Pengembangan Model Fuzzy Tsukamoto untuk Penilaian Kondisi Lingkungan Kerja Fisik dalam Rangka Mencapai Standar K3

Intan Berlianty; Indun Titisariwati; Akmal Ashriyadi

doi:10.59086/jti.v4i3.1294

Authors

Intan Berlianty Universitas Pembangunan Nasional Veteran Yogyakarta
Indun Titisariwati Universitas Pembangunan Nasional Veteran Yogyakarta
Akmal Ashriyadi Universitas Pembangunan Nasional Veteran Yogyakarta

DOI:

https://doi.org/10.59086/jti.v4i3.1294

Keywords:

Physical work environment, Tsukamoto fuzzy logic, decision support system, occupational safety and health (OSH), ergonomics

Abstract

Lingkungan kerja fisik yang tidak sesuai standar K3 menurunkan produktivitas dan membahayakan pekerja. Penelitian ini mengisi celah dengan mengintegrasikan logika fuzzy Tsukamoto ke dalam sistem pendukung keputusan (SPK) untuk evaluasi lingkungan kerja fisik—sebuah pendekatan inovatif yang belum banyak diterapkan dalam konteks K3 industri manufaktur. Tujuannya adalah mengembangkan model evaluasi yang memberikan rekomendasi perbaikan terukur sesuai standar K3. Studi kasus dilakukan di PT. ABC pada proses finishing pengecoran logam. Model fuzzy Tsukamoto dikembangkan dengan tiga variabel input (suhu, pencahayaan, kebisingan) dan satu output (waktu baku), lalu diimplementasikan dalam SPK. Kontribusi utama penelitian ini adalah model yang mampu menangani ketidakpastian data lingkungan dan menghasilkan rekomendasi perbaikan spesifik, berbeda dengan metode konvensional yang deterministik dan kurang adaptif. Hasil menunjukkan kondisi awal (suhu 33,8°C, kebisingan 92 dB) melebihi standar Permenaker No. 5/2018. Model merekomendasikan kondisi optimal: suhu 28,90°C, pencahayaan 131,9 Lux, dan kebisingan 85,02 dB, yang menurunkan waktu baku dari 22,89 menit menjadi 11,39 menit (peningkatan produktivitas 50,3%). Pengujian SPK memperoleh skor performa 9,605/10. Implikasi praktis penelitian adalah tersedianya alat bantu keputusan yang objektif bagi manajemen industri untuk mengevaluasi lingkungan kerja dan mendukung kepatuhan K3 secara sistematis. Model ini efektif dalam memberikan rekomendasi perbaikan berbasis data.

Physical work environments that do not comply with Occupational Health and Safety (OHS) standards can reduce productivity and endanger workers. This study addresses a research gap by integrating Tsukamoto fuzzy logic into a Decision Support System (DSS) for physical work environment assessment—an innovative approach that has not been widely applied in the context of OHS compliance in manufacturing industries. The objective is to develop an evaluation model that provides measurable improvement recommendations in line with OHS standards. A case study was conducted at PT. ABC in the metal casting finishing process. A Tsukamoto fuzzy model was developed with three input variables (temperature, lighting, noise) and one output variable (standard time), then implemented in a DSS. The main contribution of this research is a model capable of handling environmental data uncertainty and generating specific improvement recommendations, distinguishing it from conventional deterministic and less adaptive methods. Results indicate that the initial environmental conditions (temperature 33.8°C, noise 92 dB) exceeded the standards of Minister of Manpower Regulation No. 5 of 2018. The model recommends optimal conditions: temperature 28.90°C, lighting 131.9 Lux, and noise 85.02 dB, which reduces standard time from 22.89 minutes to 11.39 minutes (a 50.3% productivity increase). DSS testing achieved a performance score of 9.605 out of 10. The practical implication of this research is the provision of an objective decision-making tool for industrial management to systematically evaluate work environments and support OHS compliance. The model proves effective in providing data-driven improvement recommendations.

