Garuda - Garba Rujukan Digital

Aplikasi Penggunaan Metode Moire Pattern untuk Mengetahui Karakteristik Sebaran Nilai Stress-Displacement pada Material Baja AISI 304 Berbasis Image Processing Mohammad Khoirul Effendi; Agus Sigit Pramono; Ari Surya Yulianto; Hanif Pribadi
Jurnal Teknik Mesin (Sinta 3) Vol. 15 No. 1 (2014): APRIL 2014
Publisher : Institute of Research and Community Outreach, Petra Christian University

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

Stress field is an important parameter for determining the strength of a plate due the loading. Measurement of the stress field in it cannot be done directly. The mathematic explanation shows that the stress field has a relationship with the terrain displacement/displacement. In the plate theory, deflection is defined as displacement towards out plane direction. One method to get the value of deflection on the plate is a moiré method. This moiré method uses the principle of line superposition between plate and its reference. When a test plate subjected to a load, the deflection that occurs in the test material a pattern will be produced in the form of a superposition of light and dark pattern (fringe) which describes the distribution of the stress-displacement on a surface of tested material. Tested material is AISI 304.The surface of tested material was given a lattice pattern with variations in distance of 1 mm. The fourth side of the tested plate is clamped perfectly, then the center of it will be pressurized with variations in displacement (0.5, 1, 1.5, and 2 mm). The occurred Moiré patterns will be captured by the camera to turn it into a digital image. Furthermore, it will be processed through a series of image processing which consists of the four different filter algorithms (Gaussian filter and Butterworth Low Pass Filter), and also four edge detection algorithms (Sobel, Prewitt, Canny, and Roberts).The results of the stress-strain measurements will be compared with the results of analytical calculations and numerical calculations. The difference of displacement average using moiré method compared with analytical method is 6.75%, while using numerical method is 7.55%. Furthermore the difference of stress average using moiré method compared with analytical calculation is 9:08%, while using numerical methods by 9.5%.

The Comparisson between LBP and SQI Methods in the Surface Roughness Measurement Using ESPI Method Mohammad Khoirul Effendi; Agus Sigit Pramono; Pandu Pratama; Rifki Wardana
IPTEK The Journal of Engineering Vol 2, No 1 (2015)
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j23378557.v2i1.a470

Surface roughness measurement using direct contact methods raises several issues, for examples stylus wear and size limitation problems. Furthermore non-contact methods are proposed to solve these problems. One of them is Electronic Speckle Pattern Interferometry (ESPI), which use Helium-Neon (He - Ne) as laser light source. A speckle pattern is produced by scattered light on the surface of the measuring object due to the interference of laser beams, and it will be captured by Charge Coupled Device (CCD) camera. Afterwards Linear Binary Pattern (LBP) and Self Quotient Image (SQI) methods are used to reduce illumination effect in the captured image. The average gray-level from the previous process will be converted into a surface roughness value by gray level to surface roughness conversion formulation. It is obtained from correlation value between gray level and a set of standard roughness. The standard roughness value range is start from 0,05 μm to 12,5 μm. It is measured from five different final machining process, which are flat lapping, grinding, horizontal milling, and vertical milling. As verification, the results of ESPI method will be compared with the result of direct contact tools using Mitutoyo Surftest 301 and 401.

Multi-objective Optimization Using Neural Network, Differential Evolution, and Teaching Learning Based Optimization in Drilling Process of Glass Fiber Reinforced Polymer Kirana Alif Fatika; Mohammad Khoirul Effendi
JMES The International Journal of Mechanical Engineering and Sciences Vol 5, No 2 (2021)
Publisher : LPPM, Institut Teknologi Sepuluh Nopember, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j25807471.v5i2.10382

This experiment focused on the drilling process of Glass Fiber Reinforced Polymer (GFRP) composites. The data was obtained from an experiment carried out by Production Engineering Laboratory, Mechanical Engineering Department, Faculty of Industrial Technology and Systems Engineering, Institut Sepuluh Nopember Surabaya in 2019. The experiment was done with an artificial intelligence method called Backpropagation Neural Network (BPNN) as an approach to predict the response parameters (thrust force, torque, hole roundness, and hole surface roughness). The parameter inputs are drill point geometry, drill point angle, feed rate, and spindle speed. Hence the prediction would be used to gain the minimum input parameters by applying metaheuristic methods called Differential Evolution (DE) and Teaching Learning Based Optimization (TLBO). Then the result from both methods was compared to determine which method gained the better optimization values. Since BPNN-DE and BPNN-TLBO with type X drill point geometry was considerably better than type S drill point geometry, type X drill point geometry could be used to optimize the drilling process of GFRP.

