Design Optimization Process Research Articles

A Parameterized Prediction Method for Turbulent Jet Noise based on Physics-informed Neural Networks

Abstract Turbulent noise prediction is integral to fluid equipment design, and multiple simulations or experiments are often required for noise distribution under varying operating conditions during the design optimization process, which could be expensive. Recently, the Physics Informed Neural Networks (PINNs) method has emerged as an efficient machine learning method for solving parameterized partial differential equations with geometric shapes, boundary conditions, and equation parameters as variable parameters through a single training session without data. In this study, a parameterized prediction method is developed to predict turbulent jet noise based on PINNs without any training datasets. Both two-dimensional (2D) and three-dimensional (3D) jet flow problems are solved. The 2D problem is solved with the Reynolds number as a variable parameter, and the 3D problem is solved with the Reynolds number and nozzle eccentricity as variable parameters. The predicted results are in good agreement with those from conventional computational fluid dynamics (CFD), with average errors of 3% and 6% for the 2D and 3D flow and acoustic power fields, respectively. In terms of computational efficiency, the time required by the method for the three-dimensional problem with two variable parameters is only one-seventh of that of the traditional CFD method. This study demonstrates that for engineering noise scenarios with varying parameters, the method based on PINNs offers a more efficient parameterized predicting approach and is promising for future applications.

Numerical Design Structure Matrix–Genetic Algorithm-Based Optimization Method for Design Process of Complex Civil Aircraft Systems

In the requirement-driven forward design process of civil aircraft, the large number of design tasks of complex systems with varying difficulty and the complex relationships between design tasks lead to unnecessary repetitive design iterations. In order to solve the above problems, the concept of overlap coefficient is proposed to further sort out the forward and backward logical relationships between design tasks and the civil aircraft system design process optimization model based on a numerical design structure matrix. The algorithm NSGA-II is improved and verified with the flight control system design as a case study. The results show that the proposed method can effectively improve the efficiency of complex system design and provide technical support for the optimization of the design process of complex civil aircraft systems.

Design and Analysis of Electric Vehicle Wireless Charging System

because of its higher safety, convenience and flexibility than traditional wired charging. Studying the power transmission theory of the wireless charging system and improving the essential components is a significant way to increase its performance. This essay first outlines the present state of research in this field and highlights its primary issues. It then goes on to discuss the various forms of wireless power transmission also called WPT, the elements that make up a magnetic coupling resonant circuit, and its compensation structure based on the theory. Through theoretical derivation and the summary of the analysis of the design optimization scheme, it is concluded that the planar circular coil is better, and the optimization design process is explained to increase this system's efficiency even further. The results show that S-S topology is more suitable and then provides a scheme for the optimization of coil parameters.

Evaluation of Mixing Process in Batch Mixer Using CFD-DEM Simulation and Automatic Post-Processing Method

A batch mixer is an important piece of equipment for polymer filling modification, and the kinematics of agglomerate breakup and distribution are necessary for the structure design and mixing process optimization of the rotor, particularly in light of the cohesive forces that exist within the agglomerate. In this paper, computational fluid dynamics (CFD) was coupled with discrete element method (DEM) to simulate the mixing process, including breakup and distribution, which was further quantitatively evaluated by the post-processing involving numerical method. To study the mixing process of an agglomerate composed of massive spherical particles (individual particle ratio was r), the coordinates of the particles were exported from the CFD-DEM simulation results. Then, the coordinate data were automatically processed with an automate custom-built post-processing program to obtain the average radius of gyration (Rgy) and the particle distribution density (ε). The kinematics analyzation of breakup and distribution was represented by curve of Rgy/r versus mixing time (t) and curve of ε versus t, respectively. The value of Rgy/r and ε decreased over time until they reached an equilibrium and vibrated around a certain value. In particular, a notable decline in the value of Rgy/r was observed following an increase prior to critical time. The increase in Rgy/r stated that the agglomerate or aggregates undergo stretching deformation. Additionally, mixing processes of rotors with different pressurization coefficients (S) and rotation speeds could be facilitated and intensified by large S and high rotation speed. Finally, a “breakup-line” was developed by considering the influence of cohesive force and rotation speed on the agglomerate breakup process. The agglomerate could be broken if the combination of rotation speed and bonding strength was above the “breakup line”, otherwise the agglomerate was not broken. Furthermore, rotors with larger slopes exhibited stronger breakup ability.

