Dataset for Antenna Array Pattern with Sidelobe Level Control Using Deep Learning

This dataset contains simulation results (output data) from various amplitude and phase configurations applied to an 8-element linear antenna array. Each row represents a unique combination of amplitude and phase settings, followed by the resulting array factor (AF) calculated across angles from 0° to 180°.

Structure of the CSV File

Total Columns: 197

Columns 1–8: Amplitudes (A₁, A₂, …, A₈)

• Represent the amplitude weights applied to each antenna element.

• Amplitude values range from 0 to 1 in increments of 0.02.

• Higher amplitude values indicate greater contribution from the corresponding antenna element to the total radiated signal.

• An amplitude of 0 means the antenna element is effectively turned "off".

Columns 9–16: Phases (ϕ₁, ϕ₂, …, ϕ₈)

• Represent the phase shifts applied to each antenna element, expressed in radians.

• Phase values range from −90° to +90° in increments of 2°, converted to radians.

• Phases determine how each antenna element’s signal is shifted, effectively steering the beam direction.

Columns 17–197: Array Factor (AF)

• Each row contains 181 values representing the computed array factor across angles 0° to 180° (at 1° increments).

• The AF describes the spatial radiation pattern resulting from the combined amplitude and phase settings of the 8-element array.

• These values can be further processed (e.g., converted to magnitude or dB scale) for detailed analysis.

How to Use the Data

To use this dataset effectively and efficiently, follow these three basic steps.

1. Load: Load the CSV file into your preferred analytical environment (e.g., Python, MATLAB, R).

2. Extract: Columns 1–8 for amplitudes  |  Columns 9–16 for phases  |  Columns 17–197 for array factor / radiation patterns.

3. Analyze:

   • Evaluate how different amplitude and phase combinations affect the antenna array’s radiation pattern.

   • Perform conversions as needed (e.g., magnitude or decibel scale).

   • Utilize the data as input or output for machine learning and optimization tasks, such as predicting radiation patterns or optimizing array configurations.

Potential Applications

• Antenna Array Design:

  • Explore the influence of amplitude tapering and phase shifts on beamforming and radiation patterns.

• Machine Learning and Optimization:

  • Serve as a comprehensive training dataset for algorithms designed to optimize antenna element settings to meet desired radiation characteristics.

Citation

If you find this dataset useful for your research or projects, please cite it appropriately:

https://doi.org/10.5281/zenodo.14533762