Microsoft Germany has launched an initiative to help manufacturers quickly achieve results in digital transformation projects, introducing a set of 10 reference implementations for the most common use cases.
Sight Machine is one of a handful of industry partners contributing core technology to the initiative, with eight of the 10 uses cases reflecting Sight Machine’s capabilities. Sight Machine has been working with Microsoft to bring similar quick-turnaround solutions to manufacturers around the globe.
In July, Sight Machine was named a finalist for the 2021 Microsoft Manufacturing Partner of the Year Award. Sight Machine and Microsoft are working together across a variety of discrete and process industries, helping companies scale transformation on Azure across as many as dozens of plants within single firms.
The initiative was introduced by Microsoft Germany, initially targeting Germany’s massive manufacturing sector. It said the set of 10 application scenarios enable “a quick and concrete entry into the digitization of manufacturing.”
Microsoft Germany’s “Microsoft in Manufacturing” initiative “is designed to make the development of new solutions for the Industrial Internet of Things (IIoT) faster, more efficient and more reliable,” Microsoft said in its announcement. Under the initiative, experts from Microsoft Industry Solutions Consulting go to the customer together with the partners and implement the new solutions together.
The big benefit for customers, according to Microsoft, is that “reliable and scalable solutions for the most important tasks in the manufacturing industry are already available and can be used immediately.” The solutions “require only low initial investments and lead to a fast return on investment. Moreover, new IIoT business models can be implemented much faster with the pre-built use cases.”
Of the 10 scenarios, eight of them highlight Sight Machine’s core capabilities:
1) Automatic quality control
An automatic quality control system helps to check production processes as well as to transfer the resulting data into systems such as LIMS (Laboratory Information and Management System), ELN (Electronic Laboratory Notebook), MES (Manufacturing Execution System) and ERP.
2) Overall Equipment Effectiveness (OEE)
Overall Equipment Effectiveness (OEE) is a business indicator for measuring the productivity of machines, production lines or plants. It measures availability, performance and quality in relation to production time.
3) Process Information Management Systems
Process information management systems (PIMS) are the data platforms of a factory. They integrate and visualize data from various sources.
4) Anomaly detection
The automatic detection of anomalies by algorithms and artificial intelligence is an important building block for predictive maintenance and thus for more efficiency in the use of machines and plants.
5) Condition monitoring
Condition monitoring of manufacturing plants is a prerequisite for predictive maintenance. In this process, various parameters are permanently collected in real time to enable predictive maintenance at a favorable point in time.
6) Energy consumption
The manufacturing industry is an energy-intensive sector. To achieve greater sustainability and efficiency, use must be optimized. Therefore, measuring energy consumption, identifying losses, and finding the right countermeasures are of crucial importance.
7) Waste Management
Every manufacturing process produces scrap and by-products. Using data helps minimize scrap and maximize production. Building smart manufacturing ecosystems opens new opportunities for customers to sell their byproducts as raw materials to other companies. This often happens in the chemical industry.
8) Bottleneck Analysis
Bottlenecks occur in manufacturing when machines cannot meet their production quota even at maximum throughput and the flow of work is delayed or stopped as a result. Analyses of such bottlenecks help to make production more efficient.
