🚀 AI-Powered Predictive Maintenance System (ML + Streamlit)

---

🌟 Project Overview

This project presents an intelligent Predictive Maintenance System built using Machine Learning techniques with an interactive Streamlit dashboard.

The system allows users to:

• Upload datasets (CSV / Excel / TXT)
• Train machine learning models
• Analyze failure patterns
• Generate reports (PDF with graphs)
• Perform real-time predictions

---

🎯 Objective

✔ Predict machine failure (classification)

✔ Provide interactive analytics dashboard

✔ Generate downloadable PDF reports

✔ Enable real-time predictions via web UI

---

🏗️ System Architecture

🔍 Architecture Highlights

• Dataset upload and preprocessing
• Machine learning model training (Logistic Regression)
• Interactive dashboard (Streamlit)
• Graph visualization (Plotly + Matplotlib)
• PDF report generation (ReportLab)

---

🧠 Core Features

🔹 Dataset Upload & Processing

• Supports CSV, Excel, and TXT files
• Automatic data parsing and validation

---

🔹 Machine Learning Model

• Logistic Regression model
• Feature scaling using StandardScaler
• Classification report (Precision, Recall, Accuracy)

---

🔹 Interactive Dashboard (Streamlit)

• Dataset preview
• KPI metrics (Rows, Columns, Failures)
• Failure distribution visualization

---

🔹 Prediction System

• User input via UI fields
• Real-time prediction with confidence score
• Risk indicator (Failure / Healthy)

---

🔹 Report Generation

• Summary statistics
• Failure analysis
• Graph embedded in PDF
• Downloadable report

---

⚙️ Technologies Used

Category	Tools
Machine Learning	scikit-learn
Data Processing	pandas, numpy
Visualization	plotly, matplotlib
Web Deployment	streamlit
Reporting	reportlab

---

📁 Project Structure

predictive-maintenance-project/
│
├── app.py             # Streamlit application (ML + Dashboard + PDF)
├── requirements.txt   # Dependencies
├── README.md          # Documentation
└── .gitignore         # Ignored files

---

🔄 Workflow

User → Upload Dataset → Preprocessing
                          ↓
                Model Training
                          ↓
                Performance Metrics
                          ↓
            Visualization + Dashboard
                          ↓
              Prediction + PDF Report

---

🚀 Getting Started

🔹 Clone Repository

git clone https://github.com/Chaitanya5068/predictive-maintenance-project

🔹 Navigate to Directory

cd predictive-maintenance-project

🔹 Create Virtual Environment

python -m venv venv

🔹 Activate Environment

Windows: .\venv\Scripts\activate  
Linux/macOS: source venv/bin/activate

🔹 Install Dependencies

pip install -r requirements.txt

🔹 Run Application

streamlit run app.py

🌐 Application URL

https://ifwqnnb9jyeqcwyfxftn4v.streamlit.app/

---

▶️ Usage

🔹 Step 1 — Upload Dataset

• CSV / Excel / TXT supported

🔹 Step 2 — Train Model

• Click Train Model
• System performs preprocessing and training

🔹 Step 3 — Analyze Dashboard

• View metrics and graphs
• Failure distribution visualization

🔹 Step 4 — Prediction

• Enter feature values
• Get failure probability and status

🔹 Step 5 — Generate Report

• View summary
• Download PDF report

---

📊 Sample Outputs

• Failure Distribution Graph
• Classification Report
• PDF Report with Graphs
• Real-time Prediction Output

---

📜 License

This project is licensed under the MIT License — free to use, modify, and distribute with proper credit.

---

👨‍💻 Author

Chaitanya Bhosale

🔗 GitHub: https://github.com/Chaitanya5068

🔗 LinkedIn: https://www.linkedin.com/in/chaitanya-bhosale

---

⭐ Support

If you found this project useful, consider giving it a ⭐ on GitHub!