Papers by Keyword: Artificial Neural Network (ANN)

Abstract: Gyroid structures are one of the most common Triply Periodic Minimal Surfaces (TPMS) with remarkable mechanical properties, including energy absorption and stress distribution. In the current study, the compressive behavior of gyroid structures fabricated through Fused Deposition Modeling (FDM) was investigated. The deformation and failure mechanisms were predicted via extensive simulations using Finite Element Analysis tools. Experimental testing using Acrylonitrile Butadiene Styrene (ABS) specimens was performed on a Universal Testing Machine (UTM), and the results compared with computational data. To predict the compressive strength and optimize the structural parameters, an Artificial Neural Network (ANN) was trained. Results indicate a good match between the experimental and simulation findings, indicating immense potential for these gyroid structures in energy absorption.

Abstract: Oral dispersible film (ODF) containing ascorbic acid (AA) was synthesised using the electrospinning process, and its dissolving behaviour was analysed by Ultraviolet-Visible (UV-Vis) spectroscopy. The obtained time, wavelength and absorbance data were applied to train an Artificial Neural Network (ANN) using the Levenberg-Marquardt algorithm. A total of 42 datasets were separated into training (90%), validation (5%) and testing (5%) sections. The ANN model displayed good predictive ability, giving a low mean squared error (MSE) and a regression coefficient (R=1), demonstrating a significant correlation between predicted and experimental dissolution profiles. These results demonstrate that ANN can efficiently predict ODF dissolution profiles, hence lowering experimental burden and boosting efficiency in pharmaceutical formulation research.

Abstract: This study investigated the effects of mixing ratio and temperature on the electrical conductivity of a GNP-Al2O3 hybrid nanofluid. The results showed that an increase in the mixing ratio reduced the electrical conductivity ratio of the nanofluid, while an increase in temperature improved the electrical conductivity ratio. Additionally, an Artificial Neural Network (ANN) was used to predict the electrical conductivity of the nanofluid based on the mixing ratio and temperature. The optimal number of neurons in the hidden layer was found to be four neurons, with a low root mean square error (RMSE) value of 0.00696. The regression plot for the training, validation, and test data exhibited high correlation coefficients, indicating the reliability of the ANN model. These findings provide valuable insights into the behaviour of hybrid nanofluids and highlight the potential of using ANN for predicting their electrical conductivity.

Abstract: Studying the behaviour of engineering systems and processes from the perspective of applications of artificial intelligence provides an invaluable reference to improve their productivity and industrial development at large. This study comprehensively unveiled the problems faced by engineering systems and how artificial intelligence could be deployed as a technique for the future advancement of the industry. A brief background of the application of artificial intelligence in some selected engineering fields revealed that insufficient operational and process data from both plants and processes are major problems causing the survival of sustainable intelligent systems thereby, leading to incessant system failure. Furthermore, it was equally discovered that artificial intelligent for specific application are based on the data obtained from such application. Thus, there is no universally agreed artificial intelligent for a specific application. This made it a bit complex in developing intelligent systems. Keywords: Artificial Neural Network, Applications, Engineering, Training, Data.

Abstract: This paper focuses on investigating public perception in the United Arab Emirates (UAE) towards the implementation of High-Occupancy Toll (HOT) lanes in major freeways. HOT lanes provide the UAE government with significant potential to enhance the transportation network through decline in motorway accidents, procuring additional revenues, decreasing the overall sector costs, as well as lessening the carbon footprint ensuing from this sector. However, the primary challenge encountered during the implementation of HOT lanes in the UAE is public perception and Willingness to Pay (WTP). A questionnaire-based survey was developed and circulated among the public in the UAE to deduce the public’s attitude towards the utilization of HOT lanes. The survey intended to capture the socio-economic, demographic, and commute-related characteristics of respondents, as well as their current knowledge of HOT lanes. The survey data were collected and processed to identify the features of the obtained sample. Comparative statistical and advanced numerical analyses, in the form of Linear Regression (LR) and Artificial Neural Networks (ANN) were conducted to model the relationships between different characteristics and the public’s WTP. Additionally, the significance of the factors affecting the WTP were ranked using Bayesian Networks. The results showed that monthly income was the most significant factor affecting public WTP followed by age, frequency of trips, employment status, peak hour traffic, and emirate of residence. Prediction equations generated from ANN and LR, utilizing the most significant factors, indicated that ANN had significantly higher accuracy and lower MSE compared to linear regression. Overall, this study could significantly help decision-makers for future transportation systems improvement.

