A design of fuzzy inference systems to predict tensile properties of as-cast alloy

Tan, He; Tarasov, Vladimir; Jarfors, Anders E. W.; Seifeddine, Salem

doi:10.1007/s00170-020-06502-4

Cited by 4 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tan et al [135] presented a Mamdani fuzzy inference system (FIS) to predict tensile properties of molten alloys. The approach used combined with genetic algorithm showed high precision.…”

Section: Supriadi and Manabementioning

confidence: 99%

Hybrid manufacturing process planning with predictive approach: a comprehensive literature review

Velázquez

Simon²,

Helleno³

2022

Preprint

View full text Add to dashboard Cite

The hybrid manufacturing has attracted industrial community interest due to its ability to produce functional parts with varied geometries, using different types of materials in the most varied applications. As with most manufacturing processes, before executing the hybrid process for the manufacture of a certain geometry, it is important to make a proper process planning that allows having an integral and proactive view of the operation. This work aims to synthesize through a systematic literature review (SLR) the state of the art on hybrid manufacturing process planning (HMPP) models with predictive approach. Three SLRs were developed to extract the articles of interest (2012-2022) from Science Direct, Springer Link, and Web of Science databases. PRISMA method was used to gather the papers and oriented the qualitative and quantitative analysis. Snowballing technique was used to gather articles of interest out of the period defined. Literature review showed that there is still no consensus between existing HMPP models, regarding all the activities necessary to ensure proper operation. In addition, the developed models have a limitation regarding the inclusion of a process simulation step. The simulation step on the existing models, does not allow to proactively check whether the experimental process conditions are adequate to ensure the manufacture of the modeled geometry before running the hybrid manufacturing process. An efficient simulation step would ensure a predictive approach to operation performance and would imply the reduction of geometric deviations without the need for excessive experimentation, reducing material consumption, manufacturing time, and resulting in a better deposition strategy. Using computational and statistical methods as support for decision-making in the process will allow the processing and analysis of data to assertively direct the structuring of a robust model for HMPP with predictive approach. A differentiated, more complete, and comprehensive process planning model is a relevant study opportunity for future research. This paper contributes to the theory development since it identifies and analyzes the existing HMPP models, highlights important gaps on the subject, and proposes insights for future development.

show abstract

“…Tan et al [135] presented a Mamdani fuzzy inference system (FIS) to predict tensile properties of molten alloys. The approach used combined with genetic algorithm showed high precision.…”

Section: Supriadi and Manabementioning

confidence: 99%

Hybrid manufacturing process planning with predictive approach: a comprehensive literature review

Velázquez

Simon²,

Helleno³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Qualitative-based methods are used through expert knowledge and observation data. Tan et al proposed a model of Mamdani-type fuzzy inference system to predict the tensile properties of cast alloys, which has high accuracy and good stability [8]. However, now that expert knowledge can be uncertain, the model's accuracy will be affected.…”

Section: Introductionmentioning

confidence: 99%

A New Prediction System Based on Self-Growth Belief Rule Base with Interpretability Constraints

Li¹,

Han²,

Wang³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Prediction systems are an important aspect of intelligent decisions. In engineering practice, the complex system structure and the external environment cause many uncertain factors in the model, which influence the modeling accuracy of the model. The belief rule base (BRB) can implement nonlinear modeling and express a variety of uncertain information, including fuzziness, ignorance, randomness, etc. However, the BRB system also has two main problems: Firstly, modeling methods based on expert knowledge make it difficult to guarantee the model's accuracy. Secondly, interpretability is not considered in the optimization process of current research, resulting in the destruction of the interpretability of BRB. To balance the accuracy and interpretability of the model, a self-growth belief rule base with interpretability constraints (SBRB-I) is proposed. The reasoning process of the SBRB-I model is based on the evidence reasoning (ER) approach. Moreover, the self-growth learning strategy ensures effective cooperation between the datadriven model and the expert system. A case study showed that the accuracy and interpretability of the model could be guaranteed. The SBRB-I model has good application prospects in prediction systems.

show abstract

“…A collection of studies on additive manufacturing and material properties are discussed in detail on the wear performance of ABS parts, weaving infill pattern inspection of oil distribution in different patterns, microstructures, and mechanical properties of various additive materials. These studies contribute to the advancement in the practices of additive manufacturing in different directions and processes. − …”

Section: Introductionmentioning

confidence: 99%

Effect of Infill Patterns with Machine Learning Techniques on the Tensile Properties of Polylactic Acid-Based Ceramic Materials with Fused Filament Fabrication

et al. 2023

View full text Add to dashboard Cite

The field of additive manufacturing is quickly evolving from prototyping to manufacturing. Researchers are looking for the best parameters to boost mechanical strength as the demand for three-dimensional (3D) printers grows. The goal of this research is to find the best infill pattern settings for a polylactic acid (PLA)-based ceramic material with a universal testing machine; the impact of significant printing considerations was investigated. An X-ray diffractometer and energy-dispersive X-ray spectroscopy with an attachment of scanning electron microscopy were used to investigate the crystalline structure and microstructure of PLA-based ceramic materials. Tensile testing of PLAbased ceramics using a dog bone specimen was printed with various patterns, as per ASTM D638-10. The cross pattern had a high strength of 16.944 MPa, while the tri-hexagon had a peak intensity of 16.108 MPa. Cross3D and cubic subdivisions have values of 4.802 and 4.803 MPa, respectively. Incorporating the machine learning concepts in this context is to predict the optimal infill pattern for robust strength and other mechanical properties of the PLA-based ceramic model. It helps to rally the precision and efficacy of the procedure by automating the job that would entail substantial physical effort. Implementing the machine learning technique to this work produced the output as cross and tri-hexagon are the efficient ones out of the 13 patterns compared.

show abstract

A design of fuzzy inference systems to predict tensile properties of as-cast alloy

Cited by 4 publications

References 23 publications

Hybrid manufacturing process planning with predictive approach: a comprehensive literature review

Hybrid manufacturing process planning with predictive approach: a comprehensive literature review

A New Prediction System Based on Self-Growth Belief Rule Base with Interpretability Constraints

Effect of Infill Patterns with Machine Learning Techniques on the Tensile Properties of Polylactic Acid-Based Ceramic Materials with Fused Filament Fabrication

Contact Info

Product

Resources

About