Search Results (60)

In ethics-sensitive product development, Generative AI can improve the efficiency of concept generation, but it also raises challenges related to accountability, value alignment, and decision transparency. To address limitations in current human-AI co-design processes, including unclear allocation of decision-making authority, insufficiently structured translation from design requirements to design constraints, and limited explainability in scheme evaluation, this study proposes an explainable Human–Computer Interaction (HCI)-based decision support framework for human-AI co-design, termed GAGT. The framework integrates Generative AI with multi-criteria decision-making methods. Specifically, the Analytic Hierarchy Process (AHP) is used to structure design requirements and determine their priorities, Grey Relational Analysis (GRA) is used to compare candidate schemes, and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is used to support transparent final ranking. Within the framework, human designers are mainly responsible for requirement confirmation, priority judgment, review at key checkpoints, and final scheme selection, while AI mainly supports information organization, candidate scheme generation, and quantitative comparison. The framework was applied to the design of a community medical vehicle through a small-sample, case-based, quasi-experimental study. Compared with the human-only condition, the GAGT-supported condition reduced design time by 56.1%. Compared with the AI-autonomous condition, it showed no observed HIPAA violations and a Value Drift Index of 16.1%, indicating better consistency with human-defined priorities. The results suggest that the proposed framework may improve design efficiency while supporting clearer human oversight and decision explainability in Generative AI-assisted design, and may provide a structured approach to organizing human and AI roles in ethics-sensitive design tasks. Full article

As product aesthetics increasingly drive consumer preference, quantitative evaluation remains hindered by subjective evaluation biases and the black-box nature of modern artificial intelligence. This study proposes an advanced machine learning framework incorporating sensitivity-aware morphological features for the aesthetic evaluation of industrial products, with automotive design as a representative case. An aesthetic index system and its quantitative formulations are first developed to capture the morphological characteristics of product form. Subjective weights are determined via grey relational analysis (GRA), while objective weights are calculated using the coefficient of variation method (CVM) integrated with the technique for order preference by similarity to an ideal solution (TOPSIS). A game-theoretic weighting approach is then employed to fuse subjective and objective weights, thereby establishing a multi-scale aesthetic evaluation system. Sensitivity analysis is applied to identify six key indicators, forming a high-quality dataset. To enhance prediction performance, a novel model—improved lung performance-based optimization with backpropagation neural network (ILPOBP)—is proposed, where the optimization process leverages a maximin latin hypercube design (MLHD) to enhance exploration efficiency. The ILPOBP model effectively predicts aesthetic ratings based on limited morphological input data. Experimental results demonstrate that the ILPOBP model outperforms baseline models in terms of accuracy and robustness when handling complex aesthetic information, achieving a significantly lower test set mean absolute relative error (MARE = 4.106%). To further enhance model interpretability, Shapley additive explanations (SHAP) are employed to elucidate the internal decision-making mechanisms, offering reverse design insights for product optimization. The proposed framework offers a novel and effective approach for integrating machine learning into the aesthetic assessment of industrial product design. Full article

With the rapid development of the offshore wind power industry, the construction process of offshore wind power jackets faces numerous quality risks, particularly in welding, coating, and assembly operations. This paper aims to investigate the identification, assessment, and management of quality risks during the construction of offshore wind turbine foundation structures. By establishing a multidimensional quality risk assessment framework, key risk factors affecting quality were identified through expert interviews and brainstorming sessions. Comprehensive evaluations of these risk factors were conducted using the Entropy Weight Method (EWM), the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), and Grey Relational Analysis (GRA). The findings indicate that welding and coating processes pose the highest risks during construction. Based on these assessments, corresponding risk mitigation measures are proposed, including process optimization, automation enhancement, environmental control, and management system refinement. This study provides theoretical foundations and practical guidance for improving construction quality and reducing costs in offshore wind turbine foundation manufacturing. It advances quality risk management by introducing an integrated evaluation model that addresses the limitations of single-method approaches in complex construction scenarios. Full article