References

Akgün, A. E., Tatar, B., Erdil, O., Keskin, H., & Müceldili, B. (2023). Development and validation of the organizational nostalgia scale and its relationship with affective commitment and organizational discontinuity. Current Psychology, 42(32), 28060–28085. https://doi.org/10.1007/s12144-022-03898-y

Amri, A., Zakaria, M., & Chandra, Y. (2024). Work system improvement model with macro ergonomic analysis and design method approach. Edelweiss Applied Science and Technology, 8(6), 7490–7507. https://doi.org/10.55214/25768484.v8i6.3627

Asgarova, B., Jafarov, E., Babayev, N., Ahmadzada, A., & Abdullayev, V. (2024). Development process of decision support systems using data mining technology. Indonesian Journal of Electrical Engineering and Computer Science, 36(1), 703–714. https://doi.org/10.11591/ijeecs.v36.i1.pp703-714

B, A., & Joseph, G. (2025). Embracing resilience in pharmaceutical manufacturing: “digital twins” – forging a resilient path in the VUCA maze. International Journal of Pharmaceutical and Healthcare Marketing, 19(3), 750–772. https://doi.org/10.1108/IJPHM-03-2024-0024

Balci, S. G., Ersöz, S., Lüy, M., Türker, A. K., & Barişçi, N. (2023). Optimization of indoor thermal comfort values with fuzzy logic and genetic algorithm. Journal of Intelligent and Fuzzy Systems, 45(2), 2305–2317. https://doi.org/10.3233/JIFS-223955

Bastida-Escamilla, E., Elías-Espinosa, M. C., & Nava-Tellez, I. A. (2023). A Decision Support System for Teaching Vehicle Routing. 126–130. https://doi.org/10.1109/ICIET56899.2023.10111461

Cahyadi, B., & Timang, G. A. (2023). Mapping of noise contours due to the production process of bolts and nuts in the production department and residences environment of Pasir Angin Village, Cileungsi, Bogor Regency. In W. Septiani, W. Wahyukaton, R. Maulidya, & D. R. Ningtyas (Eds.), AIP Conference Proceedings (Vol. 2485, Issue 1). American Institute of Physics Inc. https://doi.org/10.1063/5.0110259

Dalle Mura, M., & Dini, G. (2022). Job rotation and human–robot collaboration for enhancing ergonomics in assembly lines by a genetic algorithm. International Journal of Advanced Manufacturing Technology, 118(9–10), 2901–2914. https://doi.org/10.1007/s00170-021-08068-1

Farismana, R., Sholihah, D. N., Pramadhana, D., & Lena, S. (2024). IMPLEMENTASI FUZZY TSUKAMOTO DALAM SISTEM PREDIKSI PANEN PADI DI KABUPATEN INDRAMAYU. Jurnal Teknoif Teknik Informatika Institut Teknologi Padang, 12(2). https://doi.org/10.21063/jtif.2024.v12.2.100-110

Gardashova, L. A., & Mammadova, K. A. (2023). Optimal Implicatıon Based Fuzzy Control System for a Steam Generator. In A. R.A., K. J., P. W., J. M., B. M.B., & S. F. (Eds.), Lecture Notes in Networks and Systems: Vol. 610 LNNS (pp. 234–246). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-25252-5_34

Gazzawe, F., & Alturki, R. (2022). Data Mining and Soft Computing in Business Model for Decision Support System. Scientific Programming, 2022. https://doi.org/10.1155/2022/9147444

Hirashima, K., Okawara, M., Tateishi, S., Eguchi, H., Tsuji, M., Ogami, A., Mori, K., Matsuda, S., Fujino, Y., Hino, A., Ando, H., Muramatsu, K., Mafune, K., Kuwamura, M., Matsugaki, R., Ishimaru, T., Nagata, T., & Igarashi, Y. (2024). Association Between Physical Work Environment During Work From Home and Sleep During the COVID-19 Pandemic: A Prospective Cohort Study in Japan. Journal of Occupational and Environmental Medicine, 66(12), 956–961. https://doi.org/10.1097/JOM.0000000000003216

Inda, I., Rantung, V. P., & Santa, K. (2024). PENERAPAN FUZZY TSUKAMOTO PADA SISTEM IRIGASI SAWAH BERBASIS INTERNET OF THINGS DI KECAMATAN REMBOKEN SULAWESI UTARA. Journal of Innovation And Future Technology (IFTECH), 6(2). https://doi.org/10.47080/iftech.v6i2.3314

