David Schwarz / Ball Bearing Fault Detection Public
Target: TI LAUNCHXL-CC1352P (Cortex-M4F 48MHz) Clone this project

Test data

Set confidence thresholds
Model variants
Test 'Unoptimized (float32)' model Test 'Quantized (int8)' model
Set the 'expected outcome' for each sample to the desired outcome to automatically score the impulse.
Sample name Expected outcome Length Accuracy Result
class2.Parameterset1.test.json.2g1i3jij ball-bearing-fault 1s 100% 10 ball-bearing-fault
Show classification Show in data acquisition
class2.Parameterset2.test.json.2g1i3je4 ball-bearing-fault 1s 100% 10 ball-bearing-fault
Show classification Show in data acquisition
class2.Parameterset3.test.json.2g1i3j95 ball-bearing-fault 1s 100% 10 ball-bearing-fault
Show classification Show in data acquisition
class2.Parameterset4.test.json.2g1i3iqt ball-bearing-fault 1s 100% 10 ball-bearing-fault
Show classification Show in data acquisition
class2.Parameterset5.test.json.2g1i3il5 ball-bearing-fault 1s 100% 10 ball-bearing-fault
Show classification Show in data acquisition
class2.Parameterset6.test.json.2g1i3iee ball-bearing-fault 1s 100% 10 ball-bearing-fault
Show classification Show in data acquisition
class2.Parameterset7.test.json.2g1i3ia2 ball-bearing-fault 1s 100% 10 ball-bearing-fault
Show classification Show in data acquisition
class2.Parameterset8.test.json.2g1i3i5t ball-bearing-fault 401ms 100% 4 ball-bearing-fault
Show classification Show in data acquisition
class1.Parameterset2.test.json.2g1i3hme normal 1s 100% 10 normal
Show classification Show in data acquisition
class1.Parameterset3.test.json.2g1i3hfv normal 1s 100% 10 normal
Show classification Show in data acquisition
class1.Parameterset4.test.json.2g1i3h4a normal 1s 100% 10 normal
Show classification Show in data acquisition
class1.Parameterset6.test.json.2g1i3gl1 normal 1s 100% 10 normal
Show classification Show in data acquisition
class1.Parameterset5.test.json.2g1i3g2p normal 1s 40% 6 ball-bearing-fault, 4 normal
Show classification Show in data acquisition
class1.Parameterset7.test.json.2g1i3f99 normal 1s 100% 10 normal
Show classification Show in data acquisition
class1.Parameterset1.test.json.2g1i3f5k normal 1s 100% 10 normal
Show classification Show in data acquisition
class1.Parameterset8.test.json.2g1i3f5j normal 401ms 100% 4 normal
Show classification Show in data acquisition

Model testing output

Results

Model version:
Accuracy
95.95%

Confusion matrix

Loading...

Feature explorer

Loading...
Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy