In this study, an experimental investigation was conducted on the mechanical properties of lightweight aggregate concrete (LWAC) with different chopped fibers, including basalt fiber (BF) and polyacrylonitrile fiber (PANF). The LWAC performance was studied in regard to compressive strength, splitting tensile strength and shear strength at age of 28 days. In addition, the oven-dried density and water absorption were measured as well to confirm whether the specimens match the requirement of standard. In total, seven different mixture groups were designed and approximately 104 LWAC samples were tested. The test results showed that the oven-dried densities of the LWAC mixtures were in range of 1.819–1.844 t/m³ which satisfied the definition of LWAC by Chinese Standard. Additionally, water absorption decreased with the increasing of fiber content. The development tendency of the specific strength of LWAC was the same as that of the cube compressive strength. The addition of fibers had a significant effect on reducing water absorption. Adding BF and PANF into concrete had a relatively slight impact on the compressive strength but had an obvious effect on splitting tensile strength, flexural strength and shear strength enhancement, respectively. In that regard, a 1.5% fiber volume fraction of BF and PANF showed the maximum increase in strength. The use of BF and PANF could change the failure morphologies of splitting tensile and flexural destruction but almost had slight impact on the shear failure morphology. The strength enhancement parameter β was proposed to quantify the improvement effect of fibers on cube compressive strength, splitting tensile strength, flexural strength and shear strength, respectively. And the calculation results showed good agreement with test value.

Urban municipal water supply is an important part of underground pipelines, and their scale continues to expand. Due to the continuous improvement in the quality and quantity of data available for pipeline systems in recent years, traditional pipeline network risk assessment cannot cope with the improvement of various monitoring methods. Therefore, this paper proposes a machine learning-based risk assessment method for municipal pipe network operation and maintenance and builds a model example based on the data of a pipeline network base in a park in Suzhou. We optimized the random forest learning model, compared it with other centralized learning methods, and finally evaluated the model’s learning effect. Finally, the risk probability associated with each pipe segment sample was obtained, the risk factors affecting the pipe segment’s failure were determined, and their relevance and importance ranking was established. The results showed that the most influential factors are pipe material, soil properties, service life, and the number of past failures. The random forest algorithm demonstrated better prediction accuracy and robustness on the dataset.