Manufacturing Parameters Research Articles

Review of Electrical Steels with their Properties and Recent Trends for Improvement

Objectives: This review study provides a thorough analysis of the magnetic behavior and characteristics of electrical steels, including established and novel materials (3%wt Silicon). Methods: We investigate how composition, microstructure, and processing methods affect the magnetic performance of these steels as well as the basic principles guiding their behavior. Thermomechanical processing can be observed for its impact on the material’s microstructure and magnetic properties. This review discusses testing over samples for conventional processes for different % of cold worked or strain hardening and annealing at higher temperatures i.e., 1200°C. For uncertainties regarding the impact of impurities or inclusions on their magnetic properties, the study was carried out to know the effect of cerium addition on the material’s magnetic properties of the material. Findings: It was observed that rolling temperature has significant effect over magnetic properties of the material. A notable improvement in the magnetic permeability of the material and its critical performance metric for soft magnetic materials is indicated by the increase in “Gamma max”. Similarly, the effects of compressive stresses, doping effect, grain size, annealing, and other manufacturing processes were studied, and observed their impact on magnetic properties. This review discusses the literature on future scope with the latest trends. This helps clarify the trade-offs associated with maximizing electrical steels for certain uses. Novelty: This study presents a novel approach towards electrical steel and its magnetic properties by incorporating different alloying elements and optimizing rolling & annealing parameters. A key innovation is the application of machine learning and neural network to predict and optimize material behavior, core loss and provide methods to improve magnetic properties of electrical steels. Significance: Electrical steels are crucial in transformers and electric motors, enhancing efficiency by minimizing energy losses and improving magnetic performance. This can be achieved by changing manufacturing parameters and operating conditions with the help of latest trends. Keywords: Electrical steel, Magnetic properties, Machine learning, Composition, Microstructure, Core loss

The Influence of the Plasma Electrolytic Oxidation Parameters of the Mg-AZ31B Alloy on the Micromechanical and Sclerometric Properties of Oxide Coatings

This manuscript presents the influence of manufacturing process parameters (peak current density, frequency, process time) on the micromechanical and sclerometric properties of oxide coatings. These parameters were selected based on Hartley’s experimental design, considering three variables at three levels. The coatings were produced on the AZ31B magnesium alloy using the plasma electrolytic oxidation (PEO) method. A trapezoidal voltage waveform and an alkaline, two-component electrolyte were used during the process. The micromechanical and sclerometric properties were assessed by measuring the hardness (HIT) and Young’s modulus (EIT) and determining three critical loads: Lc1 (the critical load at which the first coating damage occurred—Hertz tensile cracks within the scratch), Lc2 (the critical load causing the first cohesive damage to the coating), and Lc3 (the load at which the coating was completely destroyed). Scratch tests were supplemented with profilographometric measurements, which were used to generate isometric images. To identify the relationship between micromechanical and sclerometric properties and the manufacturing parameters, statistical analysis was performed. Research has demonstrated that the plasma electrolytic oxidation (PEO) process improves the micromechanical and adhesive properties of oxide coatings on the AZ31B magnesium alloy. The key process parameters, including peak current density, frequency, and duration, are crucial in determining these enhanced properties.

Model‐Driven Manufacturing of High‐Energy‐Density Batteries: A Review

AbstractThe rapid advancement in energy storage technologies, particularly high‐energy density batteries, is pivotal for diverse applications ranging from portable electronics to electric vehicles and grid storage. This review paper provides a comprehensive analysis of the recent progress in model‐driven manufacturing approaches for high‐energy‐density batteries, highlighting the integration of computational models and simulations with experimental manufacturing processes to optimize performance, reliability, safety, and cost‐effectiveness. We systematically examine various modeling techniques, including electrochemical, thermal, and mechanical models, and their roles in elucidating the complex interplay of materials, design, and manufacturing parameters. The review also discusses the challenges and opportunities in scaling up these model‐driven approaches, addressing key issues such as model validation, parameter sensitivity, and the integration of machine learning and artificial intelligence for predictive modeling, process optimization, and quality assurance. By synthesizing current research findings and industry practices, this paper aims to outline a roadmap for future developments in model‐driven manufacturing of high‐energy density batteries, emphasizing the need for interdisciplinary collaboration and innovation to meet the increasing demands for energy storage solutions.

