Multi-scale analysis and optimisation of three-dimensional woven composite structures combining response surface method and genetic algorithms

Based on the concept of multi-objective optimization, the requirement for the design of un-round cross-sectioned airframe and stealthy performance combines the Pareto methodology and Genetic Algorithm, by using the selected operators which are the reproduction, niche and the Pareto set filter. Niched Pareto Genetic Algorithm gives better distribution and also to improve the optimization efficiency of response surface method (RSM). Based on the N-S equations numerical method to calculate the aerodynamic performance and the application of physical theory of optics and diffraction to calculate the cross-sectional area of the scattering radar, it compromises and optimizes the objective of being non-cylindrical cross-sectioned and stealthy. Hence, optimized design results are obtained.

This study conducts the simulation on optimisation of injection moulding process parameters using Autodesk Moldflow Insight (AMI) software. This study has applied some process parameters which are melt temperature, mould temperature, packing pressure, and cooling time in order to analyse the warpage value of the part. Besides, a part has been selected to be studied which made of Polypropylene (PP). The combination of the process parameters is analysed using Analysis of Variance (ANOVA) and the optimised value is obtained using Response Surface Methodology (RSM). The RSM as well as Genetic Algorithm are applied in Design Expert software in order to minimise the warpage value. The outcome of this study shows that the warpage value improved by using RSM and GA.

Hybrid approach based on response surface methodology and artificial neural networks coupled with genetic algorithm (RSM-GA-ANN) for the Prediction and optimization for the Photodegradation of dye using nano ZnO anchored glass fiber under solar light irradiation

Adaptive neuro-fuzzy inference system-genetic algorithm vs. response surface methodology: A case of optimization of ferric sulfate-catalyzed esterification of palm kernel oil

This study examined the modelling and optimisation of the electrocoagulation-flocculation (ECF) recovery of aquaculture effluent (AQE) using aluminium electrodes. The response surface methodology (RSM), artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) were used for the modelling, while the optimisation tools were the numerical RSM and genetic algorithm (GA). Furthermore, the kinetics of the ECF process was studied to provide insight into the mechanism governing the ECF of AQE. The experimental design was performed using the central composite design (CCD) of the RSM. The ANFIS modelling was accomplished via the Grid Partition (GP) of the data set, while the ANN used the multi-layer perceptron (MLP) based feed-forward system. Statistically, the prediction accuracy of the models followed the order: ANFIS (R2: 0.9990), ANN (R2: 0.9807), and RSM (R2: 0.9790). The process optimisation gave optimal turbidity (TD) removal efficiencies of 98.98, 97.81, and 96.01% for ANFIS-GA, ANN-GA, and RSM optimisation techniques, respectively. The ANFIS-GA gave the best optimization result at optimum conditions of pH 4, current intensity (3 A), electrolysis time (7.2min), settling time (23min), and temperature (43.8°C). In the kinetics study, the experimental data was analysed using pseudo-first-order (0.8787), pseudo-second-order (0.9395), and Elovich (R2: 0.9979) kinetic models; the Elovich model gave the best correlation with the experimental data showing that the process is governed by electrostatic interaction mechanism. This study effectively demonstrated that ECF recovery of AQE can effectively be modelled using RSM, ANN, and ANFIS and be optimised using RSM, ANN-GA, and ANFIS-GA techniques, and the order of performance is ANFIS > ANN > RSM and ANFIS-GA > ANN-GA > RSM, respectively.

