Using fuzzy sets in the prediction of flexural strength and density of silicon nitride ceramics
- National Aeronautics and Space Administration, Cleveland, OH (United States). Lewis Research Center
- Univ. of Toledo, OH (United States)
In this work the authors use fuzzy sets theory to evaluate and predict flexural strength and density of NASA 6Y silicon nitride ceramic. Processing variables of milling time, sintering time, and sintering nitrogen pressure are used as an input to the fuzzy system. Flexural strength and density are the output parameters of the system. Data from 273 silicon nitride modulus of rupture bars tested at room temperature and 135 bars tested at 1,370 C (2,500 F) are used in this study. Generalized mean operator and Hamming distance are used to construct the fuzzy predictive model. The maximum test error for density does not exceed 3.3 percent, and for flexural strength 7.1 percent. These results demonstrate that fuzzy sets theory can be incorporated into the process of designing materials such as ceramics, especially for assessing more complex relationships between the processing variables and parameters like strength, which are governed by randomness of manufacturing processes.
- OSTI ID:
- 7103941
- Journal Information:
- Materials Evaluation; (United States), Vol. 52:5; ISSN 0025-5327
- Country of Publication:
- United States
- Language:
- English
Similar Records
Radial basis function network learns ceramic processing and predicts related strength and density
Radial basis function network learns ceramic processing and predicts related strength and density
Related Subjects
42 ENGINEERING
NONDESTRUCTIVE TESTING
FUZZY LOGIC
SILICON NITRIDES
DENSITY
FLEXURAL STRENGTH
ERRORS
NEURAL NETWORKS
MATERIALS TESTING
MATHEMATICAL LOGIC
MECHANICAL PROPERTIES
NITRIDES
NITROGEN COMPOUNDS
PHYSICAL PROPERTIES
PNICTIDES
SILICON COMPOUNDS
TESTING
360203* - Ceramics
Cermets
& Refractories- Mechanical Properties
360204 - Ceramics
Cermets
& Refractories- Physical Properties
420500 - Engineering- Materials Testing