Course taught by our partner AIC – Automotive Intelligence Center
The continuous irruption of new technologies, as well as the continuously changing conditions that any process faces, are an opportunity for maintenance management to bet on an advanced management model where predictive, and even prescriptive maintenance, are the main players and driving forces that ensure the availability of assets, their health and maximize their useful life.
To achieve these goals requires that organizations adopt maintenance techniques appropriate to the behavior of their assets and processes, as well as embedding them in the required enabling technologies.
October 30, November 6 and November 13, 2024
At the AIC Academy (Amorebieta-Etxano).
LENGTH:3 days – 24 hours
Attendees will be trained to acquire the necessary skills to enable them to adapt and adopt the most appropriate predictive maintenance technique(s) to their own environment in the field of Maintenance.
Managers and technicians involved in the areas of Maintenance Engineering and Industrial Performance Management. Also of relevance to Process Engineering and Production Engineering personnel.
Condition Monitoring – 1st session:
- Introduction to the training program. Objectives and expectations of the participants
- The basics of Condition Monitoring:
- Introduction to CM and its importance in asset management.
- Principles of asset condition monitoring.
- Principios de la monitorización del estado de los activos.
- Selection of monitoring parameters and sampling strategies.
- Interpretation of monitoring data and anomaly detection
- Integration of CM in predictive maintenance programs.
- Condition Monitoring techniques:
- Vibration analysis for machinery failure detection.
- Temperature analysis and infrared thermography in equipment monitoring
- Ultrasound and Acoustic Emission
- Lubricant analysis and oil analysis for wear and contamination evaluation.
- Electrical current monitoring and electrical signature analysis for the identification of problems in motors and electrical components.
Data, signals, diagnosis and prognosis – 2nd session:
- Data analysis and signal processing:
- Signal preprocessing for data analysis.
- Multivariate statistical analysis of signals.
- Feature extraction in signal processing.
- Signal modeling and prediction using machine learning techniques.
- Correlation and causation analysis in the context of signals and data.
- Diagnosis and prognosis:
- Fault detection and classification methods.
- Modeling and simulation of diagnostic systems.
- Signal analysis and data processing in diagnostics.
- Forecasting techniques of expected operating lifespan and failures.
- Application of machine learning algorithms in diagnosis and prognosis.
CBM, AI and Big Data – 3rd session:
- Integration and Implementation of CBM systems:
- Design and integration of CBM systems.
- Selection of sensors for CBM.
- Data integration in CBM systems.
- Development of analysis algorithms for CBM.
- Implementation of CBM in critical infrastructures.
- Strategic management of CBM, CM, PDM and PHM
- CBM strategic planning.
- Selection of condition monitoring techniques.
- Key performance indicators (KPIs) for CBM.
- Integration of CBM in the asset life cycle.
- Continuous improvement of CBM through data analysis.
- Artificial Intelligence and Massive Data Analysis in the field of maintenance:
- AI in Industrial Maintenance.
- Big Data analytics in Maintenance.
- Arquitectures
- Data analytics in
- Asset optimization with AI.
- OT/IT Convergence. Data integration in intelligent maintenance.
- Doubts and recommendations: where do I start?