This study focuses on the modeling and optimization of geothermal binary Organic Rankine Cycle (ORC) systems to enhance power generation from geothermal systems using water as geofluid. Aspen HYSYS, utilizing the Peng-Robinson property package, was used to simulate the process, generating critical process data for subsequent modeling and optimization. Response Surface Methodology (RSM) and an Artificial Neural Network (ANN) were employed to model the relationships between input factors and output response, utilizing a Box-Behnken Design (BBD) for three key input variables: working fluid flow rate, working fluid outlet pressure, and turbine outlet pressure. Both RSM and ANN demonstrated strong predictive capabilities, with RSM achieving an R2 value of 0.9966 and an RMSE of 12.254, while ANN achieved an R2 value of 0.9886 and an RMSE of 23.722, indicating that RSM marginally outperformed ANN in terms of modelling accuracy. Optimization of the ORC system was conducted using RSM and ANN coupled with a Genetic Algorithm (ANN-GA), aimed at determining the optimal values for input and output parameters. The ANN-GA optimization results were validated using Aspen HYSYS and showed superior performance over RSM. ANN-GA predicted optimal values of working fluid flow rate, working fluid outlet pressure, and turbine outlet pressure as 12 kg/s, 19 bar, and 1.2 bar, respectively, which perfectly matched the Aspen HYSYS validation results. This optimization yielded a power output of 958.48 kW, which closely aligned with the Aspen HYSYS validation output of 952.9 kW, reflecting a minimal percentage error of 0.59%. Conversely, RSM predicted slightly deviated optimal values of 11.8 kg/s, 18.47 bar, and 1.2 bar, with a corresponding power output of 940.78 kW. When validated with HYSYS, the RSM-predicted output was 927.2 kW, resulting in a higher percentage error of 1.46%, thereby underperforming relative to ANN-GA. The study highlights the comparative strengths of RSM and ANN-GA, demonstrating that while RSM excels in accurately modeling the relationship and interactions between input factors and output responses, the ANN-GA framework exhibits a significantly higher capability in navigating complex nonlinear optimization landscapes. This highlights the effectiveness of integrating machine learning models with meta-heuristic algorithms for enhanced optimization performance. The findings contribute to advancing the methodology for optimizing geothermal ORC systems and offer a robust framework for improving power generation efficiency in geothermal energy applications.

This study presents a comprehensive thermal analysis, design, and optimization framework for electrothermal heating systems integrated into composite wing structures. Thermal behavior is first investigated using finite volume simulations conducted with a commercial solver. An in-house thermal solver is then developed based on the governing heat transfer equations and a second-order finite difference discretization scheme. The in-house solver is validated against the commercial solver, showing a maximum deviation of less than 1%. The validated solver is subsequently coupled with a genetic algorithm to perform multi-objective optimization of the electrothermal heating system. A novel correlation for the convection heat transfer coefficient over airfoil surfaces is developed based on extensive turbulent flow simulations and a genetic algorithm. The developed correlation equation has significantly lower percent relative error (from 34% to 6%) compared to flat plate correlations. The developed convection coefficient is incorporated into the optimization process. Key design variables, including heat generation intensity, heater strip dimensions, and the thermal conductivity of composite and surface protection materials, are included in the optimization process. An original objective function is formulated to simultaneously minimize electrical power consumption, prevent ice formation on the external surface, and limit internal temperatures to safe operating ranges for composite materials. The optimized design is evaluated under both spatially varying and constant convection heat transfer coefficients to assess the impact of convection modeling assumptions. The proposed methodology provides a unified and extensible framework for the optimal design of electrothermal ice protection systems and can be readily extended to three-dimensional composite wing configurations.

The three‐dimensional (3D) printed poly lactic acid (PLA) bone plates lack mechanical strength, resulting in premature failure. Coating these plates with polydopamine (PDM) forms covalent bonds with the PLA molecular structure, enhancing their mechanical properties. The mechanical strength of the coated bone plates is influenced by infill density, submersion time, shaker speed, and coating solution concentration. However, conducting experiments for each parameter value to achieve maximum biomechanical tensile strength (BTS) and biomechanical flexural strength (BFS) is time‐consuming and costly. Overall, the combination of response surface methodology (RSM) and machine learning (ML) enables determination of the best printing parameters, leading to reduced material waste, personalized bone plates tailored to individual anatomy, improved implant fit, and functionality. Moreover, this approach has the potential to reduce the need for additional surgeries and overall costs. To optimize coating parameters, this study employs RSM and ML techniques, including genetic algorithm (GA), particle swarm optimization (PSO), random search optimization (RSO), and differential evolution (DE). Experimental validation of the optimized process parameters and their corresponding fitness values is carried out using both RSM and ML approaches. The results demonstrate that GA has the closest relationship between experimental and fitness values, followed by DE, RSM, PSO, and RSO. Highlights Direct immersion coating of polydopamine on 3D printed PLA bone plates. Evaluating mechanical strength for bone plates coated at varying parameters. Statistical modeling and optimization of mechanical strength using RSM. Mechanical strength optimization and convergence properties for ML models. Experimental validation of RSM and ML‐based optimization algorithms.

