Fuzzy neural network analysis on gray cast iron with high tensile strength and thermal conductivity
To develop a high performance gray cast iron with high tensile strength and thermal conductivity, multivariable analysis of microstructural effects on properties of gray cast iron was performed. The concerned parameters consisted of graphite content, maximum graphite length, primary dendrite perce...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Foundry Journal Agency
2019-05-01
|
| Series: | China Foundry |
| Subjects: | |
| Online Access: | http://ff.foundryworld.com/uploadfile/2019052848166097.pdf |
| _version_ | 1828260251289255936 |
|---|---|
| author | Gui-quan Wang *Xiang Chen1,2 Yan-xiang Li1,2 |
| author_facet | Gui-quan Wang *Xiang Chen1,2 Yan-xiang Li1,2 |
| author_sort | Gui-quan Wang |
| collection | DOAJ |
| description | To develop a high performance gray cast iron with high tensile strength and thermal conductivity,
multivariable analysis of microstructural effects on properties of gray cast iron was performed. The concerned
parameters consisted of graphite content, maximum graphite length, primary dendrite percentage and
microhardness of the matrix. Under the superposed influence of various parameters, the relationships between
thermal conductivity and structural characteristics become irregular, as well as the effects of graphite length on the
strength. An adaptive neuro-fuzzy inference system was built to link the parameters and properties. A sensitivity
test was then performed to rank the relative impact of parameters. It was found that the dominant parameter
for tensile strength is graphite content, while the most relative parameter for thermal conductivity is maximum
graphite length. The most effective method to simultaneously improve the tensile and thermal conductivity of gray
cast iron is to reduce the carbon equivalent and increase the length of graphite flakes. |
| first_indexed | 2024-04-13T03:20:43Z |
| format | Article |
| id | doaj.art-a9d9d92533f4428cbe26b7b644e76d39 |
| institution | Directory Open Access Journal |
| issn | 1672-6421 1672-6421 |
| language | English |
| last_indexed | 2024-04-13T03:20:43Z |
| publishDate | 2019-05-01 |
| publisher | Foundry Journal Agency |
| record_format | Article |
| series | China Foundry |
| spelling | doaj.art-a9d9d92533f4428cbe26b7b644e76d392022-12-22T03:04:47ZengFoundry Journal AgencyChina Foundry1672-64211672-64212019-05-0116319019710.1007/s41230-019-9012-yFuzzy neural network analysis on gray cast iron with high tensile strength and thermal conductivityGui-quan Wang0*Xiang Chen1,21Yan-xiang Li1,22School of Materials Science and Engineering, Tsinghua University, Beijing 100084, China1. School of Materials Science and Engineering, Tsinghua University, Beijing 100084, China 2. Key Laboratory for Advanced Materials Processing Technology, Ministry of Education, Beijing 100084, China1. School of Materials Science and Engineering, Tsinghua University, Beijing 100084, China 2. Key Laboratory for Advanced Materials Processing Technology, Ministry of Education, Beijing 100084, ChinaTo develop a high performance gray cast iron with high tensile strength and thermal conductivity, multivariable analysis of microstructural effects on properties of gray cast iron was performed. The concerned parameters consisted of graphite content, maximum graphite length, primary dendrite percentage and microhardness of the matrix. Under the superposed influence of various parameters, the relationships between thermal conductivity and structural characteristics become irregular, as well as the effects of graphite length on the strength. An adaptive neuro-fuzzy inference system was built to link the parameters and properties. A sensitivity test was then performed to rank the relative impact of parameters. It was found that the dominant parameter for tensile strength is graphite content, while the most relative parameter for thermal conductivity is maximum graphite length. The most effective method to simultaneously improve the tensile and thermal conductivity of gray cast iron is to reduce the carbon equivalent and increase the length of graphite flakes.http://ff.foundryworld.com/uploadfile/2019052848166097.pdfhigh performance gray cast ironfuzzy neural networktensile strengththermal conductivity |
| spellingShingle | Gui-quan Wang *Xiang Chen1,2 Yan-xiang Li1,2 Fuzzy neural network analysis on gray cast iron with high tensile strength and thermal conductivity China Foundry high performance gray cast iron fuzzy neural network tensile strength thermal conductivity |
| title | Fuzzy neural network analysis on gray cast iron with high tensile strength and thermal conductivity |
| title_full | Fuzzy neural network analysis on gray cast iron with high tensile strength and thermal conductivity |
| title_fullStr | Fuzzy neural network analysis on gray cast iron with high tensile strength and thermal conductivity |
| title_full_unstemmed | Fuzzy neural network analysis on gray cast iron with high tensile strength and thermal conductivity |
| title_short | Fuzzy neural network analysis on gray cast iron with high tensile strength and thermal conductivity |
| title_sort | fuzzy neural network analysis on gray cast iron with high tensile strength and thermal conductivity |
| topic | high performance gray cast iron fuzzy neural network tensile strength thermal conductivity |
| url | http://ff.foundryworld.com/uploadfile/2019052848166097.pdf |
| work_keys_str_mv | AT guiquanwang fuzzyneuralnetworkanalysisongraycastironwithhightensilestrengthandthermalconductivity AT xiangchen12 fuzzyneuralnetworkanalysisongraycastironwithhightensilestrengthandthermalconductivity AT yanxiangli12 fuzzyneuralnetworkanalysisongraycastironwithhightensilestrengthandthermalconductivity |