Design Of Experiments Approach Research Articles

Multiobjective design of automated order fulfillment systems: A case study for an existing surgical complex

We present a case study that introduces a systematic framework for designing an automated guided vehicle (AGV) order fulfillment system. The multi-stage framework integrated discrete event simulation (DES), super-efficiency data envelopment analysis (S-DEA) model, and Design of Experiments (DOE) methodologies for the design of an AGV system in an existing large-scale surgical complex within a comprehensive hospital in Singapore. Performance metrics derived from this model were consolidated into a single relative efficiency score using the S-DEA model. This efficiency score was then utilized in a DOE methodology, combined with a post-hoc model selection process, to robustly identify appropriate models for evaluating alternative system designs. The proposed framework optimizes AGV deployment by first identifying opportunities for AGVs to add value within the surgical system through a value-stream mapping approach. It then derives the optimal system design by balancing cost efficiency, manpower reallocation, and order fulfillment rates, facilitated by the S-DEA model augmented with the DOE approach and post-hoc model selection. Application of this framework to the surgical complex revealed several insights that can significantly enhance AGV efficiency prior to actual deployment. However, a key limitation of this case-study-based approach is its limited generalizability across different systems. Despite this, the methodology provides a robust foundation for AGV system design in similar healthcare environments.

Iron and Zinc Metallates Supported on Ion Exchange Resins: Synergistic Catalysts for the Solvent‐free Cyclic Carbonate Synthesis from Epoxides and CO2

Despite extensive research into developing efficient and environmentally friendly catalysts for converting CO2 over the last decade, the search for a robust and cost‐effective catalytic system is ongoing. This study describes developing and applying a new catalytic system using inexpensive ferrate and zincate anions immobilized on easily available commercial ion exchange resins (IER) to produce cyclic carbonates from CO2 with high efficiency and low cost. Two polystyrene‐based anion exchange resins, AmberlystTM A26‐Cl (A26‐Cl) and AmberliteTM IRA‐400‐Cl (IRA400‐Cl), were compared. The results demonstrated the catalysts' remarkable activity under mild conditions and demonstrated the synergistic effect between the polystyrene support and the active ammonium metallates, presenting a scalable, eco‐friendly method for cyclic carbonate production using waste CO2. A Design of Experiment approach was implemented to optimize the catalytic cycloaddition of CO2. The reaction scale‐up to produce a 5 g batch of propylene oxide and conducting recycling tests demonstrated that the catalyst retained its activity over four cycles. The research also explored the use of various epoxides and found that terminal epoxides produced very good yields. In summary, this study introduces a cost‐effective, scalable method for converting CO2 into valuable cyclic carbonates, leveraging the synergistic effects of polystyrene supports and active ammonium metallates.

EthoCRED: a framework to guide reporting and evaluation of the relevance and reliability of behavioural ecotoxicity studies.

Behavioural analysis has been attracting significant attention as a broad indicator of sub-lethal toxicity and has secured a place as an important subdiscipline in ecotoxicology. Among the most notable characteristics of behavioural research, compared to other established approaches in sub-lethal ecotoxicology (e.g. reproductive and developmental bioassays), are the wide range of study designs being used and the diversity of endpoints considered. At the same time, environmental hazard and risk assessment, which underpins regulatory decisions to protect the environment from potentially harmful chemicals, often recommends that ecotoxicological data be produced following accepted and validated test guidelines. These guidelines typically do not address behavioural changes, meaning that these, often sensitive, effects are not represented in hazard and risk assessments. Here, we propose a new tool, the EthoCRED evaluation method, for assessing the relevance and reliability of behavioural ecotoxicity data, which considers the unique requirements and challenges encountered in this field. This method and accompanying reporting recommendations are designed to serve as an extension of the "Criteria for Reporting and Evaluating Ecotoxicity Data (CRED)" project. As such, EthoCRED can both accommodate the wide array of experimental design approaches seen in behavioural ecotoxicology, and could be readily implemented into regulatory frameworks as deemed appropriate by policy makers of different jurisdictions to allow better integration of knowledge gained from behavioural testing into environmental protection. Furthermore, through our reporting recommendations, we aim to improve the reporting of behavioural studies in the peer-reviewed literature, and thereby increase their usefulness to inform chemical regulation.

