With the rapid expansion of the Electric Sport Utility Vehicle (ESUV) market, capturing consumer aesthetic preferences and emotional needs through front-end styling has become a key issue in automotive design. However, traditional Kansei Engineering (KE) approaches suffer from limited timeliness, subjectivity, and low predictive accuracy when extracting affective vocabulary and modeling the nonlinear relationship between product form and Kansei imagery. To address these challenges, this study proposes an improved KE-based ESUV styling framework that integrates data mining, machine learning, and generative AI. First, real consumer reviews and front-end styling samples are collected via Python-based web scraping. Next, the Biterm Topic Model (BTM) and Analytic Hierarchy Process (AHP) are used to extract representative Kansei vocabulary. Subsequently, the Back Propagation Neural Network (BPNN) and Support Vector Regression (SVR) models are constructed and optimized using the Seagull Optimization Algorithm (SOA) and Particle Swarm Optimization (PSO). Experimental results show that SOA-BPNN achieves superior predictive accuracy. Finally, Stable Diffusion is applied to generate ESUV design schemes, and the optimal model is employed to evaluate their Kansei imagery. The proposed framework offers a systematic and data-driven approach for predicting consumer affective responses in the conceptual styling stage, effectively addressing the limitations of conventional experience-based design. Thus, this study offers both methodological innovation and practical guidance for integrating affective modeling into ESUV styling design.

To design an asymmetric supercapacitor device with high capacitance, high energy density, and excellent cycling stability, a NiCo₂O₄@NiWO₄/MXene ternary composite cathode and a hydrophilic carbon nanotube (H-CNTs) anode were constructed and matched for device assembly. The NiCo₂O₄@NiWO₄/MXene cathode with a “nanowire@nanosheet” core-shell hierarchical structure was prepared through a two-step hydrothermal method combined with high-temperature annealing, while hydrophilic carbon nanotubes were obtained by concentrated nitric acid modification. The microstructure, crystal structure, elemental valence states, and pore characteristics of the electrode materials were systematically characterized by SEM, TEM, XRD, XPS, and nitrogen adsorption–desorption measurements. The results showed that the introduction of Ti₃C₂T_x MXene formed an effective conductive network, while the core-shell hierarchical structure provided abundant electrochemically active sites and increased the specific surface area of the ternary composite to 156.4 m²/g. In a three-electrode system, the NiCo₂O₄@NiWO₄/MXene electrode exhibited a specific capacitance of 1830 F/g at 1 A/g and retained 983 F/g at 15 A/g, while the H-CNTs anode delivered a specific capacitance of 774 F/g at 1 A/g. Based on the working potential windows, specific capacitances, and charge balance relationship of the positive and negative electrodes, the active material mass ratio was optimized to approximately 1:2.8. An asymmetric supercapacitor was subsequently designed using a “cathode–separator–anode” laminated configuration with NiCo₂O₄@NiWO₄/MXene as the cathode, H-CNTs as the anode, glass fiber as the separator, and 6 M KOH as the electrolyte. The assembled NiCo₂O₄@NiWO₄/MXene//H-CNTs device operated stably within a voltage window of 0–1.6 V and achieved a specific capacitance of 256 F/g at 1 A/g. The device delivered an energy density of 91.0 Wh/kg at a power density of 800 W/kg and maintained 97.3% of its initial capacitance after 12,000 charge–discharge cycles. These results demonstrate that the proposed electrode matching and laminated structural design can effectively improve the capacitive performance, energy storage capability, and cycling stability of the asymmetric supercapacitor, providing a useful basis for the design and performance optimization of high-performance supercapacitor devices.