Neural nets have recently become the focus of much attention, largely because of their wide range of complex and nonlinear problems. This paper presents a new integrated approach using neural networks for diagnosing process failures. The fault propagation in process is modeled by causal relationships from the fault tree and its minimal cut sets. The measurement patterns required for training and testing the neural network were obtained from fault propagation model. The network is able to diagnose even in the presence of malfunction of certain sensors. We demonstrate via a nitric acid cooler process how the neural network can learn and successfully diagnose the faults.