NASA Bearing Data Migration
Introducing the NASA Bearing Data Migration
1. Check raw data
The file structure is such that the filename represents a time value, and the internal content consists of data values, similar to the format shown in the image below.

2. Set the Preprocessing Plan
- Get datetime from filename
- Convert to UTC time & Convert to the format: Name, Time, Value.
Get datetime from filename
Set the date from the filename in the directory as the time column.
Convert to UTC time Convert to the format: Name, Time, Value
Load the files in the directory, convert the previously set time column to UTC, and transform the data into the format of Name, Time, and Value, then combine them.
Once the data frame is restructured as shown in the image below, it will be ready for upload to Machbase Neo.

3. Data Upload
Finally, the data can be uploaded to Machbase Neo using the command below.
machbase-neo shell import --input ./datahub-2024-3-bearing.csv.gz --compress gzip --header --method append --timeformat ns bearing
Check the entire code.
datahub/dataset/2024/03.NASA Bearing/conv/convert_nasa.py at main · machbase/datahub
All Industrial IoT DataHub with data visualization and AI source - machbase/datahub
4. Check the results after uploading

Output when executing the following code in the Machbase Neo internal shell.
select * from v$bearing_stat;
※ Subsequent link to the AI training process: NASA Bearing Data