Search Results (349)

Optimizing the injection molding of short-fiber-reinforced thermoplastics (SFRTs) is a persistent challenge due to the complex interplay between processing parameters and final mechanical performance. To address this, we developed and validated a machine learning (ML) pipeline to maximize both the tensile strength and Charpy impact resistance in polyamide 6 with 30% glass fiber (PA6-GF30). Through a designed experimental campaign, we systematically varied four key process parameters—melt temperature (260–300 °C), injection pressure (600–1000 bar), packing pressure (400–800 bar), and cooling time (15–35 s). The resulting dataset was used to train and compare three different regression models: Random Forest (RF), Gradient Boosting (GB), and Support Vector Regression (SVR). Our findings indicate that the Gradient Boosting (GB) algorithm yielded the most reliable predictions, significantly outperforming the other evaluated models. Further analysis using SHAP (Shapley Additive exPlanations) identified packing pressure as the dominant factor influencing tensile strength (contributing approximately 40% to the prediction), while melt temperature emerged as the key driver for impact resistance (around 35% contribution). By integrating our best-performing GB model with a multi-objective genetic algorithm, we identified an optimal set of parameters that simultaneously enhances both mechanical properties. Among the evaluated models (Random Forest, Support Vector Regression, and Gradient Boosting), the Gradient Boosting algorithm achieved the highest predictive accuracy. Compared to the baseline condition (280 °C melt temperature, 800 bar injection pressure, 600 bar packing pressure, 25 s cooling time), experimental validation of these optimized settings demonstrated substantial improvement: tensile strength increased from 145 MPa to 171 MPa (an 18% enhancement), and impact resistance rose from 45 kJ/m² to 55 kJ/m² (a 22% gain). This work establishes that an integrated ML and optimization framework can serve as a transformative approach for high-precision manufacturing of advanced engineering polymers. The primary novelty of this work lies in the development of a fully integrated, bias-free methodological framework that explicitly couples physical interpretability with multi-objective optimization, bridging the critical gap between black-box predictions and actionable industrial insights. Full article

This contribution presents a simulation-based approach for optimizing injection molding processes using digital twins. It combines surrogate modeling via response surface methodology (RSM) with the evolutionary algorithm NSGA-II to efficiently capture complex relationships between process parameters and objectives. A key element is the adaptive enhancement of the training dataset within the decision-relevant region of interest (ADEROI) by a modified greedy max–min algorithm. This strategy closes data gaps, improves model accuracy in the potentially optimal region, and directs additional simulations to informative areas. Leave-one-out (LOO) and hold-out (HO) cross-validations show strong root mean square error (RMSE) and $R^2$ values for deformation, shrinkage, cycle time, and mass. NSGA-II converges after 403 generations and results in 191 Pareto-optimal solutions, which are consolidated into preference-consistent operating points. These points make trade-offs between analyzed objectives’ deformation, shrinkage, and cycle time explicit for process pre-design. Preferred solutions are identified through weighted sums of normalized objectives and inversely mapped process parameters. Their agreement with the physics-based digital twin at the hundredths level supports the plausibility of the selected operating points within the investigated simulation-based workflow. A retrospective benchmark against a scaled single-stage LHS baseline shows that ADEROI achieves ROI-equivalent point density with fewer simulation runs for the investigated case, reducing the estimated runtime by $39.1\%$ and resulting in a $1.64\times$ speed-up. The quantitative validation is limited to one thin-walled PP keyholder component; further geometries, mold layouts, and polymer materials are required to empirically assess generalizability. Full article

Large glass fiber-reinforced polypropylene (GF-PP) shells are widely used in HVAC and automotive industries, but their injection molding suffers from severe warpage deformation, residual stress concentration, and inaccurate mechanical performance prediction due to neglected molding history. This study proposes an integrated optimization framework for a 30% GF-PP fan face shell. The optimal two-gate molding configuration was determined via Moldflow simulation. A Central Composite Design (CCD) combined with NSGA-II was used to optimize process parameters for minimizing warpage and residual stress. A Moldflow-Ansys co-simulation process was established to characterize fiber orientation-induced mechanical anisotropy, and full-scale mold trials were conducted for validation. The optimized process reduced maximum warpage by 58.03% (from 5.299 mm to 2.224 mm) and residual stress by 13.67% (from 54.93 MPa to 47.42 MPa). The average tensile modulus along the flow direction was 1.85 times that perpendicular to the flow direction. Mold trial results showed a warpage prediction error of only 7.583%. The proposed framework effectively addresses the critical quality issues in large GF-PP injection molding, providing a systematic engineering solution for molding quality control and accurate performance characterization. Full article