Intan Berlianty, & Miftahol Arifin. (2025). Classification of Fatigue Levels of Tofu Industrial Workers Based on MOQS and Cardiovascular Load Variables Using Decision Tree Algorithm. Green Engineering: International Journal of Engineering and Applied Science, 2(3). https://doi.org/10.70062/greenengineering.v2i3.220

Jalali, S. S., & Mohammadi, M. (2024). Point estimation of descriptive univariate process capability indices with allowable limits and uncertain quality measurement method. Journal of Industrial and Production Engineering, 41(7), 591–617. https://doi.org/10.1080/21681015.2024.2351550

Ji, X., Hettiarachchige, R. O., Littman, A. L. E., Lavery, N. L., & Piovesan, D. (2023). Prevent Workers from Injuries in the Brewing Company via Using Digital Human Modelling Technology. Applied Sciences (Switzerland), 13(6). https://doi.org/10.3390/app13063593

Li, J. (2021). Design and Simulation of DC Motor Controller Based on the Fuzzy Control. Journal of Physics: Conference Series, 1861(1). https://doi.org/10.1088/1742-6596/1861/1/012121

Liu, H., Zhou, Y., Zhang, Y., & Su, Y. (2021). A rough set fuzzy logic algorithm for visual tracking of blockchain logistics transportation labels. Journal of Intelligent and Fuzzy Systems, 41(4), 4965–4972. https://doi.org/10.3233/JIFS-189983

Nursubiyantoro, E., & Yulianto, W. W. E. (2019). Desain Lingkungan Kerja Berdasarkan Pendekatan Kesehatan dan Keselamatan Kerja. OPSI, 12(2). https://doi.org/10.31315/opsi.v12i2.3101

Safitri, A., & Berlianty, I. (2023). Analisis Simulasi Keuntungan Perusahaan CPO melalui Intervensi Ergonomi pada Lingkungan Kerja Fisik dalam Proses Produksi. Jurnal Teknik Mesin, Industri, Elektro Dan Informatika (JTMEI) Vol.2, No.2 Juni 2023, 2(2).

Samudra, T., Juhardi, U., Rifqo, M. H., & Darmi, Y. (2024). Implementasi Algoritma Fuzzy Tsukamoto Dalam Menentukan Harga Jual Udang Pada Tambak Udang Desa Linau Kabupaten Kaur P-Issn. Jurnal Media Infotama, 20(1).

Saoudi, K., Ghellab, M. Z., Guesmi, K., & Bdirina, K. (2022). Adaptive Fuzzy Sliding Mode Control of TRMS. 2022 19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022, 1269–1274. https://doi.org/10.1109/SSD54932.2022.9955839

Sari, L. R., Sadi, & Berlianty, I. (2019). Pengaruh Lingkungan kerja Fisik terhadap Produktivitas dengan Pendekatan Ergonomi Makro (Studi Kasus di PT. Murakabi Jaya Mandiri). Jurnal Optimasi Sistem Industri, 12(1).

Ukhti Filla, S., & Kurniawan, R. R. (2024). PROTOTYPE ALAT PENGATUR TEMPERATUR RUANG KERJA PADA RUMAH MENGGUNAKAN LOGIKA FUZZY TSUKAMOTO BERBASIS IOT. In Journal of Science and Social Research (Issue 1).

Wåhlin, C., Sandqvist, J., Enthoven, P., Buck, S., Karlsson, N., & Nilsing-Strid, E. N. (2025). Perceived health, musculoskeletal disorders, work conditions and safety climate in relation to patient handling and movement − a multicentre cross-sectional study at healthcare workplaces. BMC Musculoskeletal Disorders, 26(1). https://doi.org/10.1186/s12891-025-09330-3

Wahlström, V., Öhrn, M., Harder, M., Eskilsson, T., Fjellman-Wiklund, A., & Pettersson-Strömbäck, A. (2024). Physical work environment in an activity-based flex office: a longitudinal case study. International Archives of Occupational and Environmental Health, 97(6), 661–674. https://doi.org/10.1007/s00420-024-02073-z

Zhou, P., Tian, J., Sun, J., Yao, J., Zou, D., & Yu, W. (2021). Research on tool control system of double cutters experimental platform based on fuzzy neural network predictive control. Journal of Intelligent and Fuzzy Systems, 40(1), 65–76. https://doi.org/10.3233/JIFS-182804