Asset reliability though social network analysis: A framework proposal

Asset management and reliability are major challenges for any company, especially for those characterized by production processes consisting of a large number of components. Thanks to the development of Data Mining techniques and tools, data produced by such systems can be analyzed in order to predict their behavior. In this work, asset’s performance in terms of reliability is addressed through the development of a Social Network Analysis-based framework. Considering the asset as a social system composed of several interacting components, the purpose of the framework is to identify the relationships between component failures and avoid them through the predictive replacement of critical ones, in order to eliminate or at least limit the impact of the resulting failures on the entire process. Moreover, since Social Network Analysis is based on the development of a graph, results interpretation is rather easy. An example-case of a process industry is presented to validate the proposed model and to discuss its applicability, as its implementation on practical cases can provide a further opportunity of predictive maintenance.