Torque marker inspection for threaded connections
Industry
Manufacturing
Description
Checks if a torque seal is broken or straight. Detects a threaded connection (nut or bolt) head with a torque seal. If the nut slips or starts to loosen, the painted line will be broken and classified as DEFECT. If the line is straight - the model returns OK.
Architecture / Pipeline Pipeline:
Pipeline: Input -> Detector -> Tracker -> Selector -> Pre-processing -> Classifier -> Output
Input: still images from GigE camera
Detector: YOLOX Tiny@288x480, patches of unrestricted size containing objects.
Tracker: SORT
Selector: allows to filter out partially visible objects on the frame borders.
Pre-processing: object box is extended to given % in height/width from the center and cropped according to frame borders
Classifier: ResNet34, predicting probability of two classes, resolution 64x64, RGB, aspect ratio preserved
Output: softmax(preds)[:, 1] (Anomaly score)
Classes
Objects: "NUT", Classification: "OK", "DEFECT"
Thresholds
The following thresholds were used for test: XXX, XXX. Thresholds can be defined in a config file.
Code optimization
ONNX, TensorRT
Use case keywords
assembly, bolt, nut, marker, threaded connection, torque seal
Current State
Ready to deploy
Version
1.20, build 15.12.2022
Intended uses
Inspection of torque seals (markers) on threaded connections
How to use
1. Get a fresh GPU 2. Fill it with well-pruned models 3. Stir
Input
Still images
Output
Object name ("Nut"), Object class ("OK", "Defect"), bounding box location and size
Limitations and bias
The module was tested with input image sizes from 640x480 to 1920x1080 on Siemens IPC 520A industrial PC.
Training data
Real-life images: 212; synthetic images: 3,110 (generated in NVIDIA Omniverse with domain, light, optics, textures, size, shape randomization)
Training procedure
6 epochs, trained on DGX2 server (NVIDIA V100 GPU)
Evaluation results
Accuracy, performance, ROC/AUC Precision: 96.2%, Recall: 97.4% with confidence threshold 0.43
Target hardware
GPU: NVIDIA Jetson Xavier NX, CPU: ARM64; RTX4000/amd64 version is under development
Benchmark
Frame rate: 20 FPS on Jetson Xavier NX
Size
3.4 GB
Profile Image
<path to hi-res image at google drive>
Dataset samples
<path to hi-res images at google drive>