Random generation of industrial pipelines’ data using Markov chain model

Random generation of data sets is a vital step in simulation modeling. It involves in generating the variation associated with the real system behavior. In the industrial fabrication of construction components, unique products such as pipelines are produced. The fabrication processes are dependent on pipelines features, and complexity; randomly generating pipelines structure is imperative in the simulation of such processes. This paper investigates the nature of industrial pipelines and proposes a Markov chain model to randomly generate pipelines data structure. The performance of Markov chain model was tested against real pipelines through a three-stage validation process. The validation process includes (1) a validation based on the number of components and the pipelines components correlation analysis, (2) clustering-based model validation, and (3) model validation using similarity distances between pipelines feature vectors. The Markov chain model was found to generate a reasonable pipelines data structure when compared with real pipelines. It was found that 89% of the generated pipelines share similar properties equivalent to 0.88 (a scale from 0 (not identical) to 1 (identical)) to 85.5% of the original pipelines.