![]() ![]() ![]() The PSPP design chart represents end-to-end knowledge in the form of relationships among factors, as shown in Figure 1. The properties in the third stage give the total performance of the new material. The third stage is ‘property’ that the structure gives. The second stage is ‘structure’ of the material that the processes build. The first stage is ‘process’ that can be controlled to develop a new material. The processing-structure-property-performance (PSPP) reciprocity explains effect of processes on properties in three stages. We believe it is beneficial to provide the end-to-end knowledge for accelerating material developments. Such knowledge is technical and might not be well formalized, so they spend long time to obtain such knowledge. In practice, researchers find these processes relying on their end-to-end knowledge including effects of processes to the properties. On the contrary, such efficient development is challenging because 1) The relation between a process and a property is unclear and indirect and 2) The search space (the set of possible processes) is too large to look up. Minimizing the number of trials is critical for an efficient development. In this approach, a trial is a time-consuming experiment. In most practical cases, the desired process cannot be envisioned, and instead it is constructed by trial and error. Material design is a process of developing new materials with specific properties. Footnote 1 The impressive performance of machine learning appears promising for knowledge extraction in material design as well. For example, relationships among scientific knowledge are extracted from scientific literature in ScienceIE, and a knowledge base is extracted from Web text in TAC. Knowledge extraction is to find desired knowledge from text. Machine learning and data science for knowledge extraction are studied in a wide variety of field. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |