To date, data fusion and sensor management systems have largely been implemented with centralized and hierarchical architectures. Numerical and statistical methods are the most common data fusion methods found in these systems. Some recent research has taken on distributed and decentralized systems, while there are other efforts that try to apply qualitative reasoning. However, little has been done to apply qualitative reasoning as an inference mechanism in distributed and decentralized systems. Based on other work by the authors, a sensor may be treated as a highly autonomous (decentralized) unit. In this context, this paper describes a distributed sensor-data-fusion theory based on a qualitative theory to interpret measurements, and on qualitative procedures to reason and make decisions based on the measurement interpretations. In this manner, fusion is done at a high-qualitative level, thus making it possible the implementation of intuitive (effective) methods to monitor, diagnose, and compensate processes/systems and their sensors.