A multi-sensor attitude data fusion method and system based on a neural network

Abstract

The invention discloses a multi-sensor attitude data fusion method and system based on a neural network. The method comprises the following steps: generating original attitude data through a pluralityof sensors; Taking the original attitude data as the input of the convolutional neural network, and taking the attitude data output after the convolution layer, the pooling layer, the full connectionlayer and the first activation function as the output of the convolutional neural network for output; Taking the output of the convolutional neural network as the input of the artificial neural network; and according to a preset general kernel structure, not outputting input of a preset node corresponding to any hidden layer of the artificial neural network through a second activation function, and outputting the input of the remaining nodes corresponding to any hidden layer through a second activation function, and outputting the attitude angle data output by the neuron node of the hidden layer at the tail end as the output of the artificial neural network. According to the fusion method, the convolutional neural network and the optimized artificial neural network are effectively combined, so that the measurement precision of the attitude angle data is improved.

Description

technical field [0001] The present invention relates to the technical field of multi-sensor data fusion, in particular, to a neural network-based multi-sensor data fusion method and system. Background technique [0002] Multi-sensor data fusion is a technology that comprehensively processes and optimizes the acquisition, representation and internal relations of various information. It processes and synthesizes from the perspective of multi-information, and obtains the internal connections and laws of various information, thereby eliminating useless and wrong information, retaining correct and useful components, and finally achieving the purpose of information optimization. The fusion method for multi-sensor attitude data has also become one of the most critical issues in many industrial application fields. [0003] Disclosed in the related art is a miniature strapdown attitude system and its working method, which relates to a multi-sensor data fusion technology based on MEM...

AI Technical Summary

Problems solved by technology

[0005] The above-mentioned related technologies have the following defects: (1) The Kalman filter can only achieve the optimal result when the system noise and measurement noise are known, and the method using the Kalman filter needs to ignore the second-order And above high-order items, the error is relatively large in the complex model; (2) The quaternion algorithm based on the neural network has fewer types of sensor data, the error of attitude detection is larger, and the accuracy of data fusion needs to be further improved

For the general neural network algorithm, in practical applications, with the increase of the number of sensors, there will be a problem that the amount of calculation will increase due to the increase of the number of parameters, and the convergence and time characteristics of the neural network cannot be optimized.

Images