A data-driven machine learning approach for the 3D printing process optimisation

4D printing: Pragmatic progression in biofabrication

BackgroundRice is one of the major food crops in the world, and the monitoring of its growth condition is of great significance for guaranteeing food security and promoting sustainable agricultural development. Leaf area index (LAI) is a key indicator for assessing the growth condition and yield potential of rice, and the traditional methods for obtaining LAI have problems such as low efficiency and large error. With the development of remote sensing technology, unmanned aerial multispectral remote sensing combined with deep learning technology provides a new way for efficient and accurate estimation of LAI in rice.ResultsIn this study, a multispectral camera mounted on a UAV was utilized to acquire rice canopy image data, and rice LAI was uniformly estimated over multiple periods by the multilayer perceptron (MLP) and convolutional neural network (CNN) models in deep learning. The results showed that the CNN model based on five-band reflectance images (490, 550, 670, 720, and 850 nm) as input after feature screening exhibited high estimation accuracy at different growth stages. Compared with the traditional MLP model with multiple vegetation indices as inputs, the CNN model could better process the original multispectral image data, effectively avoiding the problem of vegetation index saturation, and improving the accuracies by 4.89, 5.76, 10.96, 1.84 and 6.01% in the rice tillering, jointing, booting, and heading periods, respectively, and the overall accuracy was improved by 6.01%. Moreover, the model accuracies (MLP and CNN) before and after variable screening showed noticeable changes. Conducting variable screening contributed to a substantial improvement in the accuracy of rice LAI estimation.ConclusionsUAV multispectral remote sensing combined with CNN technology provides an efficient and accurate method for the unified multi-period estimation of rice LAI. Moreover, the generalization ability and adaptability of the model were further improved by rational variable screening and data enhancement techniques. This study can provide a technical support for precision agriculture and a more accurate solution for rice growth monitoring. More feature extraction and variable screening methods can be further explored in future studies by optimizing the model structure to improve the accuracy and stability of the model.

Over the past few decades, threedimensional (3D) printing has greatly aided in the creation of patient-specific prosthesis, drug administration, tissue and organ manufacturing, and surgery planning. Since the US established its Precision Medicine Initiative in 2015, there has been a surge in interest in personalized healthcare. The term "personalized medicine" basically describes patient-specific medical treatment. However, the biomedical materials used in 3D printing are frequently stable and incapable of responding to or being intelligently and adaptively adapted to the inside environment of the body. A disparity between the printed section and the target portions may result from ex-situ manufacturing of these materials, which involves printing on a flat substrate before releasing it onto the target surface. One technique that could be applied to offer individualized care is 3D printing. The components used in the development of four-dimensional (4D) printing can be adjusted through stimulation. Recently, a number of academics have begun examining a novel field that combines 3D and 4D printing with medications. Many of these problems are resolved by the development of 4D printing, which also bodes well for thebiomedical sector going forward. Pre-programmed smart materials can be utilized in 4D printing to produce structures that respond interactively to external stimuli

Accurate and efficient prediction of the temperature field in press-pack IGBTs (PPIs) is essential for the reliable operation of flexible high-voltage direct current (HVDC) systems. This paper proposes a data-driven thermal modeling approach based on the Deep Operator Network (DeepONet) to enable fast and accurate estimation of temperature distributions in PPIs. A high-fidelity dataset is generated via finite element method (FEM) simulations under diverse operating conditions, and DeepONet is trained to learn the nonlinear mapping from operating parameters and spatial coordinates to the temperature field. Experimental results demonstrate that the proposed model achieves high predictive accuracy, with the temperature distribution error remaining below 2 °C across diverse operating conditions. Furthermore, the inference time per sample is less than 10 ms, significantly improving computational efficiency. Comparative experiments with multilayer perceptron (MLP) and convolutional neural network (CNN) models further reveal that DeepONet exhibits superior convergence behavior and prediction accuracy. The proposed approach offers strong potential for real-time monitoring and digital twin applications.

Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation

3D Printing, sometimes referred to as additive manufacturing, has made the concept of personalized medicine a reality. The primary objective of 3D and 4D printing is to produce intricate, customized pharmaceuticals at a reasonable cost. With improvements in materials, resolution, and speed, 3D printing technology is quickly developing. It includes faster construction, cost efficiency through reduced waste, design flexibility for complex structures, and sustainability through optimized material usage. An extensive literature survey was done on 3D and 4D printing of pharmaceuticals using PubMed, Elsevier, ScienceDirect, and Springer. The results were then filtered based on the titles, abstracts, and accessibility of the complete texts. The search engine Google Scholar was accessed for literature data mining. From the data mining, it was found that from the year 2009 to 2024 the number of research publications surged more than 200 times on the current topic. Even though 3-D and 4-D printing technologies have advanced significantly in a short amount of time, the most often used ones are still stereolithography, nozzle-based deposition, inkjet, and selective laser sintering. Their use has been modified for the production of nanoparticles, polypills, tablets, and implants, etc. Pharma's aspirations for tailored medications are being revolutionized by 3D printing, but cost, flexibility, and bioequivalence still need to be investigated. The present review offers a thorough analysis of various 3D and 4D printing methods and emphasizes the major advantages and disadvantages and major key challenges of 3D and 4D printing related to pharmaceuticals. Compared to 3D Printing, 4D printing offers better quality, efficacy, and functionality.

The existing 3D printing methods exhibit certain fabrication-dependent limitations for printing curved constructs that are relevant for many tissues. Four-dimensional (4D) printing is an emerging technology that is expected to revolutionize the field of tissue engineering and regenerative medicine (TERM). 4D printing is based on 3D printing, featuring the introduction of time as the fourth dimension, in which there is a transition from a 3D printed scaffold to a new, distinct, and stable state, upon the application of one or more stimuli. Here, we present an overview of the current developments of the 4D printing technology for TERM, with a focus on approaches to achieve temporal changes of the shape of the printed constructs that would enable biofabrication of highly complex structures. To this aim, the printing methods, types of stimuli, shape-shifting mechanisms, and cell-incorporation strategies are critically reviewed. Furthermore, the challenges of this very recent biofabrication technology as well as the future research directions are discussed. Our findings show that the most common printing methods so far are stereolithography (SLA) and extrusion bioprinting, followed by fused deposition modelling, while the shape-shifting mechanisms used for TERM applications are shape-memory and differential swelling for 4D printing and 4D bioprinting, respectively. For shape-memory mechanism, there is a high prevalence of synthetic materials, such as polylactic acid (PLA), poly(glycerol dodecanoate) acrylate (PGDA), or polyurethanes. On the other hand, different acrylate combinations of alginate, hyaluronan, or gelatin have been used for differential swelling-based 4D transformations. TERM applications include bone, vascular, and cardiac tissues as the main target of the 4D (bio)printing technology. The field has great potential for further development by considering the combination of multiple stimuli, the use of a wider range of 4D techniques, and the implementation of computational-assisted strategies.

Redesigning deep neural networks: Bridging game theory and statistical physics.

Recent 3D and 4D intelligent printing technologies: A comparative review and future perspective

Three-dimensional (3D) bioprinting is a versatile technique for biomedical applications, and includes organ printing, 3D disease model development, and drug delivery. The bioprintable materials combined with live cells have been utilized as bioinks in 3D bioprinter to fabricate versatile 3D printed structures. The 3D structures developed with smart and responsive materials can change their dimension, a technique similar to self-assembly, unfolding a new branch termed as four-dimensional (4D) printing. This manuscript reviews the details of various bioprintable materials and 3D printers, the application of 3D printing in biomedicine, smart materials, and stimulations for 4D printing. Further, this article also summarizes the regulatory issues and the limitations involved with the bioprinting. The advancements in 3D and 4D printing technology have significantly contributed to the medical field, and adequate research and amalgamation of engineering and science ideas will strengthen the application of this technology and bring solution for the existing problems.Graphical abstract

