Optimization Tool Research Articles

RSM versus ANN for modeling and optimization of magnetic adsorbent based on montmorillonite and CoFe2O4

A highly resourceful, environmentally benign, and recyclable magnetic montmorillonite composite (MMT/CF) was obtained through a simple one-step hydrothermal method and exhibited excellent Pb (II) removal. The as-synthesized adsorbent was then characterized by XRD, SEM–EDX, FTIR, BET, and TGA-DTA. The operating parameters including adsorbent dosage, initial Pb (II) concentration, solution pH, and time were studied. Also, a comparative approach was formed between response surface methodology (RSM) and artificial neural network (ANN) to optimize and model the removal efficiency of Pb (II) by MMT/CF. The results indicated that the ANN model was more precise and quite trusted optimization tool than RSM in consideration of its higher correlation coefficient (R2 = 0.998) and lower prediction errors (RMSE = 0.851 and ADD = 0.505). Langmuir isotherm provided the best fit to the experimental data, and the maximum adsorption capacity was 101.01 mg/g. Additionally, the kinetic studies showed that the pseudo-second-order model fitted well with the experimental data. The magnetic MMT/CF composite possesses high adsorption capacity and is suitable for reuse. Therefore, this study shows that MMT/CF composite can be a potential adsorbent in Pb (II) uptake from aqueous media.

Enhancing manufacturing productivity: A review of AI-Driven supply chain management optimization and ERP systems integration

This abstract delves into the realm of manufacturing productivity enhancement through the review of AI-driven supply chain management (SCM) optimization and Enterprise Resource Planning (ERP) systems integration. As industries strive for operational excellence, the convergence of artificial intelligence (AI) and supply chain management emerges as a transformative force in driving efficiency, agility, and competitiveness. Through a comprehensive analysis, this abstract examines the synergistic relationship between AI-driven SCM optimization and the integration of ERP systems, elucidating their collective impact on manufacturing productivity. AI-driven SCM optimization encompasses a spectrum of technologies and methodologies, including predictive analytics, machine learning, and autonomous decision-making systems, aimed at optimizing various facets of the supply chain, from demand forecasting and inventory management to production planning and logistics optimization. By harnessing the power of AI, manufacturers can enhance forecasting accuracy, reduce lead times, optimize inventory levels, and mitigate supply chain disruptions, thereby improving overall productivity and customer satisfaction. Integration of ERP systems plays a complementary role in manufacturing productivity enhancement by providing a centralized platform for data management, process automation, and cross-functional collaboration. Through seamless integration with AI-driven SCM optimization tools, ERP systems enable real-time data exchange, actionable insights, and end-to-end visibility across the supply chain, facilitating informed decision-making and agile response to dynamic market conditions. Drawing insights from case studies and industry examples, this abstract highlights best practices, challenges, and emerging trends in AI-driven SCM optimization and ERP systems integration. Strategies for successful implementation, including organizational readiness assessment, change management, and stakeholder engagement, are discussed to guide manufacturers in unlocking the full potential of these transformative technologies. In conclusion, the convergence of AI-driven SCM optimization and ERP systems integration offers a compelling pathway for enhancing manufacturing productivity, driving operational excellence, and sustaining competitive advantage in the digital era.. Keywords: Artificial Intelligence, Supply Chain Management, Enterprise Resource Planning, Manufacturing Productivity, AI Integration, Predictive Analytics.

The water energy food nexus: A multi-objective optimization tool

Many methods and tools are used to model and optimize various aspects of the water energy food nexus (WEFN). This work presents a novel software tool for the multi-objective optimization of the WEFN (MOO-WEFN). The model underlying the tool captures all three nexus sectors and the interlinkages between them. In addition, the model imposes constraints that mimic forces affecting the nexus, such as economics, environment, health, and nutrition. The software tool couples Excel with Python, which facilitates the tool's accessibility and ease of use due to its widespread usage and availability. A case study application demonstrates the tool's execution and provides examples of how changes can be made to the data to simulate different nexus developments. Five scenarios are applied to reflect such changes with results demonstrating the overall impact on resource production and consumption. Removing one of the less water-intensive food items results in a 20 % increase in water consumption. Limiting the availability of surface water results in a reallocation of water resources such that 80 % of water needs are satisfied from surface water and groundwater and 20 % from wastewater, compared to the baseline of 100 % surface water. Moreover, upon introduction of the conventional activated sludge treatment technology for wastewater (compared to the incumbent membrane bioreactor technology), energy consumption decreased by 10 %. These results show changes beyond the immediate sector of change and reflect the necessity for integrated modeling that captures the impact of one change on the nexus as a whole, in terms of resource consumption and allocation. Thus, the tool supports the capability of testing how new resources, technologies, and limitations will impact nexus interactions. Furthermore, the tool facilitates carrying out sensitivity and Pareto analyses for data generation and result evaluation.

