Garuda - Garba Rujukan Digital

The hybrid design of supervised learning algorithm for design and development in classifications a defect in clay tiles Prasetio, Murman Dwi; Xavier, Rais Yufli; Rachmat, Haris; Wiyono, Wiyono; Atmaja, Denny Sukma Eka
International Journal of Industrial Optimization Vol 2, No 2 (2021)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/ijio.v2i2.4449

The strength of the company's competitiveness is needed because the current industrial development is very rapid. It is necessary to maintain the quality and quantity of the products produced according to company standards. Â One of the companies that must maintain the quality and quantity is PT. XYZ is a clay tile company. The classification of products used by this company to maintain good quality is three classes: good tile, white stone tile, and cracked tile. However, quality control based on classification still uses the traditional way by relying on sight. Â It can increase errors and slow down the process. It can be overcome with artificial visual detectors. It is a result of the rapid development of automation. So to detect defects, this research can use image preprocessing, supervised learning algorithms, and measurement methods. Â Support Vector Machine (SVM) is used in this study to perform classification, while feature extraction on clay tiles used the Local Binary Pattern (LBP) method. The algorithm is made using python, while for image retrieval, raspberry pi is used. The linear kernel on the SVM algorithm is used in this study. The conclusion in this study obtained 86.95% is the highest accuracy with a linear kernel. It takes 10.625 seconds to classify.

Rancang Bangun Klasifikasi Cacat Pada Genting Menggunakan Metode Support Vector Machine (SVM) Rais Yufli Xavierullah; Murman Dwi Prasetio; Denny Sukma Eka Atmaja
JRSI (Jurnal Rekayasa Sistem dan Industri) Vol 7 No 02 (2020): Jurnal Rekayasa Sistem & Industri - Desember 2020
Publisher : School of Industrial and System Engineering, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jrsi.v7i2.420

Pengendalian kualitas merupakan suatu sistem yang dapat membantu suatu perusahaan dalam menjaga dan mempertahankan kualitas produk agar tidak adanya terjadi cacat produk. PT. XYZ merupakan salah satu perusahaan yang berada pada bidang industri genting tanah liat. Pada setiap bulannya PT. XYZ memiliki pengembalian produk karena cacat dengan rata-rata 2225 genting. Salah satu masalah yang terjadi pada PT. XYZ yaitu proses inspeksi yang hanya mengunakan penglihatan. Penggunaan penglihatan dapat memiliki risiko seperti peningkatan biaya operasi karena pemeriksaan yang salah, kegagalan mendapatkan bisnis, dan pengerjaan ulang. Dengan perkembangan tekhnologi dapat mengatasi hal tersebut dengan ditemukannya pendeteksi bersifat buatan dengan menggunakan metode pengukuran, preprocessing gambar, dan algoritma dalam mendeteksi cacat tersebut. Pada penelitian ini menggunakan metode Support Vector Machine (SVM) dalam melakukan pengklasifikasian cacat. Pengambilan gambar secara langsung pada penelitian ini menggunakan raspberry pi dan pembuatan sistem algoritma menggunakan software pyhton. Penelitian ini menggunakan kernel linear pada algoritma SVM. Hasil pada penelitian ini menyimpulkan bahwa tingkat akurasi tertinggi yaitu 88,6% dengan menggunakan kernel linear.

OPTIMASI PROSES PENGUKURAN DIMENSI DAN DEFECT UBIN KERAMIK MENGGUNAKAN PENGOLAHAN CITRA DIGITAL DAN FULL FACTORIAL DESIGN Denny Sukma Eka Atmaja Muhammad Kusumawan Herliansyah
Jurnal Teknosains Vol 4, No 2 (2015): June
Publisher : Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/teknosains.7972

