Using ChatGPT for the intelligent diagnostics of complex technical systems
Abstract
Intelligent diagnostics of complex technical systems, particularly ship power plants (SPPs), is essential for ensuring early fault detection and maintaining operational reliability. This study presents a methodological approach for integrating the ChatGPT language model into automated SPP diagnostics. This study aimed to develop a methodological approach for using the ChatGPT language model in the automated diagnostics of complex technical systems (CTSs), particularly SPPs. The proposed methodology consists of several stages: data collection, preprocessing, model training, anomaly detection, and the generation of diagnostic recommendations. The system integrates ChatGPT with real-time data streaming (Apache Kafka) and neural network-based anomaly detection using autoencoders and Long Short-Term Memory (LSTM) models. Experimental validation was carried out using real operational datasets from ship power plant systems. The proposed approach demonstrated a significant improvement in fault detection accuracy, increasing it by 15% compared with conventional threshold-based methods. The diagnostic time was reduced by a factor of nine, which enabled near real-time identification of deviations. The model achieved an accuracy rate of 92.8% when classifying abnormal states and correctly identifying early-stage faults in key parameters such as pressure, temperature, and rotation speed. The analysis of reconstruction error distributions confirmed the ability of the system to distinguish between normal and anomalous system behaviour. Detected anomalies were crossvalidated with expert assessments, confirming the practical applicability of the model in real-world diagnostics. Furthermore, the implementation of the proposed approach enables predictive maintenance planning, which contributes to reducing operational risks and lowering maintenance costs. The integration of ChatGPT into ship power plant diagnostic systems enhances the automated processing of technical documentation and operational logs, increasing the transparency and accuracy of fault explanations. The results of this study may be applied in ship engineering, industrial automation, and technical maintenance, contributing to the improved safety and reliability of complex technical systems
Keywords
predictive maintenance; anomaly detection; shipboard energy systems; intelligent monitoring; real-time analytics; artificial intelligence-driven assessment; operational reliability
References
[1] Abdulwahid, A. (2022). Intelligent fault diagnosis method for shipboard main power system. Journal of Southwest Jiaotong University, 57(1), 475-487. doi: 10.35741/issn.0258-2724.57.1.44.
[2] Adiguzel, T., Kaya, M.H., & Cansu, F.K. (2023). Revolutionizing education with AI: Exploring the transformative potential of ChatGPT. Contemporary Educational Technology, 15(3), article number ep429. doi: 10.30935/cedtech/13152.
[3] Alzahem, A., Latif, S., Boulila, W., & Koubaa, A. (2023). Unlocking the potential of medical imaging with ChatGPT’s intelligent diagnostics. arXiv: Electrical Engineering and Systems Science. doi: 10.48550/arXiv.2305.07429.
[4] Bakhshandeh, A., Keramatfar, A., Norouzi, A., & Chekidehkhoun, M. (2023). Using ChatGPT as a static application security testing tool. The ISC Int’l Journal of Information Security. doi: 10.48550/arXiv.2308.14434.
[5] Christodoulou-Varotsi, I. (2024). Implementation of IMO instruments from a shipowning state perspective. In The Elgar сompanion to the law and practice of the International Maritime Organization (pp. 379-393). Cheltenham: Edward Elgar Publishing. doi: 10.4337/9781802206883.00030.
[6] Do, J.S., Kareem, A.B., & Hur, J. (2023). LSTM-Autoencoder for vibration anomaly detection in vertical carousel storage and retrieval system (VCSRS). Sensors, 23(2), article number 1009. doi: 10.3390/s23021009.
[7] Gordijn, B., & Have, H. (2023). ChatGPT: Evolution or revolution? Medicine, Health Care and Philosophy, 26, 1-2. doi: 10.1007/s11019-023-10136-0.
[8] Kirinuki, H., & Tanno, H. (2024). ChatGPT and human synergy in black-box testing: A comparative analysis. arxiv. doi: 10.48550/arXiv.2401.13924.
[9] Li, T., Zong, W., Wang, Y., & Tian, H. (2023). Nuances are the Key: Unlocking ChatGPT to find failure-inducing tests with differential prompting. In 38th IEEE/ACM international conference on automated software engineering (pp. 14-26). Luxembourg: Luxembourg. doi: 10.1109/ASE56229.2023.00089.
[10] Luu, Q., Liu, H., & Chen, T. (2023). ChatGPT advance software testing intelligence? An experience report on metamorphic testing. doi: 10.48550/arXiv.2310.19204.
[11] Mercorelli, P. (2024). Recent advances in intelligent algorithms for fault detection and diagnosis. Sensors, 24(8), article number 2656. doi: 10.3390/s24082656.
[12] Mudgal, P., & Wouhaybi, R. (2023). An assessment of ChatGPT on log data. In AI-generated content (pp. 148-169). Singapore: Springer. doi: 10.48550/arXiv.2309.07938.
[13] Popp, L., & Müller, K. (2021). Technical reliability of shipboard technologies for the application of alternative fuels. Energy, Sustainability and Society, 11, article number 23. doi: 10.1186/s13705-021-00301-9.
[14] Ramalho, L. (2022). Fluent python. Sebastopol: O’Reilly Media, Inc.
[15] Regattieri, F., Bortolini, A., & Galizia, F.G. (2022). Data-driven fault detection and diagnosis: Challenges and opportunities in real-world scenarios. Applied Sciences, 12(18), article number 9212. doi: 10.3390/app12189212.
[16] Suhail, A.H., Guangul, F.M., & Nazeer, A. (2024). Advanced system diagnostics tools: Innovations and applications. IntechOpen. doi: 10.5772/intechopen.114378.
[17] Theofanis, P., & Raptis, A. (2022). On efficiently partitioning a topic in Apache Kafka. In International conference on computer, information and telecommunication systems (CITS) (pp. 1-8). Greece: Piraeus. doi: 10.1109/ CITS55221.2022.9832981.
[18] Vychuzhanin, V., Rudnichenko, N., Vychuzhanin, A., & Rychlik, A. (2023). Diagnosis intellectualization of complex technical systems. In ICST-2023: Information control systems & technologies (pp. 352-362). Odesa.
[19] Wang, C., Chen, X., Qiang, X., Fan, H., & Li, S. (2024). Recent advances in mechanism/data-driven fault diagnosis of complex engineering systems with uncertainties. AIMS Mathematics, 9(11), 29736-29772. doi: 10.3934/ math.20241441.
[20] Wang, G., et al. (2021). Consistency and completeness: Rethinking distributed stream processing in Apache Kafka. In International conference on management of data SIGMOD ‘21 (pp. 2602-2613). New York: Association for Computing Machinery. doi: 10.1145/3448016.345755.
[21] Yan, W., Wang, J., Lu, S., Zhou, M., & Peng, X. (2023). A review of real-time fault diagnosis methods for industrial smart manufacturing. Processes, 11(2), article number 369. doi: 10.3390/pr11020369.