Big data analytics for preventive maintenance management

• Main Authors: Razali, Muhammad Najib, Othman, Siti Hajar, Jamaludin, Ain Farhana, Adi Maimun, Nurul Hana, Abdul Jalil, Rohaya, Mohd. Adnan, Yasmin, Zulkarnain, Siti Hafsah
• Format: Article
• Published: Malaysian Institute Of Planners 2021
• Subjects: QA Mathematics; TH434-437 Quantity surveying; TS156.6 Quality Control
• Online Access: http://eprints.utm.my/id/eprint/95707/; https://www.planningmalaysia.org/index.php/pmj/article/view/1019

Maintenance data for government buildings in Putrajaya, Malaysia, consists of a vast volume of data that is divided into different classes based on the functions of the maintenance tasks. As a result, multiple interactions from stakeholders and customers are required. This necessitates the collection of data that is specific to the stakeholders and customers. Big data can also forecast for predictive maintenance purposes in maintenance management. The current data practise relies solely on well-structured statistical data, resulting in static analysis and findings. Predictive maintenance under the Big Data idea will also use non-visible data such as social media and web search queries, which is a novel way to use Big Data analytics. The metamodel technique will be used in this study to evaluate the predictive maintenance model and faulty events in order to verify that the asset, facilities, and buildings are in excellent working order utilising systematic maintenance analytics. The metamodel method proposed a predictive maintenance procedure in Putrajaya by utilising the big data idea for maintenance management data.