The rise of Industry 4.0 has transformed manufacturing by using technologies like IoT, big data analytics, and machine learning, with predictive maintenance (PdM) being key to anticipating equipment failures and optimizing maintenance. This thesis presents an integrated PdM framework tailored for Industry 4.0, aiming to improve equipment reliability and operational efficiency by aligning PdM modules with the Reference Architectural Model Industry 4.0 (RAMI 4.0). Using design science research methodology, it develops PdM architecture, algorithms for Remaining Useful Life (RUL) estimation, and maintenance scheduling modules, implemented on the FIWARE platform. PMMI 4.0, powered by MPMMHDLA and PMS4MMC, offers a 12% cost impact and a 10% downtime reduction.