Search results

This work introduces an integrated artificial intelligence schemes to enhance accurately predicting the mechanical properties of cellulosic fibers towards boosting their reliability for more sustainable industries.

Fuzzy clustering and stacked method approach were utilized to predict the mechanical performance of the fibers. A reference dataset contains comprehensive information regarding mechanical behavior of the lignocellulosic fibers was compiled from previous experimental investigations on mechanical properties for eight different fiber materials. Data encompass three key factors: Density of 0.9–1.6 g/cm³, Diameter of 5.9–1,000 µm, and Microfibrillar angle of 2–49 deg were utilized. Initially, fuzzy clustering technique was utilized for the data. For validating proposed model, ultimate tensile strength and elongation at break were predicted and then examined against unseen new data that had not been used during model development.

The output results demonstrated remarkably accurate and highly acceptable predictions results. The error analysis for the proposed method was discussed by using statistical criteria. The stacked model proved to be effective in significantly reducing level of uncertainty in predicting the mechanical properties, thereby enhancing model’s reliability and precision. The study demonstrates the robustness and efficacy of the stacked method in accurately estimating mechanical properties of lignocellulosic fibers, making it a valuable tool for material scientists and engineers in various applications.

Cellulosic fibers are essential for biomaterials to enhance developing green sustainable bio-products. However, such fibers have diverse characteristics according to their types, chemical composition and structure causing inconsistent mechanical performance. This work introduces an integrated artificial intelligence schemes to enhance accurately predicting the mechanical properties of cellulosic fibers towards boosting their reliability for more sustainable industries. Fuzzy clustering and stacked method approach were utilized to predict the mechanical performance of the fibers.

This study aims to offer an image-based robust edge detection system that can estimate, identify, locate and label surface flaws during manufacturing for real-time surface issue diagnostics. Of great concern, this methodology extrapolates surface defect information from scanning electron microscopy (SEM) images of composite fracture surfaces. This study predicts changes in topological intensity of composite fracture surfaces and display them as real-time surface intensity values for the first time.

This work, however, introduces a novel robust edge detection method – based image processing – as it is shown to be effective in locating defects, as measured by SEM images of composite fracture surfaces created using additive manufacturing (AM). SEM images, obtained in this study, are related to previous study considering the fracture surfaces of reinforced thermoset composites created via the AM method. These SEM images are of two types: fracture surface of AM of carbon fiber reinforced thermoset composites and fracture surface of AM of syntactic foam reinforced thermoset composites. Initially, MATLAB environment is used for analyzing the SEM images; the technique used, as well as the validity are explained more in the methodology section.

The robust surface defect inspection approach used herein is found to be capable of predicting, identifying, localizing and labeling surface defects during production, allowing for real-time surface issue diagnosis. Further, this work makes it possible to use image processing and analysis of these surfaces to anticipate fluctuations in the topological intensity of the fracture surfaces of composites and represent them as values of surface intensity in real time.

Rising worldwide company rivalry requires a fast, accurate component failure diagnostic method. To create an efficient feature set, a surface defect inspection system must identify product flaws in real time. Thus, this study proposed an image-based robust edge detection system – based on MATLAB environment – that is capable of estimating, identifying, locating and labeling surface faults during production. This paves the way for an extensive set of high-quality tools for dealing with a wide range of problems associated with digital image processing in composites. As a result, the ability to define methodologies and rapidly prototype prospective solutions typically minimizes the cost and time required to implement a successful system during the design phase of an image processing system.

There are several lead-free solder alloys available in the industry. Over the years, the most favorable solder composition of tin-silver-copper (Sn-Ag-Cu [SAC]) has been vastly used and accepted for joining the electronic components. It is strongly believed that the silver (Ag) content has a significant impact on the solder mechanical behavior and thus solder thermal reliability performance. This paper aims to assess the mechanical response, i.e. creep response, of the SAC solder alloys with various Ag contents.

A three-dimensional nonlinear finite element simulation is used to investigate the thermal cyclic behavior of several SAC solder alloys with various silver percentages, including 1%, 2%, 3% and 4%. The mechanical properties of the unleaded interconnects with various Ag amounts are collected from reliable literature resources and used in the analysis accordingly. Furthermore, the solder creep behavior is examined using the two famous creep laws, namely, Garofalo’s and Anand’s models.

The nonlinear computational analysis results showed that the silver content has a great influence on the solder behavior as well as on thermal fatigue life expectancy. Specifically, solders with relatively high Ag content are expected to have lower plastic deformations and strains and thus better fatigue performance due to their higher strengths and failure resistance characteristics. However, such solders would have contrary fatigue performance in drop and shock environments and the low-Ag content solders are presumed to perform significantly better because of their higher ductility.

Generally, this research recommends the use of SAC solder interconnects of high silver contents, e.g. 3% and 4%, for designing electronic assemblies continuously exposed to thermal loadings and solders with relatively low Ag-content, i.e. 1% and 2%, for electronic packages under impact and shock loadings.