Marine seismic exploration is an important part of offshore oil and gasexploration, which requires accurate attitude information of submarine towingequipment. Conventional attitude solution algorithm or Kalman filter ...Marine seismic exploration is an important part of offshore oil and gasexploration, which requires accurate attitude information of submarine towingequipment. Conventional attitude solution algorithm or Kalman filter algorithmcannot satisfy the current requirements of high accuracy, high reliability, strongenvironmental adaptability and low cost. In view of the low accuracy and poorenvironmental adaptability of the traditional Kalman filter algorithm, this paperproposes a CNN-EKF fusion attitude calculation algorithm based on the studyof the extended Kalman filter (EKF) model and the convolutional neural network(CNN) model. The system noise variance matrix (Q) and the observationnoise variance matrix(R)of EKF were optimized by CNN, and the final solutionresults were obtained. Compared the traditional Kalman filtering model with theCNN-EKF fusion filtering model, experimental results shows that the algorithmimproves the accuracy of attitude calculation and enhances the adaptive ability tothe environment.展开更多
基金The research was supported by the National Key Research and Development Program of China(GrantNo.2016YFC0303901)Southern Marine Science and Engineering Guangdong Laboratory(Zhanjiang)(ZJW-2019-04).
文摘Marine seismic exploration is an important part of offshore oil and gasexploration, which requires accurate attitude information of submarine towingequipment. Conventional attitude solution algorithm or Kalman filter algorithmcannot satisfy the current requirements of high accuracy, high reliability, strongenvironmental adaptability and low cost. In view of the low accuracy and poorenvironmental adaptability of the traditional Kalman filter algorithm, this paperproposes a CNN-EKF fusion attitude calculation algorithm based on the studyof the extended Kalman filter (EKF) model and the convolutional neural network(CNN) model. The system noise variance matrix (Q) and the observationnoise variance matrix(R)of EKF were optimized by CNN, and the final solutionresults were obtained. Compared the traditional Kalman filtering model with theCNN-EKF fusion filtering model, experimental results shows that the algorithmimproves the accuracy of attitude calculation and enhances the adaptive ability tothe environment.
