Two steps hybrid calibration algorithm of support vector regression and K-nearest neighbors

Abstract Errors in the measurements of pipeline nondestructive tools may lead to faulty decisions causing economic and environmental loss, or system failures. Calibration models are an effective tool that is used to enhance the quality of corrosion measurements affected by inline inspection tools sizing accuracy. Parametric calibration models are limited to datasets with Gaussian behavior. On the other hand, non-parametric calibration models can overcome the normality limitation, however, they provide only a local or general estimation. This paper presents a new hybrid calibration model that is based on two steps K nearest neighbor interpolation and support vector regression. The suggested hybrid model uses both general and local estimation behaviors for the calibration process, hence resulting in a better prediction. The hybrid algorithm was evaluated using a dataset of pipeline corrosion measurements collected by a Magnetic Flux Leakage (MFL) sensor (with an error margin of ±20% of the true values), and an Ultrasonic (UT) device (with an error margin of ±4%). The suggested approach resulted in reducing the errors in MFL corrosion measurements to be only ±6.82% instead of the original ±20%.

[1]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[2]  Zuherman Rustam,et al.  Application of SVM-KNN using SVR as feature selection on stock analysis for Indonesia stock exchange , 2018 .

[3]  Kevin Spencer,et al.  A Practical Application to Calculating Corrosion Growth Rates by Comparing Successive ILI Runs From Different ILI Vendors , 2010 .

[4]  Peter Cawley,et al.  Current deflection NDE for the inspection and monitoring of pipes , 2016 .

[5]  David Harvey,et al.  Contemporary ultrasonic signal processing approaches for nondestructive evaluation of multilayered structures , 2012 .

[6]  Zahiraniza Mustaffa,et al.  The effect of different weight functions on calibrating corrosion measurements using KNN technique , 2016 .

[7]  Zahiraniza Mustaffa,et al.  Error-reduction approach for corrosion measurements of pipeline inline inspection tools , 2018, Measurement and Control.

[8]  Chinedu I. Ossai,et al.  Advances in Asset Management Techniques: An Overview of Corrosion Mechanisms and Mitigation Strategies for Oil and Gas Pipelines , 2012 .

[9]  Andrew W. Moore,et al.  Locally Weighted Learning for Control , 1997, Artificial Intelligence Review.

[10]  Robert E. Melchers,et al.  Probabilistic analysis of pipelines subjected to pitting corrosion leaks , 1995 .

[11]  Miltiadis Alamaniotis,et al.  Probabilistic kernel machines for predictive monitoring of weld residual stress in energy systems , 2018, Eng. Appl. Artif. Intell..

[12]  Mazura Mat Din,et al.  Improving inspection data quality in pipeline corrosion assessment , 2009 .

[13]  Richard Kania,et al.  In-Line Inspection Performance III: Effect of In-Ditch Errors in Determining ILI Performance , 2010 .

[14]  W. Karush.  Minima of Functions of Several Variables with Inequalities as Side Conditions , 2014 .

[15]  Pradeep Ramuhalli,et al.  Combining multiple nondestructive inspection images with a generalized additive model , 2008 .

[16]  Mrityunjay Kumar,et al.  Multi‐Sensor Data Fusion for High‐Resolution Material Characterization , 2007 .

[17]  Zahiraniza Mustaffa,et al.  Comparative Calibration of Corrosion Measurements Using K-Nearest Neighbour Based Techniques , 2016 .

[18]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[19]  Olga S. Sedova,et al.  On corrosion of a thin-walled spherical vessel under pressure , 2018, International Journal of Engineering Science.

[20]  Han Hong,et al.  Nonlinear Models of Measurement Errors , 2011 .