top of page
TwinWorX®
TwinWorX® Optimizer
TwinWorX® Optimizer harnesses the power of AI and autonomous agents to optimize processes that reduce costs and improve productivity.
TwinWorX® integrates two core technologies to create a seamless optimization platform:
​
TwinWorX Digital Twins Platform
​
-
Dynamic, virtual model of equipment
-
Continuously updated with real-time data from sensors
-
An accurate representation of physical assets for precise monitoring, simulation, and analysis.
​
Autonomous Intelligent Agents​
​
-
Machine learning algorithms to interpret data, predict outcomes, and make informed decisions.
-
Identifying patterns and predicting potential failures, bottlenecks, trending towards tolerances, before they impact production,
-
Autonomously optimize system processes, making recommendations and adjusting operational parameters in real-time
Core Capabilities
PrevPrev
-
Single Pane of Glass VisualizationReal-time dashboard with configurable views Performance scores, baselines, by system, processes, sub types Historical trends Responsive UI for desktops and mobile devices
-
Configurable Rulesets LibraryStandards-based (NIST, ASHRAE) Library of Standard analytic functions and rules Configurable analytic queries and rules expressions Optimize rules with Human Expertise, capturing their dynamic understanding of the environment and contextualizing the problem
-
HistorianData capture, validation, compression, and aggregation Captures operational process data from multiple sources at lightning speed Reliably records faults, events, alarms and other system generated data Ensures continuous access to data via redundancy and high availability
-
Stream AnalyticsEvent-driven, end-to-end serverless streaming pipeline for demanding, mission-critical, continuous-intelligence applications that are: Analyzes time-series data and uses FDD rules to detect, diagnose, identify, execute algorithms, evaluate and rank events.
-
Fault Detection & DiagnosticsDynamic, contextualized, machine enhanced fault detection Detect and diagnose equipment operational or efficiency faults Identify and prioritize control issues Advise on improving equipment performance Autonomously optimize performance through closed-loop feedback
-
Streaming Data Sources and IntegrationAddress diverse, heterogeneous environments with a secure, scalable, hybrid architecture Retrieve data from various device and system sources including: Azure IoT Hub, 3rd Party IoT systems Messaging systems (MQTT, Kafka, TCP, JMS), Databases (PostgreSQL, RDBMS, NoSQL) Services (HTTP, gRPC), File systems, E-mail and others. Transform data on JSON, XML, Text, Avro, and CSV. Secure, encrypted, reliable processing through data preprocessing, fault tolerance, and error handling.
-
AlarmingGenerates alerts based on static and dynamic thresholds. Correlates data to detect event anomalies and missing events. Supports scheduling, digest, and auto-retry of notifications. Publishes alerts via various event sinks such as email, and MQs. Portal: acknowledge, annotate, and assign issues for corrective action. Supports integration to work order systems / CMMS
bottom of page