Catalytic activity insight into sustainable Fe-hydroxyapatite application using an experimental design approach

Combining experimental design with advanced characterisation methods provides a valuable opportunity to deepen our understanding of catalytic processes and their underlying mechanisms. Here, a series of hydroxyapatite doped with Fe2+ at different molar loadings noted HAP-FeX% (X = 1; 5.5 and 10; Ca/Fe molar ratio) were elaborated using a one-pot synthesis method. Characterization of these catalysts by various techniques such as ICP, BET/BJH, TGA/DSC, XRD, Raman, UV–visible, TPD-NH3, SEM, and TEM revealed substantial Fe2+ oxidation during synthesis, inducing changes in the morphological and physical-chemical characteristics of HAP caused by Fe3+/Ca2+ substitution. Furthermore, the synthesis produced nanoparticles (approximately 0.30 nm in size) on the hydroxyapatite surface, resulting from the precipitation of Fe/O phases. The catalysts exhibited good catalytic performance in methylene blue (MB) degradation through the photo-Fenton process (95 %). The Ca/Fe molar ratio = 8.8 %, [H2O2] = 2.8 mmol L−1, and pH = 8.8 were optimized using the design of experiments (DOE) via response surface methodology (RSM). A mathematical model was developed to determine the influence of the Ca2+/Fe3+ substitution and the Fe/O phase on the catalytic activity. The results revealed the role of the Fe/O phase in the reaction initiation and the surface modification induced by Ca2+/Fe3+ substitution to facilitate the reaction chain.

Pectin Microwave Assisted Extraction from Pumpkin Peels: Process Optimization and Chemical-Physical and Rheological Characterization.

Recently, pectin, a versatile polysaccharide with different industrial applications, has gained significant attention as an eco-friendly and functional ingredient. This study investigates pumpkin peels (Cucurbita maxima L., Mantua variety) as a novel source of pectin, using a microwave-assisted extraction method with citric acid-acidified water as solvent. The extraction conditions were optimized using a Design of Experiments approach, considering the solvent-to-solid ratio (SSR), pH, temperature, and extraction time. The optimized conditions (94.8 °C, 5 min, pH 1.5, and 46 mL/g SSR) resulted in a pectin yield of 18.05%. A comprehensive characterization of the extracted pectin was performed, including FT-IR spectroscopy, DSC, TGA, rheological properties, and techno-functional assessments such as water holding capacity and fat binding capacity. The results indicated a high degree of esterification (56.19 ± 0.87%), classifying the pumpkin peels (PP) extract as a high methoxyl pectin. PP pectin demonstrated potential as a stabilizer and emulsifying agent, although its high methoxyl content limits its use as a carrier for targeted bioactive delivery. The findings support the viability of using agricultural by-products to obtain valuable polysaccharides, contributing to waste valorization and sustainable industrial practices.

An investigation into process parameters optimization for ultimate tensile strength of friction stir welded Al-10Mg-8Ce-3.5Si joint: Numerical and Design of Experiments approach

An investigation into process parameters optimization for ultimate tensile strength of friction stir welded Al-10Mg-8Ce-3.5Si joint: Numerical and Design of Experiments approach

Data-driven multi-objective optimization of aerodynamics and aeroacoustics in dual Savonius wind turbines using large eddy simulation and machine learning

Savonius rotor is a popular form of vertical-axis wind turbine (VAWT) for small-scale and urban applications because of its straightforward design and self-starting ability. Dual VAWTs present challenges in terms of wake interactions and noise, particularly in urban areas. Optimizing these parameters is essential for future wind energy adoption. This research is the first to analyze how the interaction of wakes from adjacent rotors, combined with a deflector, affects both the aerodynamic performance and noise levels of dual Savonius rotors. Large Eddy Simulation is applied, as it effectively captures detailed turbulent wind flows and their interactions with wind turbines. A multi-objective optimization method combining Machine Learning and Computational Fluid Dynamics (CFD) is developed to optimize rotors for maximum power efficiency and minimum noise, considering their wake interactions with a unique deflector system. First, the influence of geometric parameters on aerodynamics and aeroacoustics characteristics of rotors is analyzed, and the database is generated using Design of Experiment approach. Next, the CFD model is replaced by Artificial Neural Network (ANN) model established for predicting rotor performances. A Multi-Objective Genetic Algorithm method is used to optimize aerodynamics and aeroacoustics characteristics of rotors. Finally, optimal design parameters are identified from the Pareto front using the technique for order of preference by similarity to ideal solution decision-making method. The ANN model demonstrated high accuracy with an RANN2 of 0.995 and 0.971 for the average power coefficient (CP) and overall sound pressure level (OSPL) predictions, respectively. Multi-objective optimization revealed the best configuration of the deflector with bleed jets, improving the average CP up to 57.5% and reducing OSPL to an almost 5.2% compared to the dual rotor case at TSR = 0.8.

