36 Estimating Excavation Damage (Outside Force) ‘Hit Rates’ Using Machine Learning Models Trained on In-Line Inspection Data and Geographical Information

Abstract

External interference damage is one of the main causes of pipeline failure reported in publicly available industry statistics, from agencies such as the United States Pipeline and Hazardous Materials Safety Administration (PHMSA). Thus, failures due to external interference are often the most significant contributors to pipeline probability of failure in risk assessments and can play a significant role in operator decisions regarding risk-control measures, for example when it comes to the installation of additional impact protection, pipeline diversion or pressure restrictions. The probability of failure due to external interference damage can be estimated by combining the probability that damage occurs (i.e. that the pipeline is hit), the probability that the impact is sufficient to cause instant failure and the probability of degradation to failure, given that damage has occurred. Degradation to failure is assessed using industry standard engineering models (such as the limit state functions given in Annex O of CSA Z662-19). However, the key challenge is predicting where, when, and with what energy the external interference damage may happen. The prediction of a “hit-rate,” or impact frequency, is often subjective or based on statistics which may not be applicable to the pipeline under assessment. Top-of-line (ToL) deformation damage (dents) reported by in-line inspection (ILI) are a clear indicator of past external interference, which could have been caused by third parties, contractors or the operator themselves. In a recent in-house research study ILI data and pipeline parameters from ROSEN’s Integrity Data Warehouse (IDW) – which at the time of writing contains results from over 20,000 inspections – has been combined with geographical information on population density, land use, crossings and socioeconomics, and used to train machine learning models to estimate the frequency of external interference damage (per mile-year), or ‘hit-rate’ for pipelines where the route is known but reliable statistics for ‘hit-rate’ are not available. This paper presents the results of the study describing the extensive dataset used from a selection of pipelines in the USA, the development of the models and how they were trained and tested, and finally showing the model performance, discussing the capabilities and limitations, and implications for risk assessment studies.

Read/Download PaperGradeAvailable after the event