In order to improve the precision of highway asphalt pavement quality evaluation, a comprehensive evaluation model of pavement quality was built using Takagi-Sugeno (T-S) fuzzy theory combined with back propagation (BP) neural network. In this model, 4 indexes including expressway asphalt pavement condition index, pavement structure strength index, road riding quality index, and skid resistance index are taken as input variables; a nonlinear mapping relationship of the pavement quality evaluation system is established by fuzzy inference rules; pavement detection indicators undergo the fuzzy neural network learning and training, until the error between network output and the expected output reach a minimum value; after defuzzification, quantitative quality evaluation result of each pavement is obtained. In addition, the proposed method was verified by an example using the real measured data. The results show that the method has the logical reasoning ability of fuzzy system and the quantitative data processing ability of neural network. Compared to the expected values, the pavement quality comprehensive evaluation results simulated by the proposed method have a relative error of less than 2. 1% .%为提高高速公路沥青路面使用质量的评价精度,将T-S模糊理论与BP神经网络相结合,以高速公路沥青路面的路面状况指数、路面结构强度指数、道路行驶质量指数和路面抗滑性能指数4个检测指标作为输入变量,根据模糊推理规则构建路面质量评价的非线性映射关系,路面检测指标经过模糊神经网络的学习和训练,直至网络输出与期望输出的误差达到最小,去模糊化后得到各路段的精确评价结果,建立了路面使用质量的综合评价模型.用实际检测数据对该模型进行了验证,结果表明:该模型具有模糊系统的逻辑推理能力和神经网络的定量数据处理能力,通过本文方法仿真得到的路面质量的综合评价结果,与期望值的相对误差小于2.1％.
展开▼