Assessing the occurrence of barley starch annealing under heat, moisture and time conditions relevant for kilning: An experimental design approach

In this work, the possible occurrence of barley starch annealing under kilning conditions was investigated. Using an I-optimal response surface methodology, the impact of temperature (45–55 °C), moisture content (30–50%) and time (1–5h) on the gelatinisation behaviour of starch in green malt was studied. An increase in onset (0.5–4.3 °C) and peak temperature (0.5–2.7 °C) and a change in peak width (+0.5 to - 3.2 °C) of the starch gelatinisation endotherm showed the extent of annealing that occurred within an industrially relevant design space. Temperature was the main driver behind the observed changes, but also interaction effects between temperature, moisture content and time contributed. Combined with increasingly high starch gelatinisation temperatures in barley, the observed increases in peak gelatinisation temperature due to annealing could hamper fermentable sugar production during brewing.

An optimization through experimental design approach for simultaneous quantification of Remogliflozin and Teneligliptin by RP-UFLC

The combination of teneligliptin (TEN) with remogliflozin etabonate (REM) is the latest FDC approved for the treatment of type-2 diabetes. There is no QBD optimized UFLC method reported with short runtime for quantification of TEN and REM. Hence this research work aimed to find a new way to quantify a novel antidiabetic combination of TEN and REM using RP-UFLC technique with possible minimum run time, optimized with QBD. The method was executed using the Agilent Eclipse XDB C-18 column (150 x 4.6 mm; 5 μm), with the mobile phase comprising of buffer and acetonitrile (41:59) at a flow rate of 2.2 mL per minute and determination has been carried out at 230 nm. The retention time for TEN and REM was found at 0.770 and 1.465 minute correspondingly with runtime only 2 min. The method's effectiveness has been validated using ICH guideline for LOD, LOQ, linearity, precision, accuracy, robustness and forced degradation. In the proposed study, TEN and REM were successfully separated with very short run time of only 2 minutes. The results of validation for proposed UFLC method revealed the accuracy, specificity and forced degradation of the method. Furthermore, determination of TEN and REM from formulations showed the correctness of the method. The method is novel, easy to use, fast, precise and accurate and it can be used in QC laboratories for regular studies on API and dosages.

Failure analysis-based mass reduction of an aluminium alloy engine mounting bracket using Design of Experiments approach

In this study, mass reduction of an engine mounting bracket has been performed without changing the failure mode. Firstly, failure modes were determined experimentally using failure loads provided by the vehicle manufacturer. Then critical stress concentration areas and suitable mass reduction regions were determined by using Finite Element Analysis (FEA) for these load cases. A structural optimisation process was carried out using Design of Experiment-Response Surface Methodology (DOE-RSM) to minimise the mass while keeping the failure load as constant as possible. When the stress values obtained from the preliminary structure are compared with the values obtained from the optimised part, it was seen that this target has been mostly achieved. A total mass reduction of 4.31 % was achieved in the new part through failure mode analysis. Furthermore, it was found that a financial saving of 129,000 Euro could also be achieved.

A chemometric approach using I-optimal design for optimising Pb(II) removal using bentonite-chitosan composites and beads

