Project VIA-APPIA is a Fieldlab solution that will use Machine Learning to identify patterns that are out of the ordinary and to understand what these patterns mean and what impact they could have on a plant or business. The primary objective of this project will be to create a flexible model that can be used in different plants or industries, with minimal human intervention and training.

The machine learning model will also be tested on different existing project data to determine its accuracy and to teach it what some of the patterns mean, like out of balance, coupling and bearing failures etc. The model will be integrated into a backend server in order to detect faults within data and to predict when said faults might occur again. The backend server is completely modular and allows for any type of frontend for user interaction.

For more information: https://www.worldclassmaintenance.com/project/fieldlab-via-appia/ (in Dutch)

The brief for project Campione was to develop a model that would predict mechanical plant failures before they occurred. A fully automated production plant was selected as a pilot and IMS developed a model using the operational SCADA information to predict upcoming plant failures to strive for Zero-Surprises. These prediction models have successfully predicted upcoming failures within the plant including: failures of the gearboxes, electric motors, couplings, and bearings of each roller assembly as well as roller damage, wear and tear, and misalignment problems. The plant has scheduled shutdowns and the maintenance staff were able to confirm that certain components were damaged or misaligned before the component failed.

Generally, assets of this nature are run on a preventative maintenance strategy. The IMMS EAM software has proved useful to assist in identifying unseen problems in this automated plant to resolve upcoming failures by repairing, replacing, aligning, inspecting, and servicing the faulty component before it results in unplanned plant shut-down.

Furthermore, IMS established the capability to manage, analyse and process big data (50Gb per day) as input to the prediction models.

For more information: https://www.worldclassmaintenance.com/project/fieldlab-campione/ (in Dutch)

IMS International teamed up with DELTA (now DNWG) and Oliveira (now Ijssel Technologie) to provide Daisy4Offshore: a Dynamic Asset Information System for offshore wind parks.

The Daisy4Offshore system, based on the IMMS EAM solution, continuously monitors the health status of critical internal wind turbine components provided by DNWG, energy prediction models from the Energy research Centre of the Netherlands (ECN), Condition Based Monitoring (CBM) system from Ijssel Technologie, and Meteorological data providing Weather information to minimize the cost of downtime during maintenance on wind turbines. It achieved this by determining what the electrical cost will be at the time the maintenance is to be scheduled and if the weather conditions will be safe enough. It then schedules for lowest cost, provided the weather conditions are safe to proceed.

The Daisy4Offshore IMMS solution implements the complete Wind Turbine Service Plan that ensures the maintenance is performed as specified by the Wind Turbine OEM as well as used for Owner Inspections on Wind Turbines to ensure that the OEM maintenance is performed and to minimize the owner’s legal liabilities resulting from local legislation on Wind Turbines.

For more information: https://www.worldclassmaintenance.com/resultaten-toepassen-op-zee-met-daisy4offshore/ (in Dutch)

Project I2MTS is Dutch showcase project implemented at eThekwini Metropolitan Municipality (EMM) in South Africa successfully demonstrating the IMMS EAM solution used for asset and maintenance management at the Northern Wastewater Treatment Plant (NWWTP) as well as for the Water Distribution Custody Transfer Points (CTP).

The IMS EAM software is used to schedule routine inspections, services, tests and other scheduled activities. For EMM, the routine inspections at the NWWTP 150Mℓ Aeration Plant were loaded into the software and the SCADA tags were used to identify each asset. The systems capability to schedule and record routine maintenance activities was demonstrated.

The software is also able to log faults and problems found on site during an inspection. This is done on a mobile device that sends the results to a server. This capability was demonstrated during a plant walk through at the NWWTP 150Mℓ Aeration Plant where certain problems and the repair actions were identified.

The routine maintenance process of the CTP equipment was also demonstrated. The system was also used to perform a water balance between the water received and the water leaving the plant and to report on any deviations outside of an acceptable tolerance.

All information was displayed on an extensive dashboard.

Our Digital Twin is a 3-Dimensional model representation of a real plant where typical maintenance problems may occur.

It is ideal for both training and for providing overviews for maintenance operations. It features both conventional digital twin concepts, like interactive nodes, and integrates it with a fully networked scene where several users can operate in the same scene simultaneously, while under the supervision of an instructor.