Model Adequacy in Assessing the Predictive Performance of Regression Models in Pharmaceutical Product Optimization: The Bedaquiline Solid Lipid Nanoparticle Example

This study aimed to assess the predictive performance of first- and second-order regression models in optimizing bedaquiline (BQ) solid lipid nanoparticle (SLN) formulations. A three-step central composite design and graphical optimization process was employed. A design of experiments method was used to evaluate the impact of BQ, Tween 80 (T80), polyethylene glycol (PEG), and lecithin on the formulations’ response variables, including Z-average (PSD), polydispersibility index (PdI), and Zeta potential (ZP). Secondly, we quantified the relationship between experimental variables using the regression model coefficients. Lastly, we predicted the responses and verified the models’ adequacies to ensure accurate representation and effective optimization. The first-order polynomial showed poor model adequacy and required further refinement due to its lack of explanatory power and significant predictors. Conversely, the second-order models provided superior fitness, sensitivity to variability, complexity, and prediction consistency. The optimized formulation achieved a desirability value of 0.9998, indicating alignment with the desired criteria. Specifically, the levels of BQ (19.4 mg), T80 (25.2 mg), PEG (39.2 mg), and lecithin (200 mg) corresponded to PdI (0.41), PSD (250.99 nm), and ZP (−25.95 mV). Maintaining a BQ concentration between 10 and 20% and T80 between 15 and 18% is vital for maximizing ZP and minimizing PdI and PSD, ensuring stable SLN formulations. This study underscores the significance of precise model selection and statistical analysis in pharmaceutical formulation optimization for enhanced drug delivery systems.

Risk−Based Cost−Benefit Optimization Design for Steel Frame Structures to Resist Progressive Collapse

The design of structures to resist progressive collapse primarily focuses on enhancing structural safety and robustness. However, given the low probability of accidental events, such designs often lead to a negative cost–benefit. To address this problem, this paper uses risk analysis to optimize the progressive collapse resistance design of steel frame structures. The elements’ cross-section design for the progressive collapse resistance of steel frame structures is optimized using genetic algorithms and SAP2000 23, which identify the structural model with the minimum robustness index while ensuring safety. The results show that the risk-based robustness index can effectively assess the cost of progressive collapse design. More importantly, the optimization model can rapidly identify the most cost-effective structural design solution that complies with progressive collapse resistance guidelines, enhancing the simplicity and usability of the structure design optimization process. Additionally, the integration of the SAP2000 API with Python 3.8 automation streamlines the parameterization process, minimizes manual errors, and enhances the precision and efficiency of the structural design optimization. Finally, the model’s effectiveness is validated through a case study, where the refined single-frame structure shows a reduction in initial construction and collapse-related costs by 2.4% and 9.1%, respectively. Meanwhile, the three-dimensional frame shows a 2.9% rise in initial costs but a 13.5% decrease in total collapse-resistant design costs, illustrating the model’s ability to balance safety with cost-effectiveness.

Optimization of Process Design and Operating Parameters of H2S Removal Unit to Reduce Lean Amine Inlet Temperature of Amine Contactor at Upstream Oil and Gas Subsidiary SI

