Optimasi Line Balancing Adaptif dan Deteksi Bottleneck Berbasis Computer Vision dengan Mempertimbangkan Variabilitas Kinerja Operator
Downloads
Industri garmen menghadapi tantangan efisiensi akibat sifatnya yang padat karya dan variabilitas kinerja operator. Metode penyeimbangan lini (line balancing) manual yang ada saat ini seringkali statis dan gagal menangkap fluktuasi waktu nyata di lantai produksi. Sementara itu, solusi berbasis sensor fisik (wearable/IoT) dinilai mahal dan invasif. Penelitian ini mengusulkan pendekatan hibrida menggunakan Computer Vision sebagai sensor virtual dan algoritma Optimasi Robust. Tujuannya adalah mendeteksi bottleneck secara real-time dan memberikan rekomendasi penyeimbangan tenaga kerja yang tangguh terhadap variabilitas. Metode yang digunakan adalah Design Science Research (DSR) dengan studi kasus di PT. Fukuryo Indonesia. Sistem mengekstraksi fitur kinematik operator menggunakan MediaPipe Pose dan mengklasifikasikan aktivitas kerja. Hasil akhir berupa kerangka kerja sistem cerdas yang mampu meminimalkan waktu menganggur (idle time) dan risiko lintasan akibat ketidakpastian kinerja manusia. Kerangka kerja sistem yang diusulkan menawarkan solusi non-invasif, hemat biaya, dan responsif untuk mengatasi masalah variabilitas operator dalam line balancing di industri garmen. Sistem ini berpotensi meningkatkan efisiensi lini produksi melalui deteksi dini bottleneck dan rekomendasi penyeimbangan yang adaptif, sehingga mendukung pengambilan keputusan manajerial yang lebih akurat dan proaktif.
Aslan, Ayse, El-Raoui, Hanane, Hanson, Jack, Vasantha, Gokula, Quigley, John, Corney, Jonathan, & Sherlock, Andrew. (2023). Using worker position data for human-driven decision support in labour-intensive manufacturing. Sensors, 23(10), 4928.
Ashraf, M., et al. (2024). Ensemble Deep Learning Framework for Monitoring of Garment Sewing Employee Added Value. 2024 Intelligent Methods, Systems, and Applications (IMSA).
Bandara, D. T., & Senanayake, C. (2024). Digital Twin Technology in Apparel Industry: Potential for Rebalancing of Manual Assembly Lines. 2024 Moratuwa Engineering Research Conference (MERCon).
Chauhan, R., Dhyani, I., & Vaidya, H. (2023). A Review on Human Pose Estimation Using Mediapipe. 2023 International Conference on Intelligent Systems and Control Techniques (CISCT).
Hashemi Petroodi, S. E., et al. (2025). Robust multi-manned mixed-model assembly line balancing with dynamic task assignment considering product mix uncertainty. International Journal of Production Economics, 279, 109756.
Jung, W.-K., et al. (2021). Simulation-Based Hybrid Optimization Method for the Digital Twin of Garment Production Lines. Journal of Computing and Information Science in Engineering, 21(3).
Kasarapu, S. S. K., et al. (2024). Safer and efficient assemblies: Harnessing real time worker movements with digital twins. MATEC Web of Conferences, 401.
Li, F., Zhang, J., & Huang, H. (2020). Spatial-Temporal Zoning Methods for Real-Time Action Recognition in Manufacturing. Journal of Intelligent Manufacturing, 31(4), 887-901.
Marzouk, M., Ashraf, M., & Mohammed, A. (2024). Enhancing Garment Sewing Employee Added Value Monitoring Using a Video-Based Spatio-Temporal Approach. 2024 International Conference on Mechatronics (IMSA).
Meng, K., et al. (2023). Robust mixed-model assembly line balancing and sequencing problem considering preventive maintenance. Swarm and Evolutionary Computation, 77.
Patruno, C., et al. (2025). Skeleton-based human action recognition for manufacturing in assembly task by deep learning. Multimodal Sensing and Artificial Intelligence for Sustainable Future (SPIE).
Pinheiro, J., et al. (2023). A Digital Twin for dynamic line balancing and bottleneck prediction in the apparel industry. Procedia Computer Science, 219.
Santhanam, A. K. R., et al. (2024). Automatic Data Extraction from Assembly Line Videos Using Machine Learning and Computer Vision. Journal of Manufacturing Systems, 72.
Su, J.-M., et al. (2023). Machine learning approach to determine the decision rules in ergonomic assessment of working posture in sewing machine operators. Journal of Safety Research, 87.
Sunagar, P., et al. (2023). Classification of human poses using deep learning techniques. 2023 7th International Conference on Computation System (CSITSS).
Thao, P. T., et al. (2023). A stochastic simulation model for analyzing operator performance variability in garment assembly lines. International Journal of Industrial Engineering and Management, 14(1).
Wang, L., Chen, Y., & Liu, G. (2022). Lightweight Human Pose Estimation for Assembly Action Recognition Using MediaPipe. Procedia CIRP, 107.
Zouhri, C., et al. (2023). A lean manufacturing framework based on Yamazumi chart and simulation for cycle time analysis. International Journal of Production Management and Engineering.
Copyright (c) 2026 Fatahillah Aditya Ma’arif, Sri Hartini , Diana Puspita Sari
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International (CC-BY-SA). that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
