Motor Current Signature Analysis

About

This Model Context Protocol (MCP) server transforms any Large Language Model (LLM) into an expert in predictive maintenance for electric motors. Utilizing Motor Current Signature Analysis (MCSA), it conducts non-invasive spectral analysis and fault detection by examining stator-current signals. By integrating Fast Fourier Transform (FFT) and envelope analysis, the system can automatically identify mechanical and electrical anomalies in motors, making expert diagnostics accessible through natural language interfaces and enabling both interactive analysis and automated condition-monitoring pipelines.

Key Features

• 0 GitHub stars
• Real signal loading from CSV, TSV, WAV, and NumPy files
• Automated motor parameter and fault frequency calculation (rotor bars, eccentricity, bearings)
• Comprehensive signal preprocessing (DC removal, filtering, normalisation, windowing)
• Advanced spectral and time-frequency analysis (FFT, Welch PSD, envelope analysis, STFT)
• Automated fault detection with severity classification (healthy, incipient, moderate, severe)

Use Cases

• One-shot diagnosis of motor health from a signal file and nameplate data
• Step-by-step guided workflow for MCSA analysis through an AI assistant
• Predictive maintenance for electric motors by identifying faults like broken rotor bars, eccentricity, and bearing defects