Claim Missing Document
Check
Articles

Found 3 Documents
Search

Design, Construction, and Testing of an Electric Wheelchair Operated by Arduino Uno R3 Microcontroller Yusuf Subagyo; Sendie Yuliarto Margen; Baharudin Priwintoko; Fariz Wisda Nugraha; Hartanto Prawibowo
Multidisciplinary Innovations and Research in Applied Engineering Vol. 2 No. 1 (2025)
Publisher : Akademi Inovasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70935/ha1z3r27

Abstract

The research aims to design and develop an electric wheelchair based on the Arduino Uno microcontroller as a mobility solution for individuals with disabilities. A conventional wheelchair was modified by integrating an electric drive system controlled by an analog joystick, which is connected to the Arduino Uno and DC motors via a BTS 760 motor driver. The wheelchair design complies with ISO 7176-5 standards and is adapted to the anthropometric dimensions of Indonesian users. Test results indicate that the control system functions effectively, allowing responsive control of wheelchair movements forward, backward, left, and right according to joystick operation. However, several challenges were encountered during the chain adjustment and gear welding processes, requiring further development to achieve optimal performance. This study demonstrates that utilizing the Arduino Uno as the central control unit enables the production of an electric wheelchair at a more affordable cost.
Optimalisai Mesin Injection Molding Tipe Screw Dengan Produk Klem Pipa Setengah Inci Untuk Mendapatkan Parameter Produksi Dieta Wahyu Asry Ningtias; Trio Setiyawan; Timotius Anggit kritiawan; Fariz Wisda Nugraha; Mulyono; Muhammad Karel Islam
Journal of Mechanical Engineering and Applied Technology Vol. 4 No. 2 (2026): VOLUME 4 ISSUE 2 YEAR 2026 (JULY 2026)
Publisher : Politeknik Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32497/jmeat.v4i2.7696

Abstract

Injection molding is one of the methods used in plastic forming processes. This study aims to optimize the screw-type injection molding machine owned by the Mechanical Engineering Laboratory of xyz, which was previously developed by xyz students. However, the machine had several deficiencies, such as barrel leakage, imperfect feeding in the hopper, unstable heating, and only one mold variation, namely a keychain mold. These issues reduced production efficiency.To overcome these problems, the machine was optimized by replacing and redesigning components such as the screw, barrel, nozzle, transmission system, and by adding a new mold variation for a half-inch pipe clamp. The method involved redesigning and testing based on operational parameters, including feeding temperature, injection temperature, injection time, and cooling time.Testing was conducted by setting the feeding temperature to 220°C, injection temperature between 290°C and 310°C, injection time between 11 and 13 seconds, and cooling time of 15 seconds. The material used was polypropylene (PP). The results showed that the optimal parameters were a feeding temperature of 220°C, injection temperature of 310°C, injection time of 12 seconds, and cooling time of 15 seconds. The resulting product exhibited good quality, with complete filling, no flash, and smooth surface finish. This indicates that the optimized screw-type injection molding machine successfully resolved the previous issues.
Performance Enhancement of 2D CNN-Based Visual Inspection Using Data Augmentation for Defect Classification in Metal Casting Products Imaduddien Ariefa; Hutomo Jiwo Satrio; Della Kumalaningrum; Rieky Handoko; Anton Harseno; Fariz Wisda Nugraha
Jurnal Rekayasa Mesin Vol. 20 No. 3 (2025): Volume 20, Nomor 3, December 2025
Publisher : Mechanical Engineering Department - Semarang State Polytechnic

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32497/jrm.v20i3.7170

Abstract

Deep learning-based automated visual inspection has become increasingly important for reducing the subjectivity and mistakes that come with manual inspection.  However, when the image dataset is small, Convolutional Neural Networks (CNN) often do not perform optimally because the model overfits and fails to generalize effectivelyl.  This study investigates the effect of data augmentation on enhancing the performance of an AlexNet-based CNN model for classifying defect and non-defect casting images.  There were 13266 grayscale images in total, and they were divided into two groups: defect and non-defect.  To increase data variability, several augmentation techniques were used, such as rotation, flipping, zooming, and brightness adjustment.  We evaluated two different training scenarios: training a model without adding anything and training a model with adding something.  We used accuracy, precision, recall, F1-score, validation loss, and confusion matrix analysis to evaluate model perfomance.  The findings demonstrate that data augmentation significantly improves model performance.  The validation loss decreased from 0.019747 to 0.014853, and the accuracy, precision, recall, and F1-score all showed slight improvements.  The enhanced model also achieved higher true positive and true negative values, signifying improved recognition proficiency.  Tests on previously unseen samples yielded 100% correct predictions, indicating enhanced generalization.  To sum up, data augmentation is an effective strategy for mitigating small datset limitations and improving the reliability of CNN-based visual inspection systems in industrial environments.