University rankings based on scientometric indicators frequently rely on compensatory aggregation models that allow extreme values to dominate the evaluation, while also remaining sensitive to outliers and unstable weighting procedures. These issues reduce the reliability and interpretability of the resulting rankings. This study proposes a hybrid BWM–GRA–PROMETHEE (BGP) framework that combines judgement-based weighting Best-Worst Method (BWM), outlier-resistant normalization Grey Relational Analysis (GRA), and a non-compensatory outranking method Preference Ranking Organization Methods for Enrichment Evaluation (PROMETHEE II). The framework is applied to an expert-validated set of scientometric indicators to generate more stable and behaviorally grounded rankings. The results show that the proposed method maintains stability under weight and threshold variations and preserves ranking consistency even under outlier-contaminated scenarios. Comparative experiments further demonstrate that BGP is more robust than Additive Ratio Assesment (ARAS), Multi-Attributive Border Approximation Area Comparison (MABAC), and The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), achieving the highest Spearman. This study contributes a unified evaluation framework that jointly addresses three major methodological challenges in scientometric ranking, outlier sensitivity, compensatory effects, and instability from data-dependent weighting. By resolving these issues within a single integrated model, the proposed BGP approach offers a more reliable and methodologically rigorous foundation for researchers and policymakers seeking to evaluate and enhance research performance. Full article

This study focuses on improving the fatigue strength and overall performance of sustainable biopolymer polylactic acid (PLA) components manufactured via Fused Deposition Modelling (FDM) additive manufacturing process. PLA, as a biodegradable and renewable polymer derived from natural resources, represents a promising alternative to conventional petroleum-based plastics in engineering and research applications. The influence of key FDM process parameters—layer height, infill density, and number of perimeters—on critical performance indicators such as filament consumption, printing time, and fatigue strength (number of cycles to failure) was systematically analyzed using the Taguchi L9 orthogonal array. Subsequently, Grey Relational Analysis (GRA) was applied as a multi-objective optimization technique to identify the parameter settings that achieve an optimal balance between mechanical durability and resource efficiency. The obtained results demonstrate that a proper combination of process parameters can significantly enhance the mechanical reliability and sustainability profile of FDM-printed PLA parts, contributing to the broader adoption of eco-friendly materials in additive manufacturing. Full article

Assessing the accessibility of urban metro stations is essential for optimizing metro system planning and improving travel efficiency for residents. This study proposes an innovative evaluation framework—the CWM-GRA-TOPSIS model—for comprehensive metro station accessibility assessment. First, a multi-dimensional indicator system is established, encompassing three key dimensions, to-metro accessibility, by-metro accessibility, and land use accessibility, which are further refined into 14 secondary indicators for detailed analysis. A Combination Weighting Method (CWM) is then introduced, integrating the Analytic Hierarchy Process (AHP) for subjective weighting and the Criteria Importance Through Intercriteria Correlation (CRITIC) method for objective weighting, with their integration optimized through Game Theory. Subsequently, the overall accessibility of metro stations is evaluated and ranked using a hybrid Grey Relational Analysis (GRA) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) approach. The proposed method is applied to Wuhan, China, to demonstrate its effectiveness and applicability. Results show that the CWM-GRA-TOPSIS model, by balancing objectivity and practical relevance, provides a more reliable and systematic approach for identifying accessibility disparities and formulating targeted improvement strategies for urban metro systems. Full article

Interest in surface integrity has grown in the manufacturing industry; indeed, it has become an integral part of the industry. It can be studied by examining surface roughness parameters, hardness variations, and microstructure. However, evaluating all these parameters together can be a challenging task. To address this multi-criteria decision-making model (MCDM), techniques such as Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and Grey Relational Analysis (GRA) provide a suitable solution for optimizing the machining parameters that lead to improved product quality. This work investigated surface roughness parameters, including arithmetic average surface roughness (2D) (Ra), mean surface roughness depth (2D) (Rz), area arithmetic mean height (3D) (Sa), and maximum surface height (3D) (Sz), in conjunction with Vickers macrohardness (HV) and optical micrographs, to analyze machined surfaces during the turning of X5CrNi18-10 steel. The results suggest that machining with a spindle speed (N) of 2000 rpm or v_c of 282.7 m/min, a feed rate (f) of 0.1 mm/rev, and a depth of cut of 0.5 mm yields the best surface, achieving an “A” class surface finish. These parameters can be applied in manufacturing industries that utilize chromium–nickel alloys. Additionally, the method used can be applied to rank the quality of the product. Full article

The article presents a comparative analysis of experimental results from tribological tests conducted using a ball-on-disc system, applying two multi-criteria decision-making methods: Grey Relational Analysis (GRA) and TOPSIS (Technique for Order Preference by Similarity to Ideal Solution). The aim of the study was to identify the most advantageous combinations of input parameters—load, sliding speed, and sliding distance—while simultaneously evaluating three output criteria: volumetric wear (VD), coefficient of friction (CoF), and weight loss (WL). The analysis covered 27 test variants, with different weighting factors assigned to each criterion to reflect their practical significance (0.35 for VD, 0.45 for CoF, and 0.2 for WL). The results obtained using the GRA method showed good agreement with the TOPSIS rankings in identifying the best-performing variants, although differences were observed due to the distinct algorithms used to evaluate trade-offs. The optimal solutions were characterized by low wear, a low coefficient of friction, and minimal weight loss. The study demonstrates the effectiveness of both methods for tribological analysis and suggests that their combined use can serve as a robust tool for optimizing the operating conditions of friction nodes. Full article

