Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

https://cyberleninka.org/article/n/403409.pdf

A review of numerical analysis of friction stir welding

Friction stir welding/processing of metals and alloys: A comprehensive review on microstructural evolution

Stereolithography is a solid freeform technique (SFF) that was introduced in the late 1980s Although many other techniques have been developed since then, stereolithography remains one of the most powerful and versatile of all SFF techniques It has the highest fabrication accuracy and an increasing number of materials that can be processed is becoming available In this paper we discuss the characteristic features of the stereolithography technique and compare it to other SFF techniques The biomedical applications of stereolithography are reviewed, as well as the biodegradable resin materials that have been developed for use with stereolithography Finally, an overview of the application of stereolithography in preparing porous structures for tissue engineering is given

A review on stereolithography and its applications in biomedical engineering

Friction stir welding (FSW), a highly efficient solid-state joining technique, has been termed as “green” technology due to its energy efficiency and environment friendliness. It is an enabling technology for joining metallic materials, in particular lightweight high-strength aluminum and magnesium alloys which were classified as unweldable by traditional fusion welding. It is thus considered to be the most significant development in the area of material joining over the past two decades. Friction stir processing (FSP) was later developed based on the basic principles of FSW. FSP has been proven to be an effective and versatile metal-working technique for modifying and fabricating metallic materials. FSW/FSP of aluminum alloys has prompted considerable scientific and technological interest since it has a potential for revolutionizing the manufacturing process in the aerospace, defense, marine, automotive, and railway industries. To promote widespread applications of FSW/FSP technology and ensure t...

Recent Advances in Friction Stir Welding/Processing of Aluminum Alloys: Microstructural Evolution and Mechanical Properties

Abstract Background The contour method for residual stress measurement has seen significant development, but an experimental reproducibility study utilizing physical samples has not been published. Objective A double-blind reproducibly study is reported, having scope beginning with EDM cutting and ending with residual stress calculation. Methods A reinforced I-beam sample geometry is identified for its unique residual stress profile when extracted from residual stress bearing quenched aluminum bar (7050-T74). Contour measurements are prescribed on a midplane of symmetry with dimensions 24.0 mm by 50.0 mm. Fourteen identically prepared samples are fabricated from a single long bar with well characterized and uniform residual stress. Five samples throughout the bar are identified for planning measurements to validate sample uniformity and overall suitability of the residual stress field. The planning measurements employ a range of techniques: contour method, neutron diffraction, and hole-drilling. Eight samples are distributed to an international group of participants to execute their standard measurement practice. A double-blind process is followed to provide anonymity. Results Results are provided by eight participants: six being self-similar and two being quite different, the latter set aside as outliers. An average residual stress field is established from non-outlying results and the spatial distribution of reproducibility standard deviation is determined. The average stress field ranges from -60 to 70 MPa and the reproducibility standard deviation averages 8.1 MPa on the measurement plane. The average reproducibility standard deviation is about 3 × larger for points within 1.0 mm of plane boundaries (17.6 MPa) than for the remaining points (6.1 MPa). Conclusions Reproducibility standard deviation (among different labs) for contour method residual stress measurement is found to be very similar to repeatability standard deviation (in a single lab) reported in prior work. The reproducibility observed here, for the entire measurement process, is also similar to that found in a prior reproducibility study limited to contour method data analysis. 

/pdf/interlaboratory-reproducibility-of-contour-method-data-in-a-3pjqu81i.pdf

Interlaboratory Reproducibility of Contour Method Data in a High Strength Aluminum Alloy

Multiple Crack Propagation in Friction Stir Welded Aluminium Joints

In this work a numerical model is proposed to simulate Friction Stir Welding (FSW) process in AA2024-T3 plates. This model included a softening model that account for the temperature history and the hardness distribution on a welded plate can thus be predicted. The validation of the model was performed using experimental measurements of the hardness in the plate cross-section. There is an acceptable prediction of the material softening in the Heat Affected Zone (HAZ) using the adopted model.

Numerical simulation of friction stir welding (FSW): Prediction of the heat affect zone using a softening model

The present work focuses on the pultrusion of pre-impregnated glass-reinforced polypropylene tapes. An appositely designed laboratory-scale pultrusion line, consisting of a heating/forming die and a cooling die, was used. The temperature of the advancing materials and the pulling force resistance were measured by using thermocouples embedded in the pre-preg tapes and a load cell. From the analysis of the experimental outcomes, we gained insight into the nature of the material–machinery interaction and the transitions of the polypropylene matrix. The cross-section of the pultruded part was analyzed by microscope observation to evaluate the distribution of the reinforcement inside the profile and the presence of internal defects. Three-point bending and tensile testing were conducted to assess the mechanical properties of the thermoplastic composite. The pultruded product showed good quality, with an average fiber volume fraction of 23% and a limited presence of internal defects. A non-homogenous distribution of fibers in the cross-section of the profile was observed, probably due to the low number of tapes used in the present experimentation and their limited compaction. A tensile modulus and a flexural modulus of 21.5 GPa and 15.0 GPa, respectively, were measured.

/pdf/thermoplastic-pultrusion-process-of-polypropylene-glass-3e06671j.pdf

Thermoplastic Pultrusion Process of Polypropylene/Glass Tapes

Cold Spray is an innovative technology to create coatings through the impact of metallic particles on substrates. Its application to composites’ surfaces is recently attracting the attention of the scientific community thanks to the possibility to functionalize and improve their thermal and wear properties. Within this context, the generation of the first metal-to-composite layer is fundamental. This work presented an experimental investigation of a composite panel, reinforced with glass fibers and coated with aluminum particles. The coating investigation was carried out through active pulsed thermography, analyzing the thermal response of single and double hatches. The thermal outputs were compared with a standard microscopic analysis, with a critical discussion supporting the identification of factors that influence the thermal response to the pulse: (1) layer’s thickness; (2) cold spray coverage; (3) layer compactness; (4) particle-substrate adhesion; (5) particle’s oxidation; and (6) surface roughness.

Pierpaolo Carlone

Papers

Interlaboratory Reproducibility of Contour Method Data in a High Strength Aluminum Alloy

Multiple Crack Propagation in Friction Stir Welded Aluminium Joints

Numerical simulation of friction stir welding (FSW): Prediction of the heat affect zone using a softening model

Thermoplastic Pultrusion Process of Polypropylene/Glass Tapes

Thermographic Analysis of Composite Metallization through Cold Spray