Detection and segmentation of iron ore green pellets in images using lightweight U-net deep learning network

Duan, Jiaxu; Liu, Xiaoyan; Wu, X.; Mao, Chuangang

doi:10.1007/s00521-019-04045-8

Cited by 45 publications

(17 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In order to deal with the limited amount of ECM data and corresponding CT images, the U-net model architecture was chosen for CT image prediction since it allows a image segmentation with only few training samples [20]. It was widely applied in manufacturing for the automated analysis of visual inspections [10,7,28,17]. The U-net's bottle neck architecture forces the CNN to extract those features out of the input (ECM), thus it can best reconstruct the desired output (CT image).…”

Section: Deep Learningmentioning

confidence: 99%

How To Develop a NDT Method For Weld Inspection in Battery Cell Manufacturing Using Deep Learning

Rohkohl¹,

Kraken²,

Schönemann³

et al. 2021

Preprint

View full text Add to dashboard Cite

Battery cells are central components of electric vehicles. It is important for automotive OEM to utilize high quality battery cells to ensure high performance and safety of their vehicles. This results in the high demand for quality control measures and inspection methods in battery cell manufacturing. Particular relevant features of battery cells are welds for the internal electrical contact. Failures of these welds are often the cause for battery defects in the field and scrap during production. Consequently, there is a strong need to evaluate all welds during manufacturing. However, there is no established method which allows a quick, comprehensive, and cheap inline measurement of the weld quality. This paper presents a new eddy current based method for non-destructive testing of seam welds as well as a machine learning approach for its validation. A deep learning model has been trained on eddy current measurements to predict results from a reference inspection method, in this case computer tomography. The results prove that eddy current measurements can be used to replicate data acquired by computer tomography which means that eddy current measurements could be a suitable candidate for non-destructive 100% inline inspection. More general, this study demonstrates how machine learning may help to get deeper insights into measurement results and to validate new non-destructive testing techniques whose detailed features are yet unknown. The presented evaluation method enables understanding the capabilities and the limits of a new technique and to extract hidden features from the data. Furthermore, the usage of machine learning allows to perform these evaluations on artificial product samples with specific defects and features, which avoids the costly production physical samples.

show abstract

Section: Deep Learningmentioning

confidence: 99%

How To Develop a NDT Method For Weld Inspection in Battery Cell Manufacturing Using Deep Learning

Rohkohl¹,

Kraken²,

Schönemann³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Hamzeloo, et al used a combination of Principal Component Analysis (PCA) and neural networks to estimate particle size distributions on industrial conveyor belts [8]. Support Vector Machines (SVMs) have been successfully used to estimate iron ore green pellet size distributions in a steel plant [10] and a DCNN (U-Net architecture) has been proposed for the same purpose [6].…”

Section: Related Workmentioning

confidence: 99%

Detecting Slag Formations with Deep Convolutional Neural Networks

Koch¹,

Anzén²,

Fischer³

et al. 2021

Preprint

View full text Add to dashboard Cite

We investigate the ability to detect slag formations in images from inside a Grate-Kiln system furnace with two deep convolutional neural networks. The conditions inside the furnace cause occasional obstructions of the camera view. Our approach suggests dealing with this problem by introducing a convLSTM-layer in the deep convolutional neural network. The results show that it is possible to achieve sufficient performance to automate the decision of timely countermeasures in the industrial operational setting. Furthermore, the addition of the convLSTM-layer results in fewer outlying predictions and a lower running variance of the fraction of detected slag in the image time series.

show abstract

“…Singh et al [ 10 ] put forward a way of iron-manganese smelter feed ore classification based on the visual texture of manganese-rich, iron-rich, Al 2 O 3 -rich ore and radial basis neural network. Duan et al [ 11 ] improved the U-net network to realize particle detection and contour recognition from images. Hu et al [ 12 ] used a neural network classification algorithm to achieve early detection of mining vehicle faults.…”

Section: Introductionmentioning

confidence: 99%

A Method of Mining Truck Loading Volume Detection Based on Deep Learning and Image Recognition

Sun

Xiao

et al. 2021

Sensors

View full text Add to dashboard Cite

Detection of the loading volume of mining trucks is an important task in open pit mining. Aiming at the addressing the current problems of low accuracy and high cost of the detection of the loading volume of mining trucks, this paper proposes a mining truck loading volume detection model based on deep learning and image recognition. The training and test data of the model consists of 6000 sets of images taken in a laboratory environment. After image preprocessing, the VGG16 network model is used to pre classify the ore images. The classification results are displayed and the possibility of each category is determined. Then, the loading volume of mining trucks is calculated by using the classification results and the least squares algorithm. By using the labeled image data of five kinds of mining truck loading volume, the arbitrary loading volume detection of mining trucks is realized, which effectively solves the problem of a lack of labeled data types caused by the difficulty in obtaining mine data. Root mean square error (RMSE) and mean absolute error (MAE) are used to evaluate the fitting effect of the model. The experimental results show that the model has high prediction accuracy. The average absolute error is 17.85 cm3. In addition, this paper uses 400 real mining truck images of open-pit mines to verify the model and the average absolute error is 2.53 m3. The experimental results show that the model has good generality and can be applied well to the actual production of open-pit mines.

show abstract

Detection and segmentation of iron ore green pellets in images using lightweight U-net deep learning network

Cited by 45 publications

References 30 publications

How To Develop a NDT Method For Weld Inspection in Battery Cell Manufacturing Using Deep Learning

How To Develop a NDT Method For Weld Inspection in Battery Cell Manufacturing Using Deep Learning

Detecting Slag Formations with Deep Convolutional Neural Networks

A Method of Mining Truck Loading Volume Detection Based on Deep Learning and Image Recognition

Contact Info

Product

Resources

About