To address the issue of insufficient recognition accuracy caused by the continuous emergence of novel modulated signals in dynamic scenarios, an incremental recognition method for modulated signals driven by feature and semantics is proposed. First, a multi-dimensional feature representation of modulated signals is constructed. A class-incremental knowledge distillation learning mechanism is introduced into a parallel temporal convolutional network to mitigate feature drift under multi-task iteration in dynamic environments. Meanwhile, a modulated semantic map is built based on multi-dimensional features, and a nearest neighbor strategy is adopted to classify both new and existing modulated signals. Furthermore, a joint loss function is designed by integrating distance loss, Laplacian eigenvalue optimization loss, and knowledge distillation loss, which enhances intra-class compactness and inter-class separability of different modulated signals in the semantic space, thereby improving recognition accuracy. Experimental results demonstrate that the proposed method achieves an average recognition accuracy of 84.46% across multiple incremental tasks, outperforming conventional incremental recognition methods by 10%. It effectively enhances the capability of incremental recognition of signal modulation types in dynamic scenarios.