Coaching trajectory: Data-driven maintenance

The industry constantly strives for the highest possible availability of its installations (assets). One of the ways it tries to achieve this is by not having breakdowns between two consecutive planned preventive tasks.

Maintenance 4.0 - which is very popular these days - takes on its full meaning here.

However, it is a comprehensive concept with concepts ranging from identifying needs, connecting measurement systems, all the way to using artificial intelligence (AI).

During this three-day training, we will go through all these concepts in a logical order and with constant attention to their applicability. After this training, you will have all the keys in hand to make your 4.0 maintenance programme a success.

A multi-faceted 7-step approach that helps you to successfully execute a 4.0 project using intelligent data management, with a focus on visualisation and making the right decision.

• Converting fault mode detection into the right sensor and measurement system
• Integrating maintenance and process parameters
• The importance of connected data sources
• How to collect and import data from a central location
• Combining a business vision with data science aspects
• The importance of project selection
• The contribution of new methods based on artificial intelligence in maintenance

•  

Day 1

Assess

• Evaluating the "4.0 Readiness" of the organisation and its IT & OT systems
• Illustration of an AI based assessment tool
• Recognizing potential use cases

Identify

• Identifying necessary data sources, using DOFA
• Identifying a suitable business case by means of AI supported data analyses

Generate

• Generate and collect data through proper data engineering
• Overview of online Condition Based Monitoring sensors

Collect

• Collect the different data sources within the OT hierarchy (ISA-95)
• The importance of centralising the various data sources
• The importance of the right data architecture will be demonstrated on the basis of an actual case study

Day 2

Analyze

• Selection of the right algorithms (e.g. regression, classification, clustering, ...)
• Explanation of the most important algorithms in a maintenance context
• Using an actual case, the importance of AI for early detection of machine malfunctions is demonstrated

Day 3

Analyze (continued)

• Case on how PDM & Process data can be processed into effective alarm management

Visualize

• Importance of interactive KPI dashboards
• Aspects of building an effective dashboard
• Overview of the most important visualization principles

Act

• Initiating follow-up actions in the maintenance workflow
• Case about the integration with CMMS to automatically generate work orders 

Maintenance managers and engineers, reliability engineers, production managers, process engineers, IT and infrastructure managers, anyone involved in operation and maintenance of assets, or responsible for environment, safety and/or quality.