A framework to characterize, model, and optimize water-energy systems: case study of a novel HDH system

The rapid development in water-energy systems calls for advanced modeling and optimization tools to improve the technologies throughputs and minimize their energy consumption. While having a wide footprint in multiple research areas, Artificial Intelligence applications in water-energy systems are still in early stages. There is a need for generalized models to fully characterize parametric relationships, optimize technologies' performance, and have the flexibility to apply to different complex and non-linear systems. This article describes a digital twin framework that can be used for that purpose. This framework provides fundamental understanding of the process as in process-driven models alongside with the accuracy and usability of data-driven methods. The framework's structure focused on modeling and optimization aspects of digital twin models. As a part of developing a novel humidification-dehumidification desalination technology, this framework was used to model energy consumption based on 16 different operational parameters and was accurate to within 1 % of the data. Pairwise parameters sensitivities were identified by the framework for two case studies involving the whole cycle operation and a critical subsystem of the technology. Moreover, the framework was used to optimize the technology performance through data-efficient Bayesian search methods. Different search realms were used in this process. The framework was able to identify minimum and maximum energy consumption regions by sampling only 25 data points out of possible 5157 cases.

Excel as an optimization tool applied to multicomponent distillation column sizing

The unit operation of distillation is a method of significant importance for industrial separation processes, as it enables the fractionation of a mixture based on the differences in volatility among its components. Considering that a typical initial mixture generally contains three or more products of interest, studies aimed at optimizing multicomponent distillation, although scarce in the literature, are increasingly imperative to ensure efficiency and reduce operational and energy costs associated with the process. Since sizing multicomponent distillation columns using the Fenske-Underwood and Gilliland (FUG) and Kirkbride methods involves extensive and complex calculations to obtain operational parameters, the objective of this study was to develop a computational method using Microsoft Excel® software to make them more practical and enhance the accuracy of the results obtained. The functionality of the developed spreadsheet was verified through the resolution of an example of application, both manually and electronically. In both cases, the results obtained were identical, but with significantly lower time consumption and probability of error by the electronic method, demonstrating its potential for use in academic and industrial settings.

Model based data-driven optimisation of automated fibre placement set up

The composites manufacturing industry relies heavily on manual hand layup, unsuitable for increasing demands. Automated Fiber Placement (AFP) offers a solution, but setup complexity and extensive trials inflate costs. Digital tools promise to expedite development, but CPU-intensive simulations limit large-scale parameter optimisation. This paper introduces Gaussian Process (GP) models for understanding AFP parameters’ relationship with nip-point temperature. The GP emulator streamlines optimisation, offering accurate power curves with minimal simulations. An efficient method to enhance emulator performance through sequential design is also proposed, providing a cost-effective decision tool for AFP optimisation.

On the renormalisation group, protein folding, and naturalness

Abstract I am showing how the ideas behind the renormalisation group can be generalised in order to produce the desired reduction in the degrees of freedom, other that the ones considered up to now. Instead of looking only at the renormalisation group flow, inspiration from optimisation tools for regulators of truncated theories is used to show that there exists another mathematical structure, in the morphisms between various renormalisation groups, characterised by their operations, encoded by means of various regularisation functions. This expands the idea of renormalisation group to a renormalisation category. A group structure exists at the level of those morphisms, leading to new information emerging in the flowing process. Impact on problems like the naturalness and protein folding is being presented briefly.

