Process supervisory systems in large scale chemical plants have traditionally relied on single monolithic methods. However, most faults occur at an equipment level which if allowed to propagate results in leaks, fires, explosions causing loss of life, capital invested and production downtime. Monitoring the overall process for detection of such equipment failures may be futile as deviations in the process are often lagging indicators by which time plant safety may be compromised. Moreover, modern sensors and equipments have their own smart diagnostic capability which a process monitoring system should make use of. Hence, we propose a distributed process monitoring system which uses multiple FDI methods/agents capable of monitoring the plant at various sections and varying levels of granularity (tag level to unit level). When multiple FDI agents are used they need to effectively interact with one another. Hence, a custom ontology is developed to explicitly capture the hierarchy of the process and the nature of the faults. A key issue in monitoring any complex system using multiple independent methods in parallel is that the individual methods may not always concur. A suitable decision fusion/consolidator agent is used which performs the matching between the results from the various FDI agents by mapping their evidences to the ontology and seeking coherence among the various evidences. The proposed approach has been implemented as a multi-agent system using Java WADE distributed environment. The efficacy of this system is demonstrated on a distillation column case study.