Module Fingerprints for Event Analytics in Modular Plants

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In traditional non-modular industrial plants, event analytics struggles to derive meaningful rules and patterns from alarms due to the lack of information on how measurement points are connected, leading to ineffective alarm management and predictive maintenance.

Innovation Solution

Implement module-based event analytics using module fingerprints, which capture event types in a given time interval, enabling machine learning models to determine current states, predict future states, and identify rules and anomalies, thereby optimizing alarm management and predictive maintenance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional event analytics is applied to non-modular industrial plants, then alarm management and predictive maintenance can be performed, but the analysis is ineffective due to lack of connection information between measurement points

Engineering Contradiction:

Improvealarm management effectivenessVSAvoidconnection information between measurement points

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The patent segments the industrial plant into modular process units, where each unit is self-contained with defined measurement points and connections. This segmentation allows event analytics to be performed within each module using only internal connection information, eliminating the need for complete plant-wide connection data while improving analysis reliability.

Inventive Principle:

Principle #1Segmentation

2Loss of information

If manual derivation of connection information from P&ID diagrams is performed, then measurement point relationships can be obtained, but the process is cumbersome and time-consuming

Engineering Contradiction:

Improvemeasurement point connection informationVSAvoidtime for manual derivation

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The patent performs preliminary action by pre-defining the modular structure and connection information during the plant design and commissioning phase. Connection topologies are established and stored in the control system before operation begins, eliminating the need for manual derivation from P&ID diagrams during operation and significantly reducing time requirements.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If rules are generated without knowing measurement point relationships, then event analytics can proceed, but the generated rules do not make sense from the plant perspective and many useful rules are missed

Engineering Contradiction:

Improverule generation efficiencyVSAvoidrule quality and relevance

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent applies local quality by generating event analytics rules specific to each modular process unit based on its local measurement points and connection topology. Each module's rules are tailored to its specific process characteristics and relationships, ensuring high relevance and quality while maintaining efficient automated generation without requiring plant-wide connection knowledge.

Inventive Principle:

Principle #3Local quality

Data Source

PatentEP3995920B1Event analytics in modular industrial plants

Publication Date: 2025.12.31 ABB (SCHWEIZ) AG

Figure 1
Figure 2
Figure 3

AI summary

There are provided systems and methods for event analytics in a modular industrial plant (100). The method comprises: monitoring (201) events in a module (110) of the modular industrial plant during a predetermined time interval; generating (202) a module fingerprint based on the monitored events occurring in the module during the predetermined time interval; and performing (203) module-based event analytics based on the generated module fingerprint.