Additive manufacturing (AM) techniques, especially fused deposition modeling (FDM), offer significant advantages in terms of cost, material efficiency, and design flexibility. In this study, the mechanical performance of biodegradable PLA/PHA composite samples produced via FDM was optimized by evaluating the influence of key printing parameters—layer height, printing orientation, and printing speed—on both the tensile and compressive strength. A full factorial design (3 × 3 × 3) was employed, and all of the samples were triplicated to ensure the consistency of the results. Grey relational analysis (GRA) was used as a multi-objective optimization method to determine the optimal parameter combinations. An analysis of variance (ANOVA) was also conducted to assess the statistical significance of each parameter. The ANOVA results revealed that printing orientation is the most significant parameter for both tensile and compression strength. The optimal parameter combination for maximizing mechanical properties was a layer height of 0.1 mm, an X printing orientation, and a printing speed of 50 mm/s. This study demonstrates the effectiveness of GRA in optimizing the mechanical properties of biodegradable composites and provides practical guidelines to produce environmentally sustainable polymer parts. Full article

As a pivotal economic province in China, Jiangsu’s efforts in civil building energy conservation are critical to achieving the national “dual carbon” goals. This paper proposes a hybrid model that integrates wavelet transform, support vector regression (SVR), and extreme learning machine (ELM) to predict the civil building energy consumption of Jiangsu Province. Based on data from statistical yearbooks, the historical energy consumption of civil buildings is calculated. Through a grey relational analysis (GRA), the key factors influencing the civil building energy consumption are identified. The wavelet transform technique is then applied to decompose the energy consumption data into a trend component and a fluctuation component. The SVR model predicts the trend component, while the ELM model captures the fluctuation patterns. The final prediction results are generated by combining these two predictions. The results demonstrate that the hybrid model achieves superior performance with a Mean Absolute Percentage Error (MAPE) of merely 1.37%, outperforming both individual prediction methods and alternative hybrid approaches. Furthermore, we develop three prospective scenarios to analyze civil building energy consumption trends from 2023 to 2030. The analysis reveals that the observed patterns align with the Environmental Kuznets Curve (EKC). These findings provide valuable insights for provincial governments in future policy-making and energy planning. Full article

Plasma jet cutting is a non-conventional process commonly used in modern industry for processing metal sheets and preparing them for subsequent technological steps. In this context it is very important to achieve the best possible final-quality workpiece to minimize additional post-processing costs, and time. This is especially challenging by the plasma jet processing of aluminum and its alloys. In this paper, a comprehensive analysis regarding the machinability and optimal circular quality of aluminum alloy 5083 was performed. Process parameters whose effects were analyzed are the cutting speed, arc current and cutting height. The circular quality was considered through responses: the circular kerf width, circular bevel angle, and circularity error on the top and bottom sheet of the metal side. To design functional relations between the process inputs and quality performances, an artificial intelligence fuzzy logic technique supported by ANOVA was applied. In order to define the process conditions that result in optimal cut quality responses, the multi-objective optimization of hybrid grey relational analysis (GRA) and the fuzzy logic approach was presented. Corresponding surface plots were created to determine the Pareto front of optimal solutions that simultaneously optimize all circular quality objective functions. The optimization procedure was confirmed through a test in which the mean absolute percentage error represented as the validation metric. Full article

The additive manufacturing sector is rapidly developing, providing alternatives for mass production in the polymer composite industry. Due to the direction-dependent mechanical properties and high cost of fiber-reinforced polymeric materials, it is necessary to take advantage of alternative multi-materials and production technologies. In this study, a special geometric-shaped knitting technique was investigated using two different materials. The main material was polyamide 6 (PA6), and the inner or second material was PA6 with a 30 wt.% glass fiber addition by weight (PA6GF30). The special geometric shape, layer thickness, nozzle temperature, and post-heat treatment time were measured as process parameters in the production of the PA6/PA6GF30 composites with the fused deposition modeling (FDM) technique. The Taguchi design method and L9 fractional experiment were used in the experimental study. The mechanical behaviors of the PA6/PA6GF30 samples were obtained using tensile and impact tests. In addition, scanning electron microscopy (SEM) analyses were performed on the fracture lines of the PA6/PA6GF30 samples, and damage analyses were carried out in more detail. The experimental results were sorted using grey relational analysis (GRA). Moreover, the optimal experimental conditions and their related plots were obtained. As a result, the highest tensile strength of the PA6GF30 composite was 89.89 MPa with the addition of a special geometric shape. In addition, the maximum impact resistance value of the PA6/PA6GF30 composite was 83 kJ/m². Hence, the developed knitting method presented many advantages when using the FDM technique, and both were successfully used to produce the PA6/PA6GF30 composites. Full article

