ABSTRACT
Estimating corrosion growth rate for underground pipelines is a non-linear, multivariate problem. There are many potential confounding variables such as soil parameters, cathodic protection, AC/DC interference, seasonal / climate conditions, and proximity to unique geographic features such as wetlands or polluted environments. The work presented provides an approach for estimating underground corrosion growth rates using a dataset of observations from a North American pipeline operator. Extensive geospatial data is utilized that has been obtained from public and private sources and extrapolated using Inverse distance weighted (IDW) interpolation. This work presents a model using IDW to estimate parameters involving soil, interference, geography, and climate factors for any location in North America.
Using this data, this work then presents several different machine learning approaches, including Generalized Linear Models, extreme Boosted Trees, and Neural Networks. All three provide an accurate estimation for corrosion growth rates for an underground asset at any latitude and longitude pair in North America. Each method comes with potential benefits and pitfalls, specifically; trade-offs between model accuracy and transparency. This work presents a framework for comparing geo-spatial and machine learning estimates.
INTRODUCTION
The business case for this paper involves cost-effectively and efficiently assessing environmental conditions and the related impact of corrosion on underground pipeline using geographical information systems (GIS) and spatial data, with limited excavation. The objective is to proactively target those areas that have the highest likelihood of advanced corrosion (based on rate and degree of corrosion) and thus reduce risk of failure, while maximizing both capacity and related cost of inspection.
Geostatistical Analyst tools are used to emulate a phenomenon occurring in the landscape that is of interest such as pH and electrical conductivity in the soil, powerlines that contribute to alternating current (AC) interference of rectifiers, magnetic anomaly, road salts, and other known contributors to corrosion of underground pipeline.
By using the geospatial tools to generate data for inputs into machine learning, this paper proposes a tool which estimates corrosion growth rates from a large range of environmental variables. This isn’t an uncommon approach, estimating corrosion growth rates using machine learning is an active area of research for at least two decades now. This approach is similar to work done by others but by including a wider range of spatial variables, the models are specifically designed for high dimensionality geo-spatial input, representing the wide array of environmental risk factors for an underground pipeline.1 2 3
