Substation Fault Analysis Using Causality Matrix and ML

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Fault analysis in electrical substations is intricate, burdensome, and reliant on manual processes, especially with larger and more complex systems, making it difficult to accurately judge and control faults due to the need to process extensive datasets.

Innovation Solution

A method and system utilizing an intelligent electronic device (IED) to receive disturbance records, extract variable time series data, generate a causality matrix through causal analysis, predict fault types using machine learning, and retrieve probable causes from a knowledge database, with incremental learning and expert feedback for continuous improvement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional manual fault analysis techniques are used, then experts can analyze faults with human judgment and experience, but the process becomes intricate, burdensome, and time-consuming when dealing with larger and more complex systems

Engineering Contradiction:

Improvefault analysis accuracyVSAvoidfault analysis time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual expert analysis with an automated computer-based system that uses machine learning models and causal analysis algorithms to process disturbance records and determine fault causes, eliminating the time-consuming manual review process while maintaining or improving accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary automated analysis system that acts as a bridge between raw disturbance data and expert judgment, using causal analysis and machine learning to preprocess and structure information before presenting conclusions, thereby reducing both time and manual effort

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If traditional manual fault analysis techniques are used, then experts can utilize their experience to judge faults, but the complexity of the analysis process increases when dealing with larger and more sensitive faults requiring extensive dataset processing

Engineering Contradiction:

Improvefault judgment reliabilityVSAvoidanalysis process complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the complex fault analysis process into distinct automated components: disturbance record reception, variable extraction, causal analysis, machine learning prediction, and knowledge base retrieval. Each component handles a specific aspect of the analysis independently, reducing overall process complexity while improving reliability

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent replaces the complex manual analytical process with automated computational algorithms including causal analysis for variable correlation and machine learning models for fault prediction, thereby reducing process complexity while enhancing judgment reliability through consistent algorithmic application

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Loss of information

If specialists and experts manually analyze disturbance records using system data like alarm and events, disturbance or fault records, measurement reports, device settings, and electrical single line diagrams, then human expertise can be applied, but it increases difficulty in correctly judging the fault and root cause

Engineering Contradiction:

Improvecomprehensive data utilizationVSAvoidfault root cause identification difficulty

Core Design Contradiction:

Loss of informationVSDifficulty of detecting and measuring

Solution Approach 1:

The patent creates a universal automated analysis system that can process multiple types of data sources (alarm records, disturbance records, measurement reports, device settings, single line diagrams) through a single integrated platform using causal analysis and machine learning, eliminating the need for separate manual analysis of each data type and reducing identification difficulty

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent replaces manual expert judgment with automated machine learning models that objectively analyze all input data sources simultaneously, using trained algorithms to identify patterns and correlations that may be difficult for humans to detect, thereby reducing the difficulty of root cause identification while comprehensively utilizing all available information

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250315339A1System and Method for Performing Fault and Event Analysis in Electrical Substations

Publication Date: 2025.10.09 ABB (SCHWEIZ) AG

AI summary

A system and method performing fault and event analysis in electrical substations comprises receiving a disturbance record triggered by an intelligent electronic device (IED) at an electrical substation, pre-processing the received disturbance record to extract at least one variable time series data of plurality of electrical parameters, generating a causality matrix based on the extracted at least one variable time series data by applying causal analysis, predicting, using a Machine learning (ML) module, a fault type at least based on the causality matrix, retrieving, from a knowledge database, a plurality of probable causes corresponding to the predicted fault type, determining at least one exact cause from the plurality of probable causes based on the causal pattern, and providing the fault type, the plurality of probable causes, and the at least one exact cause to a user.