Utilization of the internet of things and machine learning in digital development of predictive maintenance at Finnish pulp mills
Abstract
The topic of this thesis is the utilization of the internet of things and machine learning in digital development of predictive maintenance at Finnish pulp mills. This thesis examines the architecture and steps needed to build a cloud-based internet of things data platform, studies the utilization of machine learning algorithms on rolling bearing fault detection and describes the future potential of the internet of things in the context of predictive maintenance at pulp mills. An internet of things data platform was developed during this thesis project to support the storage and analysis of large quantities of vibration sensor and other data related to pulp mill predictive maintenance and other pulp mill processes. Literature relevant to cloud data platforms, cloud computing and the internet of things was examined. Strengths, weaknesses, opportunities and threats of the developed internet of things data platform were discussed. Three different machine learning algorithms were tested using various parameter values and 8 features computed from rolling bearing vibration signals to experiment with detecting rolling bearing faults. Future work and research required for developing an automated production-grade fault detection solution were discussed. The potential of further developments in internet of things technologies with regards to predictive maintenance was also discussed.
Keywords
Not available
Specialisations
Similar theses
- Hybrid Machine Learning and Time-Series Modelling to Forecast Product Demand: A CRISP-DM Approach Niklas Virtanen · University of Vaasa · 2026
- Insurance Fraud Detection Using Supervised Machine Learning and Explainable Artificial Intelligence Paavo Laine · University of Turku · 2026
- Design and Evaluation of a Supervised Machine Learning-Based Intrusion Detection System. Tarquin Qazi · 2026
- DEVELOPMENT OF ACTIVE MACHINE LEARNING METHODS FOR PREDICTIVE MAINTENANCE PROCESSES AND REMAINING OF USEFUL LIFE (RUL) PREDICTION IN INDUSTRY 4.0 Esmaail Albarazi · 2026
- AI-Enhanced Predictive Maintenance for Industrial Robotics using Sensor Data Analysis and Machine Learning Most Arina Afrin · University of Vaasa · 2026
- Machine learning models for predictive maintenance in industrial systems Sandra Sanz Chamorro · Universidad Complutense de Madrid · 2026