Engine RPM and Battery SOC Activation Optimization in Hybrid Vehicle Energy Management System Utilizing BPNN - Genetic Algorithm and BPNN – Particle Swarm Optimization Rhema Adi Magiza Wicaksana; Bambang Sudarmanta; Mohammad Khoirul Effendi
The International Journal of Mechanical Engineering and Sciences Vol 6, No 2 (2022)
Publisher : LPPM, Institut Teknologi Sepuluh Nopember, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j25807471.v6i2.12360

The energy used in the hybrid vehicle needs to be regulated to gain further mileage and lower fuel consumption. It is achieved by selecting the correct levels of hybrid energy management system (EMS) parameters (i.e., vehicle speed, engine RPM, and activation State of Charge (SOC) of battery). This study focused on the modeling and optimization of Sepuluh Nopember Institute of Technology (ITS)’s series plug-in hybrid electric vehicle (PHEV) car mileage and fuel consumption by comparing the backpropagation neural network (BPNN) method – genetic algorithm (GA) and BPNN – particle swarm optimization (PSO). The BPNN was used to model the character of ITS’s series PHEV EMS and predict mileage and fuel consumption. The BPNN’s model obtained the best EMS parameters, most extended mileage, and minimum fuel consumption. The result of the validation experiment showed that both the integration of BPNN - GA and BPNN - PSO were able to predict and optimize the multi-objective characteristic with the same results.

Automated Corrosion Detection on Steel Structures Using Convolutional Neural Network Mohammad Khoirul Effendi; Bara Atmaja; Arif Wahjudi; Dedi Budi Purwanto
JMES The International Journal of Mechanical Engineering and Sciences Vol 7, No 1 (2023)
Publisher : LPPM, Institut Teknologi Sepuluh Nopember, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j25807471.v7i1.15881

Steel is a material that is widely used in industry and construction. The tensile and compressive force of steel is relatively high compared to other materials. On the opposite, low corrosion resistance is the main weakness of steel, which can encourage steel deterioration and fatal accidents for the user. Furthermore, regular visual inspection by a human should be performed to prevent catastrophic incidents. However, human visual inspection increases the risk of work accidents and reduces work effectiveness. Therefore, a drone with a camera is one solution to increase efficiency, increase security levels, and minimize difficulties or risks during corrosion inspection. In this research, the drone has been used to capture corroded video of a construction structure. The convolutional neural network (CNN) method is then used to detect the location of the corroded images. This study has been conducted on Surabaya’s Petekan-bridge with the Mobilenet V1 SSD pre-training model. In this study, the distance between a drone and the detected object varied between 1 and 2 m. Next, the drone speed was varied into 0.6 m/s, 0.9m/s, and 1.3m/s. As a result, CNN can detect corrosion on the surface of steel materials with the best accuracy is 84.66% and minimum total loss value of 1.673 by applying 200 images, 200000 epochs, batch size at 4, learning rate at 0.001 and 0.1, the distance at 1 m, drone speed at 0.6 m/s.