The goal of this study is to present a methodology for the determination of the optimal cutting parameters (spindle speed, feed rate and tool point angle) during the drilling process of carbon fiber reinforced polymer composites (CFRP) to maximize the material removal rate by considering surface roughness, delamination and thrust force as the constraints through coupling Response Surface Method (RSM) and Genetic Algorithm (GA). In this regard, the advantages of statistical experimental design technique, experimental measurements, Response Surface Method (RSM) and the genetic optimization method are exploited in an integrated manner. To this end, the experiments on CFRP were conducted to obtain surface roughness, delamination factor and thrust force values based on the full factorial design of experiments, and then analysis of variance (ANOVA) is performed. The predictive models for outputs were created using Response Surface Method (RSM) taking advantage of the experimental data. Material removal rate constituted the main function for the genetic algorithm, and thrust force, delamination, and surface roughness were applied as the constraints of the GA function. The function was optimized by the GA code, and finally, the optimum variables were obtained, and the results of the GA were tested experimentally. It can be clearly observed that good agreement exists between the predicted values and the experimental measurements.

As a key parameter in the adsorption process, removal rate is not available under most operating conditions due to the time and cost of experimental testing. To address this issue, evaluation of the efficiency of NH4+ removal from stormwater by coal-based granular activated carbon (CB-GAC), a novel approach, the response surface methodology (RSM), back-propagation artificial neural network (BP-ANN) coupled with genetic algorithm (GA), has been applied in this research. The sorption process was modeled based on Box-Behnben design (BBD) RSM method for independent variables: Contact time, initial concentration, temperature, and pH; suggesting a quadratic polynomial model with p-value < 0.001, R2 = 0.9762. The BP-ANN with a structure of 4-8-1 gave the best performance. Compared with the BBD-RSM model, the BP-ANN model indicated better prediction of the response with R2 = 0.9959. The weights derived from BP-ANN was further analyzed by Garson equation, and the results showed that the order of the variables’ effectiveness is as follow: Contact time (31.23%) > pH (24.68%) > temperature (22.93%) > initial concentration (21.16%). The process parameters were optimized via RSM optimization tools and GA. The results of validation experiments showed that the optimization results of GA-ANN are more accurate than BBD-RSM, with contact time = 899.41 min, initial concentration = 17.35 mg/L, temperature = 15 °C, pH = 6.98, NH4+ removal rate = 63.74%, and relative error = 0.87%. Furthermore, the CB-GAC has been characterized by Scanning electron microscopy (SEM), X-ray diffraction (XRD) and Brunauer-Emmett-Teller (BET). The isotherm and kinetic studies of the adsorption process illustrated that adsorption of NH4+ onto CB-GAC corresponded Langmuir isotherm and pseudo-second-order kinetic models. The calculated maximum adsorption capacity was 0.2821 mg/g.

Structured lipids were prepared from mustard oil by enzymatic acidolysis reaction with capric acid (C10) using lipase enzyme TLIM from Thermomyces lanuginosus as biocatalyst. Parameters such as substrate molar ratio, enzyme concentration, reaction temperature, stirring speed and time of maximum incorporation, were studied for the optimization of the reaction. The optimized set of process conditions was predicted by response surface methodology (RSM) and genetic algorithm (GA). The robustness of GA and RSM was evaluated using regression coefficient and p value. The R(2) found out by GA was 0.996 while from RSM was 0.973. The results proved that GA models have better performance than RSM models. From the result, it could be concluded that optimal conditions for synthesis of capric acid rich mustard oil were: Temperature = 39.5°C ; time = 21.1hr; Substrate ratio = 3.5; Enzyme content = 8.8%; Speed = 570.8rpm.

Patch‐repaired plain woven composite structures were exposed to internal damage caused by impact during service, which reduced mechanical properties. A multi‐scale modeling strategy was proposed to study the impact resistance characteristics of patch‐repaired plain woven carbon‐fiber‐reinforced‐polymer (CFRP) laminates. The micro representative volume element (RVE) was extracted from the yarn; a local homogenization method was used to obtain the equivalent cross‐ply laminate (ECPL) cells corresponding to the mesoscale RVE. The finite element model (FEM) of patch‐repaired plain woven laminate was established by extending the ECPL cells. The FEM was checked by the low‐velocity impact (LVI) tests, and the impact parameter errors were within 10%. Furthermore, impact resistance of repaired specimens under different impact conditions (e.g., the impact energy was 3 ~ 20 J) was studied. Finally, patch parameters (patch thickness, patch size, off‐axis angle) of the repaired specimen were optimized by multi‐objective optimization based on the surrogate model and response surface method (RSM). After multi‐objective function optimization, the optimal patch parameter configuration (the thickness of the patch was 0.87 mm, the diameter was 66 mm, and the off‐axis angle was 44.2°) reduced the absorbed energy value of the repaired specimen from 4.9089 to 4.1640 J, and the delamination area of the repaired specimen from 605 to 280 mm2. All the results provide a reference for patch repair of plain woven composites.

