# aditya12333/predictive-maintenance-platform-ml architecture

> Architecture diagram of the GitHub repository aditya12333/predictive-maintenance-platform-ml, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-20). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/aditya12333/predictive-maintenance-platform-ml
- Repository: https://github.com/aditya12333/predictive-maintenance-platform-ml

## Overview

This is a predictive-maintenance platform that turns historical engine data into governed RUL models, then scores live telemetry and exposes fleet health and alerts. The principal workflow is data preparation and model training, candidate packaging and approval, streaming ingestion and quality-aware inference, persistence, and dashboard/API consumption. The graph also includes batch orchestration and monitoring/retraining. Relationships are grounded in the README and shown source excerpts or SOURCE INDEX references; unsampled implementations are represented only at supported subsystem paths.

Main entry points: [`src/predictive_maintenance/api/app.py`](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/api/app.py) (Telemetry API), [`src/predictive_maintenance/streaming/consumer.py`](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/streaming/consumer.py) (Stream consumer), [`frontend/components/fleet-dashboard.tsx`](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/frontend/components/fleet-dashboard.tsx) (Fleet dashboard), [`src/predictive_maintenance/training/train.py`](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/train.py) (Model training)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data foundation"]
  node_data_prep["Dataset preparation<br/>[prepare.py]"]
  node_data_validation["Data validation<br/>[validate.py]"]
  node_data_manifest["Data lineage<br/>[manifest.py]"]
  node_feature_builder["Feature generation<br/>[builder.py]"]
end

subgraph group_models["Model lifecycle"]
  node_model_training["Model training<br/>[train.py]"]
  node_model_evaluation["Model evaluation<br/>[evaluate.py]"]
  node_model_package["Candidate packaging<br/>[package.py]"]
  node_model_registry["Candidate registry<br/>[registry.py]"]
  node_model_approval["Human approval<br/>[approval.py]"]
  node_model_promotion["Model promotion<br/>[promotion.py]"]
end

subgraph group_serving["Telemetry serving"]
  node_inference_registry["Approved model loading<br/>[registry.py]"]
  node_api_ingestion["Telemetry API<br/>[app.py]"]
  node_event_stream["Event streaming<br/>[producer.py]"]
  node_event_consumer["Stream consumer<br/>[consumer.py]"]
  node_inference_worker["Inference decisions<br/>[worker.py]"]
end

subgraph group_operations["Operations"]
  node_operational_store[("Operational persistence<br/>[operational.py]")]
  node_alert_store[("Alert lifecycle<br/>[alerts.py]")]
  node_monitoring["Monitoring reports<br/>[report.py]"]
  node_retraining["Retraining policy<br/>[retraining.py]"]
  node_training_dag["Candidate pipeline"]
  node_monitoring_dag["Monitoring schedule"]
end

subgraph group_experience["Fleet experience"]
  node_dashboard["Fleet dashboard"]
  node_frontend_api["Dashboard API client<br/>[api.ts]"]
end

node_operator(("Maintenance operator"))
node_producer(("Telemetry producer"))

node_operator -->|"reviews fleet"| node_dashboard
node_producer -->|"submits telemetry"| node_api_ingestion
node_data_prep -->|"validates data"| node_data_validation
node_data_prep -->|"publishes lineage"| node_data_manifest
node_model_training -->|"uses features"| node_feature_builder
node_model_training -->|"compares models"| node_model_evaluation
node_model_package -->|"registers candidate"| node_model_registry
node_model_registry -->|"submits evidence"| node_model_approval
node_model_approval -->|"authorizes promotion"| node_model_promotion
node_model_promotion -->|"updates champion"| node_inference_registry
node_inference_registry -->|"verifies registry"| node_model_registry
node_api_ingestion -->|"publishes events"| node_event_stream
node_event_consumer -->|"processes events"| node_inference_worker
node_event_consumer -->|"publishes dead letters"| node_event_stream
node_inference_worker -->|"builds features"| node_feature_builder
node_event_consumer -->|"persists outcomes"| node_operational_store
node_api_ingestion -->|"serves fleet data"| node_operational_store
node_api_ingestion -->|"handles alerts"| node_alert_store
node_monitoring -->|"evaluates persisted data"| node_operational_store
node_monitoring_dag -->|"runs reports"| node_monitoring
node_monitoring_dag -->|"checks failures"| node_retraining
node_retraining -->|"requests candidate"| node_training_dag
node_training_dag -->|"orchestrates training"| node_model_training
node_frontend_api -->|"calls operations API"| node_api_ingestion
node_dashboard -->|"loads fleet data"| node_frontend_api
node_dashboard -->|"manages alerts"| node_alert_store

click node_data_prep "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/data/prepare.py"
click node_data_validation "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/data/validate.py"
click node_data_manifest "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/data/manifest.py"
click node_feature_builder "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/features/builder.py"
click node_model_training "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/train.py"
click node_model_evaluation "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/evaluate.py"
click node_model_package "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/package.py"
click node_model_registry "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/registry.py"
click node_model_approval "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/approval.py"
click node_model_promotion "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/promotion.py"
click node_inference_registry "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/inference/registry.py"
click node_api_ingestion "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/api/app.py"
click node_event_stream "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/streaming/producer.py"
click node_event_consumer "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/streaming/consumer.py"
click node_inference_worker "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/inference/worker.py"
click node_operational_store "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/storage/operational.py"
click node_alert_store "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/storage/alerts.py"
click node_monitoring "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/monitoring/report.py"
click node_retraining "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/monitoring/retraining.py"
click node_training_dag "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/airflow/dags/rul_training_pipeline.py"
click node_monitoring_dag "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/airflow/dags/monitoring_pipeline.py"
click node_dashboard "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/frontend/components/fleet-dashboard.tsx"
click node_frontend_api "https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/frontend/lib/api.ts"