The increasing demand for porous stainless-steel materials produced by selective laser melting (L-PBF) for biomedical implants, filtration systems, heat exchangers, and energy devices has created an urgent need to improve their mechanical performance. Optimizing process parameters and microstructural properties is therefore critical for enhancing the overall functionality and reliability of L-PBF porous stainless-steel structures. This paper studies the effect of an aging heat treatment on the mechanical properties of L-PBF specimens, manufactured with stainless steel Uddeholm Corrax powders. The porosity was selected to be about 3%, based on manufacturer’s experience on the production injection mold inserts, with the ability to drain air. To reach this porosity, a set of manufacturing variables were selected, quantified in terms of VED (Volumetric Energy Density) of 59.01 J/mm³. The analysis of the mechanical behavior was focused on the compressive and flexural strength, dynamic Young’s modulus and the energy dissipation during earlier fatigue loading cycles. This study concluded that the heat treatment produces a negligible effect on dynamic Young’s modulus and increases the bending strength by about 25% and the compressive plateau strength by about 17%. Both specimens’ batches exhibit similar fatigue strain accumulation for cyclic compressive tests. Full article

This study investigates laser transmission welding of 30% glass fiber-reinforced polybutylene terephthalate (PBT-GF30). Injection-molded plates were used as base material, from which specimens were prepared, welded, and experimentally tested. The influence of key process parameters, including laser power, beam size, and scanning speed, on weld quality was systematically evaluated through an iterative optimization approach. An optimized parameter set (400 W laser power, reduced beam size, and increased scanning speed) enabled stable and repeatable weld formation with minimal thermal degradation. Experimental results were further supported by finite element analysis, showing good agreement between numerical and experimental data. The findings confirm the feasibility of laser welding for PBT-GF30 and its potential for aerospace applications requiring precision, weight reduction, and structural reliability. Full article

In ultra-high-voltage GIS and GIL systems, epoxy resin insulators are still the mainstream choice. However, as a thermosetting material, epoxy resin is difficult to recycle after disposal, which limits its environmental benefits. Thermoplastic insulators, due to their recyclability, are potential alternatives. This study focuses on 30% glass fiber-reinforced PET and PA6 materials. Their injection molding behavior, hydraulic pressure performance, and insulation performance were systematically analyzed using Moldflow, ANSYS, and COMSOL, respectively. For injection molding, Moldflow simulations were conducted for filling, packing, and cooling stages. Melt temperature was varied from 260 to –310 °C (PET) and 250–300 °C (PA6), while mold temperature was varied from 80 to –130 °C (PET) and 70–120 °C (PA6). An optimization objective function, Y = Δp/20 + Δx/0.5 + Δs/1.8, was developed to determine optimal processing parameters. Based on this function, the optimal parameters identified are: PET at 290 °C melt temperature and 120 °C mold temperature; PA6 at 250 °C melt temperature and 70 °C mold temperature. For hydraulic testing, Moldflow–ANSYS coupled simulations were performed under 2.4 MPa pressure with the compliance criteria of bulk stress < 90 MPa and insert-contact stress < 20 MPa. PA6 passed within a processing window of melt temperature < 270 °C and mold temperature < 120 °C. PET failed under all tested conditions, with insert-contact stress ranging from 24.25 to 27.55 MPa, consistently exceeding the 20 MPa threshold. In terms of insulation performance, this paper utilizes COMSOL to study the electric field distribution of thermoplastic insulators in SF₆ GIS/GIL and provides optimization suggestions for insulator geometry design. This study systematically compares the injection molding processes and hydraulic pressure performance of PET and PA6 thermoplastic insulators. These results provide important process insights and design guidance for evaluating thermoplastic materials as potential alternatives to epoxy resin in GIS/GIL applications. Full article