Pelatihan Keterampilan Las Listrik untuk Masyarakat Sekitar Kampus ITS Suhardjono; Triyogi Yuwono; Herman Sasongko; Djatmiko Ichsani; Bambang Pramujati; Bambang Sudarmanta; Yusuf Kaelani; Sampurno; Mohammad Khoirul Effendi
Sewagati Vol 5 No 1 (2021)
Publisher : Pusat Publikasi ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (531.732 KB)

Pengangguran di Indonesia secara umum masih cukup tinggi sekitar 7 juta orang sesuai data BPS pada Agustus 2018. Sebenarnya bukan hanya tugas pemerintah yang harus menurunkan jumlah pengangguran tersebut, tetapi juga peran Perguruan Tinggi dalam tugas Tridharmanya, yaitu Pengabdian kepada Masyarakat. Selain daripada itu pekerja konstruksi Indonesia yang jumlahnya 8,3 juta masih mempunyai kualitas rendah. Hanya sekitar 7,4% yang mempunyai sertifikat atau sekitar 616.000 orang dan hampir 2/3 yang bersertifikat tersebut masih dalam tingkatan “TERAMPIL” dan sisanya bersertifikat tingkat “AHLI”. Dari alasan itulah maka Laboratorium Proses Manufaktur dengan peralatan praktikum las listrik yang tersedia akan ikut berpartisipasi aktif dalam mengurangi angka pengangguran dan menciptakan keterampilan dalam bidang MEKANIKAL dengan subbidang Tukang Las. Pelatihan keterampilan las listrik ini bertujuan selain memberikan keterampilan bagi peserta baru yang ingin menjadi tukang las. Dampak yang diharapkan untuk Pelatihan keterampilan Las listrik ini adalah terciptanya tukang las baru yang siap bekerja baik di bengkel-bengkel las dan tukang las yang dapat mengisi lowongan kerja sebagai tukang las. Internet memasarkan menjadi Tukang Las lepas “Freelance” bermodal kecil yang dapat dipanggil ke Rumah. Untuk itu pada pelatihan ini diberikan suatu proyek sederhana untuk membuat produk seperti rak sepatu, gantungan handuk dan sejenisnya.

Path Planning Optimization of Automated Ground Vehicle in Inspecting Boeing 757-200 Aircraft Using Genetic Algorithm and Simulated Annealing Methods Mohammad Khoirul Effendi; Ryan Filbert Wijaya; Aida Annisa Amin Daman
JMES: The International Journal of Mechanical Engineering and Sciences Vol 9 No 1 (2025)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j25807471.v9i1.22396

Transportation plays a critical role in modern society, with air travel being a key component of long-distance mobility. Despite strict regulations by the Federal Aviation Administration (FAA) and mandatory periodic inspections, aircraft maintenance issues often arise due to human error. Factors such as fatigue and the challenges of working in hard-to-reach areas contribute to these errors. Automated Ground Vehicles (AGVs) equipped with automated inspection systems offer a promising solution by reducing reliance on human performance, enabling inspections that are more accurate, efficient, and automated. However, optimizing inspection routes to minimize travel distance remains a challenging issue. This study aims to optimize the inspection distance for AGVs inspecting the underside of a Boeing 757-200 aircraft using MATLAB R2023a simulation tools. The input data for the simulation consists of the x, y, and z coordinates of various inspection points on the aircraft, and the output is the total distance travelled by the AGV during inspection. The objective is to minimize the travel distance, calculated as a vector from one point to the next. Two optimization methods to be compared include Simulated Annealing (SA) and Genetic Algorithm (GA). The SA method involves varying parameters such as the number of iterations, initial temperature, and cooling rate. Meanwhile, the GA method varies the number of iterations, population size, and crossover and mutation percentages. The study evaluates the performance of both methods using a dataset of 34 inspection points. The results show that Simulated Annealing produces the most optimal path-planning distance, achieving a minimum of 85.099 meters across all parameter variations. This optimized solution contributes to more efficient and reliable aircraft maintenance processes, reducing human error and enhancing air travel safety and reliability.

