Software fault localization remains challenging due to limited feature diversity and low precision in traditional methods. This paper proposes a novel approach that integrates multi-objective optimization with deep learning models to improve both accuracy and efficiency in fault localization (FL). By framing feature selection as a multi-objective optimization problem (MOP), we extract and fuse three critical fault-related feature sets: spectrum-based, mutation-based, and text-based features, into a comprehensive feature fusion model. These features are then embedded within a deep learning architecture, comprising a multilayer perceptron (MLP) and gated recurrent network (GRN), which together enhance localization accuracy and generalizability. Experiments on the Defects4J benchmark dataset with 434 faults show that the proposed algorithm reduces processing time by 78.2% compared to single-objective methods. Additionally, our MLP and GRN models achieve a 94.2% improvement in localization accuracy compared to traditional FL methods, outperforming state-of-the-art deep learning-based FL method by 7.67%. Further validation using the PROMISE dataset demonstrates the generalizability of the proposed model, showing a 4.6% accuracy improvement in cross-project tests over state-of-the-art deep learning-based FL method.