Injection molding process optimization has predominantly relied on simulation-generated data, which cannot capture machine-specific variability and stochastic process noise inherent in real manufacturing environments. This paper presents an experiment-driven machine learning framework for multi-objective optimization of injection molding process parameters targeting volumetric shrinkage, warpage, cycle time, and part weight. Physical experiments were conducted on an industrial injection molding machine using high-density polyethylene with a face-centered central composite design. Systematic benchmarking of four machine learning algorithms under identical cross-validation protocols identified Gaussian process regression as the best-performing surrogate model for the majority of quality metrics, while warpage prediction remained challenging across all algorithms due to its complex thermo-mechanical origins. Permutation-based feature importance analysis established a clear parameter hierarchy, identifying holding time as the dominant factor governing multiple quality responses. Constrained Bayesian optimization with progressive constraint tightening was employed to identify optimal parameter sets and fundamental process capability boundaries. The resulting parameter configurations were validated against a held-out test set. This work demonstrates that rigorous, data-driven optimization using exclusively experimental data provides a viable and practically achievable alternative to simulation-based approaches, contributing to experiment-centric smart manufacturing in polymer processing. Full article

Background/Objectives: Hot-melt injection molding (HMIM) was evaluated as a solvent-free process for the preparation of glibenclamide (GLB), a poorly soluble BCS Class II drug, glassy solutions with the objective of improving dissolution and bioavailability for diabetes. Methods: GLB was blended at a concentration of 10% w/w with PVP K25, PVP VA64, and Soluplus^® (SOL) matrices. The miscibility of the GLB–polymer systems (matrices) was calculated based on the Hansen solubility parameters and validated using differential scanning calorimetry (DSC) analysis. The HMIM extrudates were milled into granules and analysed for their solid-state properties (DSC, XRPD, FTIR, and SEM studies), and flow properties. The produced granules were compressed into immediate release tablets and assessed for in vitro performance, stability, and in vivo bioavailability using 20 healthy male Sprague Dawley rats. Results: Findings revealed the formation of single-phase glassy solutions, specifically for PVP VA64 and SOL, which also exhibited advantageous manufacturing and extrudate clarity. The glassy solution formulations showed considerably improved dissolution characteristics compared with the crystalline GLB and the commercial product. The glassy solution formulations displayed fast drug release for PVP K25 and PVP VA64, and biphasic drug release for SOL. Stability testing confirmed the capability of PVP VA64 and SOL to maintain GLB in a molecularly dispersed, amorphous state for 12 months. The in vivo assessment revealed an increase in relative bioavailability to 246.3% and 124.5% for the SOL and PVP VA64 formulations when compared to the commercial formulation. Conclusions: Overall, the findings demonstrate the potential of HMIM-processed glassy solutions, especially those prepared using SOL, as promising platforms for promoting oral delivery of the poorly soluble antidiabetic GLB. Full article

This study proposes a useful multi-criteria optimization approach for defining the proper fabrication factors for the CNC milling process on the inclined surfaces of SKD 11 material. The method is to be used in mold fabrication technology within the field of mechanical engineering. A combination technique of the Taguchi technique (TM), response surface method (RSM), and Lichtenberg optimization algorithm (LA) was proposed to optimize the fabrication factors for enriching the superiority attributes. In the first stage, several initial experiments of the fabricating parameters were generated by the TM. Secondly, the mathematical equations among the main fabricating parameters, the surface roughness, the flatness, and the CNC milling time were then established by the RSM. Significant influences of fabrication elements on surface roughness, flatness, and CNC milling time were evaluated by variance analysis and sensitivity analysis based on three distinct CNC milling toolpath strategies. Finally, the Lichtenberg optimization algorithm was carried out based on regression equations to define the optimized factors for three cutting strategies. The optimized results showed that the reverse CNC milling toolpath strategy was the best for achieving the three quality responses. Furthermore, the results demonstrated that the inaccuracies among optimized as well as experiment confirmations for the surface roughness, flatness and CNC milling time were 6.54%, 18.182% and 11.972%, respectively. The verifications of experiment results were relatively suitable with the anticipated consequences. The outcomes reveal that an integration optimization methodology is a successful approach to tackling the multi-objective optimal problem of determining the best CNC milling parameters for the cartwheel specimen made of SKD11 material in injection mold technology. It can also be expanded to apply to complicated multi-criteria optimization problems. Full article