This paper reports adsorption studies of Pb(II) ions onto Bentonite-Chitosan (Bt-Ch) composites or beads when using an I-optimal design experiment approach. Three adsorption factors (pH, adsorbent dosage, and initial concentration) were optimised whilst simultaneously investigating multiple adsorbents. The Bt-Ch composites and beads (type A and B) adsorbents were made using weight ratios 90%/10% and differed characteristically due to their preparation methods of solution blending and precipitation, respectively. A batch procedure was used for adsorption experiments, and the amounts of Pb(II) ions (adsorbed onto Bt-Ch composites/beads) were analysed using inductively coupled plasma optical emission spectrometry (ICP-OES). Adsorption experimental parameters were analysed and optimised by using a response surface method (I-optimal design) generated from Design-Expert® 13.0 software. The main achievements of this study were to intensify the understanding and application of I-optimal experimental designs, which allow simultaneous determination of adsorption capacities and efficiencies across multiple adsorbents in an economical manner. A reduced quadratic model provided the best fit for the experimental data and exhibited minimal deviation between predicted and experimental values. This was evidenced by the very small covariance (CV) values of 1.81% and 1.33% observed for adsorption capacity and adsorption efficiency, respectively, also suggesting high reproducibility. It was observed that the adsorption factors studied (pH, adsorbent dose, and initial concentration) have a more pronounced effect on the adsorption capacity (F-value = 714.37) compared to adsorption efficiency (F-value = 140.62). Adsorbent dosage was found to have the greatest effect on adsorption capacity, while the initial pH of Pb(II) solution had the greatest effect on adsorption efficiency. Under optimal conditions, the adsorption capacities of beads-A (73.2 mg/g) and beads-B (77.6 mg/g) were found to be higher than that of the corresponding composite (51.7 mg/g). Whilst the optimum adsorption efficiency values for all three adsorbents were ∼100% (with ranges of pH 2–5, initial concentrations 50–200 mg/L, and adsorbent dosage 0.05–0.5 mg). The desirability indexes for the optimised conditions for these respective responses (and each adsorbent) were found to be within the ranges of 0.892–0.974 and 0.945–0.967 for adsorption capacity and adsorption efficiency, respectively. These high desirability index values for both responses indicate that the optimised conditions lead to very good performance for both measures. The information obtained in this study provides detailed understanding of the adsorption phenomena of the adsorbents studied. It gives confidence in the use of I-optimal designs to be applied as a chemometric tool for the specific adsorbents studied herein and others.

Apremilast Amorphous Solid Dispersions: Formulation Optimization using QbD and Comprehensive In vitro-In silico Assessment

Aim: The study aims to develop a 3rd generation amorphous solid dispersion (ASD) of Apremilast (APST) employing the Design of Experiment (DoE) methodology, followed by a thorough assessment including in silico pharmacokinetics. Background: APST, classified as a BCS-Class IV molecule due to its low solubility and permea-bility, exhibits highly variable oral bioavailability across different species. Objective: In this study, a 3rd generation ASD of APST was developed using the DoE approach. Methods: The miscibility of APST within polymers was assessed using solubility parameters and Flory Huggin equations. Phase solubility studies were conducted to identify the most suitable polymer-surfactant combination for maximizing drug solubility. The produced solid dispersions were characterized using FTIR, DSC, XRD, DVS, and SEM. Results: The combination of APST and Soluplus® in a 1:5 ratio resulted in the highest improve-ment in solubility and dissolution, with vitamin E TGPS being identified as the most efficient sur-factant. Stability studies were carried out, and findings revealed that the ASD remained stable un-der accelerated conditions for up to 3 months, suggesting its suitability for scaling up for industri-al applications. In silico predictions of the pharmacokinetics of APST following oral administra-tion of solid dispersion formulations were determined by PBBM using GastroPlus™. Conclusion: The simulation of oral absorption profiles for APST showed a significant improve-ment in both Cmax and AUC for the solid dispersion formulations compared to plain drugs. This study makes a significant contribution to the field of pharmaceutical science by addressing the formulation complexities inherent in poorly water-soluble compounds like APST.

EFEKTIVITAS MEDIA ULAR TANGGA EDUKASI TERHADAP HASIL BELAJAR DALAM PEMBELAJARAN IPAS PADA KELAS IV SD ATTIN NAMOSAIN

This research is a quantitative research, this research aims to determine the effect of the effectiveness of snakes and ladders media on the learning outcomes of class IV students in science and science learning at Attin Namosain Elementary School. The type of Quasi Experimental Design approach is Pretest Posttest Nonequivalent Control Group Design. This research used a population and sample, namely all class IV students consisting of 44 students (22 control class students and 22 experimental class students). The data collection techniques used were test techniques and observation sheets for the implementation of learning media. Based on the analysis of the data results, it shows that the sig (2-tailed) value is 0.000<0.005, with a significance level = 0.05(5%). Furthermore, the results of the N-Gain Score test in the experimental class which applied snakes and ladders media was 71.16% and was included in the effective category. There is a significant influence of snakes and ladders media on the learning outcomes of class IV students in science learning at Attin Namosain Elementary School.

