Modern industry is migrating from reactive to proactive or predictive maintenance of its assets to increase operational availability and efficiency, extend its useful life cycle and reduce its life cycle cost. Multiphysics modeling together with data-driven analytics generate a new paradigm called “Digital Twin,” which creates a living model of industrial asset. The living model can continually adapt to the environmental and operational changes using real-time sensory data and forecast the future condition of corresponding physical counterpart. It becomes possible to predict the operational condition and the remaining useful life of the physical twin. Data fusion techniques particularly play a significant role in the digital twin framework. The flow of information from raw data to high-level decision making is propelled by sensor-to-sensor, sensor-to-model, and model-to-model fusion. This chapter identifies and highlights the role of data fusion in the digital twin ecosystem for predictive maintenance of industrial assets.