Claim Missing Document
Check
Articles

Analisis Perbandingan Metode Quenched Terhadap Sifat Mekanik Baja Tahan Karat Austenitik Berbasis Big Data Leni, Desmarita; ., Islahuddin; ., Mulyadi; ., Hendra; Sumiati, Ruzita
Rekayasa Material, Manufaktur dan Energi Vol 7, No 2: Juli 2024
Publisher : Fakultas Teknik UMSU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30596/rmme.v7i2.18025

Abstract

A profound understanding of the mechanical properties of stainless steel is crucial in modern industrial applications. However, comprehensively understanding the mechanical properties of stainless steel requires sufficient testing to gather data on its characteristics. In this research, an analysis was conducted on the influence of chemical composition and heat treatment on the mechanical properties of stainless steel, utilizing data from the Material Algorithm Project (MAP), which is a material database. The dataset comprises 986 samples, encompassing 11 chemical elements, variations in quenching, and 3 mechanical properties of stainless steel. The data was analyzed using descriptive statistics and Pearson correlation to examine the relationships between these variables. The research results indicate a negative correlation of -0.35 between temperature and Yield Strength (YS) in samples of steel undergoing air cooling. The YS values in this treatment can reach 300 MPa at temperature combinations ranging from 1300 K to 1330 K, with heating times ranging from 180 seconds to 420 seconds. Meanwhile, water cooling exhibits a wide range of cooling times and relatively high temperatures. Combinations of time between 1400 seconds and 2200 seconds and temperatures between 1300 K and 1400 K result in YS ranging from 240 MPa to 260 MPa. This research suggests that experimental material testing datasets not only play a passive role in validating an experiment but can also be actively utilized in the analysis and design of materials more effectively.
Mengoptimalkan Analisis Sifat Mekanik Material Berbasis Data Dengan Pandas Profiling Leni, Desmarita; Earnestly, Femi; Angelia, Nike; Nofriyanti, Elsa; Adriansyah, Adriansyah
Jurnal Mesin Nusantara Vol 7 No 1 (2024): Jurnal Mesin Nusantara
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/jmn.v7i1.21206

Abstract

The analysis of mechanical properties based on data is a method used to analyze the mechanical properties of a material using data, typically obtained from a material database. This process encounters several challenges, such as large volume of data, complexity in data processing, as well as difficulties in data visualization and interpretation. In this study, Pandas Profiling, a Python library designed specifically for automated dataset analysis, was employed. The dataset used consisted of tensile test results for various austenitic stainless steel types such as SUS 304, SUS 316, SUS 321, SUS 347, and NCF 800H. This dataset comprised 1916 samples with attributes related to mechanical properties and factors influencing them. The analysis results using Pandas Profiling indicated a strong negative correlation between heat treatment temperature and Yield Strength (YS) and Ultimate Tensile Strength (UTS). Additionally, a positive correlation was found between chemical elements such as Copper (Cu) and Nickel (Ni) with Elongation (EL). Furthermore, the analysis results revealed that stainless steel treated with water cooling exhibited a higher average UTS value, measuring at 493 MPa, compared to air cooling, which only reached 403 MPa. Pandas Profiling offers an effective solution to overcome common challenges in data-based mechanical property analysis, including dealing with large data volumes, complex data processing, as well as challenges in data visualization and interpretation. By utilizing Pandas Profiling, researchers can easily comprehend the dataset comprehensively, identify patterns, trends, and relationships among variables, and optimize the analysis process of data-based material mechanical properties.
Evaluasi Pemodelan Augmentasi Data Sifat Mekanik Aluminium Menggunakan Generative Adversarial Networks Leni, Desmarita; Berli, Ade Usra; Kesuma, Dytchia Septi; Haris, Haris; Sumiati, Ruzita
Jurnal Engine: Energi, Manufaktur, dan Material Vol. 8 No. 1 (2024)
Publisher : Proklamasi 45 University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30588/jeemm.v8i1.1645

Abstract

Materials informatics is a new approach in material science that integrates information technology and material science to optimize the discovery of new materials more efficiently and innovatively. In materials informatics, experimental and simulation data are combined with data-driven methods such as big data, data augmentation, and machine learning to gain a deeper understanding of material properties. However, limitations in the availability of samples with desired characteristics and the lack of accurate experimental data pose challenges in materials informatics. In this study, we attempt to address these challenges by modeling the augmentation of mechanical properties of aluminum using Generative Adversarial Networks (GAN). GAN is used to generate synthetic data of aluminum's mechanical properties that closely resemble experimental data. This modeling is trained using experimental testing data consisting of aluminum's mechanical properties and chemical elements in the alloy, obtained from the material database. The dataset comprises 9 chemical element variables in the aluminum alloy and 2 mechanical property variables. The synthetic data generated from the modeling is evaluated using descriptive statistics, Pearson correlation, and Kolmogorov-Smirnov (KS) test to assess the extent to which the synthetic data resembles the original data. The evaluation results indicate that the distribution of synthetic data is similar to the original data. The Pearson correlation results show that most variables of chemical elements and mechanical properties of aluminum in the synthetic data have a correlation that is quite similar to the original data. The KS test results also indicate that the distribution of synthetic data does not significantly differ from the distribution of the original data. This indicates that the synthetic data generated has a high resemblance to the experimental data, enabling its use in materials informatics research. Thus, modeling the augmentation of aluminum's mechanical property data using GAN provides a significant contribution to expanding data availability in material science.
MODELING PISTON DAMAGE DETECTION USING A CONVOLUTIONAL NEURAL NETWORK BASED ON DIGITAL IMAGE Utami, Lega Putri; Leni, Desmarita
International Journal of Multidisciplinary Research and Literature Vol. 3 No. 2 (2024): INTERNATIONAL JOURNAL OF MULTIDISCIPLINARY RESEARCH AND LITERATURE
Publisher : Yayasan Education and Social Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53067/ijomral.v3i2.189

Abstract

Product inspection is a crucial component of product quality control, aiming to evaluate and ensure that products meet predefined standards. In this research, the modelling of piston damage detection is conducted using a Convolutional Neural Network (CNN). The dataset employed consists of images of pistons categorized into three groups: Defected1, Defected2, and Normal. Two hundred eighty-five images are utilized as training data, with the data distribution percentages for Defected1, Defected2, and Normal being 30.9%, 34.4%, and 34.7%, respectively. The model is validated using newly generated data through augmentation techniques, resulting in 60 images. The CNN model uses a sequential Keras architecture comprising convolutional layers, pooling layers, fully connected layers, and softmax activation. The Adam optimizer with a learning rate 0.0001 is employed for model training, with validation using a 5-fold cross-validation. The model is evaluated using the Loss, Accuracy, and Confusion Matrix, achieving a training accuracy of 0.722 and a validation accuracy of 0.689. An early stopping function is applied to halt training when there is no improvement in validation accuracy. The confusion matrix results indicate that the model adequately classifies data with Accuracy, Recall, and Precision values of 69%, 69%, and 70%, respectively
THE EFFECT OF TEMPERATURE AND ROASTING TIME ON CHANGES IN THE CHARACTERISTICS AND PHYSICAL PROPERTIES OF SOLOK ARABIKA COFFEE BEANS K, Arwizet.; Leni, Desmarita; Peng, Lim Hooi; Sumiati, Ruzita; Kusuma, Yuda Perdana
International Journal of Multidisciplinary Research and Literature Vol. 3 No. 1 (2024): INTERNATIONAL JOURNAL OF MULTIDISCIPLINARY RESEARCH AND LITERATURE
Publisher : Yayasan Education and Social Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53067/ijomral.v3i1.202

Abstract

High-temperature coffee roasting is a key initiator of the degradation of complex compounds in coffee beans, ultimately producing the desired taste and aroma for coffee enthusiasts. The aim of this research is to explore the influence of temperature and roasting duration on the changes in the mechanical properties of coffee beans using the conduction heat method. In this study, 500 grams of dried Arabica coffee with an initial moisture content of 12% were placed in a roasting apparatus equipped with a roasting machine. The heat source used was a gas stove, where the surface temperature of the roasting chamber was kept constant through a thermocouple temperature measuring device. The roasting process was carried out for 15 minutes at surface temperatures of 160°C, 180°C, 200°C, and 220°C, respectively. The final moisture content for each surface temperature was 3.72%, 3.65%, 2.13%, and 1.81%. Identification of the degree of roasting was conducted through the evaluation of the physical properties of coffee beans, including color, weight loss, moisture content, texture, and bean density. The decrease in hardness and density could be modeled using kinetic equations, while the color change was indicated by a decrease in the L, a, and b values. The research results confirm that roasting temperature significantly impacts the changes in the mechanical properties of coffee beans. The minimum temperature required to achieve satisfactory roasting levels is 180°C, while roasting at 200°C for 15 minutes produces coffee beans with optimal roasting levels. These findings provide new insights into optimizing the coffee roasting process to achieve the desired quality of coffee beans
Perancangan Turbin Crossflow untuk Pembangkit Listrik Tenaga Mikro Hidro di Padayo Indarung Padang Hendra, Hendra; Leni, Desmarita; Erawadi, Dedi; Nusyirwan, Nusyirwan; Maimuzar, Maimuzar
JURNAL ILMIAH MOMENTUM Vol 20, No 1 (2024)
Publisher : Universitas Wahid Hasyim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36499/jim.v20i1.10652

