AbstractCasing strings are an indispensable component in the design of any well and serve numerous purposes in oil and gas wells, constituting 20-30% of the total well cost. An alarming rate of failures, up to 50%, have been observed yet hushed under the rug, due to reputation, company profile, and privacy. In this work, The designed workflow follows 6 acceptance criteria, namely, (1) identification of potential risk factors amongst different exposures, (2) evaluation of the type and magnitude of the impact for each risk factor, (3) identification of the levels within each potential risk factor that impose the highest risk on casing failure, (4) acknowledgement of the depths most susceptible to casing failure, (5) prediction of the overall probability of casing failure given the information for pre-defined risk factors, and finally (6) have a scheme for mitigating casing failure.Case-control study design was adopted to test the association between the different exposures and the occurrence of casing failure. Impact type and magnitude of identified risk factors were determined through various statistical association measurements. Non-parametric survival analysis techniques were used for identification of the levels within each potential risk factor that impose the highest risk on casing failure and the depths most susceptible to casing failure.The scheme provided quantifiable numeric percentage increase/decrease for significant risk factors at lower, intermediate, and higher depth of casing. One importance of such conclusions is that although the conclusions coincide with already proven theories, unlike physics-based models, we did not need to acquire any domain knowledge to reach to those outputs. Moreover, in addition to exploring the significance of subcategories with respect to imposed risk, we managed to quantify those impacts which would be of great value when calibrating malpractices later using the proposed "correction-prediction" procedure.
