MindSphere and The Industrial IoT – What’s New April 2022
MindSphere releases deliver advanced industrial IoT capabilities that bring the physical and digital worlds closer together. Over the past month, MindSphere has unveiled enhancements such as new and improved asset rules in Operations Insight and AI for Everyone – Anomaly Detection made available to subscribers of Basic, Standard, or Premium capability packages.
This update includes many of the newest and most exciting capabilities from the most recent MindSphere releases:
- Define rules by asset type in Operations Insight
- AI for Everyone – Anomaly Detection integrated in Operations Insight
- Docker version of the MindConnect Software Agent
Our first update is for rules by asset type in Operations Insight. MindSphere users know that Operations Insight seamlessly brings together powerful features and capabilities in an intuitive way. Now, with an enhanced rules feature, you can define rules for an asset type and then activate it for some or all asset instances of this asset type. Before, you needed to create and assign a new rule for every asset of the same type even though evaluation criteria in the rule remained unchanged. This update makes rule creation and assignment easier than ever for multiple assets that belong to same asset type.
Next up, we’re extending the availabilities of AI for Everyone with essential Anomaly Detection which has been made available to Basic, Standard and Premium Capability Packages.
AI for Everyone is accessible from the user interface of Operations Insight. It offers an end-to-end, out-of-the-box model building strategy that identifies relevant features and generates a unique GAM (Generalized Additive Model) for each time series forecasting or anomaly detection use case. To accomplish this, AI for Everyone leverages the mathematics of Information Geometry to expand the original explanatory variables into many different features and then very efficiently reduces them into a unique GAM model.
Essential Anomaly Detection capabilities comprise:
- Define “Use Case” to manage both Forecast and Anomaly Detection experiment jobs and linked dataset MindSphere based on asset model.
- Build Anomaly Detection model via parameters configuration of the training dataset, detection KPI and predictors, Perspective & Sensitivity, Normal behaviors, Data imputation and so on
- Detect anomaly spots from the in-sample dataset based on built model
- Visualize model building and detection results of anomaly spots, perspectives, predictor importance, historic model building and detection records, etc.
Subscribers of Basic, Standard or Premium Capability Packages can try out the Anomaly Detection capabilities with up to 20 Anomalies per month. By purchasing the corresponding add-on the limit is increased by additional 200 anomalies per month.
Finally, this release includes the introduction of MindConnect Software Agent also available as Docker version. MindConnect Software Agent is a pure software agent for collecting data using different protocols and transferring the data to MindSphere. The device supports the transmission of data through a secure internet connection, to enable cloud-based applications and services.
With the Docker version, a Debian installer can be downloaded and installed on a device. There the Docker container will be installed and started automatically or the Docker file and the Docker compose file can be used individually. These files are available for x86 systems. This update enables huge possibilities for how and where to use this solution—the base functionality will be the same as the already released MindConnect Software Agent for Windows.