Software AG’s TrendMiner 2021.R2 Release Extends the Reach of Machine Learning and AI
Democratization of Machine Learning makes operational experts better able to improve and predict process and asset performance
New multi-variate Anomaly Detection Model automatically detects deviations from desired operational behavior.
Self-service integration with webMethods.io from Software AG breaks down data silos and allows to easily create cross departmental workflows.
Houston, Belgium and, Germany, 6 May 2021: Software AG’s TrendMiner has announced the release of TrendMiner 2021.R2. This new release extends the reach of previously released notebook integration, allowing analytics expert-users to make their data model outputs available to the rest of the organization, giving operational experts better insights. Additionally, the new multi-variate Anomaly Detection Model allows optimal process conditions to be trained on historical data and can detect anomalies on new incoming data. TrendMiner 2021.R2 also allows self-service integration via webMethods.io. This enables contextual process information from other business applications to be taken into account and workflows in external systems to be triggered through the new Anomaly Detection Model.
Democratizing Machine Learning with Extended Notebook Capabilities
TrendMiner 2021.R2 extends the notebook capabilities of released in 2021.R1, enabling them to be operationalized by deploying custom created data models into an embedded scoring/inference engine the through use of Machine Learning Model tags. These ‘Machine Learning Model’ tags are available for all TrendMiner users, as if they were tags originating from an enterprise historian or any other time-series data source. All existing TrendMiner capabilities can be applied, such as visualizing recent & historical data, searching for patterns or threshold values as well as monitoring using the machine learning model patterns.
“Classical data science depends on bringing process / asset know-how to data science (expert) teams and using their scripting, hacking and parsing skills to come to increased insights, in their expert silo. With the new TrendMiner capabilities we aim to break apart the traditional silo-approach and really bring the data scientist in the loop. While crafting the prepared data into something useful for themselves and others, they can work in close collaboration with all other TrendMiner users to contextualize the raw data with operational knowledge. Afterwards they have an easy out-of-the-box way to operationalize their findings within the organization, empowering others to get better and easier insights.”
Nick Van Damme, TrendMiner Director of Products
Introducing the TrendMiner multi-variate Anomaly Detection Model
The TrendMiner 2021.R2 release now offers a proprietary model for multi-variate anomaly detection via the mentioned notebook and ‘Machine Learning Model’ tags functionality. The TrendMiner Anomaly Detection Model can be trained on a trend view containing normal operating conditions of the process. After learning the desired process conditions, the model will then be able to detect anomalies on new incoming data. The model will return whether a new datapoint is an outlier or not based on a given threshold (anomaly class) or return an anomaly score. The higher the anomaly score, the more likely it is that the datapoint is an outlier.
Self-service Integration for cross data silo collaboration
Factories today are capturing and storing an enormous amount of data directly or indirectly related to the production process. All this data typically ends up in best of breed business applications serving specific operational purposes. All this contextual information residing in various business applications can give new insights for improving operational performance, if the operational experts can actually access that data. With the introduction of the integration add-on powered by webMethods.io within the TrendMiner platform, engineers can now create integrations to crucial business applications themselves. On top of that, the self-service integration via webMethods.io allows workflows to be created across the business applications on premises and in cloud solutions. This can for example be used to notify your colleagues with a MS Teams or Slack message and to simultaneously add a maintenance work request in SAP, when a TrendMiner monitor fires an alert.
Asset specific context types: Additional configuration for the context types in the platform, letting administrators decide which context types are available for a certain part of the asset tree.
Component filter in ContextHub adds support to easily include all context items related to a unit or equipment in your views.
Pinning rows within Gantt charts allows you to specify which components, types or fields should always be displayed, regardless of there being content available in the timeframe you are viewing
Improved search result and chart data export
Improved disablement strategy for monitors that better indicates system disabled monitors and allows for health-checks to re-enable these monitors.
Improved DashHub user experience including a more compact tile view, presentation mode and scrollable dashboards.
DashHub’s ‘Trend Tile’ now lets you enjoy all the features like stacked plot mode, grouping, axis visibility, scatter plot mode with histograms, etc. Well known tools in TrendMiner.
Gantt chart ordering by drag and drop to move types, field or complete component block on the Gantt overview.
Parallel connections: In ConfigHub it is now possible to configure the number of parallel connections per data source, giving the option to limit the load on low capacity data sources and increasing throughput to TrendMiner for high capacity data sources.
Various scatter plot improvements.
Support for TrendHub NextGen views in Notebooks.
Miscellaneous security improvements.
Full support for (latest version of) the Microsoft Edge browser (as a replacement for support of Internet Explorer 11, which will be dropped in the 2021.R3 release)
Each release adds a range of new features and enhancements that are requested by TrendMiner users. There are many more improvements in the TrendMiner 2021.R2 release, which users of the software can find in the release notes. For more information, please visit: www.trendminer.com. To see TrendMiner’s functionality in-action and learn how analytics-empowered process and asset experts can help accelerate operational performance, click here to request a demo.
TrendMiner, a Software AG company and part of the IoT & Analytics division, delivers self-service data analytics to optimize process performance in industries such as chemical, petrochemical, oil & gas, pharmaceutical, metals & mining and other process manufacturing industries. TrendMiner software is based on a high-performance analytics engine for time-series data that allows users to question data directly, without the support of data scientists. The plug-and-play software adds immediate value upon deployment, eliminating the need for infrastructure investment and long implementation projects. Search, diagnostic and predictive capabilities enable users to speed up root cause analysis, define optimal processes and configure early warnings to monitor production. TrendMiner software also helps team members to capture feedback and leverage knowledge across teams and sites. In addition, TrendMiner offers standard integrations with a wide range of historians such as OSIsoft PI, Yokogawa Exaquantum, AspenTech IP.21, Honeywell PHD, GE Proficy Historian and Wonderware InSQL.
Founded in 2008 and now part of Software AG, TrendMiner’s global headquarters is located in Belgium, and has offices in the U.S., Germany, Spain and the Netherlands.