Identifying and optimizing critical process parameters for large-scale manufacturing of iPSC derived insulin-producing β-cells

BackgroundType 1 diabetes, an autoimmune disorder leading to the destruction of pancreatic β-cells, requires lifelong insulin therapy. Islet transplantation offers a promising solution but faces challenges such as limited availability and the need for immunosuppression. Induced pluripotent stem cells (iPSCs) provide a potential alternative source of functional β-cells and have the capability for large-scale production. However, current differentiation protocols, predominantly conducted in hybrid or 2D settings, lack scalability and optimal conditions for suspension culture.MethodsWe examined a range of bioreactor scaleup process parameters and quality target product profiles that might affect the differentiation process. This investigation was conducted using an optimized High Dimensional Design of Experiments (HD-DoE) protocol designed for scalability and implemented in 0.5L (PBS-0.5 Mini) vertical wheel bioreactors.ResultsA three stage suspension manufacturing process is developed, transitioning from adherent to suspension culture, with TB2 media supporting iPSC growth during scaling. Stage-wise optimization approaches and extended differentiation times are used to enhance marker expression and maturation of iPSC-derived islet-like clusters. Continuous bioreactor runs were used to study nutrient and growth limitations and impact on differentiation. The continuous bioreactors were compared to a Control media change bioreactor showing metabolic shifts and a more β-cell-like differentiation profile. Cryopreserved aggregates harvested from the runs were recovered and showed maintenance of viability and insulin secretion capacity post-recovery, indicating their potential for storage and future transplantation therapies.ConclusionThis study demonstrated that stage time increase and limited media replenishing with lactate accumulation can increase the differentiation capacity of insulin producing cells cultured in a large-scale suspension environment.

Assessing the Manufacturability and Critical Quality Attribute Profiles of Anti-IL-8 Immunoglobulin G Mutant Variants.

Early-phase manufacturability assessment of high-concentration therapeutic monoclonal antibodies (mAbs) involves screening of process-related risks impacting their translation into the clinic. Manufacturing a mAb at scale relies on cost-effective and robust approaches to derisk manufacturability parameters, such as viscosity, conformational stability, aggregation, and process-related impurities. Using a panel of model anti-IL-8 IgG1 mutants, we investigate upstream and downstream processability, phase behavior, and process-related impurities. We correlate trends in the biophysical properties of mAbs with their cell growth, expression, filtration flux, solubility, and post-translational modifications. We find significant trends in increased relative free light chain expression with heavy chain mutants and detect a requirement for adjusted operation pH for cation exchange polishing steps with charge-altering variants. Moreover, trends between phase stability and high-concentration viscosity were observed. We also investigated unique correlations between increased glycosylation and biophysical behavior. Further in-depth analysis and modeling are required to elucidate the impact of the mAb sequence on the metabolism of the expression system, solubility limits, and alternative gelation models as future directions.

A Hybrid Modelling Approach Coupling Physics-based Simulation and Deep Learning for Battery Electrode Manufacturing Simulations

Lithium-ion battery (LIB) performance is significantly influenced by its manufacturing process. Manufacturing of an optimized electrode can incur high production costs such as high energy consumption, high scrap rates and emissions. This is due to the process that consists of a series of manufacturing steps presenting a complex interrelationship, thus limiting the understanding of performance as a function of manufacturing parameters. While several empirical and computational methods are employed for optimization, they are demanding in terms of resources such as materials or computational effort. By leveraging Deep Learning (DL), we can enhance our understanding of the complex manufacturing processes and accelerate its optimization. We propose a data-driven supervised DL methodology to complement physics-based LIB cathode manufacturing simulations. The trained DL-based predictive model integrates well into the manufacturing simulation framework to forecast cathode slurry microstructures. The DL model demonstrates robust predictive performance for LIB NMC-111 and LiFePO4–based slurries and slurries for a solid-state battery NMC-622/argyrodite composite electrode preparation. While the current work is focused on the cathode slurry process, the proposed methodology has potential for application to drying and calendering steps. This approach will be helpful in streamlining lab-scale electrode manufacturing, and reducing errors, waste and resource consumption.