Theinspection process of surface quality of ceramic tile could be done by using image processing technique throughthe optimization by using Center for Ceramics’s parameteron Indonesian National Standard (SNI) ISO 10545.This research will analyze from light intensities (level 300lx, 600lx, and 900lx), and camera distances (50cm, 75cmand 100cm), with three times replication using full factorial design. This research uses Matlab 2009a softwareto identify area and defect on dry spots ceramic tile’s surface. The result obtained from this research is there weresignificant influencing factors: light intensity, and camera distance, as well as the interaction of these factorstowards the error rate percentage of measuring areaand defect on ceramic tile’s surface. The smallest error ratevalue from measuring tile’s surface and diameter of dry spots with light intensity of 300lx and camera distance of50cm had been obtained the error rate value for each measurement about 0.0675% and 2.30%, with combinationof grayscale value for the error rate measurements of tile’s surface and diameter of dry spots were 0.2989 x 0.1140x R + G+0.5870 x B. Based on the correlation coefficient value between light intensity, camera distance towardsthe error rate of measuring areaand defect on tile’s surface, each of them was obtained correlation coefficient valueof camera distance with error rate had 0.518 and 0.516, which meant a strong correlation. The positive correlationcoefficient value showed a unidirectional relationship of two variables, where the rise of one variable would causethe rise of another variable and the decline of one variable would cause the decline of another variable.

Optimasi Parameter Pengukuran Dimensi dan Defect Ubin Keramik dengan Metode Taguchi Denny Sukma Eka Atmaja; Muhammad Kusumawan Herliansyah
Jurnal Sistem Cerdas Vol. 4 No. 3 (2021)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v4i3.182

The ceramics industry in Indonesia has a large contribution to the growth of various aspects in Indonesia. But in reality, there is still an imbalance between exports and imports for ceramic products. One way is to improve the quality of the ceramic industry in Indonesia. In fact, the ceramic quality inspection process in the ceramic industry is still done manually which can make mistakes in identifying defects. In this study, the design of variable identification system of ceramics was carried out specifically in the area of ceramics and dry spot defects on ceramic surfaces using image processing. Whereas to get a low error rate against the applicable variables, a design of experiment with the Taguchi approach is carried out. The results show that 50 cm distance, 300 lux light, 1x resize and 0.06 threshold can produce an image that has the smallest error value when identifying ceramic area and dry spot defects on the ceramic surface.

The hybrid design of supervised learning algorithm for design and development in classifications a defect in clay tiles Murman Dwi Prasetio; Rais Yufli Xavier; Haris Rachmat; Wiyono Wiyono; Denny Sukma Eka Atmaja
International Journal of Industrial Optimization Vol. 2 No. 2 (2021)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/ijio.v2i2.4449

The strength of the company's competitiveness is needed because the current industrial development is very rapid. It is necessary to maintain the quality and quantity of the products produced according to company standards. Â One of the companies that must maintain the quality and quantity is PT. XYZ is a clay tile company. The classification of products used by this company to maintain good quality is three classes: good tile, white stone tile, and cracked tile. However, quality control based on classification still uses the traditional way by relying on sight. Â It can increase errors and slow down the process. It can be overcome with artificial visual detectors. It is a result of the rapid development of automation. So to detect defects, this research can use image preprocessing, supervised learning algorithms, and measurement methods. Â Support Vector Machine (SVM) is used in this study to perform classification, while feature extraction on clay tiles used the Local Binary Pattern (LBP) method. The algorithm is made using python, while for image retrieval, raspberry pi is used. The linear kernel on the SVM algorithm is used in this study. The conclusion in this study obtained 86.95% is the highest accuracy with a linear kernel. It takes 10.625 seconds to classify.

