Food industries in a country depend on the packaging system to preserve the product commonly use the plastic based material. Generally, commercial plastic type for packaging in Indonesia are Polystirine (PS) and Polyvinyl Chlorida (PVC). One of problem in home industries (UKM) especially in food sectoris to find the appropriateand particular packaging for their food products. Vacuum Thermoforming machines commonly used by industries to provide the packaging product. However, the forms and materials for the product are too general. In order to provide specific forms for definite products, small-scale vacuum forming machines produced by other countries can be found in the market. Nevertheless, the price still considered high for a home industrial entrepreneur. This study investigates the appropriate automatic control system for the designed small-scale industrial vacuum forming. The control decision achieved via a software based on LabView through a laptop. Thus, it can be displayed, monitored and also being recorded continuously. The test shows that the heater stable at 20 minutes meanwhile the plastic sheet can be shapedafter 15 minutes heating process.Keywords: Plastic, vacuum forming, home industry, automatic.ABSTRAKIndustri makanan yang jumlahnya cukup besar di Indonesia tidak dapat lepas dari proses pengemasan terutama penggunaan kemasan plastik. Jenis plastik yang banyak digunakan untuk kemasan makanan adalah Polystirine (PS)dan Polyvinyl Chlorida (PVC) yang umumnya dijual bebas di pasar/ toko dengan ukuran yang sudah spesifik. Masalah yang banyak dihadapi oleh industrik kecil menengah (UKM) umumnya adalah kesulitan dalam penggunaan kemasan yang sesuai baik ukuran maupun bentuk dari produknya. Mesin Vacuum Thermoforming seperti yang dimiliki oleh industri untuk produk kemasan umumnya memiliki skala yang besar dan memiliki jenis serta bentuk standar. Sementara mesin dalam skala kecil masih dirasa cukup mahal dari segi biaya karena produk dari negara luar. Karenanya mesin Vacuum Forming otomatis skala UKM dengan biaya yang ekonomis ini sangat penting. Penelitian ini ditujukan untuk melakukan otomatisasi dari karakter pemanas yang digunakan dengan mempertimbangkan posisi optimal agar dicapai unjuk kerja yang optimal dari system yang sudah dibuat. Keputusan dari pengendalian alat dilakukan menggunakan software LabView melalui laptop. Oleh sebab it, data dapat ditampilkan, dimonitor serta disimpan secara langsung dan terus-menerus. Hasil uji fungsi menunjukkan bahwa pemanas bekerja dengan stabil setelah 20 menit sedangkan obyek plastik dapat dibentuk setelah dipanaskan selama 15 menit.Kata kunci: Plastik,,Vacuum Forming, UKM, otomatis.

No abstract

Predictive Maintenance (PdM) is an adoptable worth strategy when we deal with the maintenance business, due to a necessity of minimizing stop time into a minimum and reduce expenses.  Recently, the research of PdM is now begin in utilizing the artificial intelligence by using the machine data itself and sensors. Data collected then analyzed and modelled so that the decision can be made for the near and next future. One of the popular artificial intelligences in handling such classification problem is Support Vector Machines (SVM). The purpose of the study is to detect machine failure by using the SVM model. The study is using database approach from the model of Machine Learning. The data collection comes from the sensors installed on the machine itself, so that it can predict the failure of machine function. The study also to test the performance and seek for the best parameter value for building a detection model of machine predictive maintenance The result shows based on dataset AI4I 2020 Predictive Maintenance, SVM is able to detect machine failure with the accuracy of 80%.

This article focuses on the application of deep learning methods for failure prediction. Failure prediction plays a crucial role in various industries to prevent unexpected equipment failures, minimize downtime, and improve maintenance strategies. Deep learning techniques, known for their ability to capture complex patterns and dependencies in data, are explored in this study. The research employs Multi-Layer Perceptron as deep learning architectures. This model is trained on AI4I 2020 Predictive Maintenance data to develop accurate failure prediction models. Data preprocessing involves cleaning, feature engineering, and normalization to ensure the quality and suitability of the data for deep learning models. The dataset is split into training and testing sets for model development and evaluation. Performance evaluation metrics such as accuracy, ROC, and AUC are utilized to assess the models' effectiveness in predicting failures. The experimental results demonstrate the effectiveness of deep learning methods in failure prediction. The models showcase high accuracy and outperform SVM approaches, particularly in capturing intricate patterns and temporal dependencies within the data. The utilization of Multi-Layer Perceptron architecture further enhances the models' ability to capture long-term dependencies. However, challenges such as the availability of diverse and high-quality data, the selection of appropriate architecture and hyperparameters, and the interpretability of deep learning models remain significant considerations. Interpretability remains a challenge due to the inherent complexity and black-box nature of deep learning models. In conclusion, deep learning method offer significant potential for accurate failure prediction. Their ability to capture complex patterns and temporal dependencies makes them well-suited for analyzing operational and sensor data. Future research should focus on addressing challenges related to data quality, interpretability, and model optimization to further enhance the application of deep learning in failure prediction.

Welding technology is used because besides being easy to use, it can also reduce costs so it is cheaper. Especially for welding repair. From the welding repair the extent to which the strength of GMAW welds can repair components from the molded plastic mold room made of AISI 420 stainless steel. Repair of the print room components using deposit welding is tested using tensile strength and hardness as realization of resistance when holding the rate of liquid plastic entering the print room by 25 to 40 MPa, depending on the plastic viscosity, the precision of the mold and the filling level of the print room. Deposition welding method as a welding repair can affect a procedure to be able to produce a component that is safe and capable of being used in accordance with the provisions. The welding process used is reverse polarity GMAW DC with 125 A current and ER 70 S welding wire diameter 1.2 mm. Test material AISI 420. Tests carried out were tensile test, impact test and hardness test in weld metal, HAZ and base metal. From the Charpy impact test and tensile test obtained the value of welding strength which is close to the strength of the complete object, which is equal to 65%. The energy absorbed by the impact test object with GMAW welding is 5.4 Joule while for the whole test object is 8.1 Joule. The welding tensile strength is 520 MPa compared to the tensile tensile strength of 820 MPa.