According to Google, only 21% of manufacturers are currently actively using AI in production. One reason for this reluctance is that, although data from different systems can be processed manually for AI and analytics pilot projects, the isolated data sets need to be accessible centrally and in real time for widespread use. In addition, many existing AI and analytics solutions are designed for data scientists and cannot be easily used by production managers.

With the two new product announcements, Google aims to help manufacturers connect traditionally isolated assets, process and standardize data and improve transparency from the factory floor to the cloud.

The two new tools

• Manufacturing Data Engine is an end-to-end solution that processes, contextualizes and stores manufacturing data on the Google Cloud. It provides a configurable, customizable and scalable approach to importing, transforming, storing and accessing this data. The solution integrates key Google Cloud products such as Cloud Dataflow, PubSub, BigQuery, Cloud Storage, Looker, Vertex AI, Apigee and more into a single, manufacturing-specific solution.
• Manufacturing Connect is a factory edge platform developed in partnership with Litmus Automation. Based on an extensive library of more than 250 machine protocols, the platform quickly connects to and transfers data from virtually any manufacturing equipment and industrial system to the Google Cloud. Thanks to deep integration with Manufacturing Data Engine, Google Cloud can quickly ingest machine and sensor data for processing. The ability to provide containerized applications and machine learning (ML) models "on the edge" opens up new dimensions of use cases.

Possible use cases

Once the data is centralized and harmonized with the two tools, it can be used for a growing number of industry-specific use cases. These include:

• Analytics & Insights for manufacturing: Manufacturers can create custom dashboards to visualize key data - from KPIs such as overall equipment effectiveness (OEE) to sensor data from individual machines. Thanks to the integration with Manufacturing Data Engine, engineers and plant managers can automatically set up new machines and factories to gain new insights across the plant with standardized dashboards, KPIs and on-demand drill-downs into the data. This information can then be shared across the company and with partners.
• Machine-level anomaly detection: Helps manufacturers detect anomalies as soon as they occur and - using Google Cloud's Time Series Insights API - provides alerts based on real-time machine and sensor data, such as noise, vibration or temperature.
• Predictive maintenance: Enables manufacturers to predict the maintenance needs of a machine, reducing downtime and maintenance costs. Manufacturers can use ML models and high-precision AI optimizations that can be implemented within weeks.

The new solutions for manufacturing will be presented live for the first time at Hannover Messe 2022 from May 30 to June 2.