This paper presents research findings on the turning of AZ31B magnesium alloy using ceramic-coated tungsten carbide tool inserts in a dry environment. Fifteen experiments were conducted according to the Box–Behnken design (BBD) for the straight turning of AZ31B magnesium alloy to investigate the variations in two important machinability indicators, i.e., material removal rate ‘MRR’ and mean roughness depth ‘R_Z’, with variations in cutting speed ‘C_S’, feed rate ‘f_r’, and depth of cut ‘DoC’. The cutting speed and feed rate had the maximum influence on the mean roughness depth and material removal rate, respectively. To address the challenge of optimizing conflicting machining responses, desirability function analysis (DFA) and grey relational analysis (GRA) were employed to identify the optimal turning parameters for conflicting machinability indicators or responses. These techniques enabled the simultaneous maximization of the material removal rate and the minimization of the mean roughness depth, ensuring an effective balance between productivity and surface quality. The optimal turning conditions—cutting speed of 90 m/min, feed rate of 0.2 mm/rev, and depth of cut of 1.0 mm—yielded the best multiperformance results with an MRR of 18,000 mm³/min and an R_Z of 2.21 µm. Scanning electron microscope (SEM) analysis of the chip and flank surface of the cutting tool insert used in the confirmation tests revealed the formation of band-saw-type continuous chips and tool wear caused by adhesion and abrasion. Full article

Micro-milling is increasingly recognized as a crucial technique for machining intricate and miniature 3D aerospace components, particularly those fabricated from difficult-to-cut Ti-6Al-4V alloys. However, its practical applications are hindered by significant challenges, particularly the unavoidable generation of burrs, which complicate subsequent finishing processes and adversely affect overall part quality. To optimize the burr formation in the micro-milling of Ti-6Al-4V alloys, this study proposes a novel hybrid-ranking optimization algorithm that integrates Grey Relational Analysis (GRA) with the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). This approach innovatively combines GRA and TOPSIS with a random forest regression (RFR) model, facilitating the exploration of nonlinear and complex relationships between input parameters and machining outcomes. Specifically, the effects of spindle speed, depth of cut, and feed rate per tooth on surface roughness and burr width generated during both down-milling and up-milling processes were systematically investigated using the proposed methodology. The results reveal that the depth of cut is the most influential factor affecting surface roughness, while feed rate per tooth plays a critical role in controlling burr formation. Moreover, the GRA-TOPSIS-RFR method significantly outperforms existing optimization and prediction models, with the integration of the RFR model enhancing prediction accuracy by 42.6% compared to traditional linear regression approaches. The validation experimental results agree well with the GRA-TOPSIS-RFR-optimized outcomes. This research provides valuable insights into optimizing the micro-milling process of titanium components, ultimately contributing to improved quality, performance, and service life across various aerospace applications. Full article

This study investigates the correlation between bluff body parameters and vortex flowmeter performance through big data modeling and machine learning techniques. Vortex flowmeters are widely used in industry due to their high accuracy and minimal pressure loss. Nonetheless, optimizing their design remains challenging due to the complex relationship between input and output parameters. Symmetry in bluff body design is crucial for vortex formation and stability. In this study, Latin Hypercube Sampling (LHS) was employed to generate 10,000 symmetry bluff bodies, and efficient serial simulations were conducted using Ansys Fluent, significantly reducing computational costs compared to traditional CFD methods. A regression model was developed using scikit-learn to map eight geometric parameters to eight performance indicators, achieving excellent fitting accuracy with residuals far smaller than the simulation accuracy of ANSYS Fluent. Through Grey Relational Analysis (GRA), objective function analysis, and in conjunction with CFD contour maps, this study has analyzed the relationships between input and output parameters and their impact on the Karman vortex street. This work has significantly improved the speed of big data collection and provided a solid theoretical foundation for data-driven optimization through big data analysis. In addition, the improvement of existing machine learning methods has achieved high-precision prediction and system parameter optimization, promoting the design of vortex flowmeters. Full article