Abstract: According to Vision Indonesia, data on people with eye diseases in Indonesia in 2018-2019 were 3 million people or about 1.5% of the total population. So far, public information or knowledge about the recognition of eye disease disorders is still lacking. The problem in this study is how to educate the public about the introduction of eye diseases based on information on symptoms of the disease and how to apply the web-based Artificial Neural Network (ANN) algorithm for the introduction of eye diseases. The ANN algorithm in the eye disease recognition education system can conclude knowledge even though it does not have certainty and takes it into account sequentially so that the process is faster. In terms of educational content about eye disease recognition, this is a novelty to use. This research aims to create an educational system for introducing eye diseases based on information on symptoms of the disease and applying a web-based Artificial Neural Network (ANN) algorithm for the recognition of eye diseases. The method used is the Artificial Neural Network algorithm method. The work of ANN in the education system for the introduction of eye diseases is to make parameters of eye disease symptoms or indicators that will produce the type of eye disease. The research material used is data on types of eye diseases and symptoms of each type of eye disease. The research results are to create an education system that can help the public recognise eye diseases based on the symptoms of these eye diseases that can be run on a web platform. The Artificial Neural Network (ANN) algorithm can manage input analysis data from disease indicators and show the initial results of eye diseases that can be detected. suffered by someone based on Training Results Weights and Bias v11= 1.6769, v01= 0.4356, w11= -1.5233, w01= 0.3242. Based on white box testing, the test results are free from logical errors. The results of this study indicate that the use of the ANN algorithm for eye disease recognition shows accurate results based on eye disease symptom data.

Abstract: Wire Electrical Discharge Machining (WEDM) is a specialized thermal machining process capable of accurately machining parts with varying hardness or complex shapes, which have sharp edges that are very difficult to be machined by the main stream machining processes. Selection of process parameters for obtaining higher cutting efficiency or accuracy in WEDM is still not fully solved, even with most up-to-date CNC wire EDM machine. It is widely recognised that Acoustic Emission (AE) is gaining ground as a monitoring method for health diagnosis on rotating machinery. The advantage of AE monitoring over vibration monitoring is that the AE monitoring can detect the growth of subsurface cracks whereas the vibration monitoring can detect defects only when they appear on the surface. This study outlines the optimization of titanium material using L₁₆ design of experiment. Each experiment has been performed varying the process parameters like pulse-on time, pulse-off time, current and bed speed. Among different process parameters voltage and flush rate were kept constant. Molybdenum wire having diameter of 0.18 mm was used as an electrode. Simple functional relationships between the parameters were plotted to arrive at possible information on Electrode Wear (EW) and AE signals. But these simpler methods of analysis did not provide any information about the status of the electrode. Thus, there is a requirement for more sophisticated methods that are capable of integrating information from the multiple sensors. Hence, method like Artificial Neural Network (ANN) has been applied for the estimation of EW, AE signal strength, AE count and AE RMS. The ANN algorithm is designed to learn the process by training the algorithm with the experimental data. The experimental observations are divided into three sets: the training set, validation set and testing set. The training set is used to make the ANN learn the process and the testing set will check the performance of ANN. Different models can be obtained by varying the percentage of data in the training set and the best model can be selected from these, viz., 50%, 60% and 70%. The best model is selected from the said percentages of data. Estimation of the EW and AE signals parameters by ANN at 70% of data training set showed the best correlation with the measured value.

Abstract: Tribotesting is necessary to understand the behaviour of the material under various operating lubrication conditions. This paper deals with the training of an artificial neural network (ANN) model with Bio-lubricant properties and machining conditions for prediction of surface roughness and coefficient of friction in Tribotesting by Tool chip Tribometer. Experimental results obtained from Tool chip tribometer for tested bio-lubricants are compared with those obtained by ANN prediction. A good agreement in results recommends that a well trained neural network is competent enough to predict the parameters in Tribotesting process.

Abstract: In tribological analysis of machine elements (such as gears, ball/roller bearings etc.), surface roughness plays very important role, ultimately it affects the friction coefficient, wear, rolling contact fatigue (micro pitting) and other failure mechanisms. Surface geometry and topography changes with time (number of cycles) during rolling/sliding motion of contacting surfaces. So, it is important to show the variation of surface topography parameter during wear process. This work presents the evolution of roughness parameters, wear and friction coefficient during pin-on-disc tribotesting under dry condition. The test is performed using pin on disc apparatus under room temperature condition. The pin (25mm long, 6mm diameter) is made of medium carbon steel (AISI 1038) whereas the disc (165mm diameter, 8mm thickness) is made of high carbon steel (SAE 52100). This works demonstrates the potential of Artificial Neural Network (ANN) for prediction of roughness parameters, friction coefficient and wear coefficient. Experimental results obtained from wear testing are compared with those obtained using artificial neural network (ANN) analysis. A very good agreement in results suggests that a well trained neural network is capable to predict the parameters in wear process.

Abstract: Warm stamping techniques have been employed to solve the formability problem in forming aluminium alloy panels. The formability of sheet metal is a crucial measure of its ability for forming complex-shaped panel components and is often evaluated by forming limit diagram (FLD). Although the forming limit is a simple tool to predict the formability of material, determining FLD experimentally at warm/hot forming condition is quite difficult. This paper presents the artificial neural network (ANN) modelling of the process based on experimental results (different temperature, 20°C-300°C and different forming rates, 5-300 mm.s^-1) is introduced to predict FLDs. It is shown that the ANN can predict the FLDs at extreme conditions, which are out of the defined boundaries for training the ANN. According to comparisons, there is a good agreement between experimental and neural network results