Pemodelan Prediksi Temperatur Freezer Menggunakan Pendekatan Machine Learning Berbasis Framework TensorFlow

Ahmad Davi; Farkhan Jatmiko  Sidiq; Muhammad Aziz Arrizal; Fahrizal Agil Wibowo; Taopik Sendy Gunawan; Andini Nur Aisyah; Alif Nur Hidayat

doi:10.35261/gijtsi.v5i02.12524

Penulis

Ahmad Davi Program Studi Teknik Mesin, Universitas Singaperbangsa Karawang
Farkhan Jatmiko Sidiq Program Studi Teknik Mesin, Universitas Singaperbangsa Karawang
Muhammad Aziz Arrizal Program Studi Teknik Mesin, Universitas Singaperbangsa Karawang
Fahrizal Agil Wibowo Program Studi Teknik Mesin, Universitas Singaperbangsa Karawang
Taopik Sendy Gunawan Program Studi Teknik Mesin, Universitas Singaperbangsa Karawang
Andini Nur Aisyah Program Studi Teknik Kimia, Universitas Singaperbangsa Karawang
Alif Nur Hidayat Program Studi Teknik Mesin, Universitas Singaperbangsa Karawang

DOI:

https://doi.org/10.35261/gijtsi.v5i02.12524

Abstrak

Pengendalian temperatur dalam freezer sangat penting untuk menjaga kualitas dan keamanan produk, terutama di industri makanan dan farmasi. Fluktuasi temperatur yang tidak terkontrol dapat menyebabkan kerusakan produk, meningkatkan pemborosan, dan menurunkan kualitas. Teknologi machine learning menawarkan solusi yang efektif untuk memprediksi dan mengendalikan temperatur, memungkinkan pemantauan yang lebih akurat dan respons yang cepat terhadap perubahan kondisi. Penelitian ini bertujuan mengembangkan model machine learning menggunakan framework TensorFlow untuk memprediksi temperatur dalam freezer. Data temperatur dikumpulkan dari sensor-sensor yang dipasang di dalam freezer dan digunakan untuk melatih serta menguji beberapa arsitektur model machine learning, termasuk long short-term memory (LSTM) dan Convolutional 1D (Conv1D). Pengembangan model menggunakan TensorFlow memanfaatkan fitur canggih yang memungkinkan pembuatan, pelatihan, dan pengujian model secara efisien. Hasil penelitian menunjukkan bahwa model Conv1D dengan komposisi data 90% data latih, 5% data validasi, dan 5% data uji menghasilkan prediksi terbaik dengan nilai RMSE uji sebesar 0,02085°C, dan nilai MAPE uji sebesar 0,33522%. Model prediksi ini berpotensi digunakan sebagai sistem peringatan dini untuk mencegah kerusakan produk. Penelitian ini diharapkan memberikan kontribusi signifikan dalam pengembangan sistem pemantauan dan kontrol temperatur yang lebih efisien di freezer, dengan penerapan potensial dalam berbagai industri, termasuk makanan dan farmasi. Hasil penelitian juga memperkuat potensi besar penerapan machine learning dalam prediksi serta pemantauan lingkungan.

Unduhan

Data unduhan belum tersedia.

Referensi

Y. Hu dan B. Shen, “Experimental insights into thermoelectric freezer systems: Feasibility and efficiency,” Energy Convers. Manag. X, vol. 23, no. June, 2024, doi: 10.1016/j.ecmx.2024.100676.

P. Yang dkk., “Performance improvement of a household freezer with a microchannel flat-tube evaporator,” Case Stud. Therm. Eng., vol. 49, no. August, 2023, doi: 10.1016/j.csite.2023.103394.

J. Liu dan Y. Liu, “Experimental investigation of a bypass two-circuit cycle refrigerator-freezer with low GWP zeotropic refrigerants,” Case Stud. Therm. Eng., vol. 54, no. January, 2024, doi: 10.1016/j.csite.2024.104071.

O. Surucu, S. A. Gadsden, dan J. Yawney, “Condition Monitoring using Machine Learning: A Review of Theory, Applications, and Recent Advances,” Expert Syst. Appl., vol. 221, no. October 2021, 2023, doi: 10.1016/j.eswa.2023.119738.

S. Russel dan P. Norvig, Artifical Intelligence: A Modern Approach, 4 th. Cambridge: e press synd icate o f the un ivers ity o f cambr idge, 2021.

M. A. Alrowaily, O. Alruwaili, M. Alghamdi, M. Alshammeri, M. Alahmari, dan G. Abbas, “Application of extreme machine learning for smart agricultural robots to reduce manoeuvering adaptability errors,” Alexandria Eng. J., vol. 109, no. May, hal. 655–668, 2024, doi: 10.1016/j.aej.2024.09.062.

M. Dorraki dkk., “Improving Cardiovascular Disease Prediction With Machine Learning Using Mental Health Data: A Prospective UK Biobank Study,” JACC Adv., vol. 3, no. 9, 2024, doi: 10.1016/j.jacadv.2024.101180.

R. Novella, B. Pla, P. Bares, dan A. Aramburu, “Identification of Adequate Combustion in Turbulent Jet Ignition Engines using Machine Learning Algorithms,” hal. 102–107, 2021, doi: https://doi.org/10.1016/j.ifacol.2021.10.148.

R. Akbar, R. Santoso, dan B. Warsito, “Prediksi Tingkat Temperatur Kota Semarang Menggunakan Metode Long Short-Term Memory (Lstm),” J. Gaussian, vol. 11, no. 4, hal. 572–579, 2023, doi: 10.14710/j.gauss.11.4.572-579.

