Engineering Innovations
Vol. 12
Vol. 12
Engineering Innovations
Vol. 11
Vol. 11
Engineering Innovations
Vol. 10
Vol. 10
Engineering Innovations
Vol. 9
Vol. 9
Engineering Innovations
Vol. 8
Vol. 8
Engineering Innovations
Vol. 7
Vol. 7
Engineering Innovations
Vol. 6
Vol. 6
Engineering Innovations
Vol. 5
Vol. 5
Engineering Innovations
Vol. 4
Vol. 4
Engineering Innovations
Vol. 3
Vol. 3
Engineering Innovations
Vol. 2
Vol. 2
Engineering Innovations
Vol. 1
Vol. 1
Engineering Innovations Vol. 4
Paper Title Page
Abstract: The main shaft of shot blasting machine mainly uses cylindrical roller bearing as the supporting part. The influence of stress, strain and temperature on bearing damage was studied by thermal structural coupling analysis of the bearing through finite element simulation. The causes and main damage forms of bearing surface were verified by super depth of field observation and finite element analysis. It is found that there exists pyramidal strain in the contact area between inner and outer raceway and roller, and its distribution form is continuous point distribution. The stress concentration is mainly distributed in the contact area between the roller face and the retaining edge, and the roller temperature is more concentrated in the area near the end face. The maximum length and depth of spalling pit on racetrack surface were 572.2μm and 14.15μm respectively. The maximum width and depth of the scratches on the roller surface are 386.7μm and 10.7μm, and the damage degree of the roller surface is not uniform. The thermo-structural coupling analysis is used to simulate the running state of bearings, which is of guiding significance to analyze the failure forms of bearings and improve the service life of bearings.
1
Abstract: In 21st century, battlefields are being occupied by Artificial Intelligence (AI) controlled machines and one of its kind is mini-unmanned aerial vehicles. Upon arming the mini-UAVs, the load distribution and characterizing the vibrational behavior are important for its safe operation. Usually, the gun recoil force gets transferred to the platform of the mini-UAV, leading to instability or failure of the platform along with the gun. Mini-UAVs being too small don’t have the space to set the conventional recoil reduction mechanism. So, it is important to design a mechanism or alternative propellant for achieving the equivalent explosive force instead of TNT. Also, the influence of explosion on the vibration characteristics of the mini-UAV is studied. The high-pressure gas is found as the best alternative to TNT material, for reducing the deflection produced. This work primarily concentrates on determining the deflection and frequency induced in mini-UAVs. By using a pressure canister arrangement, the vibration characteristics under recoil can be improved.
9
Abstract: Present, artificial intelligence methods play a huge role in solving complex engineering problems such as the fracture toughness of materials, which is one of the parameters to be considered for engineering design. Fracture toughness tests can be prepared materials and test configured in a variety of ways, resulting in different fracture toughness depending on the preparation method. In this study, fracture toughness of PMMA under the effect of loading rate is one of the testing configs that can be adjusted according to the actual load characteristics of the material and the crack geometry (crack width and crack length ratio) according to crack preparation to test specimens and the effect of these factors was predicted with generalized regression neural network (GRNN) and Gaussian processes regression (GPR) models which are one of the artificial intelligence models, compared to traditional fracture toughness predictions. The results showed that artificial intelligence prediction was able to more accurately predict the effect of the factors studied on the fracture toughness of PMMA compared to the traditional fracture toughness prediction.
15
Abstract: The effects of increasing volumetric air flow rate and inlet particulate loading on overall collection efficiency of MR-deDuster; a developed multi-cyclone system was investigated using various segregated sizes of palm oil mill boiler fly ash. The operating conditions of the fabricated pilot plant scale of the unit were predicted theoretically and screened experimentally. Increasing volumetric air flow rate theoretically will increase the overall collection efficiency, yet the experimental results during screening stage demonstrated contradict finding when the increment of volumetric air flow rate caused the overall collection efficiency to be decreased for a constant particulate loading. Subsequently, the optimization work was done to determine the optimum operating conditions of the system using Response Surface Method (RSM) with Box-Behnken design. The parallel arrangement of multi-cyclone units proved the ability of the system to uniformly disseminate the gas flow with high volume of gas carrier. Nevertheless, excessive pressure drops between each unit of multi-cyclone due to high volumetric air flow rate should be avoided as such condition may lower the overall collection efficiency by allowing dust re-entrainment from the hopper to circulate between the cyclones. Through statistical analysis of variance (ANOVA), validation and verification studies, it is suggested that the developed pilot scale multi-cyclone unit would be able to meet the targeted limit of 150 mg/m3 for solid fuel burning equipment industry in Malaysia by operating with optimized volumetric air flow rate of 0.27 m3/s, and maximum inlet particulate loading rate and size of 2 g/m3 and 1000 μm respectively.
