In this article is described a knowledge-based system or expert system for failures identification in onshore pipelines. This expert system is called Failure Analysis Expert System (FAES). The FAES development has been split in two parts. In the present part I, the database structure and knowledge acquisition process are described, while in second part, the End-User interface and learning algorithm will be described. The proposed FAES includes a structured database with document processing of typical failures of pipeline collected from failure analysis reports and which were supported by expertise of failure analysis experts. A total de 854 cases of onshore pipeline failures were considered for FAES development; 683 cases for training and 171 cases for testing. Several failure mechanisms were identified with the following frequency order: external corrosion, internal corrosion, third parties, erosion, material failure, and vandalism. For machine learning, an inductive learning algorithm through Artificial Neural Network (ANN) was used.