Overview / Usage

Project Overview:

This project focuses on analyzing and predicting the Excitation Current of a Synchronous Motor using Machine Learning techniques. The goal is to optimize motor performance, reduce energy consumption, and improve overall efficiency.

Problems Being Solved:

1. Inefficient Motor Performance: Synchronous motors can experience reduced performance due to incorrect excitation current settings.

2. Energy Waste: Inefficient motor performance leads to increased energy consumption and waste.

3. Difficulty in Predicting Excitation Current: The relationship between load current, power factor, and excitation current is complex, making it challenging to predict the optimal excitation current.

Usage in Production:

This project's outcome can be used in various industrial applications, including:

1. Motor Control Systems: The predicted excitation current values can be used to optimize motor performance in real-time.

2. Energy Management Systems: The energy consumption patterns can be analyzed to identify opportunities for energy savings.

3. Condition Monitoring: The project's findings can be used to develop condition monitoring systems that detect anomalies in motor performance.

Methodology / Approach

Methodology:

This project employs a data-driven approach to predict the Excitation Current of a Synchronous Motor. The methodology involves

Data Collection:

1. Data Gathering: Collecting historical data on Load Current, Power Factor, and Excitation Current from motor control systems or sensors.

Data Preprocessing:

1. Data Cleaning: Handling missing values, outliers, and noisy data using techniques like imputation, normalization, and feature scaling.

2. Feature Engineering: Extracting relevant features from the data, such as mean, standard deviation, and correlation coefficients.

Model Development:

1. Machine Learning Algorithms: Implementing and comparing various machine learning algorithms, including Linear Regression, Decision Trees, Random Forest, and Support Vector Machines.

2. Hyperparameter Tuning: Optimizing model hyperparameters using techniques like grid search, random search, and Bayesian optimization.

Model Evaluation:

1. Metrics: Evaluating model performance using metrics like Mean Absolute Error (MAE), Mean Squared Error (MSE), and Coefficient of Determination (R-squared).

2. Cross-Validation: Validating model performance using techniques like k-fold cross-validation and walk-forward optimization.

Technologies Used

Python: Programming language for data analysis, machine learning, and visualization.

1. Scikit-learn: Machine learning library for data preprocessing, feature selection, and model development.

2. Pandas: Library for data manipulation, analysis, and visualization.

3. Matplotlib: Library for data visualization and presentation.

4. NumPy: Library for numerical computing and data analysis.

5. SciPy: Library for scientific computing and signal processing.

6. Keras: Deep learning library for building neural networks.

7. TensorFlow: Open-source machine learning framework for building and training neural networks.

8. Intel Core i7: High-performance processor for data processing and analysis.

9. Jupyter Notebook: Interactive environment for data analysis, visualization, and prototyping.

Documents and Presentations

Repository

https://www.kaggle.com/code/zengamer/ac-machines-excitation-currentofsynchronousmotor