Fault Diagnosis Python Packages

bearing-datasets

Python library to download public bearing and rotating-machinery fault datasets (CWRU, Paderborn, XJTU-SY, FEMTO, IMS, …) from their original sources and convert them into one Parquet format, with the same columns and labels for every dataset.

predictive-maintenance-mcp

MCP server for predictive maintenance and machinery fault diagnosis. Gives AI assistants evidence-based vibration analysis - FFT, envelope, bearing fault detection, ISO 20816-3 severity - with a measured, blind CWRU benchmark. Local-first: raw signals never leave your machine. Includes a Claude Code plugin.

cwru-plus

Ultra-fast, customizable CWRU dataset pipeline optimized for Deep Learning, Domain Adaptation, and parallel digital signal processing.

bibmon

Python package that provides predictive models for fault detection, soft sensing, and process condition monitoring.

iflow-mcp-lgdimaggio-predictive-maintenance-mcp

MCP server for predictive maintenance and machinery fault diagnosis. Gives AI assistants evidence-based vibration analysis - FFT, envelope, bearing fault detection, ISO 20816-3 severity - with a measured, blind CWRU benchmark. Local-first: raw signals never leave your machine. Includes a Claude Code plugin.

mseep-predictive-maintenance-mcp

An open-source MCP server that turns LLMs into condition monitoring assistants for reliability engineers. It gives your AI assistant evidence-based vibration diagnostics: machine fault detection, severity assessment and diagnostic reports, for faster predictive maintenance decisions. Also available as a Claude Code plugin.

manastone-diag

Offline fault diagnosis assistant for the AgiBot X2 Ultra humanoid: drop in a log package, get a three-round reviewed diagnosis. Rules + causal inference + LLM agent.

statorscope

Motor Current Signature Analysis that knows when to refuse. Detect broken rotor bars, stator faults and eccentricity from 3-phase current - and get told when your data can't support the answer.

grape-mathlab

GRAph Parallel Environment

modenexus

Compile system models to d-DNNF circuits, then diagnose, track, and learn on one artifact: exact posteriors, ranked diagnoses, mode tracking, EM — with a PyTorch backend for GPU inference.

ccrl

CCRL is a research framework for continual fault diagnosis in aero-engines. It integrates contrastive representation learning with reinforcement learning strategies to support incremental fault pattern discovery while maintaining stable diagnostic performance on previously learned conditions.

pusion

Pusion (Python Universal Fusion) is a generic and flexible framework written in Python for combining multiple classifier’s decision outcomes.