Search

In order to solve the problem of inaccurate positioning in the process of target tracking due to illumination, scale change and occlusion, a correlation filtering tracking algorithm based on generate compression network is proposed. Firstly, the encoder is used to compress the high-dimensional depth features extracted from VGG16 network, and the soft quantizer reduces floating-point operation so that improves the operation speed. Secondly, the discriminator of generative adversarial network guides the encoder and generator to better compress and recover the original depth features by generating a discriminator against the network, so as to enhance the ability of the encoder to extract the key features of the target, then, the compressed depth features, gray features and hog features are combined to improve the ability of target representation. Thirdly, the correlation filter and PCA feature dimensionality reduction are used to complete the target precise location and discriminant scale estimation. The experimental results show that the tracking accuracy of the proposed algorithm is 87.1%, and the tracking rate is up to 70fps.

With the development of deep learning, target detection from vision sensor has achieved high accuracy and efficiency. However, small target detection remains a challenge due to inadequate use of semantic information and detailed texture information of underlying features. To solve the above problems, this paper proposes a small target detection algorithm based on Mask R-CNN model which integrates transfer learning and deep separable network. Firstly, the feature pyramid fusion structure is introduced to enhance the learning effect of low-level and high-level features, especially to strengthen the information channel of low-level feature and meanwhile optimize the feature information of small target. Secondly, the ELU function is used as the activation function to solve the problem that the original activation function disappears in the negative half axis gradient. Finally, a new loss function F-Softmax combined with Focal Loss was adopted to solve the imbalance of positive and negative sample proportions. In this paper, self-made data set is used to carry out experiments, and the experimental results show that the proposed algorithm makes the detection accuracy of small targets reach 66.5%.

In the field of fault diagnosis technology of integrated navigation, traditional methods require high precision of system model, and the single neural network detection has the defects of misdiagnosis, missed diagnosis and large error rate. This paper presents a fault diagnosis method based on fusion neural network. The algorithm takes the error data as the input of neural network. Firstly, BP neural network and improved dynamic particle swarm optimization (PSO) BP neural network are used for fault diagnosis, then the detection results of these two neural networks are fused by D-S evidence theory, and finally verified by simulation. The experimental results show that the method can effectively reduce the error rate of fault detection and improve the accuracy and reliability of fault detection.

In the recycling process of lithium-ion battery, the poor external environment will lead to the degradation of battery performance, so it is necessary to predict the residual life of lithiumion battery. However, the aging cycle of lithium-ion battery is long, so it is difficult to obtain sufficient aging data in a short time. Aiming at the problem of low prediction accuracy of lithium battery residual life under the condition of small samples, a BP neural network modelling algorithm fused with expert knowledge is proposed. Firstly, indirect health factors were extracted from the aging data of lithium battery in NASA PCOE laboratory. Secondly, the initial weight and threshold of BP neural network were optimized by genetic algorithm, and the initial multiplier value of the augmented Lagrange function was set according to Spearman correlation coefficient. Finally, the expert knowledge is integrated into the training process of BP neural network through the augmented Lagrange multiplier method. Simulation results show that the proposed algorithm has higher prediction accuracy than the traditional BP neural network under the condition of small samples.

Fault detection plays an increasingly important role in the reliability of integrated navigation systems. Aiming at the problem of fewer fault samples and non-linearity of data in integrated navigation system, a fault detection algorithm based on resampling One-Class SVM (a kind of support vector machine) is proposed. Firstly, the data is preprocessed by the re-sampling algorithm-kernel fisher discriminant analysis (]CFDA) to achieve the balance of the model data. Then, the data is machine-learned. Finally, the failure of the non-linear data is detected by using the kernel technique. The simulation shows that the method can effectively detect the abrupt and soft faults of the small sample integrated navigation system and improve the detection rate of the integrated navigation system.

Many Bayesian networks display community structure; study community structure helps to reduce the complexity of learning Bayesian network in high-dimensional data. To find the community structure of Bayesian networks, this paper proposes an improved K-means algorithm by incorporating the mutual information into the K-means algorithm and modifying the iteration conditions. Experiments show that the proposed algorithm is suitable for block tasks of Bayesian network. Compared with FastNewman algorithm, the proposed algorithm can obtain accurate results in a shorter time.