The current research paper will discuss a new patent-based design that uses non-destructive testing (NDT), artificial intelligence (AI), and machine learning (ML) to forecast and eliminate failures of water pipes throughout the US. It is a systematic review of eight current peer-reviewed papers (2015-2025) dedicated to the topic of AI-based predictive analytics, bio-inspired robotic movement, and the economic sustainability of pipeline inspection. The quantitative results of the algorithm show that deep learning and tree-based models, such as CNN, YOLO, LSTM, and Gradient Boosting, achieved defect detection accuracy of 91 to 95%, which greatly decreases manual inspection time and, on average, excavation costs by 70 and 55 %, respectively. Moreover, the stylus of the bio-inspired robots was presented, e.g. the robots with mechanically inflatable bodies had demonstrated the ability to control 70-79% locomotion efficiency and complete 5.8 kg loads in a variable pipeline size, with these properties confirming their scalable robots with non-invasive continuous inspection. The study offers a multidisciplinary synthesis towards demonstrating how AI, robotics, and predictive maintenance are converging towards a system of developing sustainable infrastructure resilience. The proposed structure works together with making 300,000-plus ageing water mains in the United States more modernised through the adoption of cost-efficient automation, along with high diagnostic accuracy, to encourage safer, data-informed and more environmentally friendly processes. Regardless of the difficulties in the computational and operational planning, the research highlights that AI-robotic synergy has the potential to transform asset management in the civil infrastructure framework.

Artificial Intelligence, Machine Learning, Non-Destructive Testing, Predictive Maintenance, Robotic Inspection, Infrastructure Modernisation, Cost Efficiency, Water Mains

1. ASCE (2021). ASCE’s 2021 report card marks the nation’s infrastructure progress. [online] https://www.asce.org/publications-and-news/civil-engineering-source/civil-engineering-magazine/issues/magazine-issue/article/2021/03/asce-2021-report-card-marks-the-nations-infrastructure-progress. (Accessed: 06 October 2025)

2. Atalla, M.A., Trauzettel, F., van Gelder, S.P., Breedveld, P., Wiertlewski, M. and Sakes, A., 2024, April. Mechanically-Inflatable Bio-Inspired Locomotion for Robotic Pipeline Inspection. In 2024 IEEE 7th International Conference on Soft Robotics (RoboSoft) (pp. 586-592). IEEE. https://doi.org/10.1109/RoboSoft60065.2024.10521968 (Accessed: 06 October 2025)

3. Chen, R., Wang, Q. and Javanmardi, A. (2025). A Review of the Application of Machine Learning for Pipeline Integrity Predictive Analysis in Water Distribution Networks. Archives of Computational Methods in Engineering, [online] (1). https://doi.org/10.1007/s11831-025-10251-6. (Accessed: 06 October 2025)

4. Cheong, H.I., Lyons, A., Houghton, R. and Majumdar, A., 2023. Secondary qualitative research methodology using online data within the context of social sciences. International Journal of Qualitative Methods, 22, p.16094069231180160. Available at: https://doi.org/10.1177/16094069231180160 (Accessed: 06 October 2025)

5. Expósito, A. and Díez Cebollero, E. (2025). How the digital revolution is reshaping water management and policy: A focus on Spain. Utilities Policy, [online] 96, p.102020. https://doi.org/10.1016/j.jup.2025.102020. (Accessed: 06 October 2025)

6. Fan, X., Wang, X., Zhang, X. and Yu, P.E., F.ASCE Xiong (2021). Machine Learning based Water Pipe Failure Prediction: The Effects of Engineering, Geology, Climate and Socio-Economic Factors. Reliability Engineering & System Safety, p.108185. https://doi.org/10.1016/j.ress.2021.108185. (Accessed: 06 October 2025)

7. Hespeler, S.C., Nemati, H., Masurkar, N., Alvidrez, F., Marvi, H. and Dehghan-Niri, E., 2024. Deep Learning–Based Time-Series Classification for Robotic Inspection of Pipe Condition Using Non-Contact Ultrasonic Testing. Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems, 7(1), p.011002. https://doi.org/10.1115/1.4063694 (Accessed: 06 October 2025)

8. Jeon, K.-W., Jung, E.-J., Bae, J.-H., Park, S.-H., Kim, J.-J., Chung, G., Chung, H.-J. and Yi, H. (2024). Development of an In-Pipe Inspection Robot for Large-Diameter Water Pipes. Sensors, 24(11), p.3470. https://doi.org/10.3390/s24113470. (Accessed: 06 October 2025)

9. Latifi, M., Beig Zali, R., Javadi, A.A. and Farmani, R., 2024. Efficacy of tree-based models for pipe failure prediction and condition assessment: A comprehensive review. Journal of Water Resources Planning and Management, 150(7), p.03124001. https://doi.org/10.1061/JWRMD5.WRENG-6334 (Accessed: 06 October 2025)

10. Macaulay, M.O. and Shafiee, M. (2022). Machine learning techniques for robotic and autonomous inspection of mechanical systems and civil infrastructure. Autonomous Intelligent Systems, 2(1). https://doi.org/10.1007/s43684-022-00025-3. (Accessed: 06 October 2025)

11. Mazhar, S.A., Anjum, R., Anwar, A.I. and Khan, A.A., 2021. Methods of data collection: A fundamental tool of research. Journal of Integrated Community Health, 10(1), pp.6-10. Available at: https://doi.org/10.24321/2319.9113.202101 (Accessed: 06 October 2025)

12. Moreno-Rodenas, A., Verbist, K., Mertens, A., Gerritsma, I. and Amarnath, G. (2025). Applications of AI for water management. [online] https://doi.org/10.54677/VGVL7976. (Accessed: 06 October 2025)

13. Preiser, R., García, M.M., Hill, L. and Klein, L., 2021. Qualitative content analysis. In The Routledge handbook of research methods for social-ecological systems (pp. 270-281). Routledge. Available at: https://library.oapen.org/bitstream/handle/20.500.12657/49560/1/9781000401516.pdf#page=303 (Accessed: 06 October 2025)

14. Ravichandran, T., Gavahi, K., Ponnambalam, K., Burtea, V. and Mousavi, S.J. (2021). Ensemble-based machine learning approach for improved leak detection in water mains. Journal of Hydroinformatics, [online] 23(2), pp.307–323. https://doi.org/10.2166/hydro.2021.093. (Accessed: 06 October 2025)

15. Rusu, C. and Tatar, M.O. (2022). Adapting Mechanisms for In-Pipe Inspection Robots: A Review. Applied Sciences, 12(12), p.6191. https://doi.org/10.3390/app12126191. (Accessed: 06 October 2025)

16. Zhang, Y., Chow, C.L. and Lau, D., 2025. Artificial intelligence-enhanced non-destructive defect detection for civil infrastructure. Automation in Construction, 171, p.105996. https://doi.org/10.1016/j.autcon.2025.105996 (Accessed: 06 October 2025)