This project uses machine learning to focus on Predictive Maintenance for industrial equipment. The goal is to predict potential machine failures before they occur, enabling proactive maintenance and reducing downtime.
The dataset contains sensor data from industrial machines, including features such as:
- Air Temperature (K)
- Process Temperature (K)
- Rotational Speed (rpm)
- Torque (Nm)
- Tool Wear (min)
- Machine Failure Indicators (TWF, HDF, PWF, OSF, RNF)
The goal is to build a machine-learning model that predicts whether a machine will fail based on sensor readings. This helps industries reduce downtime, optimize maintenance costs, and improve operational efficiency.
- Programming Language: Python 🐍
- Libraries: Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn
- Modeling: Machine Learning (Logistic Regression, Random Forest, XGBoost)
- Evaluation Metrics: Accuracy, Precision, Recall, F1-score, Confusion Matrix
-
Exploratory Data Analysis (EDA)
- Data visualization & insights
- Handling missing values & outliers
-
Feature Engineering
- Data transformation & scaling
- Feature selection
-
Model Development
- Training multiple machine learning models
- Hyperparameter tuning
-
Model Evaluation
- Performance comparison
- Confusion matrix & classification reports
The best-performing model achieved:
- Accuracy: 97.855%
- Precision: 97.78%
- Recall: 97.85%%
- F1-score: 97.81%
- Clone the repository:
git clone https://github.com/BatthulaVinay/Predictive-Maintenance.git
- Navigate to the project folder:
cd Predictive-Maintenance - Install required dependencies:
pip install -r requirements.txt
- Run the Jupyter Notebook:
Jupiter notebook
- Implement Deep Learning models (ANN, LSTM)
- Enhance feature selection & engineering
- Deploy the model as an API for real-time predictions
- LinkedIn: linkedin.com/in/batthula-vinay
- GitHub: github.com/BatthulaVinay
⭐ Star this repository if you found it useful!