DCS Troubleshooting Assistant for IT-OT Anomaly Diagnosis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Diagnosing software and hardware problems in large distributed systems is challenging due to the complex interplay of thousands of components, leading to delayed troubleshooting and prolonged downtimes.

Innovation Solution

A method utilizing a DCS Software Troubleshooting Assistant that monitors data from DCS and automation equipment, performs anomaly detection, conducts similarity searches on historic data, and queries a large language model (LLM) for diagnosis and recommendations, providing outputs through a conversational interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If observability software focuses only on software component data (logs, metrics, traces), then software problem diagnosis is improved, but hardware problem diagnosis capability deteriorates

Engineering Contradiction:
Improvesoftware problem diagnosis accuracyVSAvoidhardware problem diagnosis capability
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The diagnostic system is designed to handle both software and hardware problems through a unified architecture. The anomaly detection module monitors both IT infrastructure metrics and OT production data, while the LLM provides universal diagnostic capabilities across different problem types. This multi-functional design allows the same system to diagnose both software issues (using traditional log/metric/trace analysis) and hardware issues (using production process data correlation), thereby improving versatility without sacrificing software diagnosis accuracy.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If manual correlation of IT and OT data is required, then data accuracy is maintained, but troubleshooting time increases significantly

Engineering Contradiction:
Improvedata accuracyVSAvoidtroubleshooting delay
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The LLM acts as an intermediary that automatically correlates IT and OT data. Instead of requiring manual correlation of infrastructure metrics with production data, the LLM processes both data types together, understanding their relationships and generating unified diagnostic insights. This automated intermediary function maintains data accuracy by carefully analyzing both data sources while dramatically reducing the time required for correlation and diagnosis.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system transforms multiple data parameters from different sources (IT logs, metrics, traces, and OT production data) into a unified diagnostic representation that the LLM can process. By changing the parameter representation to be compatible across different data types, the system enables automatic correlation without manual intervention, maintaining accuracy while reducing troubleshooting time.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If comprehensive monitoring of all system components is implemented, then diagnostic coverage is improved, but system complexity increases

Engineering Contradiction:
Improvediagnostic coverageVSAvoidmonitoring system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system extracts only the most relevant features and anomalies from the comprehensive monitoring data rather than processing all raw data. The anomaly detection module identifies significant deviations, and the LLM focuses its analysis on these extracted key elements. This extraction approach maintains comprehensive diagnostic coverage by not missing important issues while reducing system complexity by avoiding processing of all raw monitoring data.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP4653967A1DCS software troubleshooting assistant
Publication Date: 2025.11.26 ABB (SCHWEIZ) AG
  • EP4653967A1 patent drawingFigure 1
  • EP4653967A1 patent drawingFigure 2
  • EP4653967A1 patent drawingFigure 3

AI summary

There is disclosed a method for supporting troubleshooting software and hardware issues in a distributed control system, DCS, associated with an automation equipment in industrial plant. The method comprises monitoring data from the DCS and/or monitoring data from the automation equipment. The method further comprises detecting an anomaly in the monitored data based on predetermined anomaly detection rules. The method further comprises, based on a result of the detecting, performing, for a detected anomaly, a similarity search on historic anomaly data associated with the DCS and/or the automation equipment. The method further comprises, based on a result of the performed similarity search, querying a large language model, LLM, (160) for diagnosis and/or recommendation for troubleshooting the detected anomaly. The method further comprises, based on the querying, obtaining an output from the LLM (160), wherein the output is indicative of a diagnosis and/or recommendation for troubleshooting the detected anomaly. The method further comprises providing the output to a user (180).