The anomalies in the High Voltage Converter Modulator (HVCM) remain a major down time for the Spallation Neutron Source (SNS) facility. To improve the reliability of the HVCMs, several studies using machine learning techniques were to predict faults ahead of time in the SNS accelerator using a single modulator. In this study, we present a multi-module framework based on Conditional Variational Autoencoder (CVAE) to detect anomalies in the power signals coming from multiple HVCMs that vary in design specifications and operating conditions. By conditioning the VAE according to the given modulator system, the model can capture different representations of the normal waveforms for multiple systems. Our experiments with the SNS experimental data show that the trained model generalizes well to detecting several fault types for several systems, which can be valuable to improve the HVCM reliability and SNS as a result.