Track trajectory, molten pool and defect characterization in NiTi single-track selective laser melting (SLM) experiments

In order to explore the law of selective laser melting (SLM) forming of Nitinol alloy, and obtain high quality additive manufacturing parameters of Nitinol alloy, a series of single-track SLM experiments on Nitinol alloy were conducted under different combined parameters of laser power and scanning speed. The effects of laser power, scanning speed and linear energy density on track forming, molten pool evolution and pore formation were systematically discussed by characterizing the track trajectory, molten pool morphology, dimensions and defects of the molten pool, and the ideal process parameters were obtained. The experimental results revealed that the average track width and width uniformity decreased with the increase of the scanning speed, the spheroidization phenomenon and height fluctuation became more pronounced, and the phenomena of necking, subsection and interruption increased significantly at the fixed laser power. Under the fixed scanning speed, the width, height and width uniformity of the molten track gradually increased with the increase of the laser power, and the phenomena of spheroidization, subsection and interruption gradually reduced. Moreover, the upper zone of the molten pool is shaped like an inverted bowl, and the lower zone is mainly divided into five categories, which are lack of fusion, shallow bowl shape, deep bowl shape, keyhole shape and deeper keyhole shape under different process parameters. The defects of the molten pool mainly include lack of fusion and trapped gas. An ideal molten pool without defects can be obtained under the parameter conditions of 100-150W laser power and 100-200mm/s spanning speed.

Deformation Evolution and Perceptual Prediction for Additive Manufacturing of Lightweight Composite Driven by Hybrid Digital Twins

This paper proposes a deformation evolution and perceptual prediction methodology for additive manufacturing of lightweight composite driven by hybrid digital twins (HDT). In order to improve manufacturing quality of irregular lightweight composite through boosting conceptual design in aeronautic and aerospace engineering, the HDT meaning hybridization of physical and digital domains, including deformation and energy efficiency can be built, where the essential parameters can be perceptually predicted in advance, by virtue of the fusion of physical sensors and digital information. The long short term memory (LSTM) can be employed to void vanishing gradient problem and improve predicting precision via Recurrent Neural Networks, thereby laying a foundation for the HDT. The diverse manufacturing requirements of different regions are integrated into the parameters designing phase by attaching region weights confirmed via empiricism and in-service simulation. The effects of slicing strategy and external support structures on manufacturing quality are considered from the perspective of improving dimensional accuracy. The manufacturing efficiency and comprehensive costs are accounted as consideration factors, which are perceptually predicted via LSTM. The designed manufacturing parameters through HDT were virtually examined by evaluating the deformation and equivalent stress distributions of fabricated lightweight component with composite material through AM process simulation. The physical experiments were conducted to verify the HDT-based pre-designing and optimization method of manufacturing parameters via fused deposition modeling (FDM). The energy consumption of actual manufacturing process was measured via digital power meter and applied to evaluate accuracy of perceptual prediction outcomes. The dimensional accuracy and distortion distribution of the manufactured lightweight prototype made with composite material were measured through the coordinate measuring machine (CMM) and 3D optical scanner. The proposed method demonstrates effectiveness in improving manufacturing quality and accurately predicting energy consumption, which have been verified with a three-way solenoid valve element, in which the maximum deformation was reduced by 39.78% and the mean absolute percentage error for perceptual prediction was 3.76%.

