Multitarget prediction and optimization of pure electric vehicle tire/road airborne noise sound quality based on a knowledge- and data-driven method

•The bidirectional knowledge graph of the tire/road airborne sound quality is proposed.•A multitarget prediction method based on the adaptive balanced learning mechanism for ResNet is proposed.•A knowledge- and data-driven method is developed for the prediction and optimization of TRA sound quality.•The proposed method overperformed the conventional prediction and optimization methods in effectiveness and robustness.