Perancangan Electronic Kanban Menggunakan Metode Constant Quantity Withdrawal System untuk Mengurangi Keterlambatan pada Assembly Junction di PT Dirgantara Indonesia Puput Nidaul Choiriyah; Denny Sukma Eka Atmaja; Widia Juliani
Performa: Media Ilmiah Teknik Industri Vol 20, No 2 (2021): Performa: Media Ilmiah Teknik Industri
Publisher : Industrial Engineering Study Program, Faculty of Engineering, Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/performa.20.2.53211

PT Dirgantara Indonesia merupakan salah satu perusahaan milik Negara yang bergerak dalam bidang kedirgantaraan. Saat ini perusahaan sedang mengalami permasalahan pada keterlambatan dalam pengiriman Tailboom. Tailboom merupakan ekor dari helicopter. Permasalahan ini disebabkan karena keterlambatan pada salah satu komponen Tailboom yaitu Junction. Komponen Junction mengalami keterlambatan pada proses assembly dikarenakan kekurangan part di assembly line. Kekurangan part disebabkan karena tidak lengkapnya work package yang dikirimkan dari fabrikasi. Untuk mengatasi keterlambatan pada assembly Junction dibutuhkan sistem kontrol produksi yang berupa Kanban. Kanban merupakan tools dari Just In Time untuk sistem produksi tarik atau pull system. Dengan menggunakan kanban dapat mengontrol aliran produksi sesuai quantity yang dibutuhkan dan waktu yang tepat. Hasil dari penelitian ini adalah perancangan sistem Electronic Kanban menggunakan metode constant quantity withdrawal system yang diimplementasikan di area fabrikasi, assembly store dan assembly line. Hasil simulasi dengan menggunakan electronic kanban pada assembly Junction mampu mengurangi keterlambatan sebesar 56% yang disebabkan karena factor part. Hal ini disebabkan karena level stock di departemen assembly store dapat terjaga, kemudian material dan kapasitas pada fabrikasi memenuhi.Selain itu, electronic kanban memberikan informasi antar departemen saling terintegrasi sehingga mudah diketahui kesalahan yang terjadi secara realtime. Dengan demikian production control dapat mengambil kebijakan terkait permasalahan yang dideteksi. Electronic kanban dapat menginformasikan apa, berapa, dan kapan harus memproduksi part atau komponen.

Optimasi Multi-Objektif Proses Pemesinan Milling dengan Metode Taguchi Kolaborasi Grey Relational Analysis Nadila Attin Miftah; Denny Sukma Eka Atmaja; Ayudita Oktafiani
Jurnal Sistem Cerdas Vol. 5 No. 2 (2022)
Publisher : APIC

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

This research focus on multi-objective optimization to minimize surface roughness and maximize material removal rate (MRR) on aluminum alloy 6061 T6. The experiment was designed based on the L9 orthogonal array and was carried out by milling machining process. The input parameters selected from the milling machining conditions are spindle speed, feed rate, and depth of cut. The responses obtained from these experiments are surface roughness and material removal rate. To achieve these two objectives simultaneously, the Taguchi method collaboration with of gray relational analysis can be used. The effect of cutting parameters on surface roughness and MRR can be determined using ANOVA and interaction plots. The optimal parameters to achieve minimum surface roughness and maximum MRR are the combination of a spindle speed of 600 rpm, a feed rate of 50 mm/min, and a depth of cut of 0.7 mm.

Pelatihan Google Classroom pada Guru SDITQ Imam Malik Bandung untuk Mendukung Pembelajaran Daring pada Masa Pandemi Covid-19 Ayudita Oktafiani; Murni Dwi Astuti; Denny Sukma Eka Atmaja
Charity : Jurnal Pengabdian Masyarakat Vol 5 No 2a (2022): Special Issue
Publisher : PPM Universitas Telkom

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/charity.v5i2a.5109

Pada masa pandemi Covid-19, pelaksanaan pembelajaran daring di SDITQ Imam Malik memanfaatkan aplikasi Whatsapp dan Google Form. Pemanfaatan teknologi tersebut belum mampu mengoptimalkan interaksi siswa dengan guru. Terdapat sebuah platform pembelajaran daring yang memberikan solusi untuk kondisi tersebut yaitu Google Classroom. Akan tetapi, pengetahuan dan pemahaman terkait platform pembelajaran tersebut belum merata pada seluruh guru di sekolah tersebut. Kegiatan pengabdian kepada masyarakat ini bertujuan memberikan pelatihan platform Google Classroom kepada guru di SDITQ Imam Malik agar dapat mengembangkan metode pembelajaran daring yang lebih interaktif. Selain itu, guru dapat menyimpan konten pembelajaran digital pada platform tersebut serta adanya kemudahan bagi siswa dan guru dalam bertukar pesan, yang menjadikan proses pembelajaran lebih interaktif.