A Novel Method for Development and Validation of the Degradation Products Analysis of N-Carbamylglutamate with UHPLC by Using Design of Experiment Approach.

Carglumic acid, also known as N-carbamyl-l-glutamic acid, is a medication used in the treatment of a rare genetic disorder called N-acetylglutamate synthase (NAGS) deficiency. To the authors' knowledge, there was no method reported in the literature for the determination of degradation products suitable for quality control analyses of carglumic acid. Thus, the aim of the presented study is to develop an impurity method with a UHPLC/DAD detector configuration compatible with industrial standards from the European Pharmacopeia and the United States Pharmacopeia, making the drug more accessible for developing and underdeveloped countries through its precise evaluation. The method involved the separation of carglumic acid and its degradation products using a reverse-phase C18 column (Waters, BEH 150 mm × 2.1 mm, 1.7 μm) at a flow rate of 0.39 mL/min with a stop time of 10 min. To separate all unknown and known impurities, a gradient elution (phosphate buffer, pH 2.4, and acetonitrile) system was used. The detection was performed at 214 nm. Forced degradation studies were conducted under different stress conditions, including acidic, basic, oxidative, thermal, and photolytic stress. Placket-Burman statistical experimental design was used to demonstrate the robustness of this method, and the suitability of the method was confirmed under the applied conditions. Box-Behnken design was used to provide the optimum resolution between the peaks determined to be critical during the optimization. The developed method was validated according to ICH guidelines for specificity, linearity, accuracy, precision, and robustness. The limit of detection and limit of quantification were 0.7 and 0.15 μg/mL for carglumic acid, respectively.

SUSTAINABLE FASHION DESIGN WITH GAZENNE WOVEN FABRIC THE CULTURAL HERITAGE OF KEMALIYE

This study explores garment design applications that enhance the sustainability of Gazenne fabric. The primary objective is to promote this fabric as a tangible cultural asset, integrating it with sustainable and slow fashion movements to embed it in daily life. The featured collection, “Boomerang,” embodies the theme of sustainability and caters to women who value longevity and versatility in their wardrobe. The collection showcases designs characterized by recyclable, sustainable, and interchangeable elements. It aims to create a nexus between historical and futuristic fashion by utilizing “Gazenne Weaving Fabric,” indigenous to the Kemaliye district of Erzincan. This fabric, which received its geographical indication in 2013, has revitalized traditional weaving techniques and provided new employment opportunities. A central goal of this research is to rejuvenate Gazenne weaving—an endangered intangible cultural heritage—and repurpose it for contemporary apparel. Accordingly, the collection comprises garments designed for durability and versatility, facilitating various combinations with other clothing pieces. The research methodology includes a collection design of ten outfits conceptualized under the “Sustainability” theme, supported by a literature review and an experimental design approach. Two selected garments from this collection exemplify the practical application of sustainable fashion principles, emphasizing the use of Gazenne woven fabric. Ultimately, this study underscores the potential positive impacts on sustainable fashion, cultural heritage preservation, and local economic development. These findings may inspire similar initiatives and encourage the adoption of more sustainable, responsible practices in the fashion industry.

Comprehensive investigation of factors influencing the degradation of polysorbate 20: Insights into mechanisms and interactions using a design of experiments approach

This study investigates the degradation of polysorbate 20 (PS20 HP) in a protein-free formulation under various storage conditions, examining the factors (i) Fe2+, (ii) Fe3+, (iii) H2O2, (iv) glass vial type, (v) fill volume, (vi) oxygen concentration, (vii) PS20 HP batches, (viii) light exposure before storage, and (ix) storage time by a design of experiments approach. In order to ascertain the impact of the factors under examination, realistic concentration ranges have been selected on the basis of observations made in industrial settings. The findings of our investigation demonstrate that the presence of Fe2+ and Fe3+, in addition to oxygen, has a significant influence on the degradation of PS20 HP, with Fe2+ exerting a more pronounced effect. The reduction of the oxygen content through nitrogen degassing has been demonstrated to have a pronounced inhibitory effect on PS20 HP degradation, even in the presence of iron ions. Interestingly, the concentration of intact PS20 HP was not significantly affected by H2O2 (tested concentration: 29.4 μM (1 ppm)). Furthermore, other factors including fill volume, PS20 HP batch, and light exposure, did not exert a statistically significant impact on the degradation of PS20 HP over a 12-month period in relation to the other factors.