This study presents an integrated optimization framework that combines the Design of Experiments (DOE) approach with Machine Learning (ML) techniques to minimize defects in the injection molding of Fuel Vapor Charcoal Canisters. The research focuses on five critical process parameters—melt temperature, mold temperature, filling time, pressure holding time, and pure cooling time—whose combined influence on major molding defects (warpage, shrinkage, shear stress, residual stress, and short shots) was systematically investigated. A Taguchi L25 orthogonal array was employed to structure the experiments and identify the optimal parameter levels through signal-to-noise (S/N) ratio analysis using the “smaller-the-better” quality criterion. The Taguchi results revealed that pressure holding time was the most influential factor, followed by mold temperature and melt temperature. Simulation results from SolidWorks Plastics confirmed the reduction in major defects under the optimized settings. To further validate and generalize the DOE findings, a Random Forest regression model was trained on the same dataset to capture nonlinear interactions between parameters. The model achieved an average RMSE of 2.451 ± 0.591 in five-fold cross-validation, demonstrating strong predictive accuracy. Feature importance analysis indicated that pressure holding time accounted for approximately 77.5% of the variance in the defect index, reaffirming its dominant role. A 3D response surface of the global parameter space (mold temperature vs. pressure holding time) revealed a distinct minimum defect region, consistent with the DOE-optimized settings. The Taguchi analysis identified the optimal parameter settings as Melt Temperature at Level 2, Mould Temperature at Level 3, Filling Time at Level 4, Pressure Holding Time at Level 5, and Pure Cooling Time at Level 4, which collectively produced the highest S/N ratios and the lowest overall defect index. The overall discrepancy between DOE and ML predictions was only 12.5%, confirming methodological consistency. The integration of DOE and ML not only enhances parameter interpretability and defect prediction accuracy but also provides a scalable, data-driven approach for intelligent process control and quality assurance in automotive injection molding. Full article

The conducted study was focused on the development of a new type of polymer blends intended for additive manufacturing applications, in particular, the material extrusion method (MEX). The developed materials were prepared from recycled poly(ethylene terephthalate) and amorphous copolymers poly(ethylene terephthalate-glycol) (PETG), and poly(cyclohexylenedimethyl terephthalate-glycol) (PCTG). The basic blend systems were additionally modified with POE-g-GMA impact modifier (IM) during the reactive extrusion process. The main aim of the work was to assess the effectiveness of using composite additives and their influence on the mechanical and thermomechanical parameters of the tested systems. To prepare the composites, selected polymer blends were modified with 10% of talc (T) and carbon fibers (CF). The properties evaluation includes the mechanical/thermomechanical testing, thermal analysis and structural observations. The accuracy of printing was measured using optical scanning methods. The test results indicate that even the relatively small amount of the CF filler could lead to a significant increase in tensile modulus from reference 1.6 GPa to 2.9 GPa; the same improvement applies to strength values, where the CF-modified materials reached 45 MPa, compared to the reference 31 MPa. The heat deflection tests (0.455 MPa) after annealing revealed the maximum HDT of around 170 °C for both types of CF-modified materials. The Vicat test results were also favorable for annealed materials. Considering that the Vicat/HDT results after the 3D-printing process usually reach around 70 °C, the performed heat treatment strongly enhanced the heat resistance for most of the prepared blends. The performed studies revealed that for most of the prepared materials, the brittleness was a common drawback for both MEX-printed and injection-molded materials. Full article

In addition to the inherent challenges associated with controlling polymerization reactors, the “Sclairtech” technology for the production of Linear Low-Density PolyEthylene (LLDPE) presents specific characteristics (e.g., high temperature and pressure and a residence time in the reactor of less than 1 min) which add further difficulties to the effective control of the main quality parameters of the polymer produced. This work presents a strategy for implementing advanced control in a real LLDPE production unit (“Sclairtech” technology) followed by a systematic evaluation of the economic benefits in accordance with best international practices. Melt Index (MI), density and conversion were considered as controlled variables. The methodology for implementing advanced control involved analysis by resin classes (rotational molding, low-density injection, octene film and high-density injection) and effective contributions such as an innovative strategy for reactor temperature control. The proposed control strategy is capable of efficiently addressing two of the main problems associated with “Sclairtech” technology, namely, the generation of out-of-specification product during grade transitions and wide specification ranges. The benefits analysis involved the use of real process data, a statistical analysis of key variables to identify the dispersion and percentage of out-of-specification products, and the calculation of the net present value of financial indicators capable of validating the investment. Regarding quantitative outcomes, an annual gain of US$ 791,812 was estimated, with US$ 494,883 coming from the reduction in catalyst consumption and US$ 296,929 from other sources (reduction in out-of-specification product and production losses associated with grade transitions). Full article