H. Yang, S. Yoon, H. T. Lee, K. S. Kim, H. J. Han, dan Y. J. Park, “Abnormal high water temperature prediction in nearshore waters around the Korean Peninsula using ECMWF ERA5 data and a deep learning model,” J. Sea Res., vol. 202, no. September, 2024, doi: 10.1016/j.seares.2024.102546.

Y. B. Kebede, M. Der Yang, dan C. W. Huang, “Real-time pavement temperature prediction through ensemble machine learning,” Eng. Appl. Artif. Intell., vol. 135, no. November 2023, 2024, doi: 10.1016/j.engappai.2024.108870.

X. Gu, W. Lei, J. Xi, dan M. Song, “Structural optimization and battery temperature prediction of battery thermal management system based on machine learning,” Case Stud. Therm. Eng., vol. 62, no. September, 2024, doi: 10.1016/j.csite.2024.105207.

A. Augusto dkk., “A novel seaweed-based biodegradable and active food film to reduce freezer burn in frozen salmon,” Food Hydrocoll., vol. 156, no. June, 2024, doi: 10.1016/j.foodhyd.2024.110332.

H. Jouhara dkk., “Low-temperature heat transfer mediums for cryogenic applications mid InfraRed Instrument,” J. Taiwan Inst. Chem. Eng., vol. 148, no. January, hal. 104709, 2023, [Daring]. Tersedia pada: https://doi.org/10.1016/j.jtice.2023.104709

Q. Xu, B. Deng, Y. Wang, W. Liu, dan G. Chen, “Small, affordable, ultra-low-temperature vapor-compression and thermoelectric hybrid freezer for clinical applications,” Cell Reports Phys. Sci., vol. 4, no. 12, 2023, doi: 10.1016/j.xcrp.2023.101735.

D. Eriksson dkk., “Survival of Campylobacter jejuni in frozen chicken meat and risks associated with handling contaminated chicken in the kitchen,” Food Control, vol. 145, no. June 2022, 2023, doi: 10.1016/j.foodcont.2022.109471.

J. Ullah, P. S. Takhar, dan S. S. Sablani, “Effect of temperature fluctuations on ice-crystal growth in frozen potatoes during storage,” Lwt, vol. 59, no. 2P1, hal. 1186–1190, 2014, doi: 10.1016/j.lwt.2014.06.018.

S. S. Sorour, C. A. Saleh, dan M. Shazly, “A review on machine learning implementation for predicting and optimizing the mechanical behaviour of laminated fiber-reinforced polymer composites,” Heliyon, vol. 10, no. 13, 2024, doi: 10.1016/j.heliyon.2024.e33681.

Y. G. Lv, Y. T. Wang, T. Meng, Q. W. Wang, dan W. X. Chu, “Review on thermal management technologies for electronics in spacecraft environment,” Energy Storage Sav., vol. 3, no. 3, hal. 153–189, 2024, doi: 10.1016/j.enss.2024.03.001.

L. Wiranda dan M. Sadikin, “Penerapan Long Short Term Memory pada Data Time Series untuk Memprediksi Penjualan Produk PT. Metiska Farma,” J. Nas. Pendidik. Tek. Inform., vol. 8, no. 3, hal. 184–196, 2019.

F. Le Peng, Y. K. Qiao, dan C. Yang, “A LSTM-RNN based intelligent control approach for temperature and humidity environment of urban utility tunnels,” Heliyon, vol. 9, no. 2, 2023, doi: 10.1016/j.heliyon.2023.e13182.

I. Elafi, N. Zrira, A. Kamal-Idrissi, H. A. Khan, dan A. Ettouhami, “STA-SST: Spatio-temporal time series prediction of Moroccan Sea surface temperature,” J. Sea Res., vol. 200, no. May, 2024, doi: 10.1016/j.seares.2024.102515.

M. H. Zafar, S. M. S. Bukhari, M. A. Houran, M. Mansoor, N. M. Khan, dan F. Sanfilippo, “DeepTimeNet: A novel architecture for precise surface temperature estimation of lithium-ion batteries across diverse ambient conditions,” Case Stud. Therm. Eng., vol. 61, no. February, 2024, doi: 10.1016/j.csite.2024.105002.

M. W. Liemohn, A. D. Shane, A. R. Azari, A. K. Petersen, B. M. Swiger, dan A. Mukhopadhyay, “RMSE is not enough: Guidelines to robust data-model comparisons for magnetospheric physics,” J. Atmos. Solar-Terrestrial Phys., vol. 218, no. March, 2021, doi: 10.1016/j.jastp.2021.105624.

Z. Mustaffa dan M. H. Sulaiman, “Battery remaining useful life estimation based on particle swarm optimization-neural network,” Clean. Energy Syst., vol. 9, no. May, 2024, doi: 10.1016/j.cles.2024.100151.

A. Hightower, A. Ziedan, J. Guo, X. Zhu, dan C. Brakewood, “A comparison of time series methods for post-COVID transit ridership forecasting,” J. Public Transp., vol. 26, no. May, 2024, doi: 10.1016/j.jpubtr.2024.100097.

T. Zhang, Y. Pan, L. Huang, dan X. Zhong, “An empirical study of combinational load forecasting in a city power company of China,” Energy Reports, vol. 11, no. December 2023, hal. 637–650, 2024, doi: 10.1016/j.egyr.2023.12.015.