Strategies for producing probiotic biomass and postbiotics from Akkermansia muciniphila in submerged cultivations incorporating prebiotic sources.

This research propounds an innovative technology focused on sustainability to increase the biomass yield of Akkermansia muciniphila, the next-generation probiotic, using prebiotic sources to replace or reduce animal mucin levels. A series of experimental design approaches were developed aiming to optimize the growth of Akkermansiamuciniphila by incorporating extracts of green leafy vegetables and edible mushroom into the cultivation media. Experiments using kale extract (KE), Brassica oleracea L., associated with lyophilized mushroom extract (LME) of Pleurotus ostreatus were the most promising, highlighting the assays with 0.376% KE and 0.423% LME or 1.05% KE and 0.5% LME, in which 3.5 × 1010 CFU (Colony Forming Units) mL- 1 was achieved - higher than in experiments in optimized synthetic media. Such results enhance the potential of using KE and LME not only as mucin substitutes, but also as a source to increase Akkermansia muciniphila biomass yields and release short-chain fatty acids. The work is relevant to the food and pharmaceutical industries in the preparation of the probiotic ingredient.

When and why do cuteness cues intensify the power of message framing in promoting pro-environmental behaviors?

Gain and loss message framing has been utilized to encourage consumers’ pro-environmental behaviors in the hospitality and tourism industries. However, little is known about when and why presenting different types of cuteness cues influences the relative effectiveness of gain-framed and loss-framed messages, despite the commonness of cuteness cues in the service environment. To address this gap, this research examines the interaction effects between message framing (gain vs. loss) and cuteness type (kindchenschema vs. whimsical) on consumers’ pro-environmental responses. Through three cross-cultural studies using the experimental design approach, our results show that when kindchenschema cuteness cues are present, loss-framed (vs. gain-framed) messages generate more favorable pro-environmental responses. In contrast, gain-framed (vs. loss-framed) messages are more effective when whimsical cuteness cues are present. Moreover, results from the mediation analyses revealed that the sense of feeling right is the underlying mechanism explaining these effects. These findings provide critical implications for theory and practice.

Extraction of Centella asiatica herb using microwave-assisted solvent extraction: Optimization of crude extract using Box-Behnken design

Centella asiatica, is renowned in traditional medicine for its diverse applications, such as treating lupus, skin ailments, leprosy, fever, gastrointestinal issues, mental disorders, neurodegenerative conditions, and enhanced cognitive functions. Microwave-assisted solvent extraction (MASE) was chosen as a more effective, efficient, and environmentally friendly extraction method than the conventional method used to extract Centella asiatica. This study aims to optimize the extraction process for Centella asiatica using the Box-Behnken Design experimental approach. The experimental results showed that the highest yield, 62.25 %, was obtained at a microwave power of 450 W, feed-solvent (F/S) ratio of 0.05, and extraction time of 5 min. The lowest yield, 20.69 %, was obtained at a microwave power of 450 W, F/S ratio of 0.10, and extraction time of 10 min. The critical parameters under investigation include extraction time, microwave power, and F/S ratio. Employing Box-Behnken design (BBD) allows the identification of conditions that provide optimal results. The results showed the optimum conditions to achieve a maximum extraction yield of 62.4912 % were microwave power of 546.18 W, F/S ratio of 0.05 g/mL, and extraction time of 5.10 min.

Can We Simplify Liposome Manufacturing Using a Complex DoE Approach?

Microfluidic liposome production presents a streamlined pathway for expediting the translation of liposomal formulations from the laboratory setting to clinical applications. Using this production method, resultant liposome characteristics can be tuned through the control of both the formulation parameters (including the lipids and solvents used) and production parameters (including the production speed and mixing ratio). Therefore, the aim of this study was to investigate the relationship between not only total flow rate (TFR), the fraction of the aqueous flow rate over the organic flow rate (flow rate ratio (FRR)), and the lipid concentration, but also the solvent selection, aqueous buffer, and production temperature. To achieve this, we used temperature, applying a design of experiment (DoE) combined with machine learning. This study demonstrated that liposome size and polydispersity were influenced by manipulation of not only the total flow rate and flow rate ratio but also through the lipids, lipid concentration, and solvent selection, such that liposome attributes can be in-process controlled, and all factors should be considered within a manufacturing process as impacting on liposome critical quality attributes.