A novel multiscale strategy is proposed for the damage analysis of masonry structures modeled as periodic composites. Such a computational strategy, whose aim is to reduce the typically high computational cost exhibited by fully microscopic numerical analyses, is based on a multiscale/multidomain model equipped with an adaptive capability, which allows to automatically zoom-in the zones incipiently affected by damage onset. The associated model refinement criterion requires the determination of microscopically informed first failure surfaces, which take into account both classical and bending deformation effects, by taking advantage of a couple-stress based homogenization technique. In order to assess the efficacy of the proposed multiscale modeling strategy, some numerical simulations are presented, involving a medium-sized wall test subjected to combined shear and flexure loading conditions. The related accuracy and computational performances of this methodology are investigated via suitable comparisons with a purely discrete model of masonry. Special attention is devoted to the analysis of the bending macroscopic deformation effects. Further comparisons with experimental results taken from the literature are carried out in order to validate its predictive capability in terms of peak and post-peak mechanical behavior.

Purpose This paper aims to construct a quantitative model using response surface methodology and optimize the structural parameters of Chip Scale Package (CSP) solder joints through genetic algorithms. This approach enhances the reliability of CSP solder joints under coupled tensile and shear loading, thereby improving the overall reliability of electronic products. Design/methodology/approach A finite element model for CSP solder joints was established using ANSYS software. Stress−strain finite element analysis was performed under coupled tensile and shear loading conditions. The resulting stress and strain distribution within the solder joints under this coupled loading was obtained. An experimental platform was constructed, and stress measurement experiments on CSP solder joints under coupled tensile and shear loading were conducted, thereby validating the accuracy of the simulation results. Taking solder joint diameter, solder joint height, pad diameter and pad thickness as design parameters, and the coupled tensile-shear stress value in the CSP solder joint as the objective, 27 sets of parameter level combinations were designed using the Response Surface Methodology. Corresponding finite element models for these 27 sets were established and subjected to simulation analysis under coupled tensile and shear loading. The relationship between the 27 sets of coupled stress values and the CSP solder joint morphological parameters was fitted using the response surface method, establishing a quantitative relationship equation. This equation was then subjected to optimization analysis using a genetic algorithm. Findings The results indicate that the location of maximum stress and strain is at the interface between the solder joint and the lower pad, which is identified as a potential failure site. The theoretically optimal combination of morphological parameters for the CSP solder joint, obtained via the genetic algorithm, is as follows: solder joint diameter of 0.3180 mm, solder joint height of 0.2302 mm, pad diameter of 0.2286 mm and pad thickness of 0.0168 mm. Simulation verification of this optimal parameter set demonstrated that the coupled tensile and shear stress value under the optimal combination is superior to those obtained from the 27 simulation experiments. This successfully achieves the morphological parameter optimization of CSP solder joints under coupled tensile and shear loading. Originality/value The relationship between the 27 sets of coupled stress values and the CSP solder joint morphological parameters was fitted using the response surface method, establishing a quantitative relationship equation. This equation was then subjected to optimization analysis using a genetic algorithm.

In performing structural design or demonstrating the reliability of electronic devices, it is necessary to take various scatters into consideration which are induced in the load assessment, material characteristics, stress analyses and manufacturing. Therefore, a new method for probabilistic reliability design for electronics packages is proposed in this paper. In this method, firstly the probability distributions of the characteristic values such as stress values are calculated by combining stress analysis, response surface methodology and the Monte Carlo method. Consequently, the fracture probability can be derived by comparison of the probability distributions with the design criteria. Secondly, the probability on many assumptions can be updated using a new method based on Bayes theory for the purpose of estimating the reliability of the packages more accurately in combination with actual data or reliability tests. The new method was applied for the structural design of flip-chip BGA packages. The results of the application fro flip-chip BGA package design indicate that the new method is useful for the structural reliability design.