Predicting the fatigue life of additively manufactured AlSi10Mg alloy using a physics-informed neural network incorporating continuous damage mechanics

The material characteristics of additively manufactured AlSi10Mg alloy, including the random distribution of process-induced micro defects, microstructual anisotropy, and grain morphologies with complex diversity, poses a significant challenge in accurately predicting its fatigue life, limiting its application in the aircraft field. This work herein introduces a novel approach incorporating a physics-informed neural network (PINN), in which an artificial neural network (ANN) is embedded with a damage mechanics model (CDM) and the critical process parameters of laser powder bed fusion (L-PBF) additive manufacturing. The partial differential equations of the updated CDM model are introduced into the training procedures of the PINN to building a loss function, effectively “teaching” the PINN to learn the physical knowledge. A comparison of the fatigue life prediction results of ANN and the proposed PINN models shows that the PINN model outperforms its counterparts with a 38.71% higher prediction accuracy. The effects of L-PBF process parameters on the fatigue life of as-built AlSi10Mg is examined using both ANN and PINN, proving the better predictive performance and data-physics consistency of the PINN model. The scheme of this work can inform the efficient prediction of fatigue life of additively manufactured alloys and also reverse prediction or fast finding of optimized process parameters for additive manufacturing.

AI-Driven Optimization of Roll Forming Parameters for Defect-Free Manufacturing in Advanced High-Strength Steels

This paper presents an innovative and novel AI-driven approach to optimizing the roll forming process for advanced high-strength steels (AHSS), which are prone to defects like wrinkling, springback, and cracking due to their high strength and low formability. Traditional trial-and-error methods for parameter selection are time-consuming and inefficient. The proposed framework integrates machine learning models, such as artificial neural networks (ANN), support vector machines (SVM), and random forests, with genetic algorithms for multi-objective optimization. The novelty of this paper lies in the real-time monitoring and adjustment capabilities, allowing for dynamic process control that adapts to variations in material properties. This approach not only predicts and reduces defects by 30%, but also decreases parameter selection time by 50%, significantly improving production efficiency. A case study on an AHSS automotive component demonstrates the effectiveness of this system in achieving defect-free manufacturing, reducing equipment costs, and enhancing throughput. The AI-based methodology represents a paradigm shift in roll forming, offering a more flexible, scalable, and cost-efficient solution for modern manufacturing. Future work will explore integration with finite element analysis (FEA) and reinforcement learning for further improvements in process control.

Valorization and optimization of Prosopis africana pod and cowpea husk wastes for densified hybrid briquette production

Biomass is an eco-friendly alternative sustainable renewable energy source when agricultural wastes are effectively utilized. It has become critical to assess the suitability of biofuel briquettes as an energy source for cooking, electricity, and fuel for heating. Certainly, the integration of energy sources into energy policies is warranted, considering the huge potential to provide energy for rural communities and the peri-urban poor with alternative fuel. This research describes a technique to generate densified hybrid solid biofuels from biomass waste and valorize them. Prosopis africana pod (PAP) and cowpea husk (CPH) wastes were combined to create high-energy-density fuel briquettes. The experiment involves improving briquette manufacturing parameters using response surface methodology to better understand the impacts of particle sizes, composition, binder concentrations, and densification pressures on briquette performance. The optimal conditions were particle size 150 µm, 50% PAP, 10% binder concentration, and densification pressure 103.42 kN/m2. The optimum values for burning rate, ignition time, specific fuel consumption, and heating value were 0.35 g/min, 2.75 min, 0.186 g/L, and 22.98 MJ/kg, respectively. The findings show the potential for using PAP and CPH biomass waste to produce environmentally friendly energy sources. This increases the potential agro-waste feedstocks for bioenergy in developing countries, reducing energy insecurity while promoting waste management, renewable energy generation, and environmental sustainability.

Offset-stoichiometric reflowable composite bonding method with adhesive for mitigating strict faying surface tolerances

