SISTEM DIAGNOSA KERUSAKAN MESIN PESAWAT CESSNA C208-B MENGGUNAKAN PENDEKATAN CASE-BASED REASONING BERBASIS TEKS
Article Sidebar
Main Article Content
Abstract
Proses diagnosis kerusakan mesin pesawat memerlukan keahlian teknis tinggi dan pengalaman dalam memahami gejala serta riwayat perawatan. Teknisi junior sering mengalami kesulitan mengidentifikasi masalah tanpa bimbingan teknisi senior. Penelitian ini bertujuan mengembangkan sistem troubleshooting berbasis teks menggunakan pendekatan Case-Based Reasoning (CBR) untuk memberikan rekomendasi solusi terhadap kerusakan engine pesawat Cessna C208-B berdasarkan kemiripan kasus sebelumnya. Dataset terdiri atas 100 data kerusakan yang mencakup deskripsi gejala (symptom), penyebab (cause), dan tindakan perbaikan (solution). Proses retrieve meliputi text preprocessing (case folding, tokenizing, stopword removal, filtering, dan stemming), pembobotan TF-IDF, serta perhitungan kemiripan menggunakan Cosine Similarity. Hasil pengujian menunjukkan sistem mampu mencapai Precision@1 sebesar 100% dan akurasi keseluruhan 100% dengan waktu pencarian rata-rata 2,8 detik. Meskipun tingkat kemiripan menurun dari 81,7% menjadi 74,7% pada pengujian generalisasi, sistem tetap menunjukkan performa yang konsisten. Hasil ini membuktikan bahwa pendekatan CBR berbasis teks efektif dalam membantu teknisi junior menemukan solusi kerusakan mesin secara cepat dan akurat, serta berpotensi menjadi decision support tool untuk mempercepat proses diagnosis dan mengurangi kesalahan identifikasi di hanggar.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
M. Chen et al.. “Case-Based Reasoning System for Aeroengine Fault Diagnosis.” Applied Sciences. vol. 12. no. 10. pp. 10045–10060. 2022.
N. Azevedo et al., “Developing Troubleshooting Chatbots for Technical Maintenance,” Applied Sciences, 2023.
X. Li et al., “Textual Fault Diagnosis of Aircraft Engine Systems using NLP and Semantic Similarity,” Aerospace Science and Technology, 2024.
M. Rahman et al., “CBR for Turbofan Fault Detection using Deep Features,” Engineering Applications of AI, 2023.
D. Park and J. Kim, “Adaptive CBR for Industrial Machine Faults,” Expert Systems with Applications, 2022.
X. Zhao et al., “Hybrid NLP–CBR Model for Maintenance Knowledge Retrieval,” IEEE Access, 2023.
T. Lawanna, “Case-based Maintenance Model for Aircraft Systems,” Engineering Journal, 2023.
Y. Ortakci et al., “Investigating Transfer Learning Capacity of SBERT Models,” Springer AI Review, 2024.
J. Zhou et al., “Investigating Response Behavior via TF-IDF and Word2Vec,” Expert Systems, 2024.
Y. Li and J. Han, “CBR with Choquet Integral for Aeroengine Diagnosis,” Applied Sciences, 2022.
X. Xie et al., “HybridRAG for Guided Troubleshooting of Aircraft Engines,” IEEE Transactions on AI, 2025.
X. Zhu et al., “Knowledge Graph-Guided Retrieval-Augmented Generation,” in Proc. NAACL, 2025.
A. Schultheis, “Comparison of Modern CBR Frameworks,” AI & Society, 2023.
I. Watson, Applying Case-Based Reasoning: Techniques for Maintenance Systems. Morgan Kaufmann, 2020.
M. T. Keane, “DeepCBR: Combining Deep Learning and CBR,” arXiv, 2021.
H. Lee et al., “Knowledge Reuse in Aircraft Maintenance using CBR,” Aerospace Science and Technology, 2024.
S. Han et al., “Hybrid TF-IDF and Embedding Approach for Technical Text Retrieval,” IEEE Access, 2024.
N. Rahmawati et al., “Implementasi CBR untuk Diagnosa Mesin Industri,” Jurnal Teknologi Informasi dan Komputer, 2023.
K. Alshawkani, “Chatbot Dialogue Breakdown Solutions,” Knowledge-Based Systems, 2025.
D. Delen and M. Crossland, “Text Mining in Business Intelligence,” Expert Systems with Applications, 2023.