Causal Map Root Cause Identification for Industrial Fault Diagnosis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Root cause identification in manufacturing and process industries is challenging due to complex multivariate data and high dependency on manual inputs and subject matter knowledge, making it difficult to automate the process effectively.

Innovation Solution

A system and method that processes time-series data to predict soft sensed parameters, detect fault variables, generate causal maps, and identify root causes using the Fault Traversal and Root Cause Identification (FTRCI) technique, reducing reliance on manual inputs by analyzing causal relationships and contribution scores.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If knowledge-based techniques are used for root cause identification, then prior knowledge of faults and relationships can be utilized, but manual inputs and subject matter knowledge are heavily required

Engineering Contradiction:

Improveroot cause identification accuracyVSAvoidautomation level

Core Design Contradiction:

ReliabilityVSExtent of automation

Solution Approach 1:

The system performs self-learning by automatically acquiring knowledge from historical process data and fault information without requiring manual knowledge base construction. The algorithm independently identifies causal relationships and builds the knowledge structure, enabling the system to serve itself rather than relying on external expert inputs

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual knowledge engineering activities with an automated computational algorithm. Instead of experts manually constructing knowledge bases, the system uses data-driven methods to automatically discover fault patterns and causal relationships, substituting mechanical manual processes with automated computational procedures

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Extent of automation

If data-driven methods are used for root cause identification, then automation is improved, but dependency on historical and current operating data increases

Engineering Contradiction:

Improveautomation levelVSAvoiddependency on data completeness

Core Design Contradiction:

Extent of automationVSLoss of information

Solution Approach 1:

The system performs preliminary learning by continuously analyzing historical process data to build a knowledge base of causal relationships before actual fault occurrence. This advance preparation ensures that when faults occur, the system can immediately apply pre-learned knowledge without being overly dependent on complete real-time data

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system cushions against data incompleteness by pre-acquiring and storing knowledge from historical data during normal operation. This beforehand preparation creates a buffer that allows the system to function effectively even when real-time data is incomplete or unavailable during fault conditions

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

3Reliability

If manual identification of causal structures is performed, then subject matter expertise can be applied, but the process becomes complex and time-consuming

Engineering Contradiction:

Improvefault diagnosis accuracyVSAvoidanalysis time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual expert analysis with an automated algorithm that processes process data and identifies causal structures. The computational system substitutes human experts in performing the time-consuming task of causal relationship identification, maintaining diagnostic accuracy while dramatically reducing analysis time

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Measurement precision

If complex multivariate data is analyzed manually, then detailed inspection is possible, but the complexity increases and automation becomes difficult

Engineering Contradiction:

Improvefault detection precisionVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the complex multivariate data analysis into distinct computational steps: data preprocessing, pattern recognition, causal relationship identification, and fault localization. By dividing the complex analysis task into manageable segments, the system maintains high detection precision while enabling automated processing of complex data

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12026047B2Method and system for root cause identification of faults in manufacturing and process industries

Publication Date: 2024.07.02 TATA CONSULTANCY SERVICES LTD

AI summary

The disclosure is a method and a system for root cause identification (RCI) of faults in manufacturing and process industries. With complex interrelated multivariate data in manufacturing and process industries, the process of root RCI of faults is challenging. Further, the existing techniques for RCI have significant dependency on manual inputs and subject matter knowledge/experts. The disclosure is method and a system for root cause identification of a fault based on causal maps. The root cause of fault is identified in several steps including: generation of casual maps using data received from a manufacturing and process industry and root cause identification from the causal maps based on a Fault Traversal and Root Cause Identification (FTRCI) technique. The FTRCI identifies root cause from the causal map by identifying a fault traversal pathway from a leaf node in the causal map, wherein the fault traversal pathway is identified for even cyclic paths.