Inherent susceptibility of adhesive bonds to miniscule quantities of contamination can cause undetectable weakened bonds. For this reason, the Federal Aviation Administration (FAA) places strict regulations on adhesively bonded joints in primary aircraft structures. To meet certification requirements aircraft manufactures resort to redundant load paths in the form of fasteners which inherently add weight to the structure and increase manufacturing time. In prior work, a secondary bonding technique called AERoBOND was developed, which utilized off-stoichiometric epoxy-matrix resins to facilitate reflow and diffusion of the resin within the joint interface during a secondary bonding/cure process, thus achieving a bond similar to a co-cured joint. However, the AERoBOND process required tight spatial tolerances between the two parts being joined. This study examined the utilization of conventional adhesive with the AERoBOND method to act as a filler in the joint line, effectively reducing the need for tight tolerances on the joining parts and serving as a flexible alternative for existing manufacturing processes. Ultrasonic inspection, optical microscopy, and ASTM International standard tests were performed to analyze the joints for defects and to quantify the mode-I and mode-II interlaminar fracture toughness and short beam strength of the proposed methodology with varying manufacturing parameters. The comprehensive results indicate that the AERoBOND+ method with and without surface preparation performs comparably to co-cured and conventional, adhesively bonded joints when secondary cured in an autoclave with 791 kPa of pressure. As an example, the AERoBOND+ panel without surface preparation bonded with 791 kPa of pressure (referred to as AB+3 throughout paper) had a mode-I fracture toughness (GIc) of 0.643 kJ/m2 and a mode-II fracture toughness (GIIc) of 4.000 kJ/m2 in the non-precracked condition and 4.218 kJ/m2 in the precracked condition at the adhesive-to-prepreg interface. These results were 96 %, 142 %, and 217 %, respectively, of a co-cured baseline panel (referred to as C1 throughout paper).

Manufacturing and aging behavior of CuCr1Zr powder: Analysis and modelling of close-coupled gas atomization of CuCr1Zr and its impact on the melt beam disintegration and analysis powder oxidation kinetics

Powder bed-based additive manufacturing methods represent an increasingly vital role in industrial applications. Specifically, there has been considerable focus on highly reflective metals, such as CuCr1Zr, in recent years. However, current research primarily revolves around developing appropriate manufacturing parameters e.g. laser powder bed fusion (PBF/LB-M) and assessing the corresponding mechanical and electrical properties of CuCr1Zr. The impact of manufacturing routines and oxidation behavior of CuCr1Zr powder are seldom discussed in additive manufacturing. Therefore, the present study addresses the analysis of powder production and the oxidation behavior of CuCr1Zr powder via close-coupled gas atomization to analyze the disintegration of a CuCr1Zr melting jet during gas atomization of CuCr1Zr by using a high-speed camera. Critical conditions for secondary disintegration were calculated as a function of the initial gas pressure. Additionally, calorimetric measurements and isothermal oxidation experiments were conducted to quantify oxide formation and growth. According to the results, initial oxide formation occurs after 42 days with CuCr1Zr powder at room temperature in a nitrogen atmosphere. Subsequently, oxide growth follows a logarithmic law, associated with the formation and conversion of Cu2O to CuO.

Experimental investigation of FDM manufacturing of 316 l stainless steel

Continuous research in the field of metal additive manufacturing has led to the need for constant improvement of manufacturing parameters especially in the case of FDM (Fused Deposition Modeling) manufacturing. In recent years, the main directions outlined for productivity and quality improvement were related to higher printing speed and the use of ironing-type processes. This article aims to study the manufacturing parameters of the dimensional accuracy and surface quality of FDM-manufactured 316L stainless steel. The degree of novelty is given by the application of the ironing process for the green part. A full factorial 33 experimental design was designed for this study, in which the factors studied were ironing angle, ironing speed, and layer spacing during ironing. The dimensional accuracy and surface roughness were analyzed by means of deviation measurement from CAD to the green part and final part after the sintering process. Using the design of experiments offers the possibility of applying the analysis of variance (ANOVA) which provides information about the degree of influence of each of the studied factors. The results obtained for the dimensional accuracy showed that the ironing direction had the biggest influence on the Z-axis shrinkage. Overall, approximately 6% shrinkage in the Z and Y directions was obtained while in the X directions, the shrinkage percentage was around 20%. Surface roughness showed an improvement with higher ironing speeds for the green part while for the sintered part the most significant factor was ironing spacing.