Upstream Oil and Gas Subsidiary SI is a natural gas processing company that operates an H2S removal unit to convert natural gas rich in CO2 and H2S into sweet gas. The main problem of this unit is the high temperature of lean amine entering the Amine Contactor. The purpose of this study is to determine the factors of high lean amine temperatures, evaluate the lean amine cooler, amine regenerator overhead cooler, and plate exchanger performance, and determine the optimal process design configuration and operating parameters. The method used is the simulation of the H2S removal unit with Aspen HYSYS, followed by a comparative analysis between simulation data and equipment design data. The independent variables of this study include Reboiler duty, reflux ratio, and heat transfer area in the Plate Exchanger, with the main dependent variable being lean amine temperature. The results showed that the high lean amine temperature was caused by a decrease in the performance of the Lean Amine cooler and amine regenerator overhead cooler, as seen from the UA and LMTD values of the simulation results which were smaller than the design. In contrast, the Plate Exchanger still functions well with a UA value greater than the design. Optimization was carried out by adjusting the process design and operating parameters of the H2S removal unit. The optimized design involves bypass reflux from the regenerator to the rich amine stream entering the rich/lean amine exchanger and increasing the heat transfer surface area of the plate exchanger to 62.17 m². The influential operating parameters are reboiler duty, liquid flow rate to the mixer, and plate exchanger heat transfer surface area. Optimal operating conditions were achieved at a Reboiler duty of 1,642 kW, a liquid flow rate of 1.4 m³/h, the reflux to Mixer ratio is 100%, and a heat transfer surface area of 62.17 m². In addition, it can be concluded that the optimization of process design and operating parameters successfully reduced the lean amine inlet temperature of the Amine Contactor.

Optimizing Perforation Phasing through Nearest Neighbor Lookup and Delaunay Triangulation

Summary Sand production is a common occurrence in reservoirs with weak sandstone undergoing pressure depletion during hydrocarbon extraction. Among available techniques, the adoption of the cased, cemented, and perforated well completions (CCPs) stands out for its inherent safety measures and cost-effectiveness compared to alternative methods. This approach is anticipated to offer substantial potential for bolstering hydrocarbon yields when juxtaposed with the openhole completion methodology, positioning it as a preferable well completion strategy for such reservoirs. In the design of perforation arrangements, the determination of shots per linear foot (SPF, spf) is typically contingent upon the targeted hydrocarbon production capacity. Thus, fine-tuning the phase angle becomes imperative to forestall overlap within the damaged zones surrounding neighboring perforations, thereby mitigating the interaction between them—a pivotal consideration in the design optimization process. In light of the absence of constraints and the relative ease of implementing a single helical perforation pattern (SHPP) over other intricate designs, this research is centered on ascertaining the minimal separation between adjacent perforations, termed the minimum perforation-to-perforation spacing (PPSm), across various phase angles within this pattern. This objective is pursued through a swift exploration of nearest neighbors (NN) facilitated by a spatial-partitioning data structure, specifically a k-dimensional tree (KDTree), aimed at probing the optimal phase angles for customary values of SPF, predicated on a well diameter of 8½ in. Achieving a uniform distribution of the perforations has been realized through the application of mathematical and statistical principles, utilizing a parameter known as the equilateral likeness score (ELS). Employing the Delaunay triangulation, the arrangement of the perforations has been meticulously configured to minimize this score, thereby signifying the most even distribution of them. The optimal phase angles have been discerned from two distinct vantage points—maximizing the spacing between adjacent perforations and maximizing the feasible angle values for the phasing. A comparative analysis between the outcomes derived from the proposed theory and those from prior theories—including the isosceles obtuse triangle pattern (IOTP)—reveals the likelihood of notable disparities in the calculated optimal phase angles. Particularly within the realm of the two-wrapped-based methodologies, variations in the magnitude of these angles can be substantial, extending up to approximately 80° for certain shot densities. Notably, the optimal phase angles of 97° and 77° have been estimated for two prevalent shot densities of 6 spf and 12 spf, respectively, contrasting with the values of 99° and 143° previously obtained using IOTP. This substantial difference in phase angles observed for the shot density of 12 spf has been minimized to approximately 1° through refinement of the previous method, achieved by removing its constraint on the number of wraps.

