Pressure vessels are a tool for storing liquid and gas fluids. The temperature difference between the pressure vessel and the surrounding environment causes failure to occur. One of the causes of that failure is uniform corrosion that can be avoided by conducting a risk-based inspection (RBI) by calculating the probability and consequence of failure. Deep learning is a subfield of machine learning, which is prominent in recent years due to its capability to handle high dimensional data. Among the deep learning models for analyzing risk in pressure vessels is artificial neural networks (ANNs). This model can shorten the time, increase accuracy and efficiency, and lower the cost. This article discusses the design of a pressure vessel dataset based on the API 581 standard and the calculation of failure predictions using ANNs. High accuracy 93% for the classification of the probability of failure and 100% for the consequences of failure have been obtained. The classification determination of those failure categories was also continued by calculating precision and recall parameters. The results obtained confirmed the accuracy of the classification, and hence indicated the succeeding of the ANNs model to classify the data.