# mvmalyi/llm-semantic-maintenance-logs-analysis architecture

> Architecture diagram of the GitHub repository mvmalyi/llm-semantic-maintenance-logs-analysis, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-19). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/mvmalyi/llm-semantic-maintenance-logs-analysis
- Repository: https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis

## Overview

This is a reproducible research workflow for exploring semantic reliability insights in wind turbine maintenance logs. The documented user journey is to inspect data preparation, then run a processing notebook containing four LLM-based analyses. The repository also includes JSON, report, and timeline artifacts, but the README does not describe how they are produced or consumed. Relationships below are limited to those explicitly documented; notebook internals were not available for inspection.

Main entry points: [`2_processing_log.ipynb`](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb) (Semantic analysis), [`1_data_cleaning.ipynb`](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/1_data_cleaning.ipynb) (Data preparation)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_workflow["Analysis workflow"]
  node_preparation["Data preparation"]
  node_processing["Semantic analysis"]
end

subgraph group_capabilities["Analysis capabilities"]
  node_failure_modes["Failure modes"]
  node_causal_chains["Causal chains"]
  node_comparative["Comparative analysis"]
  node_quality_audit["Data quality audit"]
end

subgraph group_artifacts["Repository artifacts"]
  node_converter_data["Converter data<br/>[converter.json]"]
  node_farms_data["Farm data<br/>[farms.json]"]
  node_turbine_data["Turbine data<br/>[turbine.json]"]
  node_gemini_report["Gemini quality report"]
  node_gpt_report["GPT quality report"]
  node_timeline["Interactive timeline"]
end

node_analyst(("Researcher"))

node_analyst -->|"inspects"| node_preparation
node_preparation -->|"run sequentially"| node_processing
node_analyst -->|"runs"| node_processing
node_processing -->|"includes"| node_failure_modes
node_processing -->|"includes"| node_causal_chains
node_processing -->|"includes"| node_comparative
node_processing -->|"includes"| node_quality_audit

click node_preparation "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/1_data_cleaning.ipynb"
click node_processing "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb"
click node_failure_modes "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb"
click node_causal_chains "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb"
click node_comparative "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb"
click node_quality_audit "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb"
click node_converter_data "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/converter.json"
click node_farms_data "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/farms.json"
click node_turbine_data "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/turbine.json"
click node_gemini_report "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/data_quality_report_gemini.md"
click node_gpt_report "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/data_quality_report_gpt.md"
click node_timeline "https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/interactive_timeline.html"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_preparation,node_processing toneBlue
class node_failure_modes,node_causal_chains,node_comparative,node_quality_audit toneAmber
class node_converter_data,node_farms_data,node_turbine_data,node_gemini_report,node_gpt_report,node_timeline toneMint
class node_analyst toneIndigo
```

## Components

### Analysis workflow

- [Data preparation](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/1_data_cleaning.ipynb): `1_data_cleaning.ipynb`
- [Semantic analysis](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb): `2_processing_log.ipynb`

### Analysis capabilities

- [Failure modes](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb): `2_processing_log.ipynb`
- [Causal chains](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb): `2_processing_log.ipynb`
- [Comparative analysis](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb): `2_processing_log.ipynb`
- [Data quality audit](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/2_processing_log.ipynb): `2_processing_log.ipynb`

### Repository artifacts

- [Converter data](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/converter.json): `converter.json`
- [Farm data](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/farms.json): `farms.json`
- [Turbine data](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/turbine.json): `turbine.json`
- [Gemini quality report](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/data_quality_report_gemini.md): `data_quality_report_gemini.md`
- [GPT quality report](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/data_quality_report_gpt.md): `data_quality_report_gpt.md`
- [Interactive timeline](https://github.com/mvmalyi/llm-semantic-maintenance-logs-analysis/blob/main/interactive_timeline.html): `interactive_timeline.html`

### Other components

- **Researcher**

## Connections

- Researcher → Data preparation: inspects (evidence: `README.md`)
- Data preparation → Semantic analysis: run sequentially (evidence: `README.md`)
- Researcher → Semantic analysis: runs (evidence: `README.md`)
- Semantic analysis → Failure modes: includes (evidence: `README.md`)
- Semantic analysis → Causal chains: includes (evidence: `README.md`)
- Semantic analysis → Comparative analysis: includes (evidence: `README.md`)
- Semantic analysis → Data quality audit: includes (evidence: `README.md`)
