High accuracy keyway angle identification using VGG16-based learning method

Sarker, Soma; Tushar, Sree Nirmillo Biswash; Chen, Heping

doi:10.1016/j.jmapro.2023.04.019

Cited by 13 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, in terms of feature capture, it can be analyzed that the processing methods of ResNet50 and SepViT will have an important impact on the results, as shown in Figure 13a,b. In addition, we compared the integration model SV-ERnet proposed in this paper with other deep learning methods such as ResNet101 [32], VGG16 [33], MobileNetV2 [34], EfficientV1 [35], and AlexNet. Table 3 shows the recognition results of the different models on the datasets.…”

Section: Visual Interpretation Of Intelligent Classification Results ...mentioning

confidence: 99%

“…Specifically, the depth separable Vision Transformer (SepViT) we use improves the recognition accuracy by 1.8-6.8% compared with some conventional networks. In addition, we compared the integration model SV-ERnet proposed in this paper with other deep learning methods such as ResNet101 [32], VGG16 [33], MobileNetV2 [34], Effi-cientV1 [35], and AlexNet. Table 3 shows the recognition results of the different models on the datasets.…”

Section: Visual Interpretation Of Intelligent Classification Results ...mentioning

confidence: 99%

See 1 more Smart Citation

Research on an Intelligent Classification Algorithm of Ferrography Wear Particles Based on Integrated ResNet50 and SepViT

He,

Wei,

Gao

2023

Lubricants

View full text Add to dashboard Cite

The wear particle classification algorithm proposed is based on an integrated ResNet50 and Vision Transformer, aiming to address the problems of a complex background, overlapping and similar characteristics of wear particles, low classification accuracy, and the difficult identification of small target wear particles in the region. Firstly, an ESRGAN algorithm is used to improve image resolution, and then the Separable Vision Transformer (SepViT) is introduced to replace ViT. The ResNet50-SepViT model (SV-ERnet) is integrated by combining the ResNet50 network with SepViT through weighted soft voting, enabling the intelligent identification of wear particles through transfer learning. Finally, in order to reveal the action mechanism of SepViT, the different abrasive characteristics extracted by the SepViT model are visually explained using the Grad-CAM visualization method. The experimental results show that the proposed integrated SV-ERnet has a high recognition rate and robustness, with an accuracy of 94.1% on the test set. This accuracy is 1.8%, 6.5%, 4.7%, 4.4%, and 6.8% higher than that of ResNet101, VGG16, MobileNetV2, AlexNet, and EfficientV1, respectively; furthermore, it was found that the optimal weighting factors are 0.5 and 0.5.

show abstract

Section: Visual Interpretation Of Intelligent Classification Results ...mentioning

confidence: 99%

Section: Visual Interpretation Of Intelligent Classification Results ...mentioning

confidence: 99%

Research on an Intelligent Classification Algorithm of Ferrography Wear Particles Based on Integrated ResNet50 and SepViT

He,

Wei,

Gao

2023

Lubricants

View full text Add to dashboard Cite

show abstract

“…Therefore, the VGG16 network has a large network width. The increase in network width enables the network layers to learn richer image features, such as color and texture [27,28].…”

Section: Based On Vgg16-unet Semantic Segmentation Modelmentioning

confidence: 99%

Accurate tool wear and breakage monitoring method for milling process based on vision and laser sensor fusion

Li,

Xu,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Accurate online acquisition of tool wear degradation indicators is an important prerequisite for tool wear monitoring and tool remaining life prediction. The tool degradation process is usually accompanied by the flank face of cutting tool wear and blade breakage, however, the existing degradation indicators only consider the flank face wear value, but not the tool breakage value, resulting in the lack of accuracy of degradation indicators. To this end, an online identification method of tool degradation indicators based on the fusion of image sensors and laser displacement sensors is proposed, which adopts the VGG16-UNet network to identify the wear value in the image and obtains the tool breakage value based on the time series data of the laser displacement sensor. Finally, the tool wear and breakage degradation label containing wear and breakage values is established. Compared to manual measurements, the absolute average error is within 15 microns for cutter face damage values and within 3 microns for cutter face wear values.

show abstract

“…Machine learning technology has also been widely used in fire image classification, where researchers have utilized machine learning algorithms such as support vector machines (SVM) and random forests to classify and identify fire images [8]. These algorithms can automatically learn the features of flame images and classify and recognize them with high accuracy [9,10].…”

Section: Introductionmentioning

confidence: 99%

Fire image detection and classification analysis based on VGG16 image processing model

Hou

2024

ACE

View full text Add to dashboard Cite

Fire image classification technology refers to the classification and recognition of fire images through computer vision technology in order to take timely countermeasures. With the development of computer vision technology, fire image classification technology has been widely studied and applied. Deep learning techniques have achieved great success in the field of image classification, with researchers classifying and identifying fire images by using deep learning models such as convolutional neural networks. This paper introduces the research background and application of fire image classification technology, and the experimental results of detection and classification analysis of fire image based on vgg16 image processing model. The model can classify and identify fire images well and achieve good prediction effect. The accuracy of training set and test set is stable at 99%, the accuracy and accuracy of the model reach 98%, and the recall rate and F1 score reach 99%. The application of fire image classification technology is of great significance. By using computer vision technology to classify and identify fire images, it can improve the accuracy and efficiency of fire monitoring and early warning system, timely detect and control fire, and reduce the loss caused by fire. At the same time, the continuous development of deep learning technology also provides a broader space for the research and application of fire image classification technology.

show abstract

High accuracy keyway angle identification using VGG16-based learning method

Cited by 13 publications

References 18 publications

Research on an Intelligent Classification Algorithm of Ferrography Wear Particles Based on Integrated ResNet50 and SepViT

Research on an Intelligent Classification Algorithm of Ferrography Wear Particles Based on Integrated ResNet50 and SepViT

Accurate tool wear and breakage monitoring method for milling process based on vision and laser sensor fusion

Fire image detection and classification analysis based on VGG16 image processing model

Contact Info

Product

Resources

About