Application of inverse analysis with metamodelling for identification of metal flow stress

Sztangret, Łukasz; Szeliga, Danuta; Kusiak, J.; Pietrzyk, M.

doi:10.1179/1879139512y.0000000035

Cited by 17 publications

(13 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods are, however, not as effective as neural networks and support vector machine. They do not achieve so good results mainly due to the discretization of quantitative variables, which demand forced generalization [34,35].…”

Section: Machine Learning Using Knn Cart Chaid and Ann Classifiersmentioning

confidence: 99%

Comparative analysis of the properties of the nodular cast iron with carbides and the austempered ductile iron with use of the machine learning and the support vector machine

Wilk-Kołodziejczyk

Regulski

Gumienny

2016

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The use of modern casting materials allows the achievement of higher product quality indices. The conducted experimental studies of new materials allow obtaining alloys with high performance properties while maintaining low production costs. Studies have shown that in certain areas of applications, the expensive to manufacture austempered ductile iron (ADI) can be replaced with ausferritic ductile iron or bainitic nodular cast iron with carbides, obtained without the heat treatment of castings. The dissemination of experimental results is possible through the use of information technologies and building applications that automatically compare the properties of materials, as the machine learning tools in comparative analysis of the properties of materials, in particular ADI and nodular cast iron with carbides.

show abstract

Section: Machine Learning Using Knn Cart Chaid and Ann Classifiersmentioning

confidence: 99%

Comparative analysis of the properties of the nodular cast iron with carbides and the austempered ductile iron with use of the machine learning and the support vector machine

Wilk-Kołodziejczyk

Regulski

Gumienny

2016

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…Examples of successful applications of artificial neural networks in metamodelling can be found in [28,29]. The approach of applying a metamodel to solve an optimization task in the inverse analysis of plastometric tests was proposed in [26].…”

Section: Metamodelsmentioning

confidence: 99%

“…Identification of the microstructure evolution model is described in [8], phase transformation models in [13], and identification of fracture criteria is described in [27]. Extensive application of the system to the identification of flow-stress models on the basis of uniaxial compression tests is presented in [26]. Validation confirmed good efficiency of the system as far as the identification of material models is considered.…”

Section: Case Studymentioning

confidence: 99%

Hybrid Computer System for the Identification of Metallic Material Models on the Basis of Laboratory Experiments

Rauch¹,

Górecki²,

Pietrzyk³

2016

csci

View full text Add to dashboard Cite

The identification of the proper parameters of material models plays a crucial role in the design of production technologies, especially in the case of modern materials with diversified properties under different boundary conditions. The procedure of identification is usually based on an optimization algorithm that uses sophisticated numerical simulations as a part of the goal function and compares the obtained results with experimental tests. Despite its reliability, such an approach is numerically inefficient. This paper presents the concept of how to replace the most numerically-demanding part of the identification procedure with metamodels, allowing us to maintain uniform result quality. The computer system, which allows us to manage input data, metamodels, and calculations, is proposed and described in detail in this paper. Finally, the proposed approach is validated on the basis of tests performed in the laboratory.

show abstract

“…The principle of operation of neural networks is based on processing a set of input signals independently by each neuron in each layer, where the decisive influence on the output signal have the weights on Fig. 4 The effect of various alloying elements on microstructure [36][37][38][39][40]. The essence of the training of neural network is based on the modification of weights at the inputs to the neurons.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Data mining tools in identifying the components of the microstructure of compacted graphite iron based on the content of alloying elements

Wilk-Kołodziejczyk

Regulski

Gumienny

et al. 2017

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The application of data mining techniques in the design of modern foundry materials allows achieving higher product quality indicators. Designing of a new product always requires thorough knowledge of the effect of alloying elements on the microstructure and hence also on the properties of the examined material. The conducted experimental studies allow for a qualitative assessment of the indicated relationships, but it is the use of intelligent computational techniques that enables building an approximation model of the microstructure and, owing to this, make predictions with high precision. The developed model of prediction supports the technology-related decisions as early as at the stage of casting design and is considered the first step in selecting the type of material used.

show abstract

Application of inverse analysis with metamodelling for identification of metal flow stress

Cited by 17 publications

References 8 publications

Comparative analysis of the properties of the nodular cast iron with carbides and the austempered ductile iron with use of the machine learning and the support vector machine

Comparative analysis of the properties of the nodular cast iron with carbides and the austempered ductile iron with use of the machine learning and the support vector machine

Hybrid Computer System for the Identification of Metallic Material Models on the Basis of Laboratory Experiments

Data mining tools in identifying the components of the microstructure of compacted graphite iron based on the content of alloying elements

Contact Info

Product

Resources

About