Programmable Direct-Patterning for High-Density Fiber Bragg Grating Sensor Arrays

Programmable direct-patterning assembly enables the high-density integration of brittle fiber Bragg grating (FBG) sensors onto complex, non-planar surfaces. The dataset includes raw and processed strain signals, paired with deep learning architectures like 3D-CRNN, BiLSTM, and WGAN-GP for spatiotemporal signal decoding. This supports research in structural-sensing integration and intelligent systems for applications such as speech and gesture recognition.

Use Cases

• Developing programmable manufacturing methods for conformal sensor integration based on the described 5-axis direct-patterning assembly.
• Training spatiotemporal signal decoding models based on the included 3D-CRNN, BiLSTM, and WGAN-GP architectures with dual-attention mechanisms.
• Analyzing strain signal patterns for structural health monitoring based on the provided raw and processed strain data.
• Benchmarking sensor array performance on non-planar surfaces based on the multi-scale mechanical modeling approach.

Strengths

• Includes both raw and processed strain signals for full reproducibility.
• Provides code for multiple advanced deep learning architectures (3D-CRNN, BiLSTM, WGAN-GP).
• Dataset is openly licensed under CC-BY-4.0.
• Cross-platform presence on figshare indicates established sharing and importance.

Limitations

• Column names and a precise row count are not provided, limiting immediate understanding of data structure.
• The dataset size is large (376329698 bytes), which may require significant storage and bandwidth.
• The primary description is repeated across entries, suggesting potential metadata duplication rather than expansion.

Provenance

Source

Yin Tao, supporting the manuscript 'Programmable direct-patterning assembly enables high-density and surface-conformal integration of fiber Bragg grating sensor arrays'.

Collection Method

Data collected via a custom-built 5-axis direct-patterning assembly and multi-scale mechanical modeling.

Time Range

null

Freshness

Last updated on 2026-04-12.

Geography

null