Abstract

Perancangan Turbin Crossflow untuk Pembangkit Listrik Tenaga Mikro Hidro di Padayo Indarung Padang merupakan aplikasi praktis dari pengetahuan yang diperoleh selama studi akademik. Tujuan dari penelitian ini adalah merancang turbin crossflow yang sesuai dengan parameter awal yang diperoleh dari survei lapangan. Turbin crossflow berfungsi mengkonversi energi potensial air menjadi energi mekanik yang menggerakkan turbin, kemudian diubah menjadi energi listrik. Berdasarkan data awal perancangan, dengan debit air 0,04 m3/s dan ketinggian air 5 m, dimensi turbin yang didapatkan adalah diameter luar runner 0,3 m, lebar runner 0,15 m, diameter dalam runner 0,2 m, dengan 18 sudu dan jari-jari kelengkungan sudu 48,13 mm. Putaran yang dihasilkan turbin adalah 296,72 rpm. Poros runner memiliki diameter Ø34 mm dan panjang 470 mm. Untuk mentransmisikan daya dari turbin ke generator, digunakan dua buah puli dengan diameter Ø16 inchi dan Ø3 inchi, serta 2 sabuk V type A79. Metode yang digunakan dalam penelitian ini adalah perancangan turbin crossflow berdasarkan parameter hidrokinetik dan dimensi yang disesuaikan dengan karakteristik aliran air yang tersedia di lokasi penelitian. Penelitian ini penting karena memberikan kontribusi dalam pengembangan teknologi energi terbarukan dengan memanfaatkan sumber daya air secara efisien dan ramah lingkungan.
Analisis Exergoeconomic Pada Kompresor Gas Engine Siklus Miller Berbahan Bakar Pome Fajri, Ahmad Hasnul; Adriansyah, Adriansyah; Mayana, Hendri Candra; Leni, Desmarita
Jurnal Teknik Mesin Vol 17 No 2 (2024): Jurnal Teknik Mesin
Publisher : Politeknik Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/jtm.17.2.1636

Abstract

Energy efficiency is a crucial challenge in energy resource management. One innovative approach to improving efficiency is through exergy and exergoeconomic analysis. Exergy analysis considers not only the quantity of energy but also its quality, based on the second law of thermodynamics. Meanwhile, exergoeconomic analysis integrates exergy analysis with economic aspects, such as cost calculations. This study uses the Tandun Biogas Power Plant (PLTBg) as a case study to evaluate energy efficiency and operational costs. The analysis begins with the collection of economic data, including investment costs, fixed operation and maintenance (OM) costs, and variable OM costs.The results show that the investment cost is $0.016/kWh, fixed OM costs are $0.030/kWh, and variable OM costs are $0.009/kWh. The cost losses due to exergy destruction before the overhaul of the gas engine were recorded at $127.23/hour, with contributions from each component as follows: combustion chamber ($51.63/hour), compressor ($21.62/hour), and turbocharger ($53.98/hour). After the overhaul, the total cost losses significantly decreased to $3.3752/hour, with detailed losses from the combustion chamber ($1.168/hour), compressor ($2.193/hour), and turbocharger ($0.0142/hour). This study demonstrates that exergy and exergoeconomic analysis can identify significant opportunities to improve energy efficiency and reduce operational costs in biogas-based power plants. This approach serves as a practical guideline for optimizing energy systems in the renewable energy industry sector.
Predictive Modeling For Low Alloy Steel Mechanical Properties: A Comparison Of Machine Learning Algorithms And Parameter Optimization Leni, Desmarita; Putri Utami, Lega; Sumiati, Ruzita; Camim, Moh.; Khan, Sharif
IJIMCE : International Journal of Innovation in Mechanical Construction and Energy Vol. 1 No. 1 (2024): IJIMCE : International Journal of Innovation in Mechanical Construction and Ene
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ijimce.v1i1.7

