Form Design of Manual Wheelchair Products Based on Evaluation Grid Method and BP Neural Network

In modern rehabilitation assistive devices, manual wheelchairs are a key tool for improving the quality of life for people with mobility impairments. Their design should consider functionality and safety and deeply explore users' emotional needs to achieve a more humane and attractive product form design. This study is based on the theory of Kansei Engineering, combined with the Evaluation Grid Method (EGM) and Back-propagation Neural Network (BPNN) methods, aiming to establish a mapping relationship model between user emotional needs and the design elements of manual wheelchair product form to explore manual wheelchair product design solutions that meet user emotional needs. Firstly, the manual wheelchair samples were evaluated using the EGM to identify attractiveness factors based on user preferences. Then, the semantic difference (SD) method is used to quantify users' Kansei imagery evaluation of manual wheelchair products. Finally, by constructing a BPNN model, the mapping relationship between the design elements of the manual wheelchair form and the user's Kansei imagery was achieved. Mean square error (MSE) was used as a metric to measure the accuracy of the BPNN model to validate the effectiveness of the BPNN prediction model. This study not only enhances the rationality of the form design of manual wheelchair products but also provides valuable references for product design and manufacturing driven by user attractiveness.