Iraq’s arid climate faces intricate challenges due to volatile precipitation patterns and limited water resources. Prediction of precipitation environmental isotopes using neural network techniques represents optimistic way in water science. This technique has demonstrated effectiveness in interpreting intricate data and producing significant insights on the water cycle. The present study aimed to develop the neural network model by using daily precipitation samples gathered from different sites across Iraq from 2010 to 2024. The input variables used for the ANN models include measurements of stable isotope in precipitation, specifically δ¹8O, δ2H and deuterium excess (d-excess). The Multi-Layer Perceptron (MLP) and Radial Basis Neural Network (RBNN) models are employed for comparison with observed values to assess model accuracy and robustness. Additionally, The performance of the applied models is evaluated using statistical metrics such as the coefficient of determination (R2), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) statistics. The results of the study demonstrate that the (RBNN) model outperforms the (MLP) in predictive accuracy and overall performance. Reduced error metrics (RMSE and MAE) and stronger explanatory power (R2) demonstrate the higher accuracy of RBNN, particularly when modelling data with complex spatial and temporal patterns. This demonstrates that, particularly in dynamic climates and environmental systems.

From the previous couple of decades most of the research is goes on the sunshine weight material on different applications like marine, aerospace, defense and industry. In this paper, 3D printing process is considered to manufacture jet engine with PLA (poly lactic acid) material. This 3D printing process, now a day’s mostly using in various applications like medical, aerospace, defense etc., due to its quality of parts making with desired specifications without any errors, generally this is using for making prototype parts. 3D printing is mostly using because, it can manufacture complex parts, due to this aerospace is showing more interest. How the 3D printed components are affected with changes in 3D printed parameters such as, Raster Angle, Layer Thickness, Extrusion Temperature, Infill Density and different color PLA material. The paper presents the design and sizing of the jet engine components, like engine inlet, compressor impeller, compressor diffuser, turbine blades, combustion chamber, and its zones as well as the exit nozzle. Improvements in reliability, safety, and operational efficiency of aero engines can be brought in a cost-effective way using advanced control concepts. Keywords: 3D printing, Infill Density, PLA, Printing parameters, Turbojet Engine

Experimental analysis and low-damage machining strategy for composite ultrasonic vibration-assisted grinding of silicon carbide based on DA-MLP-NSGA-II algorithm

Electromagnetic 2D scanning micromirror fabricated with 3D printed polymer parts for LiDAR applications

Alumina (Al2O3) suspensions were prepared for the effective application in the stereolithography three-dimensional (3D) printing process. Thermal treatment of -Al2O3 could optimize the ceramic slurries to meet the requirements of stereolithography 3D printing technique. In this study, alumina powders were modified by thermal treatment at different temperatures for the preparation of well dispersed ceramic slurries. The influence of thermal treatment on the raw powder, printed green bodies, and sintered alumina parts was systematically studied. Thermogravimetric analysis indicated that the decomposition temperature of photosensitive resin was between 390C and 460C. The alumina powders became denser, the crystal grains changed from round sphere-shaped to long cylinder-shaped, and the pores disappeared with increasing thermal treatment temperature. After the 3D printing process, the microstructure of green bodies and sintered alumina ceramics exhibited significant variation. Decomposition and removal of photosensitive resin led to higher water absorption, higher porosity, and lower bulk density of alumina ceramics compared to the printed green bodies. The scattering phenomenon in ceramic slurries and layer-by-layer forming characteristic determined the different shrinkage in three directions. Experimental results suggested that 1500C was considered as the optimal thermal treatment temperature, with the water absorption of 107%, open porosity of 91%, and bulk density of 0.67g·cm3. The higher thermal treatment temperatures would cause alumina powders to clump and agglomerate.