This study reports the application of an electronic nose for the identification and classification of red wines aged three different methods. The signals of the different wines detected by the 10 sensors present in the E-nose are significantly different from each other. The response to the signal generates a typical chemical fingerprint of the volatile compounds present in the wines. Principal Component Analysis can be applied for the dimensionality reduction of the collected signal. Since the total contribution rate of the first three principal components is up to 97.27%, different wines can be distinguished from each other by the three principal components. Euclidean distance, correlation analysis, Mahalanobis distance and linear discrimination analysis can offer 100% accuracy for known samples, and the accuracy rate can reach 88.9% for the 18 test samples. In addition, numerous advantages exist compared with sensory analysis in both authentication and quality control of wines.

The surface quality of aluminum ingot is crucial for subsequent products, so it is necessary to adaptively detect different types of defects in milled aluminum ingots surfaces. In order to quickly apply the calculations to a real production line, a novel two-stage detection approach is proposed. Firstly, we proposed a novel mask gradient response-based threshold segmentation (MGRTS) in which the mask gradient response is the gradient map after the strong gradient has been eliminated by the binary mask, so that the various defects can be effectively extracted from the mask gradient response map by iterative threshold segmentation. In the region of interest (ROI) extraction, we combine the MGRTS and the Difference of Gaussian (DoG) to effectively improve the detection rate. In the aspect of the defect classification, we train the inception-v3 network with a data augmentation technology and the focal loss in order to overcome the class imbalance problem and improve the classification accuracy. The comparative study shows that the proposed method is efficient and robust for detecting various defects on an aluminum ingot surface with complex milling grain. In addition, it has been applied to the actual production line of an aluminum ingot milling machine, which satisfies the requirement of accuracy and real time very well.

No abstract

No abstract

No abstract