This paper presents our co-operative hybrid algorithm for fault diagnosis in power transmission networks. When a fault occurs in a transmission network, it must be identified and eliminated as soon as possible. Since control centers are flooded with hundreds of alarm messages during a fault, fault diagnosis, which involves the analysis of alarm messages, is a time consuming task. Towards the development of a fault diagnostician, model-based, heuristic, and neural networks are applied to the domain and the results are presented in this paper. The algorithm is a hierarchical model which combines several reasoning methods such as heuristic, temporal and model-based diagnosis and incorporates a network of neural networks at one of the levels of the hierarchy. The working of this co-operative algorithm is discussed and its results are analysed.