Completion and Stimulation Design Evolution in Tight Chalk Formations in Offshore Norway

Summary Lower completion and acid stimulation designs for low-permeability chalk formations in a series of North Sea fields were modified from historical/legacy approaches to improve well performance for both production and injection purposes. The modifications included (1) a stimulation change from high-rate matrix acidizing to acid fracturing and (2) optimization of ball-activated sliding sleeve designs. The improvement in well performance was validated by actual productivity comparisons to offset wells. Further improvements are being developed for future extended reach wells. A ball-activated sliding sleeve completion was chosen for a new series of improved horizontal well completions. Sleeve spacing, the number of sleeves, and port sizes were subsequently optimized for targeted stimulated lateral lengths by pipe flow modeling and limited-entry design methods. Optimization of acid fracturing designs was achieved after incorporating critical findings from various laboratory tests including rotating disk tests, acid-etched fracture conductivity tests, and gel shear history simulator tests. The new acid fracturing treatment designs were generated with the help of numerical simulations that were continuously fine-tuned based on new observations made during treatments and rigorous analysis of bottomhole injection pressures during the treatment. As a result of the lower completion design optimization process, different-size nozzles were introduced into the sliding sleeves to treat up to five sleeves per stimulation stage with effective, limited-entry, fluid diversion. This allowed (1) use of available pumping weather windows effectively in the often-challenging North Sea offshore environment, (2) reducing or eliminating time-consuming wireline perforation runs, and (3) limiting acid exposure to mitigate ball/seat zonal isolation loss events (i.e., dissolvable balls were not always compatible with acid). The new and improved acid fracturing design enabled a reduction of the number of gel/acid cycles from five to three, which reduced stimulation cost without losing stimulation effectiveness. The new design also resulted in productivity enhancements depending on the well location within the structure. The largest performance improvement was observed in wells that were placed farther downflank, where stronger reservoir rock and lower permeabilities were found. These wells required a more intensive acid fracturing treatment to generate economical and sustainable production rates. Finally, wells that used the new stimulation techniques also tended to require a lower restimulation frequency. This type of analysis work has not been presented previously and it optimizes lower completion for acid fracturing stimulation on a well-by-well basis. Further improvement is expected as stimulation designs and completion technology continue to evolve.

Construction Strategies for Residential High Rise Buildings Decoration during Structure Work

The market's attention to the quality and efficiency of engineering construction is continuously increasing. Quality inspection departments, market departments, and others have begun strict supervision and review of projects, aiming to ensure that they are completed in accordance with the correct ideas and standards. Process interleaving is achieved through design optimization and process optimization, reducing processes and measures, and fully utilizing spatial and process parameters to achieve the goals of shortening time parameters, improving quality, and reducing costs. The design of process interleaving schemes lies in the effective utilization of the plane site and spatial resources on the construction site, maintaining the improvement of utilization efficiency, installing as many construction mechanization equipment as possible, and adopting an automated construction mode to improve not only construction efficiency but also reduce the impact of external temperature, humidity, and climate, thereby achieving better improvement in engineering construction quality.

РОЛЬ ТЕХНОЛОГІЙ БУДІВЕЛЬНОГО ІНФОРМАЦІЙНОГО МОДЕЛЮВАННЯ В АРХІТЕКТУРНІЙ ОСВІТІ

The article provides a detailed analysis of the role of building information technologies in the professional training of first-level (bachelor’s) degree students in the 191 "Architecture and Urban Planning" program at the Institute of Architecture and Design, Lviv Polytechnic National University. Special attention is paid to the study of the role of modern technologies in shaping the key skills and professional competencies of future architects. In particular, the integration of Building Information Modeling (BIM) and a wide range of other licensed software tools, which are actively used both in the professional field and in the educational process, is examined. The article explores the trends regarding the growing demand for specialized software among employers in the architectural labor market. It also considers the main differences between traditional architectural design methods, based on planar drawings and conceptual sketches, and modern information-based approaches that use digital tools to ensure precision, efficiency, and optimization of design processes. The significance of BIM technologies as one of the key aspects of the digital transformation in the architectural and engineering design process is emphasized. The article also analyzes methodological approaches to forming learning outcomes and developing specialized competencies necessary for preparing competitive professionals in the field. Significant attention is given to the challenges faced by instructors and students when implementing BIM technologies into the educational process. The article discusses potential obstacles and risks associated with the integration of modern digital technologies into the academic curriculum, as well as possible ways to overcome these challenges.

