Wire breakage is a major factor in the failure of prestressed concrete cylinder pipes (PCCP). In the presented work, an automatic monitoring approach of broken wires in PCCP using fiber-optic distributed acoustic sensors (DAS) is investigated. The study designs a 1:1 prototype wire break monitoring experiment using a DN4000 mm PCCP buried underground in a simulated test environment. The test combines the collected wire break signals with the previously collected noise signals in the operating pipe and transforms them into a spectrogram as the wire break signal dataset. A deep learning-based target detection algorithm is developed to detect the occurrence of wire break events by extracting the spectrogram image features of wire break signals in the dataset. The results show that the recall, precision, F1 score, and false detection rate of the pruned model reach 100%, 100%, 1, and 0%, respectively; the video detection frame rate reaches 35 fps and the model size is only 732 KB. It can be seen that this method greatly simplifies the model without loss of precision, providing an effective method for the identification of PCCP wire break signals, while the lightweight model is more conducive to the embedded deployment of a PCCP wire break monitoring system.

The working performance of buried flexible pipelines is connected with the pipe- soil interaction; the weak stiffness of backfill leads to large long-term pipeline deformation and even structural failure. Spangler’s formula is a theory for macroscopic evaluation of pipeline deformation, which cannot reflect the deformation state of various parts around the pipe from a microscopic view. A large number of engineering practices have shown that when the macro radial deformation of the flexible pipe is not large, it is also possible that the local geometric size of the pipeline may change suddenly in the microscopic view. Combining with a diversion project, a laser scanning and piecewise elliptic curve fitting combined method was proposed to measure the empty pipeline deformation in this paper. The deformation pattern of the flexible pipeline was analysis. And then, the analysis results were verified by the elastic wave test and material test data. Based on the deformation inspections, the internal force and related reliability of pipe structure were calculated. Finally, the structural safety of each pipe was assessed to guide the replacement, repair and reinforcement of pipeline.

In order to study a novel monitoring method suitable for pressure water conveyance project, the fiber grating pressure sensor was adopted for monitoring the water pressure of in-service glass fiber reinforced plastic mortar pipeline. An emptying valve was used in the prototype test to simulate the leakage process and the dynamic water pressure process was recorded effectively by the fiber grating pressure sensor with high frequency and high precision. According to prototype test results, a fluctuation analytical method was proposed, which uses random average pressure as the equilibrium standard value. Meanwhile, an early warning system against pipe failure was developed based on this method. The system was verified by the simulated leakage tests, and the results show that the system could alarm the leakage of more than 0.25% of pipeline design flow, and the positioning accuracy was 10 m–20 m.

In order to study the applicability of leakage noise (vibration) monitoring method, an online leakage monitoring test was carried out on a large pipeline. In the test, the emptying valve on the pipeline was used to simulate the leakage point, and the vibration signal caused by leakage was monitored by the hydrophone and other floating cables installed in the pipeline. By controlling the opening degree of the emptying valve, the different degrees of leakage between 10L/s and 105L/s was simulated, and the monitoring data for 10 minutes were recorded from 5 minutes before valve opening. The analysis results of the test data showed that although the environmental background of the monitoring was very disturbing, the leakage could be detected when the leakage degree was more than 0.05% of the pipeline flow. The monitoring results also showed that the noise caused by the leakage of large buried water pipelines was mainly transmitted in the form of vibration along the soil around the pipeline.