Multi-Objective Prediction of Drilling EMS-45 with Finite Element, Backpropagation Neural Network, and Metaheuristic Model Mohammad Khoirul Effendi; Agus Sigit Pramono; Suhardjono Suhardjono; Sampurno Sampurno; Dinny Harnany; Fungky Dyan Pratiwi
JMES: The International Journal of Mechanical Engineering and Sciences Vol 8 No 1 (2024)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j25807471.v8i1.19269

Making holes with the minimum thrust force and torque using a drilling machine is challenging for researchers because of the difficulties in setting input parameter such as the type of drill tool, point of angle, and feeding speed. Therefore, the trial-and-error method to predict optimum input parameters through experiment can be replaced with the Back Propagation Neural Network (BPNN) and metaheuristic method (i.e., genetic algorithm (GA) and Simulated Annealing (SA)) method to reduce costs and time. BPNN can be used to represent the input-output correlation precisely. However, obtaining a model with minimum Mean Squared Error (MSE) requires much data for training, testing, and validation. Since the obtained data from experiments requires expensive costs, combining data from experimental and simulation using ANSYS should considered to reduce the experimental costs. This study was then conducted to answer the research problem using an EMS 45 tool steel as the workpiece, with the three input parameters: type of drill tools (HSS M2 and HSS M35), the points of angle (118 and 134 degrees) and feeding speed rates (0.07 and 0.1 mm/s). The 32 data from experimental and modeling were used to model the correlation between the input and output parameters of the drilling process using BPNN. The BPNN’s network-model with minimum MSE is then used as the objective function to determine the input parameters to obtain the smallest value of thrust force and torque using the hybrid method using GA and SA.

Automated Corrosion Detection on Steel Structures Using Convolutional Neural Network Mohammad Khoirul Effendi; Bara Atmaja; Arif Wahjudi; Dedi Budi Purwanto
JMES: The International Journal of Mechanical Engineering and Sciences Vol 7 No 1 (2023)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j25807471.v7i1.15881

Steel is a material that is widely used in industry and construction. The tensile and compressive force of steel is relatively high compared to other materials. On the opposite, low corrosion resistance is the main weakness of steel, which can encourage steel deterioration and fatal accidents for the user. Furthermore, regular visual inspection by a human should be performed to prevent catastrophic incidents. However, human visual inspection increases the risk of work accidents and reduces work effectiveness. Therefore, a drone with a camera is one solution to increase efficiency, increase security levels, and minimize difficulties or risks during corrosion inspection. In this research, the drone has been used to capture corroded video of a construction structure. The convolutional neural network (CNN) method is then used to detect the location of the corroded images. This study has been conducted on Surabaya’s Petekan-bridge with the Mobilenet V1 SSD pre-training model. In this study, the distance between a drone and the detected object varied between 1 and 2 m. Next, the drone speed was varied into 0.6 m/s, 0.9m/s, and 1.3m/s. As a result, CNN can detect corrosion on the surface of steel materials with the best accuracy is 84.66% and minimum total loss value of 1.673 by applying 200 images, 200000 epochs, batch size at 4, learning rate at 0.001 and 0.1, the distance at 1 m, drone speed at 0.6 m/s.

Engine RPM and Battery SOC Activation Optimization in Hybrid Vehicle Energy Management System Utilizing BPNN - Genetic Algorithm and BPNN – Particle Swarm Optimization Rhema Adi Magiza Wicaksana; Bambang Sudarmanta; Mohammad Khoirul Effendi
JMES: The International Journal of Mechanical Engineering and Sciences Vol 6 No 2 (2022)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j25807471.v6i2.12360

The energy used in the hybrid vehicle needs to be regulated to gain further mileage and lower fuel consumption. It is achieved by selecting the correct levels of hybrid energy management system (EMS) parameters (i.e., vehicle speed, engine RPM, and activation State of Charge (SOC) of battery). This study focused on the modeling and optimization of Sepuluh Nopember Institute of Technology (ITS)’s series plug-in hybrid electric vehicle (PHEV) car mileage and fuel consumption by comparing the backpropagation neural network (BPNN) method – genetic algorithm (GA) and BPNN – particle swarm optimization (PSO). The BPNN was used to model the character of ITS’s series PHEV EMS and predict mileage and fuel consumption. The BPNN’s model obtained the best EMS parameters, most extended mileage, and minimum fuel consumption. The result of the validation experiment showed that both the integration of BPNN - GA and BPNN - PSO were able to predict and optimize the multi-objective characteristic with the same results.

Title

Found 12 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 12 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 12 Documents
Search