Energy-efficient mobile edge computing assisted by layered UAVs based on convex optimization

The utilization of unmanned aerial vehicles (UAVs) as aerial mobile edge computing (MEC) servers presents an effective approach for mitigating the computational limitations of intelligent mobile devices. However, the limited battery capacity of UAVs poses a significant challenge in ensuring sustained service provision. To counter this obstacle and enhance energy efficiency, we introduce a partial offloading MEC scheme assisted by layered UAVs (POAL). Our objective is to minimize the total energy consumption of UAVs by jointly optimizing several factors, including wireless channels, transmit power, task partition, computing power, and UAV trajectories. Due to the non-convexity of the problem, we decompose it into three sub-problems and address them iteratively. Firstly, we employ the CVX optimization tool to allocate wireless channels and utilize Lagrangian duality to determine the optimal transmit power. Secondly, leveraging the monotonicity of the optimization objective, we derive the optimal computing power. Lastly, we employ the successive convex approximation (SCA) technique to tackle the trajectory planning sub-problem. Numerical results demonstrate that the proposed algorithm can effectively position UAVs within 15 iterations. Furthermore, our layered scheme significantly reduces overall energy consumption.

The Value of Adding Exosome-Based Prostate Intelliscore to Multiparametric Magnetic Resonance Imaging in Prostate Biopsy: A Retrospective Analysis

Introduction: Currently, there is limited evidence for the relationship of Exosome-based Prostate Intelliscore (EPI) and multiparametric magnetic resonance imaging (mpMRI) in stratifying risk for clinically significant prostate cancer. Using a retrospective cohort study design, we sought to characterize the relationship between these two noninvasive metrics and prostate biopsy outcome. Methods: Data were collected via electronic medical record for all patients who underwent EPI testing from 1 January 2019 to 3 February 2022 and had available medical records at a single mid-western university medical center. Positive test result was defined as >15.6 for EPI, ≥3 PI-RADS score and ≥3 + 4 Gleason Score for biopsy findings. Utility of EPI, mpMRI and combined use was characterized through calculation of sensitivity, specificity, positive predictive value, negative predictive value, and ROC analysis. Results: A total of 226 patients were identified as receiving EPI testing for risk stratification of clinically significant prostate cancer. Sensitivity for EPI was 91%, mpMRI was 90%, and the highest was combined use at 96%. With ROC analysis, AUC for EPI alone was 0.57 (95% CI, 0.47–0.67) and 0.78 (95% CI, 0.70–0.87) for mpMRI alone. With prior positive EPI result, AUC for combined use with mpMRI was 0.80 (95% CI, 0.71–0.89). Further subgroup analysis resulted in increased AUC values of EPI 0.67 (95% CI, 0.48–0.87), mpMRI 0.90 (95% CI, 0.76–1.0), and combined 0.90 (95% CI, 0.75–1.0) in the African American population. Discussion: We observed that the combined use of EPI and mpMRI led to an avoided biopsy in 43% of patients. Using both parameters increased the overall sensitivity and diagnostic accuracy in detecting clinically significant prostate cancer. The best test performance was observed in the African American cohort. Identifying optimal noninvasive tools to assess risk for prostate cancer is crucial to providing accurate and cost-effective care. Future study should utilize a prospective study design to further support the combined use of these metrics.

Low-Resolution Optimization for an Unmanned Aerial Vehicle Communication Network under a Passive Reconfigurable Intelligent Surface and Active Reconfigurable Intelligent Surface

This paper investigates the optimization of an unmanned aerial vehicle (UAV) network serving multiple downlink users equipped with single antennas. The network is enhanced by the deployment of either a passive reconfigurable intelligent surface (RIS) or an active RIS. The objective is to jointly design the UAV’s trajectory and the low-bit, quantized, RIS-programmable coefficients to maximize the minimum user rate in a multi-user scenario. To address this optimization challenge, an alternating optimization framework is employed, leveraging the successive convex approximation (SCA) method. Specifically, for the UAV trajectory design, the original non-convex optimization problem is reformulated into an equivalent convex problem through the introduction of slack variables and appropriate approximations. On the other hand, for the RIS-programmable coefficient design, an efficient algorithm is developed using a penalty-based approximation approach. To solve the problems with the proposed optimization, high-performance optimization tools such as CVX are utilized, despite their associated high time complexity. To mitigate this complexity, a low-complexity algorithm is specifically tailored for the optimization of passive RIS-programmable reflecting elements. This algorithm relies solely on closed-form expressions to generate improved feasible points, thereby reducing the computational burden while maintaining reasonable performance. Extensive simulations are created to validate the performance of the proposed algorithms. The results demonstrate that the active RIS-based approach outperforms the passive RIS-based approach. Additionally, for the passive RIS-based algorithms, the low-complexity variant achieves a reduced time complexity with a moderate loss in performance.

