Automatic Vickers Hardness Measurement With Neural Network Segmentation

• Published in: IEEE transactions on instrumentation and measurement Vol. 72; pp. 1 - 11
• Main Authors: Cai, Chenglin, Li, Zexian, Yin, Feng, Wang, Zhong, Chen, Yangzhuo
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Area measurement; Automatic measurement; convolutional neural network; Diamond pyramid hardness tests; Hardness measurement; hardness testing; image segmentation; Indentation; Length measurement; Location awareness; Manuals; Measurement errors; Measurement uncertainty; Neural networks; Segmentation; Vickers hardness
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2022.3227986

The Vickers hardness test is widely used for metal materials. The hardness given by the test is inversely proportional to the ratio of the test force to the indentation area. Since it is inconvenient to measure the area of the indentation manually, it is usually approximated by measuring its diagonal length. On this basis, we propose a new indentation segmentation network based on existing work. Taking advantage of its high segmentation accuracy, we use the indentation area to calculate the Vickers hardness directly, rather than relying on the measurement of the diagonal length. Experimental results show that the indentation areas obtained by this method are well below the International Standardization Organization (ISO) standard and very close to those from manual measurements. In some cases, this method can be a good alternative to manual measurements.