A photovoltaic grid-connected inverter is a strongly nonlinear system. A model predictive control method can improve control accuracy and dynamic performance. Methods to accurately model and optimize control parameters are key to ensuring the stable operation of a photovoltaic grid-connected inverter. Based on the nonlinear characteristics of photovoltaic arrays and switching devices, we established a nonlinear model of photovoltaic grid-connected inverters using the state space method and solved its model predictive controller. Then, using the phase diagram, folded diagram, and bifurcation diagram methods, we studied the nonlinear dynamic behavior under the influence of control parameters on both fast and slow scales. Finally, we investigated the methods of parameter selection based on the characteristics of nonlinear dynamic behavior. Our research shows that the predictive controller parameters are closely related to the bifurcation and chaos behaviors of the grid-connected photovoltaic inverter. The three-dimensional bifurcation diagram can be used to observe the periodic motion region of the control parameters. After selecting the optimization target, the bifurcation diagram can be used to guide the selection of control parameters for inverter design. The research results can be used to guide the modeling, stability analysis, and optimization design of photovoltaic grid-connected inverters.

Facial expressions are the main external manifestations of human emotions. Facial expression recognition technology can be used in medical, investigation, education and other application scenarios. Aiming at the disadvantages of slow convergence speed and low recognition accuracy of traditional neural networks, in order to optimize the network more efficiently and improve the recognition rate of facial expressions, a facial expression recognition method based on improved convolutional neural networks is proposed.First, the deep residual network ResNet18 is improved, and then the improved ResNet18 network is used to extract global expression features of face images, and then the self-attention weighting module is introduced to calculate the expression features of each face image and output one The corresponding weights are used to weight the loss function. Finally, the two public expression data sets of CK+ and RAF-DB are used to experimentally verify the method in the article. The accuracy of facial expression recognition reaches 98.89% and respectively. 87.13%, compared with the original deep residual network ResNet18 model and other types of network models, the facial expression recognition rate has been significantly improved, which proves that this method can effectively improve the accuracy of facial expression recognition and has certain application value.

When the SSD network uses an independent feature layer to detect objects, there is no connection between the layers, which leads to the problem of insufficient expression of contextual features. This paper proposes a pedestrian detection algorithm based on improved SSD network. The algorithm uses cross-layer feature adaptive fusion, and combines residual channel attention modules with different convolution rates of holes. While increasing the receptive field, this algorithm enhances important features and weakens unimportant features. Make the extracted features more directional, thereby improving the accuracy of pedestrian detection. Experiment on the improved network and algorithm on the INRIA pedestrian detection dataset, and the mixed pedestrian dataset extracted from the COCO dataset and the Crowd human dataset. The experimental results show that the average precision of pedestrian detection in the two datasets is improved by 1.7% and 4.0% respectively compared with the original network.