Graph-Based Alarm Handling for Faster Root Cause Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Operators in industrial plants face challenges in quickly obtaining a comprehensive overview of the status and topology of processing systems, especially during critical phases or alarm situations, due to scattered information across multiple screens and data sources, leading to time-consuming and error-prone alarm analysis.

Innovation Solution

A method that represents the processing system as a directed graph, allowing selection of a starting node to construct a subgraph, outputting relevant nodes and attributes, and using machine learning for anomaly detection and visualization to provide a clear, interactive overview of the plant's state, including alarm-related information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If operators manually analyze scattered alarm information across multiple screens and data sources, then comprehensive alarm analysis can be achieved, but time consumption and error probability increase significantly

Engineering Contradiction:
Improvealarm analysis accuracyVSAvoidtime for alarm analysis
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent merges scattered alarm information from multiple screens and data sources into a unified alarm analysis interface. The system integrates process data, alarm history, and diagnostic information into a single comprehensive view, eliminating the need for operators to manually switch between multiple screens and data sources, thus reducing time consumption while maintaining analysis accuracy

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces an intelligent alarm analysis system as an intermediary between the complex processing system and operators. This intermediary automatically collects, processes, and presents relevant alarm information, reducing the manual effort required while improving analysis accuracy through systematic data integration and presentation

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If operators manually investigate complex multi-device equipment failures, then root cause analysis can be performed, but time and costs increase due to the complexity of the investigation

Engineering Contradiction:
Improveroot cause analysis capabilityVSAvoidresponse speed to failures
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent implements preliminary action by pre-configuring diagnostic rules, relationships between process elements, and analysis algorithms before failures occur. When a failure happens, the system immediately applies these pre-prepared diagnostic frameworks to rapidly identify potential root causes, eliminating the need for operators to manually investigate complex multi-device failures from scratch

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent incorporates feedback mechanisms where the alarm analysis system continuously monitors system state, compares actual performance against expected behavior, and provides feedback about potential root causes. This automated feedback loop enables rapid identification of failures and their causes, improving both reliability and response speed

Inventive Principle:
Principle #23Feedback

3Loss of information

If comprehensive process data and topology information are displayed to provide complete overview, then understanding of plant status is improved, but information complexity and difficulty of detection increase

Engineering Contradiction:
Improvecompleteness of plant status informationVSAvoiddifficulty of analyzing process data
Core Design Contradiction:
Loss of informationVSDifficulty of detecting and measuring

Solution Approach 1:

The patent applies segmentation by dividing comprehensive process data and topology information into organized, hierarchical groups based on process areas, equipment types, or alarm severity. This segmentation allows the complete plant status to be displayed in a structured manner that reduces analytical difficulty while maintaining information completeness

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements local quality by providing different levels of information detail and presentation formats for different process areas or alarm types. Critical alarms receive prominent display with detailed diagnostic information, while normal operations show summarized data, optimizing the balance between information completeness and analytical ease for different system states

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3896545A1Method for alarm handling in a processing system
Publication Date: 2021.10.20 ABB (SCHWEIZ) AG
  • EP3896545A1 patent drawingFigure 1
  • EP3896545A1 patent drawingFigure 2~3
  • EP3896545A1 patent drawing

AI summary

The invention relates to the field of alarm handling or for providing an attribute of an element in an industrial plant or a processing system, particularly for processing systems that can be represented as a graph. For this, the processing system is represented as a directed graph comprising a plurality of nodes and directed edges, wherein each node represents an element, each node has an attribute, and each directed edge represents a relation between two elements of the plurality of elements. The method comprises the steps of: selecting one node of the plurality of nodes as a starting node; constructing a subgraph, wherein the subgraph consists of all the nodes that are forward-connected by at least one directed edge from the starting node; and outputting all nodes and the attribute of the nodes of the subgraph.