Optimizing Woven Fabric Defect Classification For Inspection Using Image Processing And Artificial Neural Network At Cv. Maemunah Majalaya Nur Endah Lizarifin; Haris Rachmat; Denny Sukma Eka Atmaja
eProceedings of Engineering Vol 3, No 2 (2016): Agustus, 2016
Publisher : eProceedings of Engineering

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

CV. Maemunah Majalaya is one of Textile Industry in Indonesia, they produce woven fabrics which will be exported to Japan. To maintain the quality it needs quality control such as inpection process. The inspection process of woven fabric still using traditional method that makes unbalance between inspection capacity and production volume. The production volume of fabric is more than 20.000 meters of fabric that should be produced every week but there is just four inspection station with two person in each station and the capacity of each station is 23 s prescreen. It caused the massive bottleneck in inspection station it is affect to the time for management to deciding strategy for fulfilling order just in time and shipment delays. In this research automation system with image processing technique and artificial neural network were used to optimize inspection process by decreasing inspection time and increasing the detection rate. Neural network models are preferred for image-understanding tasks because of their parallel-processing capabilities as well as learning and decision making abilities. The input for neural network model is come from the GLCM and edge feature extraction. The purposed method provide better result in classifying fabric defect. Using 90 data that divided into data test, data training and validation provide overall accuracy 83.9% and average processing time 3.4 second. Therefore, using automated fabric inspection can decrease process time 16 second. Keywords : Textile Industry, Inspection Process, Automation, Image Processing, Genetic Artificial Neural Network, GLCM Feature Extraction.

Optimasi Sensor Kamera Pada Proses Identifikasi Warna Dengan Pengolahan Citra Menggunakan Design Of Experiment Di Pt. Abbott Indonesia David Simangunsong; Dida Diah Damayanti; Denny Sukma Eka Atmaja
eProceedings of Engineering Vol 3, No 2 (2016): Agustus, 2016
Publisher : eProceedings of Engineering

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

Kamera merupakan salah satu sensor dari robot. Kamera sangat sensitif terhadap faktor lingkungan yang sering berubah-ubah, sehingga dibutuhkan suatu penelitian terhadap faktor yang berpengaruh pada kinerja kamera dan pengaturan kombinasi faktor untuk meminimalkan error rate dalam mengidentifikasi citra. Untuk menyelesaikannya dibutuhkan tahap design of experiment dengan pendekatan Taguchi menggunakan deteksi warna HSV pada pengolahan citra. Kelebihan metode Taguchi ialah mampu meminimalkan akibat dari variasi terhadap respon serta eksperimen dapat dilakukan dengan efisien. Sedangkan deteksi warna HSV memiliki dimensi warna yang cukup bervariasi. Analisa data dilakukan berdasarkan karakteristik â€œsmaller is betterâ€ dari Signal to Noise Ratio (S/N), uji normalitas, dan analisis varians (ANOVA). Hasil analisa terhadap rasio S/N pada palet berwarna merah optimal dengan kombinasi faktor resize (120%) dengan nilai rasio S/N sebesar 13,774, resolusi kamera (2MP) dengan nilai sebesar 12,475, jarak kamera (12 cm) dengan nilai sebesar 13,572 dan kontras (1,7) dengan nilai sebesar 2,785. Kata kunci : Pengolahan citra, segmentasi warna, HSV, design of experiment, Taguchi

Title

Found 43 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 43 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 43 Documents
Search