A novel machine learning workflow to optimize cooling devices grounded in solid-state physics

Cooling devices grounded in solid-state physics are promising candidates for integrated-chip nanocooling applications. These devices are modeled by coupling the quantum non-equilibirum Green’s function for electrons with the heat equation (NEGF+H), which allows to accurately describe the energetic and thermal properties. We propose a novel machine learning (ML) workflow to accelerate the design optimization process of these cooling devices, alleviating the high computational demands of NEGF+H. This methodology, trained with NEGF+H data, obtains the optimum heterostructure designs that provide the best trade-off between the cooling power of the lattice (CP) and the electron temperature (\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$ {\ ext{T}}_{e} $$\\end{document}). Using a vast search space of \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1.18 \ imes 10^{-5}$$\\end{document} different device configurations, we obtained a set of optimum devices with prediction relative errors lower than \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${4}\\,\\%$$\\end{document} for CP and \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${1}\\,\\%$$\\end{document} for Te. The ML workflow reduces the computational resources needed, from two days for a single NEGF+H simulation to 10 s to find the optimum designs.

Kinetic study of mineral oil removal from wastewater by the sono-electrochemical process.

Chemical kinetics can be a useful tool for determining the optimal operating time of electrochemical processes. The main objective of the study was to determine the mineral oil removal rate by sono-electrochemical treatment. In this study, zero-, first-, and second-order kinetic models were used to determine the reaction rate of mineral oil removal with the sono-electrochemical process. The reaction rate experiments were conducted under the following optimal conditions: 8 min of treatment time, a current density of 53.1 A/m2, and a flow rate of 0.23 L/s. It was found that the changes in mineral oil concentrations follow second-order kinetics with a coefficient of determination of 0.9732. The mineral oil removal efficiency was 94.4%. This study concludes that sono-electrochemical process could be a promising technology for the removal of mineral oil from wastewater, and that the mineral oil removal rate can be determined by chemical kinetics. The results obtained may be useful for the optimization of the sono-EC process and reactor design.

Dynamic modeling of post-combustion carbon capture process based on multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder network

Solvent-based post-combustion carbon capture (PCC) technology is a promising, near-term solution for decarbonizing power generation and industrial facilities. Model-based process simulation is crucial for the optimal design and operation of the PCC process. Recently, data-driven models have gained attention due to their adaptability, efficient computation and high accuracy. However, the nonlinearity, strong couplings and multi-time scale features of the PCC process pose significant challenges for model identification. To this end, this paper proposes a multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder (MMoE-DAED) network for dynamic modeling of the PCC process under wide operating conditions. An encoder-decoder composed of long short-term memory (LSTM) network is employed to extract features from the time-dependent input data and learn the complex dynamic interactions caused by the inertial and delay properties of the process. Dual-stage attention mechanism is incorporated into the encoder and decoder respectively to select the most relevant input features and their correlations within the time series data. To enhance multi-output prediction accuracy, multi-gate mixture-of-experts (MMoE) framework that considers correlations of multitask learning is implemented. Simulation results using operating data from a PCC experimental setup indicate that the proposed modeling approach accurately predicts the steady-state values and dynamic trends of the CO2 capture rate and stripper bottom temperature over a wide operating range. The RMSE, MAPE and R2 indices for the CO2 capture rate are 2.1592, 0.0295, 0.9641, respectively, and for the stripper bottom temperature are 0.1491, 0.0003, 0.9833, respectively. Validations on a PCC simulator further verify the accuracy and efficiency of the MMoE-DAED model, which enables an 80.87% reduction in computation time compared to the simulator. This paper points to a new direction for the data-driven dynamic modeling of complex energy conversion processes.

