GlobalFoundries Dresden

Predictive Maintenance for the Production of Semiconductors

GlobalFoundries is a U.S. semiconductor manufacturer with more than 16,000 employees worldwide. The company produces microchips on behalf of more than 250 customers in the automotive and manufacturing industries, computers, mobile communications and consumer electronics, among others. Therefore GlobalFoundries operates production sites in Dresden, the USA and Singapore. The Dresden plant is considered the largest and most modern semiconductor plant in Europe. The microchips are manufactured in clean rooms in more than 1,000 process steps. Both the equipment and each of the individual production stages are strictly monitored to prevent failures or quality fluctuations in production. The control valves for ultrapure water, an important supply medium in semiconductor production, pose a particular challenge. Defects in these valves were previously unpredictable and could potentially lead to disruptions. To continuously monitor the ultra-pure water valves at GlobalFoundries, T-Systems MMS developed an IoT solution based on its Cloud Shopfloor Intelligence platform in collaboration with the Smart Systems Hub and other partners.

Customer Benefits

Ensure higher reliability of production equipment

Digitized monitoring saves on personnel and time

Permanent condition monitoring and data-supported, demand-oriented maintenance

  • Dr. Axel Preusse, Fellow Process Engineer GlobalFoundries

    „With T-Systems MMS and the Smart Systems Hub, we had a team at our disposal that brought in a very broad skillset that is not available internally in this particular form. The team worked on the project with a high level of self-motivation.“

Reference Overview


The previous monitoring of production-critical ultra-pure water valves by employees on site is to be replaced by sensor technology. Defects are to be detected at an early stage or in advance and further insights gained.


Special acoustic sensors process the acoustic data within an edge computing hardware with machine learning algorithms and transmit them to the "Cloud Shopfloor Intelligence" platform for display on various dashboards.


Thanks to the scalable edge computing and cloud solution, the data obtained from the highly complex processes is evaluated and processed in such a way that the status of the valves can be retrieved at any time. Beginning defects can be detected at an early stage.

  • Michael Kaiser, CEO Smart Systems Hub

    „It is always impressive to see how large industrial partners, startups and medium-sized companies can achieve measurable results in the (free) space we created in a trusting and goal-oriented manner in just three months. The fact that after Digital Product Factory #2 all project partners are now continuing to work with the Smart Maintenance MVP makes me particularly proud.“
  • Requirements

    Predictive Monitoring of Valve Function

    GlobalFoundries manufactures microchips in many highly complex process steps at its plant in Dresden. To remove chemical residues from the wafers that are used to manufacture chips, they are cleaned in special basins with ultra-pure water. Until now, the inlet and outlet valves to these basins were laboriously checked for damage on site by experienced specialist personnel.
    To digitize this monitoring process, GlobalFoundries, together with T-Systems MMS and other partners, launched a pilot project as part of the „Digital Product Factory“ program of the Smart Systems Hub, one of 12 Digital Innovation Hubs in Germany.
    The aim was to pilot a complete IoT solution - from sensor technology and data pre-processing in edge computing hardware to presentation in cloud dashboards. Particular challenges were the selection of suitable sensors, the implementation of machine learning algorithms for the early detection of damage, and the realization of a flexible cloud platform for the clear display and evaluation of the status of the valves. The solution is intended to enable necessary maintenance to be carried out in good time and without production downtime.

  • Solution

    Edge Computing Platform With Machine Learning for Sensor Data

    In order to be able to acoustically monitor the condition of the valves directly on site, the highly integrated edge hardware from the sensor technology specialist "Sensry" was used. The data thus obtained was pre-processed by machine learning algorithms developed jointly with "Coderittern" (Code-Knights), a Dresden-based IoT startup. The data was transferred to the cloud and clearly presented in dashboards using the "Cloud Shopfloor Intelligence" platform from T-Systems MMS. This means that the data on the condition of the equipment can be accessed in real time and remotely and can be integrated into further process steps.

  • Benefits

    Dashboard With Condition Indicator Prevents Failures

    With the data-based, self-learning IoT solution, the ultrapure water valves are monitored digitally and in real time on clear dashboards. This not only lightens the workload of specialist personnel, but also enables the early and increasingly accurate determination of maintenance requirements thanks to machine learning.
    Production-critical key figures can be better complied with thanks to knowledge of the current operating status and increased fail-safety.
    The deployed "Cloud Shopfloor Intelligence" solution in its combination with state-of-the-art sensor and edge computing technologies is highly flexible, scalable and enables easy integration into further applications and business processes.

About GlobalFoundries Management Services LLC & Co. KG

The semiconductor manufacturer GLOBALFOUNDRIES employs more than 16,000 people worldwide. More than 3,000 technicians, engineers and specialists from all over the world work at the company campus in Dresden. GLOBALFOUNDRIES has helped to establish the Free State of Saxony as a leading micro- and nanoelectronics center in Europe and has significantly advanced the development of new IoT and connectivity system solutions with the Smart Systems Hub.

Contact Person