This paper proposes an integrated approach to evaluate and optimize performance of petrochemical plants based on asset integrity management criteria. The proposed approach consists of analytic network process (ANP) and data envelopment analysis (DEA). Asset management criteria are identified by surveying related standards and literature and categorized into three levels. First level criteria which are major criteria are based on plan-do-check-act (PDCA) cycle, second level criteria are sub sets of the first level criteria and third level criteria are quantitative and qualitative indicators derived from the literature. ANP is used to calculate relative importance of the second level criteria which enables decision makers to calculate the final score of each decision-making unit. Constant return to scale (CRS) and variable return to scale (VRS) DEA models in both input and output oriented forms are applied and the preferred model for measuring DMUs' efficiency is selected via normality test. The proposed approach is applied to a set of real time petrochemical plants. Sensitivity analysis is performed to find significant factors affecting DMUs' efficiency scores. The proposed approach would improve overall performance and could reduce operational loss, safety issues and incidents. (C) 2019 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.