Multi-agent based optimal sizing of hybrid renewable energy systems and their significance in sustainable energy development

This paper delves into the enhancement and optimization of on-grid renewable energy systems using a variety of renewable energy sources, with a particular focus on large-scale applications designed to meet the energy demand of a certain load. As global concerns surrounding climate change continue to mount, the urgency of replacing traditional fossil fuel-based power generation with cleaner, more cost-effective and dependable alternatives becomes increasingly apparent. In this context, a comprehensive investigation is conducted on grid connected hybrid energy system that combines photovoltaic, wind, and fuel cell technologies. The study employs three state-of-the-art optimization algorithms, namely Walrus Optimization Algorithm (WaOA), Coati Optimization Algorithm (COA), and Osprey Optimization Algorithm (OOA) to determine the optimal system size and energy management strategies, all aimed at minimizing the cost of energy (COE) for grid-based electricity. The results of the optimization process are compared with the results obtained from the utilization of the Particle swarm optimization (PSO) and Grey Wolf optimizer (GWO). The findings of this study underscore both the practical feasibility and the critical importance of adopting on-grid renewable energy systems to decrease the dependence on traditional energy sources within the grid. The proposed WaOA succeeded to reach the optimal solution of the optimal design process with a COE of 0.51758129611 $//kwh while keeping the loss of power supply probability (LPSP), the reliability index, at 7.303681e-19. The practical recommendations and forward-looking insights provided within this research hold the potential to foster sustainable development and effectively mitigate carbon emissions in the future.

Design Method for Low-Ice-Class Propellers Based on Multi-Objective Optimization

The objective of this paper was to establish a comprehensive methodology for the optimized design of propellers for ice-class vessels, aiming to enhance hydrodynamic efficiency while ensuring structural integrity. This paper begins by introducing a novel approach for calculating blade stress, which takes into account both extreme ice loads and hydrodynamic loads, to be utilized in the propeller strength design process. Subsequently, a backpropagation (BP) neural network model was developed based on the data obtained from B-series propeller charts and integrated with a genetic algorithm to achieve a preliminary optimized design of the propeller’s hydrodynamic performance. To illustrate the application of this methodology, a case study of an ice-breaking tug propeller design is presented, detailing the optimization design process, including the preliminary, intermediate, and final design stages. The study also addresses key aspects such as geometric parameterization, the selection of optimization variables, the implementation of optimization algorithms, and the balance of multi-objective trade-offs. The proposed design approach can serve as a valuable reference for the practical engineering design of propellers for ice-class vessels, providing a systematic framework for achieving optimal performance in challenging operating conditions.

Critical construction waste minimization strategies for a circular economy in developing countries: A contractor’s perspective in China

AbstractDeveloping countries are often burdened by substantial construction waste (CW) generated through urbanization and urban renewal activities, highlighting the urgent need for effective CW minimization strategies to facilitate their transition towards a circular economy. Although previous studies have examined similar topics at various stages of construction projects from different perspectives, a comprehensive study integrating all critical stages from a contractor’s perspective is still lacking. To fill this gap, this study aims to identify critical CW minimization strategies in developing countries, with a holistic concentration on the planning, design, and construction stages, using China as a case study. æThe research began by compiling a comprehensive list of CW minimization strategies tailored to developing countries, based on an extensive desktop survey and a focus group interview, resulting in 32 strategies. A subsequent questionnaire survey with leading CW management experts and rigorous statistical analyses have identified 9 strategies as critical for minimizing CW in developing countries. Finally, through exploratory factor analysis, seven fundamental principles for CW minimization have been established: “Planning for CW Minimization” for the planning stage; “Optimized Design of Building Structures,” “Optimization of Design Process,” and “Stakeholders’ Efforts in the Design Stage” for the design stage; and “Optimization of Construction Techniques,” “Stakeholders’ Efforts in the Construction Stage,” and “Efforts on CW Disposal” for the construction stage. This study offers valuable insights for stakeholders in developing countries, empowering them to effectively minimize CW through targeted strategies, facilitating the transition to a circular economy and supporting the realization of the "zero-waste city" goal.

