nuluh
c28e79b022
feat(convert): add prefix parameter to create_damage_files for customizable file naming
...
Closes #31
2025-03-16 10:57:13 +07:00
nuluh
b890e556cf
fix(notebook): correct execution counts and update file naming conventions for STFT processing
...
Closes #27
2025-03-11 19:08:56 +07:00
nuluh
fa6e1ff72b
refactor(notebook): seperate process_stft function to individual code cell.
2025-03-08 11:04:37 +07:00
nuluh
a2e339a0a0
feat: Implement STFT verification for individual test runs against aggregated data
2024-12-13 16:30:06 +07:00
nuluh
2decff0cfb
Closes #24
...
feat(stft): Implement STFT processing for vibration data with multiprocessing support to include all the data for training process instead of just using `TEST1` only
2024-12-13 16:29:08 +07:00
nuluh
8b4eedab8a
Closes #26
...
feat: Specify `fs` when calling `scipy.signal.stft`
2024-12-09 00:49:25 +07:00
nuluh
a1fbe8bd93
feat(convert): Update damage scenarios and output file naming conventions
2024-12-08 18:08:59 +07:00
nuluh
832b6c49db
feat(notebook): Implement STFT with Hann windowing. Closes #22
2024-10-21 19:08:46 +07:00
nuluh
9618714d3c
feat: Prepare all damage cases vibration record data to be merged inside two variables "signal_sensor1" and "signal_sensor2". Closes #23
2024-10-19 15:32:05 +07:00
nuluh
2f54e91197
feat: Add absolute value option to time feature extraction
2024-09-03 15:39:44 +07:00
nuluh
758255a24e
feat(notebooks): Implement Time-domain feature extraction with real data from QUGS
2024-09-03 12:52:40 +07:00
nuluh
ff5578652f
fix(script): Fix bugs taking incorrect column by changing columns and sensor_end_map index number to take the loop of enumeration.
2024-09-03 12:08:53 +07:00
nuluh
db2c5d3a4e
feat(script): Update output directory in convert.py
2024-09-03 11:50:44 +07:00
nuluh
ea978de872
-
2024-09-03 11:43:46 +07:00
nuluh
465d257850
feat(script): Add zero-padding to converted CSV filenames for standardize processing pipeline
2024-09-03 11:38:49 +07:00
nuluh
d12eea0acf
feat(data-processing): Implement CSV data transformation for SVM analysis
...
Introduce a Python script for transforming QUGS 2D grid structure data into a simplified 1D beam format suitable for SVM-based damage detection. The script efficiently slices original CSV files into smaller, manageable sets, correlating specific damage scenarios with their corresponding sensor data. This change addresses the challenge of retaining critical damage localization information during the data conversion process, ensuring high-quality, relevant data for 1D analysis.
Closes #20
2024-09-03 11:33:23 +07:00
nuluh
0306f28a68
docs(notebooks): add extract_numbers docstring
2024-09-03 11:09:47 +07:00
