부산대학교 도서관

The Yangtze River embankment project is a critical barrier to ensuring the safety of the Yangtze River channel, and it is necessary to strengthen the safety monitoring of the embankment project. Embankment safety is influenced by various factors, while the influence weight of each factor is difficult to determine, and the expert scoring method and other methods are highly subjective and mainly rely on empirical judgment. Based on machine learning theory, this paper constructs an embankment safety evaluation method based on T-S model neural network. The model primarily consists of four layers of structure. (1) the input layer, this paper selects six types of evaluation factors as input parameters; (2) the fuzzification layer; (3) the fuzzy inference layer, matching the fuzzy rules and calculating the connection weights using the concatenation algorithm; (4) output layer, outputting the embankment safety coefficient value by inverse normalization and defuzzification. This paper selected three specific experimental areas in the river core of the Nanjing section of the Yangtze River as the research objects, used the data to conduct safety evaluation tests, and compared them with the actual operation of the embankment. The experimental results show that the safety level of the embankment calculated by the design method is consistent with the existing safety state of the embankment.