In multilayered cement-based structures, the characteristics of ultrasonic waves are influenced by the laminar and meso-scale properties of the materials, leading to frequency dispersion effect. This phenomenon enables the utilization of surface wave dispersion energy (SWDE) to identify the damages in these structures. However, interpreting complex composite damages using SWDE in such structures is challenging. To address this, the potential of convolutional variational autoencoder (CVAE) in detecting complex composite damage in multilayered cement-based structures through SWDE is investigated in this work. Specifically, the finite difference method is employed to establish the model for the ultrasonic wave field in multilayered cement-based structures, incorporating the mesoscopic material properties. Subsequently, ultrasonic wave signals, indicative of different types of complex composite damages, are extracted and transformed into SWDE. Finally, the CVAE model, trained with these SWDE datasets, is employed for the identification of various damages. The results demonstrate that the proposed method is capable of effectively extracting and interpreting structural characteristics in the time, frequency, and spatial domains from SWDE, and is sensitive to changes in structural features due to invisible complex composite damages in multilayered cement-based structures. The effectiveness of the proposed method is validated by compared to other deep learning methods.