Hydrodynamic Shape Optimization of a Naval Destroyer by Machine Learning Methods

This paper explores the integration of advanced machine learning (ML) techniques within simulation-based design optimization (SBDO) processes for naval applications, focusing on the hydrodynamic shape optimization of the DTMB 5415 destroyer model. The use of unsupervised learning for design-space dimensionality reduction, combined with supervised learning through active learning-based multi-fidelity surrogate modeling, allows for significant improvements in computational efficiency while addressing complex, high-dimensional design spaces. By applying these ML techniques to both single- and multi-objective optimizations, aimed at minimizing resistance and enhancing seakeeping performance, the proposed framework demonstrates its practical value in hydrodynamic design. This approach provides a scalable and efficient solution, reducing the reliance on high-fidelity simulations while accelerating the optimization process, without substantial modifications to existing toolchains. A design-space dimensionality reduction of approximately 70% is achieved, reducing the design variables from 22 to 7 while retaining 95% of the original geometric variance. Additionally, computational cost reductions of 65% to 98% are observed, compared to using the full design space and high-fidelity simulations only.

Design and Optimization of a Piecewise Flight Controller for VTOL UAVs

The dynamic systems of unmanned aerial vehicles (UAVs) are susceptible to parametric uncertainties, unmodeled dynamics, and external vibrational disturbances during motion control. Although proportional–integral–derivative (PID) controllers are widely used in UAVs, the manual tuning process is time-consuming, and the resultant control performance is vulnerable to uncertainties in varying flight conditions, leading to suboptimal flight control throughout the entire hovering flight envelope. To address this issue, the present study designs and optimizes a novel piecewise flight controller based on a hybrid data-driven approach combining gradient-based methods and pattern search algorithms. The optimization process is validated through comprehensive flight testing, comparing the piecewise controller with the baseline controller across a wide range of flight conditions. The study examines the objective functions and design parameters, demonstrating the robustness of the optimized piecewise controller in the presence of disturbances. The results reveal significant variations in the system model under different flight conditions, and the piecewise optimized controller demonstrates a response that is more than twice as fast as the benchmark, with acceptable overshoots and steady-state errors under the predefined trajectories. The salient features of the proposed piecewise flight controller and design optimization process are verified through flight testing, which is expected to provide a framework for future UAV flight control designs.

Design optimization of quasi-rectangular tunnels based on hyperstatic reaction method and ensemble learning

The quasi-rectangular tunnel represents a novel cross-section design, intended to supersede the traditional circular and rectangular tunnel formats. Due to the limited capacity of the tunnel vault to withstand vertical loads, an interior column is often installed at the center to enhance its load-bearing capacity. This study aims to develop a hyperstatic reaction method (HRM) for the analysis of deformation and structural integrity in this specific tunnel type. The computational model is validated through comparison with the corresponding finite element method (FEM) analysis. Following comprehensive validation, an ensemble machine learning (ML) model is proposed, using numerical benchmark data, to facilitate real-time design and optimization. Subsequently, three widely used ensemble models, i.e. random forest (RF), gradient boosting decision tree (GBDT), and extreme gradient boosting (XGBoost) are compared to identify the most efficient ML model for replacing the HRM model in the design optimization process. The performance metrics, such as the coefficient of determination R2 of about 0.999 and the mean absolute percentage error (MAPE) of about 1%, indicate that XGBoost outperforms the others, exhibiting excellent agreement with the HRM analysis. Additionally, the model demonstrates high computational efficiency, with prediction times measured in seconds. Finally, the HRM-XGBoost model is integrated with the well-known particle swarm optimization (PSO) for the real-time design optimization of quasi-rectangular tunnels, both with and without the interior column. A feature importance assessment is conducted to evaluate the sensitivity of design input features, enabling the selection of the most critical features for the optimization task.