To solve common defects such as warpage deformation, interface debonding, and uneven filling during the two-color injection molding of medical goggles while meeting their multi-performance requirements, including high light transmittance, impact resistance, chemical corrosion resistance, and structural stability, this study conducts research on the process optimization of two-color injection molding. Firstly, based on the principle of material compatibility and Moldflow simulation, a suitable material combination was selected: the first-shot frame adopts Apec 1745 PC material, and the second-shot lens uses Makrolon 2858 PC material, which effectively avoids the risk of interface non-fusion. Subsequently, a high-precision 3D simulation model was established using Moldflow software, and the injection sequence of “frame first, lens second” was optimized and determined. A gating system with double-gate (for the frame) and single-gate side feeding (for the lens), as well as a cooling system with an 8 mm diameter, was designed, and all key indicators of mesh quality meet the simulation requirements. Taking the mold and melt temperatures, holding pressures, and holding times of the two shots as design variables and warpage deformation as the optimization objective, sample data were obtained through an L₃₂ (7⁴) orthogonal test. A BP neural network was constructed to describe the nonlinear relationship between parameters and quality, and the Sparrow Search Algorithm (SSA) was combined to optimize the weights and thresholds of the network, forming a BP-SSA intelligent optimization model. The results show that the mean absolute percentage error (MAPE) of the proposed model is only 2.28%, which is significantly better than that of the single BP neural network (14.36%). The optimal process parameters obtained by optimization are a mold temperature of 130 °C, first-shot melt temperature of 311 °C, second-shot melt temperature of 310 °C, first-shot holding pressure of 83 MPa, second-shot holding pressure of 70 MPa, first-shot holding time of 14 s, and second-shot holding time of 8 s. Simulation and mold test verification indicate that after optimization, the warpage deformation of the goggles is reduced to 0.8956 mm (simulation) and 0.944 mm (measured), with a relative error of only 5.4%, which is 67.9% lower than the initial simulation result. The integrated method of “material selection—CAE simulation—orthogonal test—BP-SSA intelligent optimization” proposed in this study provides technical support for the high-precision manufacturing of thin-walled transparent multi-material medical products. Full article

An accurate prediction of the final properties of injection-molded semi-crystalline parts requires models that capture crystallization kinetics during processing. This work presents two practical strategies to incorporate experimentally derived crystallization behaviors into Autodesk Moldflow, addressing cases where kinetics differ from the software’s native Avrami–Hoffman–Lauritzen formulation. We apply these methods to isotactic polypropylene (iPP T30G) displaying heterogeneous nucleation with a low-temperature plateau, and to polyoxymethylene (POM) exhibiting combined heterogeneous and homogeneous nucleation. The parameters for Moldflow were obtained by matching isothermal half-crystallization times (t_0.5) and by tuning flow-induced nucleation terms. Validation against isothermal and non-isothermal injection tests shows agreement between calculated and expected crystallinity evolution and reproduces measured spherulite diameters. Full article

The COVID-19 pandemic critically emphasized the need for rapid, flexible, and decentralized manufacturing solutions to support the urgent demand for essential medical equipment, such as oximeters. Metal wire directed energy deposition—w-DED, also known as w-LMD (wire laser metal deposition)—combines the benefits of high material utilization, increased printing speed, and reduced waste, making it an attractive alternative to traditional powder-based processes, especially under time-sensitive and resource-constrained conditions. This work presents a case study focusing on the design and fabrication of injection molds for oximeter casings using metal-wire-based DED. Martensitic stainless steel AISI-420 wire was employed as feedstock and processed via laser wire additive manufacturing to produce a robust, near-net-shape mold suitable for plastic injection molding. The material was selected due to good corrosion and wear resistance. However, poor ductility and toughness, together with AM-induced anisotropy, were the main challenges to address. Therefore, a multi-step methodology was defined to study the effect of different process parameters, which was validated through printing trials, and the optimum process parameter set was identified. The process enabled the rapid construction of intricate mold geometries, minimizing lead times and allowing for quick design iterations. Microstructural and physical properties such as microhardness of the as-built molds were thoroughly characterized. This case study not only illustrates the technical feasibility of producing functional injection molds via metal w-DED but also outlines its role as a resilient manufacturing pathway, capable of meeting emergent healthcare needs and supporting broader industrial applications in a post-pandemic context. Full article