Magnetic-Field Fault Detection in Synchronous Machines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing protection systems for synchronous machines, particularly large synchronous machines like hydropower generators, fail to detect gradual defects that can lead to future serious faults, and existing fault detection methods are invasive or not focused on magnetic field analysis for non-invasive diagnosis.
Innovation Solution
A method and system using sensors to measure magnetic field parameters, applying signal processing techniques and machine learning algorithms to identify and categorize irregularities in the magnetic field, specifically utilizing frequencies above the line frequency for fault detection in synchronous machines without invasive modifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing protection systems use voltage, current profile, or extracted data at the terminal of the stator, then immediate and correct disconnection can be achieved for severe faults, but gradual defects inside the machine cannot be detected
Solution Approach 1:
The patent introduces magnetic field sensors as an intermediary measurement medium to detect faults. By measuring the magnetic field generated by the synchronous machine and analyzing its spectral content, the system can detect both severe faults and gradual defects that are invisible to traditional voltage and current-based protection systems. The magnetic field serves as a mediator that carries information about internal machine conditions without requiring invasive modifications.
2Reliability
If invasive measurements and modifications are applied to the machine, then faults can be detected, but the machine structure is modified and disruption occurs
Solution Approach 1:
The patent replaces invasive mechanical measurement methods with non-invasive magnetic field sensing. Instead of physically modifying the machine structure to attach sensors inside the machine, the system uses external sensors to measure the magnetic field generated by the machine during operation. This substitution of measurement approach eliminates the need for mechanical modifications while maintaining fault detection capability.
3Productivity
If periodic maintenance systems are used, then maintenance can be scheduled, but unplanned outages occur due to undetected gradual defects
Solution Approach 1:
The patent implements a feedback-based condition monitoring system that continuously measures and analyzes the magnetic field of the synchronous machine. By processing the spectral content of the magnetic field signals and comparing them against baseline values, the system provides real-time feedback about the machine's health status. This enables the detection of gradual defects as they develop, allowing maintenance to be scheduled based on actual condition rather than fixed intervals, thereby preventing unplanned outages.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables effective, non-invasive detection of faults such as eccentricity and damper winding issues in synchronous machines, minimizing disruption and enhancing fault detection capabilities in large generators like hydropower units.
Implementation Method 1
using at least one sensor to determine parameters linked to the magnetic field generated within the synchronous machine including parameters based on one or more of magnetic field strength, rotor current or voltage, stator current or voltage, and vibration
Data Source
AI summary
A method of fault detection in synchronous machines includes using at least one sensor to determine parameters linked to the magnetic field generated within the synchronous machine including parameters based on one or more of magnetic field strength, rotor current or voltage, stator current or voltage, and vibration. The sensor measurements are processed to identify data artefacts linked to the magnetic field, wherein the processing includes one or more signal processing techniques based on time, frequency, and both time and frequency. Subsequently, the output of the signal processing is analysed in order to identify and categorise irregularities in the magnetic field that are indicative of a fault in the synchronous machine. The analysing step includes recognising patterns in the processed sensor measurements, via use of computer aided pattern recognition techniques such as via machine learning algorithms.