on the major conceptual innovations since the late 1990s, when the first nanostructures for the treatment of periodontal diseases were fabricated. In the opening sections, the etiology and pathogenesis of periodontitis and the anatomical and histological characteristics of the periodontium are being described, along with the general clinical manifestations of the disease and the standard means of its therapy. The most prospective chemistries in the design of polymers for these applications are also elaborated. It is concluded that the amount of innovation in this field is on the rise, despite the fact that most studies are focused on the refinement of already established paradigms in tissue engineering rather than on the development of revolutionary new concepts.

Do Artificial Neural Networks Always Provide High Prediction Performance? An Experimental Study on the Insufficiency of Artificial Neural Networks in Capacitance Prediction of the 6H-SiC/MEH-PPV/Al Diode

In this paper, we study a new model that represents the symmetric connection between capacitance–voltage and Schottky diode. This model has a symmetrical shape towards the horizontal direction. In recent times, works conducted on artificial neural network structure, which is one of the greatest actual artificial intelligence apparatuses used in various fields, stated that artificial neural networks are apparatuses that proposal very high forecast performance by the side of conventional structures. In the current investigation, an artificial neural network structure has been generated to guess the capacitance voltage productions of the Schottky diode with organic polymer edge, contingent on the frequency with a symmetrical shape. Of the dataset, 130 were grouped for training, 28 for validation, and 28 for testing. In order to evaluate the effect of the number of neurons on the prediction accuracy, three different models with different neuron numbers have been developed. This study, in which an artificial neural network model, although well-trained, could not predict the output values correctly, is a first in the literature. With this aspect, the study can be considered as a pioneering study that brings a novelty to the literature.

Artificial Neural Networking (ANN) Model for Drag Coefficient Optimization for Various Obstacles

For various obstacles in the path of a flowing liquid stream, an artificial neural networking (ANN) model is constructed to study the hydrodynamic force depending on the object. The multilayer perceptron (MLP), back propagation (BP), and feed-forward (FF) network models were employed to create the ANN model, which has a high prediction accuracy and a strong structure. To be more specific, circular-, octagon-, hexagon-, square-, and triangular-shaped cylinders are installed in a rectangular channel. The fluid is flowing from the left wall of the channel by following two velocity profiles explicitly linear velocity and parabolic velocity. The no-slip condition is maintained on the channel upper and bottom walls. The Neumann condition is applied to the outlet. The entire physical design is mathematically regulated using flow equations. The result is presented using the finite element approach, with the LBB-stable finite element pair and a hybrid meshing scheme. The drag coefficient values are calculated by doing line integration around installed obstructions for both linear and parabolic profiles. The values of the drag coefficient are predicted with high accuracy by developing an ANN model toward various obstacles.

Experimental and modeling analyses of COD removal from industrial wastewater using the TiO2-chitosan nanocomposites

In the present study, titanium oxide (TiO₂) nanoparticles, chitosan, and several nanocomposites containing different mass dosages of TiO₂ and chitosan have been applied as the adsorbent for COD removal from the industrial wastewater (Bouali Sina Petrochemical Company, Iran). The FESEM, XRD, and FTIR tests have been employed to characterize TiO₂ nanoparticles, chitosan, and fabricated nanocomposites. Then, the effect of adsorption parameters, including TiO₂–chitosan mass ratio (1:1, 1:2, and 2:1), adsorbent content (0.25–2.5 g), temperature (20–50 °C), pH (3–11), solution volume (100–500 mL), and contact time (30–180 min) on the COD reduction has also been monitored both experimentally and numerically. The Box–Behnken design of the experiment approves that TiO₂–chitosan (1:1), adsorbent content of 2.5 g, temperature = 20 °C, pH 7.4, solution volume of 100 mL, and contact time = 180 min are the condition that maximizes the COD removal (i.e., 94.5%). Moreover, the Redlich–Peterson and Pseudo-second order models are the best isotherm and kinetic scenarios to describe COD removal’s transient and equilibrium behaviors. The maximum monolayer COD adsorption capacity of the TiO₂–chitosan nanocomposite is 89.5 mg g⁻¹. The results revealed that the industrial wastewater COD is better to remove using the TiO₂–chitosan (1:1) at temperature = 20 °C.

Developing an accurate empirical correlation for predicting anti-cancer drugs’ dissolution in supercritical carbon dioxide

This study introduces a universal correlation based on the modified version of the Arrhenius equation to estimate the solubility of anti-cancer drugs in supercritical carbon dioxide (CO₂). A combination of an Arrhenius-shape term and a departure function was proposed to estimate the solubility of anti-cancer drugs in supercritical CO₂. This modified Arrhenius correlation predicts the solubility of anti-cancer drugs in supercritical CO₂ from pressure, temperature, and carbon dioxide density. The pre-exponential of the Arrhenius linearly relates to the temperature and carbon dioxide density, and its exponential term is an inverse function of pressure. Moreover, the departure function linearly correlates with the natural logarithm of the ratio of carbon dioxide density to the temperature. The reliability of the proposed correlation is validated using all literature data for solubility of anti-cancer drugs in supercritical CO₂. Furthermore, the predictive performance of the modified Arrhenius correlation is compared with ten available empirical correlations in the literature. Our developed correlation presents the absolute average relative deviation (AARD) of 9.54% for predicting 316 experimental measurements. On the other hand, the most accurate correlation in the literature presents the AARD = 14.90% over the same database. Indeed, 56.2% accuracy improvement in the solubility prediction of the anti-cancer drugs in supercritical CO₂ is the primary outcome of the current study.

A modeling approach for estimating hydrogen sulfide solubility in fifteen different imidazole-based ionic liquids

Absorption has always been an attractive process for removing hydrogen sulfide (H₂S). Posing unique properties and promising removal capacity, ionic liquids (ILs) are potential media for H₂S capture. Engineering design of such absorption process needs accurate measurements or reliable estimation of the H₂S solubility in ILs. Since experimental measurements are time-consuming and expensive, this study utilizes machine learning methods to monitor H₂S solubility in fifteen various ILs accurately. Six robust machine learning methods, including adaptive neuro-fuzzy inference system, least-squares support vector machine (LS-SVM), radial basis function, cascade, multilayer perceptron, and generalized regression neural networks, are implemented/compared. A vast experimental databank comprising 792 datasets was utilized. Temperature, pressure, acentric factor, critical pressure, and critical temperature of investigated ILs are the affecting parameters of our models. Sensitivity and statistical error analysis were utilized to assess the performance and accuracy of the proposed models. The calculated solubility data and the derived models were validated using seven statistical criteria. The obtained results showed that the LS-SVM accurately predicts H₂S solubility in ILs and possesses R², RMSE, MSE, RRSE, RAE, MAE, and AARD of 0.99798, 0.01079, 0.00012, 6.35%, 4.35%, 0.0060, and 4.03, respectively. It was found that the H₂S solubility adversely relates to the temperature and directly depends on the pressure. Furthermore, the combination of OMIM⁺ and Tf₂N^-, i.e., [OMIM][Tf₂N] ionic liquid, is the best choice for H₂S capture among the investigated absorbents. The H₂S solubility in this ionic liquid can reach more than 0.8 in terms of mole fraction.