A Machine Learning Algorithm to Aid the Development of Repair Materials for Ancient Ceramics via Additive Manufacturing

In ancient historical ceramics, for various reasons, some problems such as dirt and damage inevitably occur, and necessary repair work must be carried out. Throughout ceramics restoration work, the selection and use of materials are very important. Thus, it is necessary to explore the use of modern intelligent algorithms to assist the selection and application of restoration materials during the whole restoration process, in order to improve the effectiveness of ancient ceramics restoration. In this study, convolutional neural network (CNNs) technology and a machine learning (ML) algorithm were applied to images of ceramics for the defect identification and repair of ancient ceramics, aided by additive manufacturing (AM). The simulation results show that the recall of this algorithm for AM ancient ceramics image recognition was improved by 19.68%. In order to enhance the restoration effects on ancient ceramics, it is necessary to enhance their restoration by expanding the use of digital technology, with the intent to maintain the advantages of traditional handicrafts. Therefore, we should review experiences in the restoration of ancient ceramics, introduce digital technology according to specific needs, and enhance the advanced nature of restoration work.