With the wide application of hydraulic servo technology in control systems, the requirement of hydraulic servo position control performance is greater and greater. In order to solve the problems of slow response, poor precision, and weak anti-interference ability in hydraulic servo position controls, a Kalman genetic optimization PID controller is designed. Firstly, aiming at the nonlinear problems such as internal leakage and oil compressibility in the hydraulic servo system, the mathematical model of the hydraulic servo system is established. By analyzing the working characteristics of the servo valve and hydraulic cylinder in the hydraulic servo system, the parameters in the mathematical model are determined. Secondly, a genetic algorithm is used to search the optimal proportional integral differential (PID) controller gain of the hydraulic servo system to realize the accurate control of valve-controlled hydraulic cylinder displacement in the hydraulic servo system. Under the positioning benchmark of step signal and sine wave signal, the PID algorithm and the genetic optimized PID algorithm are compared in the system simulation model established by Simulink. Finally, to solve the amplitude fluctuations caused by the GA optimized PID and reduce the influence of external disturbances, a Kalman filtering algorithm is added to the hydraulic servo system to reduce the amplitude fluctuations and the influence of external disturbances on the system. The simulation results show that the designed Kalman genetic optimization PID controller can be better applied to the position control of the hydraulic servo system. Compared with the traditional PID control algorithm, the PID algorithm optimized by genetic algorithm improves the system’s response speed and control accuracy; the Kalman filter is a good solution for the amplitude fluctuations caused by GA-optimized PID that reduces the influence of external disturbances on the hydraulic servo system.

Problems such as low light, similar background colors, and noisy image acquisition often occur when collecting images of lunar surface obstacles. Given these problems, this study focuses on the AD-Census algorithm. In the original Census algorithm, in the bit string calculated with the central pixel point, the bit string will be affected by the noise that the central point is subjected to. The effect of noise results in errors and mismatching. We introduce an improved algorithm to calculate the average window pixel for solving the problem of being susceptible to the central pixel value and improve the accuracy of the algorithm. Experiments have proven that the object contour in the grayscale map of disparity obtained by the improved algorithm is more apparent, and the edge part of the image is significantly improved, which is more in line with the real scene. In addition, because the traditional Census algorithm matches the window size in a fixed rectangle, it is difficult to obtain a suitable window in the image range of different textures, affecting the timeliness of the algorithm. An improvement idea of area growth adaptive window matching is proposed. The improved Census algorithm is applied to the AD-Census algorithm. The results show that the improved AD-Census algorithm has been shown to have an average run time of 5.3% and better matching compared to the traditional AD-Census algorithm for all tested image sets. Finally, the improved algorithm is applied to the simulation environment, and the experimental results show that the obstacles in the image can be effectively detected. The improved algorithm has important practical application value and is important to improve the feasibility and reliability of obstacle detection in lunar exploration projects.

Forest fires have devastating impacts on ecology, the economy, and human life. Therefore, the timely detection and extinguishing of fires are crucial to minimizing the losses caused by these disasters. A novel dual-channel CNN for forest fires is proposed in this paper based on multiple feature enhancement techniques. First, the features’ semantic information and richness are enhanced by repeatedly fusing deep and shallow features extracted from the basic network model and integrating the results of multiple types of pooling layers. Second, an attention mechanism, the convolutional block attention module, is used to focus on the key details of the fused features, making the network more efficient. Finally, two improved single-channel networks are merged to obtain a better-performing dual-channel network. In addition, transfer learning is used to address overfitting and reduce time costs. The experimental results show that the accuracy of the proposed model for fire recognition is 98.90%, with a better performance. The findings from this study can be applied to the early detection of forest fires, assisting forest ecosystem managers in developing timely and scientifically informed defense strategies to minimize the damage caused by fires.

The identification of wildfires is a very complex task due to their different shapes, textures, and colours. Traditional image processing methods need to manually design feature extraction algorithms based on prior knowledge, and because fires at different stages have different characteristics, manually designed feature extraction algorithms often have insufficient generalization capabilities. A convolutional neural network (CNN) can automatically extract the deeper features of an image, avoiding the complexity and blindness of the feature extraction phase. Therefore, a wildfire identification method based on an improved two-channel CNN is proposed in this paper. Firstly, in order to solve the problem of the insufficient dataset, the dataset is processed by using PCA_Jittering, transfer learning is used to train the model and then the accuracy of the model is improved by using segmented training. Secondly, in order to achieve the effective coverage of the model for fire scenes of different sizes, a two-channel CNN based on feature fusion is designed, in which the fully connected layers are replaced by a support vector machine (SVM). Finally, in order to reduce the delay time of the model, Lasso_SVM is designed to replace the SVM in the original model. The results show that the method has the advantages of high accuracy and low latency. The accuracy of wildfire identification is 98.47% and the average delay time of fire identification is 0.051 s/frame. The wildfire identification method designed in this paper improves the accuracy of identifying wildfires and reduces the delay time in identifying them.