A cross-sector analysis of human and organisational factors in the deployment of data-driven predictive maintenance

Domains such as utilities, power generation, manufacturing and transport are increasingly turning to data-driven tools for management and maintenance of key assets. Whole ecosystems of sensors and analytical tools can provide complex, predictive views of network asset performance. Much research in this area has looked at the technology to provide both sensing and analysis tools. The reality in the field, however, is that the deployment of these technologies can be problematic due to user issues, such as interpretation of data or embedding within processes, and organisational issues, such as business change to gain value from asset analysis. 13 experts from the field of remote condition monitoring, asset management and predictive analytics across multiple sectors were interviewed to ascertain their experience of supplying data-driven applications. The results of these interviews are summarised as a framework based on a predictive maintenance project lifecycle covering project motivations and conception, design and development, and operation. These results identified critical themes for success around having a target or decision-led, rather than data-led, approach to design; long-term resourcing of the deployment; the complexity of supply chains to provide data-driven solutions and the need to maintain knowledge across the supply chain; the importance of fostering technical competency in end-user organisations; and the importance of a maintenance-driven strategy in the deployment of data-driven asset management. Emerging from these themes are recommendations related to culture, delivery process, resourcing, supply chain collaboration and industry-wide cooperation