Optimal design of steel exoskeleton for the retrofitting of RC buildings via genetic algorithm

In recent decades, steel exoskeletons have gathered significant attention as a seismic retrofitting technique for existing structures. The design methods proposed so far are focused on the identification of the system's overall parameters through simplified models. Although these methodologies provide helpful guidance at the preliminary design stage, they do not consider aspects such as the distribution of the exoskeletons and sizing of their components. To overcome these limitations, an optimization process based on the Genetic Algorithm is proposed in this paper to identify the optimal exoskeleton number and spatial arrangement, and to determine the optimal size of their constituent elements. The algorithm aims to minimize the weight of the retrofit solution while keeping the whole existing structure in the elastic field and ensuring the structural verification of the exoskeleton's elements. The analyses have been conducted using a finite-element code with an Open Application Programming Interface, which allows the models to be handled through automatic routines. The proposed optimization tool has been applied to several case studies, considering two different layouts for the exoskeletons. Finally, the effectiveness of the retrofit method has been demonstrated, and the proposed optimization tool has been able to significantly reduce the weight and cost of the intervention.

Embodied carbon optimisation of concrete pile foundations and comparison of the performance of different pile geometries

Concrete production and construction are responsible for a considerable share of the total carbon emissions annually. With the emerging need to cut carbon emissions from the construction sector, there has been a big interest in optimising the embodied carbon of superstructures. However, limited attention is given to optimising the embodied carbon of foundations as most designers are more interested in addressing the optimal foundations cost instead. For the first time in the open literature, this paper presents a generic genetic-algorithm-based tool to optimise the design of reinforced concrete piles. The algorithm is capable of allocating the optimal design parameters and geometry for reinforced concrete piles at any given soil conditions and required pile capacities. The algorithm is used to compare the environmental impact of different concrete pile types; solid cylindrical piles, hollow cylindrical piles, solid tapered piles and hollow tapered piles at different load capacities, the optimisation results are then compared to common industrial pile designs to quantify the possible carbon and material savings. Results show that a significant cut of more than 70% of the embodied carbon values can be achieved if the optimal pile type is used compared to common industrial design. Moreover, a finite element model built and validated over ABAQUS is used to compare the geotechnical performance of the different pile geometries. Finite element analysis results show a negligible difference between the stiffness of the different pile types when tested in the same soil conditions highlighting an outstanding optimisation efficiency of the proposed optimisation tool.

Intensity-modulated radiotherapy quality assurance by alanine-EPR and gel dosimetry of a simulated prostate treatment with bilateral metallic prostheses

The presence of metallic prostheses in patients undergoing prostate radiotherapy treatment can lead to scattered doses, compromising treatment reproducibility. This study aims to assess doses in the Planning Target Volume (PTV) and surrounding areas using a water phantom containing pelvic bones and bilateral metallic prostheses. Intensity Modulated Radiotherapy (IMRT) with optimization tools avoiding input dose to the prosthesis was employed. Experimental verification utilized a modified Fricke xylenol orange gel dosimeter (FXO-f) in a 63 mm diameter, 100 mm height cylinder (310 ml volume) for PTV dose checks, and alanine dosimeters for assessing doses in the PTV vicinity and near metallic prostheses. Evaluating doses near prostheses is vital as post-radiotherapy prosthesis loosening has been speculated, possibly linked to overexposure. Gamma evaluation with FXO-f dosimeter yielded approved gamma indices in 97.7% of data points versus TPS, indicating good agreement with linear accelerator-reproduced results. Alanine dosimeter results ranged between (1.0 ± 0.3), (1.2 ± 0.3) Gy, (1.4 ± 0.3) Gy, and (2.0 ± 0.3) Gy, which are comparable to TPS-calculated doses within the dosimeter volume. This result indicates that the heterogeneity correction applied by the Analytical Anisotropic Algorithm used for dose calculation and the avoidance tool employed in the treatment planning could addressed the problem. In summary, this study demonstrates that the treatment technique entering fields towards prostheses, with optimization tools to produce the desirable results.