Analysis of the interactions between laser and arc due to different geometric arrangements and laser parameters in the additive manufacturing of Ti-6Al-4V

Additive manufacturing based on arc welding (=DED-Arc) has already established itself in the world of additive manufacturing. Recent process optimizations show the increased use in a hybrid process by irradiating an additional laser beam into the active arc zone. Numerous publications can be found in the literature for steel, aluminum, or bronze, in which, among other things, a strength-enhancing effect or an improved wall surface during this hybrid process is reported. The way in which the laser beam impacts the arc, at what distance, at what angle and with what spot size or focusing appears to be random in the publications and is always chosen differently in the literature. In order to close this knowledge gap, a corresponding holder for a DED-Arc torch and laser optic is developed, which allows these geometric factors to be systematically changed and also enables the titanium alloy Ti-6Al-4V to be processed in a hybrid process. By welding individual tracks and walls with different angles, distances and spot sizes of the two energy sources, a fundamental understanding of the laser-arc hybrid process is created. The results are analyzed using a high-speed camera and evaluated on the basis of surface measurements, micrographs, and power source values. This showed that the distance between the laser and the arc has the greatest effect on the additive process stability and the arc power sources values. In the range of 2–6 mm, there are, in some cases, strong fluctuations in the wire deposition and the arc voltage, so that this range should be avoided. It also showed that a wider spot sizes range of 360–600 μm can be used, whereby different ranges are recommended depending on the target size of uniform wall height or thickness. For the laser incidence angle, the most uniform walls across all tests are achieved at 20°. As the angle of incidence becomes flatter, the walls become more irregular, although there is no linear relationship or areas that should be avoided at all.

Determination of Composition and Density of Sandwich Composites Produced by Vacuum Lamination

Purpose: This study aims to characterize the composition and density of bulkheads manufactured by vacuum lamination. Theoretical Framework: Sandwich composites are widely used due to their high specific strength, a critical factor in reducing energy consumption associated with weight, especially when manufactured through vacuum lamination. However, the final composition and density of these materials are important factors for decision-making in the project, but they are often not known beforehand. Method: Characterization was carried out on five samples taken from different regions of the laminated plates. The composition was determined by varying the area density, and the final composite density was obtained based on the observed composition and the density of the components. Results and conclusion: The results indicated a density of 0.21 g/cm³ for the laminated material. The analysis allowed determining the mass and volumetric fractions of the components, demonstrating the consistency of the manufacturing parameters and their adequacy to the project's requirements. Research Implications: This study contributes to improving the vacuum lamination process by providing a methodology for characterizing the density of sandwich composites, which can be applied in various projects, as well as providing reference values. Originality/Value: The research offers an innovative approach by exploring the variation of area density to characterize the composition of composites, contributing to the optimization of the sandwich composite manufacturing process, such as the vessel “Gigante Vermelho” used in the Desafio Solar Brasil 2022.

Frequency-Controlled Fluidic Oscillators for Soft Robots.

Electronic-free controls have recently emerged as one of the main topics in soft robotics. However, electronic-free fluidic circuits still lack controllability and reconfigurability to achieve different functions. Here, reconfigurable pneumatic valves that widen the design space of fluidic circuits are presented. The significance of two parameters on the valve's operation: a pre-defined manufacturing parameter that sets the initial operational range of the valve, and a second, on-the-fly modifiable geometric parameter that shifts the behavior of the valve during operation is shown. It is demonstrated that equipping the valve with these reconfigurable features enables the tuning of fluidic oscillatory circuits as illustrated by two examples: a frequency-controlled relaxation oscillator and a reconfigurable ring oscillator. The relaxation oscillator is employed to control the actuation frequency of a soft hopper, which is able to achieve 80 to 125 hops min-1 and a hopping speed ranging from ≈1 to ≈1.185 BL s-1. Additionally, the reconfigurable ring oscillator is used to demonstrate how each output frequency can be controlled independently, via a soft robotic crawler that can navigate in three directions, and a volume-controlled fluidic pump able to achieve mixing of solutions in environments where electronic components cannotoperate.

