基于自适应鲸鱼算法的桥梁传感器优化布置方法

Optimal Placement of Bridge Sensors Based on Adaptive Whale Algorithm

为解决桥梁健康监测系统中传感器优化布置问题,提出一种基于自适应鲸鱼优化算法的传感器布置方法。通过Fisher信息阵二范数变化率和模态有效参与质量提取模态,有效避免模态冗余。引入Kent映射生成初始测点,以模态置信准则为适应度函数。针对鲸鱼算法中参数既控制算法的全局和局部搜索又控制算法的搜索步长,且其开发能力不足等问题,将鲸鱼算法中的参数A分解为决策因子A1和衰减因子A2。通过决策因子A1控制鲸鱼算法的全局和局部搜索,增强算法跳出局部最优的能力;通过衰减因子A2动态调整算法的搜索步长,提升鲸鱼算法搜索效率和精度。通过哈齐大桥进行实例验证,结果表明,改进后鲸鱼算法的模态置信矩阵精度相比粒子群算法提升82.29%。

In order to solve the problem of Optimal Sensor Placement(OSP)for bridge health monitoring systems,an Adaptive Whale Optimization Algorithm(AWOA)sensor placement method is proposed.In this method,the mode is extracted through the change rate of the two norm of fisher information matrix and the effective participation of the mode,which can effectively avoid modal redundancy.Kent mapping is applied to generate initial chaotic variables,and the Modal Assurance Criterion(MAC)is taken as the fitness function.In the whale algorithm,parameter A not only controls the global and local search of the algorithm,but also controls the search step size of the algorithm,and its updating ability is insufficient.Therefore,parameter A in the whale algorithm is decomposed into the decision factor A1 and the attenuation factor A2.The global and local search of the whale algorithm is controlled by A1,which enhances the ability of the algorithm to jump out of the local optimum.While by dynamically adjusting the search step size of the algorithm through A2,the search efficiency and accuracy of the whale algorithm are improved.The results of verification of this method by the real Ha-qi Bridge show that the MAC accuracy of the AWOAis 82.29%higher than that of the Particle Swarm Optimization algorithm.