https://github.com/sadratehranian/pem-fuel-cell

The methodology section details the use of Python for data processing and analysis, employing statistical and machine learning-based anomaly detection techniques to identify potential issues in fuel cell stacks. It emphasizes data preprocessing, feature engineering, exploratory data analysis (EDA), and anomaly detection.
https://github.com/sadratehranian/pem-fuel-cell

anomaly-detection data-analysis data-science data-visualization exploratory-data-analysis feature-engineering fuel-cell machine-learning preprocessing python statistical-analysis visual-studio-code

Last synced: about 2 months ago
JSON representation

The methodology section details the use of Python for data processing and analysis, employing statistical and machine learning-based anomaly detection techniques to identify potential issues in fuel cell stacks. It emphasizes data preprocessing, feature engineering, exploratory data analysis (EDA), and anomaly detection.

• Host: GitHub
• URL: https://github.com/sadratehranian/pem-fuel-cell
• Owner: Sadratehranian
• Created: 2025-01-20T19:35:14.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2025-01-20T20:00:41.000Z (4 months ago)
• Last Synced: 2025-01-31T07:18:15.226Z (4 months ago)
• Topics: anomaly-detection, data-analysis, data-science, data-visualization, exploratory-data-analysis, feature-engineering, fuel-cell, machine-learning, preprocessing, python, statistical-analysis, visual-studio-code
• Language: Python
• Homepage: https://github.com/Sadratehranian/PEM-Fuel-Cell
• Size: 5.72 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Data3040 Analysis

This repository contains a Python script and a dataset for analyzing anomalies in cell voltage readings. The goal is to identify patterns, detect anomalies, and visualize results for improved analysis.

## Contents

- **`Main.py`**: Python script for loading, cleaning, and analyzing the dataset.

- **`data3040b.xlsx`**: Dataset containing voltage readings for multiple cells.

- **`README.md`**: Documentation for this project.

## Features

1. Data Cleaning:

   - Removes redundant rows (e.g., empty rows or units).

   - Ensures proper formatting for analysis.

2. Feature Engineering:

   - Calculates rolling statistics (mean, standard deviation, etc.).

   - Detects anomalies in cell voltage readings.

3. Anomaly Detection Techniques:

   - **Isolation Forest**

   - **DBSCAN**

   - **K-Means Clustering**

   - **One-Class SVM**

4. Visualization:

   - Distribution histograms

   - Time-series plots

   - Scatter plots for relationships

   - Heatmaps for correlation

## Setup and Installation

1. Clone this repository:

   ```bash

   git clone https://github.com/yourusername/Data3040_Analysis.git