基于多IMU数据融合的风电叶片动态形变感知算法研究

STUDY ON WIND TURBINE BLADE DYNAMIC DEFORMATION SENSING ALGORITHM BASED ON MULTI-IMU DATA FUSION

为精确测量风电叶片动态形变过程中的挠曲姿态与位置,提出基于多惯性测量单元(Inertial Measurement Unit, IMU)进行测量的相对运动感知算法。该算法以改进的卡尔曼滤波为基础,通过反馈式分布式结构进行多节点的数据融合。该方法不仅能提供冗余的叶片运动的惯性信息,还具有较强的容错性,即当单个IMU节点出现故障时,对该算法的测量精度影响较小。仿真结果表明:单点融合后子节点在运动方向挠曲姿态最大误差为1.068′,最大位置误差为-59.89 mm;全局融合后节点最大误差分别为1.004′,27.71 mm。该研究在全尺寸风电叶片动态形变测试领域具有很强的理论研究意义和工程应用价值。

To accurately measure the bending attitude and position of wind turbine blades during dynamic deformation,a relative motion sensing algorithm based on multi-inertial measurement unit(IMU)measurement is proposed.The algorithm is based on the improved Kalman filter and uses a feedback distributed structure to perform multi-node data fusion.This method can not only provide redundant blade motion inertial information,but also has strong fault tolerance,that is,when a single IMU node fails,the measurement accuracy of the algorithm is less affected.The simulation results show that the maximum error of the deflection attitude of the child nodes in the direction of motion after single point fusion is 1.068′,and the maximum position error is-59.89 mm;the maximum error of the node after global fusion is 1.004′,27.71 mm,respectively.This research has strong theoretical research significance and engineering application value in the field of dynamic deformation testing of full-scale wind turbine blades.