21
Abstract: Mechanical properties are important characteristics of scaffolds as biomaterials implant in tissue engineering. This study focused on the analysis of the tensile strength of the 3D printing scaffold with a geometric design of the truncated hexahedron unit with pore size variation and combinFive variations of pore size of the scaffold (600, 800, 1,000, 1,200, and 1,400 µm) were fabricated from Polylactide acid (PLA) filament using the Fused Deposition Modelling (FDM) method through an ordinary commercial 3D printer. The IBS paste was synthesized from hydroxyapatite (HA), gelatin, hydroxypropyl methylcellulose (HPMC), and streptomycin. The characterization performed in this study were the pore size test with a digital microscope, tensile strength, elongation test, porosity, and contact angle. The 3D printed scaffold formed micropores after injected with IBS paste from a range of 130-230 µm. The tensile test results showed that the tensile strength of the 3D printing scaffold increased after being injected with IBS paste. In addition, the elongation test also shows a positive trend with increasing values of elongation after injection of IBS paste. The contact angle test results indicated that the scaffold was hydrophilic. From those characterizations, it could be concluded that 3D printing scaffold meet the criteria of scaffold for bone tissue engineering and drug carrier for tuberculosis.
31
Abstract: Naturally, the epitope dataset can be presented as a graph. Dataset preparation in the previous methods is part of model development. There are many graph-based classification and regression methods. Still, it is difficult to identify their performance on the conformational epitope prediction model because datasets in a suitable format are unavailable. This research aims to build a dataset in a suitable format to evaluate kernel graph and graph convolution network. This dataset, which results from graph clustering on graph antigens, can be used to identify the performance of many graph neural network-based algorithms for conformational epitope prediction. The Ag-Ab complexes that meet the criteria for forming a conformational epitope prediction dataset from previous studies were downloaded from the Protein Data Bank. Raw datasets in the form of specific exposed antigen chain residues are labeled as epitope or non-epitope based on their proximity to the paratope. The engineering features in the raw dataset are derived from the structure of the antigen-antibody complex and the propensity score. Aggregating atomic-level interactions into residual levels create an initial graph of the antigen chain. The MCL, MLR-MCL, and PS-MCL are graph clustering algorithms to obtain labeled sub-clusters from the initial graph. A balance factor parameter is set to several values to identify the optimal dataset formation based on minimal fragmentation. The output of the MCL algorithm is used as a baseline. As a result of the fragmentation analysis that occurs, the MLR-MCL algorithm gives the best model performance at a balance factor equal to 2. PS-MCL gives the best performance at a value of 0.9. Based on the minimum fragmentation, the MLR-MCL algorithm provides the best model performance compared to MCL and PS-MCL. The dataset in a format according to benchmarking dataset can be used to identify the characteristics of antigen subgraphs formed from the graph clustering process and to explore the performance of graph-based learning conformational epitope prediction models such as graph convolution networks.
37
Abstract: In recent years, the increasing volume and availability of healthcare and biomedical data are opening up new opportunities for computational methods to enhance healthcare in many hospitals. Medical data classification is regarded as the challenging task to develop intelligent medical decision support systems in hospitals. In this paper, the ensemble approaches based on support vector machines are proposed for classifying medical data. This research’s key contribution is that the ensemble multiple support vector machines use the function kernel in the style of gradient boosting and bagging to produce a more accurate fusion model than the mono-modality models. Extensive experiments have been conducted on forty benchmark medical datasets from the University of California at Irvine machine learning repository. The classification results show that there is a statistically significant difference (p-values < 0.05) between the proposed approaches and the best classification models. In addition, the empirical analysis of forty medical datasets indicated that our models can predict diseases with an accuracy rate of 82.82 and 81.76 percent without feature selection in the preprocessing data stage.
47
Showing 1 to 7 of 7 Paper Titles