Performance, cost, and risk
What are the performance, cost, and risk impacts of implementing this product?
- Performance: Increase objectivity of prediction model selection process, extend component lifetime and increase asset reliability through failure predictions.
- Cost: Reduce frequency of preventive maintenance actions by enabling just-in-time maintenance and prevent unexpected failures.
- Risk: General risks involved with replacing PM strategies with PdM strategies (risks of catastrophic failures of unmonitored components, data quality might be inadequate).
Implementation requirements
What capabilities would a business/organization/institution need to have to implement this product?
- Processes: Preexisting monitoring and diagnostic decision processes.
- Resources: Sensor data, computational infrastructure, maintenance engineers.
- Competences: Knowledge of and experience with Bayesian filtering and failure mechanism analysis for asset management, understanding of different predictive approaches to understand selection procedure.
- Technologies: Bayesian filtering algorithms (e.g., Unscented Kalman Filter), prognostic software (mainly Python).
Related works
- Keizers (2021). Unscented Kalman Filtering for Prognostics Under Varying Operational and Environmental Conditions.
- Keizers (2022). Atmospheric Corrosion Prognostics Using a Particle Filter.
- Keizers et al. (2025). Bayesian filtering based prognostic framework incorporating varying loads.
- Silveira et al. (2023). Integration of multiple failure mechanisms in a life assessment method for centrifugal pump impellers.
- Silveira et al. (2024). Quantifying the suitability and feasibility of predictive maintenance approaches.
Contact information
For further inquiries regarding this product, feel free to get in touch with:
- Richard Loendersloot, University of Twente. r [dot] loendersloot [at] utwente [dot] nl
- Tiedo Tinga, University of Twente. t [dot] tinga [at] utwente [dot] nl