Speed Control of Induction Motors using Neuro Fuzzy Expert Systems

Induction motors and their speed control is critical aspect in several real life applications. Often, the proportional integral derivative (PID) controlling mechanism is found in several applications in industries where speed of motors or induction motors is to be controlled. The PID controller is specifically useful since it tries to minimize the steady state error as well as increase the response or speed of the system, thereby incorporating the benefits of proportional derivative and proportional integral control. However, the real time operation of PID controllers is challenging due to its tuning. The controlling mechanism is critically important for the application of the PID. Previously, manual tuning was used which needed experts and was also prone to errors. With the advent of sophisticated optimization tools, automatic tuning has gained momentum. In this work, a combination of neural networks and fuzzy logic often called neuro fuzzy expert systems has been proposed for the speed control of induction motors. It has been shown that proposed system is capable to attain better results compared to conventional techniques. The system has been designed on Matlab/Simulink. Key Words: Induction Motors, Speed Control, PID Controllers, Fuzzy Logic, Neuro Fuzzy Expert Systems.

Analysis and comparative assessment of charging dynamics in vertical multi-channel latent heat storage system with corrugated wavy channels

Latent heat thermal energy storage (LHTES) is a promising technology, but thermal response limitations caused by the relatively poor thermal conductivity of phase change materials (PCMs) remains an issue. In recent years, computational fluid dynamics (CFD) has proven to be a powerful and reliable tool in design optimization of different systems and problems in the energy sector. Building on that, the present work will use CFD to investigate the thermal performance enhancements achieved using vertical double-tube LHTES systems with multi-channel sinusoidal wavy geometries. The main parameters investigated here are the wavy channel height (H), pitch (P) and the number of channels (N) and the results are assessed in terms of melting rates and heat transfer coefficients. The analysis found that increasing the height from 1 mm to 3 mm, accelerated the phase change by 21 %, while reducing the pitch from 12.5 mm to 5 mm, enhanced the heat storage rates by 28 %. In addition, increasing the number of channels from 3 to 7 improved the charging rate by 64 %. Compared to a conventional straight channel, the enhanced wavy channel (N = 7, H = 3 mm, P = 5 mm) achieved 80 % higher thermal storage rate and 42 % faster charging time. The above findings provide new insight into the potential of utilizing compact vertical LHTES systems via customized wavy channels, with significant impact towards enhancing the existing thermal energy storage systems.

Precise correction of a spectrum of β-thalassemia mutations in coding and non-coding regions by base editors

β-thalassemia/HbE results from mutations in the β-globin locus that impede the production of functional adult hemoglobin. Base editors (BEs) could facilitate the correction of the point mutations with minimal or no indel creation, but its efficiency and bystander editing for the correction of β-thalassemia mutations in coding and non-coding regions remains unexplored. Here, we screened BE variants in HUDEP-2 cells for their ability to correct a spectrum of β-thalassemia mutations that were integrated into the genome as fragments ofHBB. The identified targets were introduced into their endogenous genomic location using BEs and Cas9/homology-directed repair (HDR) to create cellular models with β-thalassemia/HbE. These β-thalassemia/HbE models were then used to assess the efficiency of correction in the native locus and functional β-globin restoration. Most bystander edits produced near target sites did not interfere with adult hemoglobin expression and are not predicted to be pathogenic. Further, the effectiveness of BE was validated for the correction of the pathogenic HbE variant in severe β0/βE-thalassaemia patient cells. Overall, our study establishes a novel platform to screen and select optimal BE tools for therapeutic genome editing by demonstrating the precise, efficient, and scarless correction of pathogenic point mutations spanning multiple regions of HBB including the promoter, intron, and exons.

Optimization of the first wall cooling circuits to achieve an efficient coolant flow distribution in the DCLL breeding blanket

In the current design proposal of the Dual Coolant Lithium Lead (DCLL) breeding blanket for the EU DEMO reactor, the first wall is cooled down by a succession of He channels arranged along the poloidal length. In this scheme, since He extracts around 30% of the blanket thermal power, a conservative oversizing of the coolant mass flow rate compelled by highly heterogeneous heat loads, can severely jeopardize the blanket thermal efficiency and the consumption of the auxiliary systems. A meticulous design of the hydraulic network can enhance the cooling system efficiency by ensuring that each channel is fed with a mass flow rate according to its specific needs.In this study, a novel approach employing genetic algorithms has been developed to optimize the geometry of the first wall, encompassing the feeding/collecting manifolds and channels. This optimization aims to replicate the mass flow rate distribution obtained from TOMFLOW (Tool for Optimization of Helium Mass Flow Rate Distribution), a code dedicated to determine the minimum mass flow rate required in each channel to maintain the EUROFER steel structure below 550 °C.

