In the rugged terrains of Guangxi, China, where the construction of highways presents unique challenges, a recent study has shed light on innovative methods to predict and manage the settlement of high embankments. These structures, essential for highway construction in mountainous areas, often face significant settlement issues due to complex geological conditions and economic constraints. The study, led by Jinhui Wang from China Railway Communications Investment Group Co., Ltd., and published in the journal ‘Frontiers in Built Environment’ (translated from Chinese as ‘Frontiers in the Built Environment’), explores three distinct prediction methods to ensure the long-term safety and operational efficiency of these critical infrastructure projects.
High embankments are characterized by substantial settlement amounts and prolonged settlement cycles, often leading to problems such as cracking and uneven settlement. To address these issues, Wang and his team employed three prediction methods: exponential curve model fitting, grey system theory, and backpropagation neural network (BPNN). Each method was used to forecast the settlement of a high embankment section of a highway in Guangxi, with the results compared against actual measured values.
The findings revealed that the BPNN method achieved the best overall fitting performance, making it a highly reliable tool for settlement prediction. “The BPNN method’s ability to handle complex, non-linear relationships makes it particularly suitable for predicting the settlement of high embankments,” Wang explained. However, the grey system theory also showed promise, meeting accuracy requirements and being less affected by different spatial locations. “Grey system theory offers a balanced approach, providing accurate predictions while being robust to variations in data,” Wang added.
The exponential curve fitting method, while involving lower computational costs, showed greater dependence on parameter selection. However, its accuracy improved significantly as the time interval increased, making it a viable option for long-term predictions.
The implications of this research are far-reaching, particularly for the energy sector, where the stability of infrastructure is paramount. “Understanding and predicting settlement patterns can help in the design and maintenance of pipelines, power lines, and other energy infrastructure that often traverse mountainous terrains,” Wang noted. By employing these prediction methods, engineers can ensure the long-term operational safety of high embankments, thereby minimizing disruptions and maintenance costs.
This study not only provides a methodological basis for settlement prediction and control but also offers practical significance for ensuring the long-term operational safety of high embankments in mountainous expressways. As the energy sector continues to expand into challenging terrains, the insights gained from this research will be invaluable in shaping future developments and ensuring the reliability of critical infrastructure.
In the words of Jinhui Wang, “This research is a step towards enhancing the safety and efficiency of infrastructure projects in mountainous areas, ultimately benefiting the energy sector and other industries that rely on stable and reliable infrastructure.” With the publication of this study in ‘Frontiers in Built Environment’, the construction industry now has a robust set of tools to tackle the challenges posed by high embankments in mountainous regions, paving the way for more resilient and sustainable infrastructure development.