Physics-Informed Neural ODE with Heterogeneous control Inputs (PINOHI) for quality prediction of composite adhesive joints

Composite materials have long been used in various industries due to their superior properties such as high strength, light weight and corrosive resistance. Bonded composite joints are finding increasing applications, as they provide extensive structural benefits and design flexibility. On the other hand, the failure mechanism of composite adhesive joints is not fully understood. A model that bridges manufacturing parameters and final quality measures is highly desired for the design and optimization of the manufacturing process of composite adhesive joints. In this study, a novel framework of Physics-Informed Neural Ordinary Differential Equation (ODE) with Heterogeneous Control Input (PINOHI) is proposed, which links the heterogeneous manufacturing parameters to the final bonding quality of composite joints. The proposed model structure is heavily motivated by engineering knowledge, incorporating a calibrated mathematical physics model into the Neural ODE framework, which can significantly reduce the number of data samples required from costly experiments while maintaining high prediction accuracy. The proposed PINOHI model is implemented in the quality prediction of composite adhesive joints bonding problem. A set of experiments and associated data analytics are conducted to demonstrate the superior property of the PINOHI model by using both the leave-one-batch-out cross-validation and sensitivity analysis.

Prediction of composite pressure vessels’ burst strength through machine learning

In Hydrogen Fuel Cell Electric Vehicles, hydrogen is stored as compressed gas in tanks made from carbon fiber composite. Tanks are designed to withstand 2.25 times the nominal working pressure. If low variability in tank strength can be demonstrated, this margin of safety could be reduced. This requires accurate prediction of the strength of the vessel and quantification of its uncertainty. In this work, several composite pressure vessels are manufactured using filament winding, and the parameters that control the winding and curing recorded as time signals. Process parameters include fiber tension, winding speed, liner pressure, fiber volume fraction, winding time and curing pressure. The vessels are tested for burst pressure. Several configurations are defined, where each manufacturing parameter is changed. The recorded manufacturing data are fed to machine learning(ML) algorithms and trained to predict the vessel’s burst pressure. These ML algorithms include neural networks, Gaussian process regression GPR, Kernel Principal Component Analysis-Lasso (kPCA-Lasso), and an Ensemble regressor. The KPCA-Lasso and GPR models show good correlation. The Ensemble regressor yields better results by combining the KPCA-Lasso and GPR models. The study demonstrates the potential of ML algorithms in predicting the burst pressure of carbon fiber vessels from the monitored manufacturing data.

Optimizing parameters for additive manufacturing: a study on the vibrational performance of 3D printed cantilever beams using material extrusion

Purpose This study aims to investigate the impact of different printing parameters on the free vibration characteristics of 3D printed cantilever beams. Through a comprehensive analysis of material extrusion (ME) variables such as extrusion rate, printing pattern and layer thickness, the study seeks to enhance the understanding of how these parameters influence the vibrational properties, particularly the natural frequency, of printed components. Design/methodology/approach The experimental design involves conducting a series of experiments using a central composite design approach to gather data on the vibrational response of ABS cantilever beams under diverse ME parameters. These parameters are systematically varied across different levels, facilitating a thorough exploration of their effects on the vibrational behavior of the printed specimens. The collected data are then used to develop a predictive model leveraging a hybrid artificial neural network (ANN)/ particle swarm optimization (PSO) approach, which combines the strengths of ANN in modeling complex relationships and PSO in optimizing model parameters. Findings The developed ANN/PSO hybrid model demonstrates high accuracy in predicting the natural frequency of 3D printed cantilever beams, with a correlation ratio (R) of 0.9846 when tested against experimental data. Through iterative fine-tuning with PSO, the model achieves a low mean square error (MSE) of 1.1353e-5, underscoring its precision in estimating the vibrational characteristics of printed specimens. Furthermore, the model’s transformation into a regression model enables the derivation of surface response characteristics governing the vibration properties of 3D printed objects in response to input parameters, facilitating the identification of optimal parameter configurations for maximizing vibration characteristics in 3D printed products. Originality/value This study introduces a novel predictive model that combines ANNs with PSO to analyze the vibrational behavior of 3D printed ABS cantilever beams produced under various ME parameters. By integrating these advanced methodologies, the research offers a pioneering approach to precisely estimating the natural frequency of 3D printed objects, contributing to the advancement of predictive modeling in additive manufacturing.