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_data_prep,node_data_validation,node_data_manifest,node_feature_builder toneBlue
class node_model_training,node_model_evaluation,node_model_package,node_model_registry,node_model_approval,node_model_promotion toneAmber
class node_inference_registry,node_api_ingestion,node_event_stream,node_event_consumer,node_inference_worker toneMint
class node_operational_store,node_alert_store,node_monitoring,node_retraining,node_training_dag,node_monitoring_dag toneRose
class node_dashboard,node_frontend_api,node_operator,node_producer toneIndigo
```

## Components

### Data foundation

- [Dataset preparation](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/data/prepare.py): `src/predictive_maintenance/data/prepare.py`
- [Data validation](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/data/validate.py): `src/predictive_maintenance/data/validate.py`
- [Data lineage](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/data/manifest.py): `src/predictive_maintenance/data/manifest.py`
- [Feature generation](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/features/builder.py): `src/predictive_maintenance/features/builder.py`

### Model lifecycle

- [Model training](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/train.py): `src/predictive_maintenance/training/train.py`
- [Model evaluation](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/evaluate.py): `src/predictive_maintenance/training/evaluate.py`
- [Candidate packaging](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/package.py): `src/predictive_maintenance/training/package.py`
- [Candidate registry](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/registry.py): `src/predictive_maintenance/training/registry.py`
- [Human approval](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/approval.py): `src/predictive_maintenance/training/approval.py`
- [Model promotion](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/training/promotion.py): `src/predictive_maintenance/training/promotion.py`

### Telemetry serving

- [Approved model loading](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/inference/registry.py): `src/predictive_maintenance/inference/registry.py`
- [Telemetry API](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/api/app.py): `src/predictive_maintenance/api/app.py`
- [Event streaming](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/streaming/producer.py): `src/predictive_maintenance/streaming/producer.py`
- [Stream consumer](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/streaming/consumer.py): `src/predictive_maintenance/streaming/consumer.py`
- [Inference decisions](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/inference/worker.py): `src/predictive_maintenance/inference/worker.py`

### Operations

- [Operational persistence](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/storage/operational.py): `src/predictive_maintenance/storage/operational.py`
- [Alert lifecycle](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/storage/alerts.py): `src/predictive_maintenance/storage/alerts.py`
- [Monitoring reports](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/monitoring/report.py): `src/predictive_maintenance/monitoring/report.py`
- [Retraining policy](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/src/predictive_maintenance/monitoring/retraining.py): `src/predictive_maintenance/monitoring/retraining.py`
- [Candidate pipeline](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/airflow/dags/rul_training_pipeline.py): `airflow/dags/rul_training_pipeline.py`
- [Monitoring schedule](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/airflow/dags/monitoring_pipeline.py): `airflow/dags/monitoring_pipeline.py`

### Fleet experience

- [Fleet dashboard](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/frontend/components/fleet-dashboard.tsx): `frontend/components/fleet-dashboard.tsx`
- [Dashboard API client](https://github.com/aditya12333/predictive-maintenance-platform-ml/blob/main/frontend/lib/api.ts): `frontend/lib/api.ts`

### Other components

- **Maintenance operator**
- **Telemetry producer**

## Connections

- Maintenance operator → Fleet dashboard: reviews fleet
- Telemetry producer → Telemetry API: submits telemetry
- Dataset preparation → Data validation: validates data
- Dataset preparation → Data lineage: publishes lineage
- Model training → Feature generation: uses features
- Model training → Model evaluation: compares models
- Candidate packaging → Candidate registry: registers candidate
- Candidate registry → Human approval: submits evidence (evidence: `src/predictive_maintenance/training/approval.py`)
- Human approval → Model promotion: authorizes promotion (evidence: `src/predictive_maintenance/training/promotion.py`)
- Model promotion → Approved model loading: updates champion
- Approved model loading → Candidate registry: verifies registry (evidence: `src/predictive_maintenance/inference/registry.py`)
- Telemetry API → Event streaming: publishes events (evidence: `src/predictive_maintenance/api/app.py`)
- Stream consumer → Inference decisions: processes events (evidence: `src/predictive_maintenance/streaming/consumer.py`)
- Stream consumer → Event streaming: publishes dead letters (evidence: `src/predictive_maintenance/streaming/consumer.py`)
- Inference decisions → Feature generation: builds features (evidence: `src/predictive_maintenance/inference/worker.py`)
- Stream consumer → Operational persistence: persists outcomes
- Telemetry API → Operational persistence: serves fleet data (evidence: `src/predictive_maintenance/api/app.py`)
- Telemetry API → Alert lifecycle: handles alerts (evidence: `src/predictive_maintenance/api/app.py`)
- Monitoring reports → Operational persistence: evaluates persisted data
- Monitoring schedule → Monitoring reports: runs reports (evidence: `airflow/dags/monitoring_pipeline.py`)
- Monitoring schedule → Retraining policy: checks failures (evidence: `airflow/dags/monitoring_pipeline.py`)
- Retraining policy → Candidate pipeline: requests candidate
- Candidate pipeline → Model training: orchestrates training
- Dashboard API client → Telemetry API: calls operations API
- Fleet dashboard → Dashboard API client: loads fleet data
- Fleet dashboard → Alert lifecycle: manages alerts
