Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Sinergi

Bayesian networks approach on intelligent system design for the diagnosis of heat exchanger Dedik Romahadi; Fajar Anggara; Rikko Putra Youlia; Hifdzul Luthfan Habibullah; Hui Xiong
SINERGI Vol 26, No 2 (2022)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2022.2.001

Abstract

The heat exchanger highly influences the series of cooling processes. Therefore, it is required to have maximum performance. Some of the factors causing a decrease in its performance are increased pressure drop in the Plate Heat Exchanger (PHE), decreased output flow, leakage, flow obstruction, and mixing of fluids. Furthermore, it takes a long time to conclude the diagnosis of the performance and locate the fault. Therefore, this study aims to design an intelligent system for the performance diagnosis of the PHE using the Bayesian Networks (BNs) method approach. BNs are applied to new problems that require a new BNs network model. The system was designed using MSBNX and MATLAB software, comprising several implementation stages. It starts by determining the related variables and categories in the network, making a causality diagram, determining the prior probability of the variable, filling in the conditional probability of each variable, and entering evidence to analyze the prediction results. This is followed by carrying out a case test on the maintenance history to display the probability inference that occurs during pressure drop on the PHE. The result showed that the BNs method was successfully applied in diagnosing the PHE. When there is evidence of input in the form of a pressure drop, the probability value of non-conforming pressure-flow becomes 61.12%, PHE clogged at 73.59%, and actions to clean pipes of 70.18%. In conclusion, the diagnosis carried out by the system showed accurate results.
A review towards Friction Stir Welding technique: working principle and process parameters Rikko Putra Youlia; Diah Utami; Dedik Romahadi; Yang Xiawei
SINERGI Vol 27, No 3 (2023)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2023.3.001

Abstract

Friction Stir Welding (FSW) is a solid-state bonding process that employes tools that are not used up and can function to connect two opposite workpieces without melting the workpiece material. The friction force has been micro-structurally tested to reformat or transform the inner state of the structure properties (atomic formation) form in metal since the kinetic energy of friction has been utilised in one of the welding techniques. Right afterwards, the studies reported that the mechanical properties also underwent a significant deformation. The aim is to determine the effect of Welding Procedure Specification (WPS) product quality. As it develops through research and applied experiments, the branch of friction-based welding discipline can be classified depending on how the friction mechanism can produce the finest solid-state joint, which is suitable to the typical property of metal and can be maximised by joint configuration. Friction Stir Welding is a friction-based welding technique that uses the stirring tool to generate friction while the workpieces are stuck on the line of the FSW joint configuration. The relevant correlations amongst process parameters and inside its respective adjustable variables are constructed to the finest principles that produced top-grades empirical reports of the weld properties. In this review, the explanation of the working principle and clarification of process parameters are presented. The cited references are selected from creditable and verifiable articles and books in the last ten years. Expectedly, it will be able to pioneer a new face of simple and understandable review articles.
Resonance analysis of fan blade design using Finite Element Method Dedik Romahadi; Rikko Putra Youlia; Himawan S. Wibisono; Muhammad Imran
SINERGI Vol 28, No 1 (2024)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/sinergi.2024.1.014

Abstract

Fan motors move liquids, such as air, in the gas phase from one place to another. The frequency of the fan blades, which are the main components of the fan motor, can vary. It is crucial to know the frequencies of each fan blade to avoid design failures caused by resonance. This research analyzes the effect of differences in the angle and number of blades on the natural frequency of the fan to avoid resonance with the motor rotation frequency. Modeling and simulation using the finite element method in the Solidworks application are used to determine the natural frequencies of the fan. Fans come in various configurations, with blades ranging from two to four, and blade pitch can be 25°, 30°, or 40°. Variations in the number of fan blades and changes in blade pitch show that the low mode shape does not affect the natural frequency, while the high mode has a negligible effect. The natural frequency of fan blades 2, 3, and 4 exhibits variations when operated with motors running at 25, 35, or 50 Hz. The findings imply that the fan blades' inherent frequency does not align closely with the motor rotational frequency, indicating that the design is safe.
Towards enhanced acoustic fan booster damage detection: a comparative study of feature-based and machine learning approaches Youlia, Rikko Putra; Romahadi, Dedik; Feleke, Aberham Genetu; Nugroho, Irfan Evi; Alina, Alina
SINERGI Vol 30, No 1 (2026)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Machine failure detection frequently uses non-destructive monitoring techniques such as vibration analysis. Although vibration analysis can identify machine degradation, the apparatus is often costly and necessitates specialist knowledge. Additionally, many existing methods in audio classification rely on characteristics represented as pictures or vectors, which increases computational complexity. In contrast, this research introduces a novel method that substitutes vibration data with a singular numerical feature derived from audio signals, addressing both cost and complexity issues. Our objective is to develop a rapid and precise audio-based method for detecting machine damage. The acoustic signals from the machine apparatus were classified into three categories: normal, belt damage, and combined belt and bearing defect. The data processing technique involved lowering the sample rate and segmenting the data to improve computational efficiency and classification performance. We use the Welch method and appropriate statistical techniques to analyze Power Spectral Density (PSD). The performance of seven classifier models, KNN, LDA, SVM, NB, ANN, RF, and DT, was evaluated using accuracy, precision, sensitivity, specificity, and F-score. LDA achieved the highest accuracy at 92.83%, followed by ANN (92.75%), NB (92.74%), and DT (92.34%). These models outperformed KNN (89.90%) and RF (89.40%), with SVM recording the lowest accuracy at 85.40%. LDA was highly effective, achieving the highest accuracy with a single average PSD-type feature, showcasing its robustness in machine defect diagnosis. Compared to previous methods, this approach simplifies feature extraction, reduces computational demands, and maintains high diagnostic performance, providing notable benefits in terms of effectiveness and precision.