Abstract

The development of machine learning in predicting the mechanical properties of alloy steel has become an important research subject in recent years. This is due to the ability of machine learning to extract complex patterns from large and intricate data, which can be used to understand the relationship between chemical composition, microstructure, and mechanical properties of alloy steel. This research aims to design a machine learning model to predict the mechanical properties of low alloy steel, such as Yield Strength (YS) and Ultimate Tensile Strength (UTS), based on the percentage composition of chemical elements in low alloy steel and the heat treatment applied. The machine learning model in this study consists of 10 input variables and 2 target variables. The research compares the performance of 3 machine learning algorithms, namely Decision Tree (DT), Random Forest (RF), and Artificial Neural Network (ANN). The research findings indicate that the ANN algorithm model performs best in predicting the mechanical properties of low alloy steel. This model has Mean Absolute Error (MAE) values of 16.5 and 19.593 for predicting YS and UTS, Root Mean Square Error (RMSE) values of 19.111 and 22.005, and coefficient of determination (R) values of 0.964 and 0.947 for YS and UTS respectively. The modeling uses the ANN algorithm with an 80% training data and 20% testing data split, and applies the K-Fold Cross Validation method with a value of K=5. The best parameters obtained are a learning rate of 0.001, momentum of 0.1, and a hidden layer neuron count of 9. These results indicate that ANN has great potential in addressing the complexity and variability in material data. The implications of these findings are that the implementation of ANN in manufacturing and material engineering industries can enhance the accuracy and efficiency in material strength prediction processes, which, in turn, can aid in designing and developing better and more durable products.
The Influence of External Cooling Load on the Distribution of Temperature and Humidity in Conditioned Spaces Karudin, Arwizet; Sharma, Jai Kumar; Leni, Desmarita; Abbas, Muhammad Rabiu; Adriansyah, Adriansyah
IJIMCE : International Journal of Innovation in Mechanical Construction and Energy Vol. 1 No. 1 (2024): IJIMCE : International Journal of Innovation in Mechanical Construction and Ene
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ijimce.v1i1.8

Abstract

Air conditioning is not only important for the comfort of occupants in a building but also for various industrial processes. In the air conditioning process, a device called an Air Conditioner (AC) is required. The AC load can originate from inside the room and from outside the room. This study aims to determine the influence of increased cooling load from outside the room on the distribution of temperature and air humidity inside the conditioned room. The method used in this study involved conditioning four rooms. Two rooms of almost the same size were equipped with two AC units each, while the other two rooms used one AC unit each. Temperature and air humidity data inside the rooms were recorded every 20 minutes, as well as the outside air temperature. Dry bulb thermometer (Tdb) and wet bulb thermometer (Twb) were used to record temperature and humidity data, along with an environmeter. The research data were processed using available equations and with the assistance of a psychrometric chart. The research findings revealed that the average distribution of temperature and air humidity in the meeting room and office headroom of the Pertamina DP-LPG Office in Binjai was 20°C-23°C and 59%-65%. For the distribution office and sales service room of the Pertamina Fuel Filling Terminal in Kisaran, the distribution of temperature and air humidity was 25°C-29°C and 62%-66%. From the test results, it can be concluded that the distribution of temperature and air humidity is highly influenced by the capacity of the AC units and the cooling load entering the room.
Design of a Rotary Table Hydroponic System for Agricultural Improvement in Limited Urban Land Predi Maulana Putra; Leni, Desmarita; Muchlisinalahuddin, Muchlisinalahuddin; Hendra, Hendra; Kusuma, Yuda Perdana
IJIMCE : International Journal of Innovation in Mechanical Construction and Energy Vol. 1 No. 1 (2024): IJIMCE : International Journal of Innovation in Mechanical Construction and Ene
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ijimce.v1i1.10

Abstract

This research focuses on the design of a rotary table hydroponic device for effective, efficient, and space-saving plant growth. With machine dimensions of 1570 x 600 x 2360 mm, a frame made of 2 mm thick 30 x 30 mm galvanized hollow steel, and a 1.5 HP electric motor, the machine is engineered to maximize land utilization in hydroponic methods. Stress analysis on the frame reveals maximum and minimum values of 3,631e+01 MPa and 2,064e-03 MPa, respectively, while the safety factor reaches 1,211e+05 and 6,886e+00, surpassing the safety factor range for static loads. The results of this experiment confirm the effectiveness and safety of the design, demonstrating that this rotary table hydroponic device can be optimally utilized in hydroponic plant cultivation.