Fused filament fabrication using stainless steel 316L‐polymer blend: Analysis and optimization for green density and surface roughness

AbstractThis study is centered on the analysis of composite component additive manufacturing, via fused filament fabrication (FFF), comprising of 316L stainless steel particles in a polymer matrix. It examines the impact of several process factors of FFF, including extrusion speed, layer height, and extrusion temperature, on the density and surface roughness with the goal to minimize porosity. The independent and interaction impacts of these parameters were investigated using a central composite design technique. The technique of analysis of variance was utilized to determine the influence of relevant factors. Regression analysis was used to establish statistical models linking the parameters to green density and surface roughness. The green density was enhanced by reducing the layer height from 0.2 to 0.1 μm and decreasing the nozzle speed from 100 to 20 mm min−1. The surface roughness was improved by using a slow printing speed and minimum layer height. The ideal temperature range for producing favorable results in terms of green density and surface roughness during extrusion was found to be between 235 and 240°C. Significant correlations were found between the parameters and the green density and surface roughness. A genetic algorithm was used as an optimisation tool to determine the thresholds that would provide the highest green density and the lowest surface roughness values. The porosity of the samples generated with the optimized settings was evaluated using microtomography scans. The methodology presented here can be applied to composite and standard polymeric filament printing to determine optimal printing parameters.Highlights Blend of stainless steel 316L and polymer was used for fused filament fabrication. Printing speed and layer height were the dominating for density and roughness. Height 0.2 mm, speed 20 mm s−1, and temperature 239°C resulted 4.73 g cm−3 density and 21.09 μm roughness Microtomography revealed porosity of 1.7% in the optimized sample.

Hydroacoustic optimization with using Noise-GAN

In recent years, noise pollution has a significant impact on marine organisms, hence requiring some restrictions and safety protocols. The primary objective of these restrictions is to minimize the noise generated by human-driven vehicles in aquatic environments. As a result, hydroacoustical studies are becoming increasingly integrated into design studies. The objective of this study is to provide an innovative approach to the design of hydrofoils, are considered a crucial component in the field of hydroacoustic engineering. The objective of this approach is to create a cutting-edge optimization tool through the integration of machine learning and hydroacoustic performance calculations. This article presents the development of a novel method called Noise-GAN, combines Generative Adversarial Networks (GAN) algorithms with hydroacoustic optimization capabilities. The GAN algorithm is used as a dimensionality reduction method in the optimization process, allowing for quick exploration of the design space and obtaining unique profile geometries during optimization. This method is used to generate optimal hydrofoil geometry for various conditions. The hydroacoustic and hydrodynamic performances of the generated geometry are analyzed to determine the applicability and performance of the method. The results are compared to two existing dimensionality reduction method to enhance comprehension of the performance. In order to gain insight into the performance of generated geometries compared to traditional geometries, the results are also compared to the performance data of the profiles available in the literature. This article also includes comparing the performance results of the NACA0009 profile, which is typically employed in hydrofoil research, with the optimal geometries to evaluate of the method and the performance of the generated geometries. In order to determine the real-life applicability of the hydrofoil geometries generated by the method, optimization studies were performed at the five different Angle of Attack (AoA) conditions within the range of 0o - 15o. In this way, the feasibility of the method at different AoA values was also examined. The results of all these comparisons demonstrate that the Noise-GAN method, which was developed to generate hydroacoustically optimized hydrofoil geometry, is highly effective in a variety of respects. The optimization tool developed in this study generates hydrodynamically efficient and unique hydrofoil profiles while optimizing for hydroacoustical performance. The results of this study are presented in this paper.

Benchmarking AI design skills: insights from ChatGPT's participation in a prototyping hackathon

AbstractThis study provides insights into the capabilities and performance of generative AI, specifically ChatGPT, in engineering design. ChatGPT participated in a 48-hour hackathon by instructing two participants who acted out its instructions, successfully designing and prototyping a NERF dart launcher that finished second among six teams. The paper highlights the potential and limitations of generative AI as a tool for ideation, decision-making, and optimization in engineering tasks, demonstrating the practical applicability of generating viable design solutions under real-world constraints.