Space research is of great significance to increasingly decentralized and distributed space systems, and path planning in space systems has become a research hotspot for maintaining its safety, security, and reliability. To explore the passable path connecting the starting point and the target point, and optimize a smooth trajectory that can be tracked by UAVs (Unmanned Aerial Vehicle) in 3D space, a Skeleton Extraction and Greedy Algorithm based Path Planning has been proposed to guide the flight of UAVs. First, the RRT (Rapidly Exploring Random Tree) has been introduced for path search. To speed up the path search process, the spatial skeleton extraction method has been introduced to calculate the skeleton of free space. The greedy algorithm has been utilized to increase the RRT expansion and reduce unnecessary bends in the path. The Skeleton Extraction and Greedy Algorithm based Lazy RRT and RRT-Connect have been proposed to build compared experiments. Second, the minimum snap has been applied to generate a smooth flight trajectory, and the flight time is allocated according to the distance between the waypoints. Third, the UAV Simulink model has been established, and the spatial position of the optimized trajectory is tracked. The experimental results prove that the skeleton extraction can significantly speed up the search process, and greedy algorithm can shorten the path length effectively. The minimum snap combined with the time allocation strategy can produce a smooth and feasible path. The UAV Simulink model also proves that the classic PD (Proportion-Differentiation) controller can accurately track the generated trajectory. Greedy algorithm and skeleton extraction reduce the average path length of RRT by 9.780% and 8.251%, respectively. Greedy algorithm and skeleton extraction reduce the average path length of RRT, Lazy RRT and RRT-Connect by about 10%-13%. Greedy algorithm and skeleton extraction reduce the time consumption of RRT by 62.781% and 36.276%, respectively.

To accurately detect dynamic objects in dynamic scenes (DSs), a detection framework equipped with visual-based measurement methods has been proposed in this article. First, to segment dynamic objects in real time, the real-time instance segmentation network, You Only Look At CoefficienTs (YOLACT), has been introduced. Second, the geometric constraints have been utilized to further filter the missing dynamic feature points outside the segmentation mask. The dense optical flow method with adaptive threshold has been introduced to detect the missing dynamic objects driven by humans. Third, a background inpainting strategy has been proposed to restore the features occluded by dynamic objects. In order to verify the effectiveness of the dynamic object detection, the proposed method has been embedded in the visual simultaneous localization and mapping (SLAM) system to improve its performance in dynamic environments. Experiments performed on the Technische Universität München (TUM) and KITTI datasets have proved that the proposed detection method has an excellent performance in DSs, which is of great significance to improve the robustness of the SLAM system.

The accurate online detection of laser welding penetration depth has been a critical problem to which the industry has paid the most attention. Aiming at the laser welding process of TC4 titanium alloy, a multi-sensor monitoring system that obtained the keyhole/molten pool images and laser-induced plasma spectrum was built. The influences of laser power on the keyhole/molten pool morphologies and plasma thermo-mechanical characteristics were investigated. The results showed that there were significant correlations among the variations of the keyhole–molten pool, plasma spectrum, and penetration depth. The image features and spectral features were extracted by image processing and dimension-reduction methods, respectively. Moreover, several penetration depth prediction models based on single-sensor features and multi-sensor features were established. The mean square error of the neural network model built by multi-sensor features was 0.0162, which was smaller than that of the model built by single-sensor features. The established high-precision model provided a theoretical basis for real-time feedback control of the penetration depth in the laser welding process.

Sensor fault detection and diagnosis (FDD) has great significance for ensuring the energy saving and normal operation of the air conditioning system. Chiller systems serving as an important part of central air conditioning systems are the major energy consumer in commercial and industrial buildings. In order to ensure the normal operation of the chiller system, virtual sensors have been proposed to detect and diagnose sensor faults. However, the performance of virtual sensors could be easily impacted by abnormal data. To solve this problem, virtual sensors combined with the maximal information coefficient (MIC) and a long short-term memory (LSTM) network is proposed for chiller sensor fault diagnosis. Firstly, MIC, which has the ability to quantify the degree of relevance in a data set, is applied to examine all potentially interesting relationships between sensors. Subsequently, sensors with high correlation are divided into several groups by the grouping thresholds. Two virtual sensors, which are constructed in each group by LSTM with different input sensors and corresponding to the same physical sensor, could have the ability to predict the value of physical sensors. High correlation sensors in each group improve the fitting effect of virtual sensors. Finally, sensor faults can be diagnosed by the absolute deviation which is generated by comparing the virtual sensors’ output with the actual value measured from the air-cooled chiller. The performance of the proposed method is evaluated by using a real data set. Experimental results indicate that virtual sensors can be well constructed and the proposed method achieves a significant performance along with a low false alarm rate.

When wireless sensor network (WSN) is running, it needs data acquisition, fusion, and transmission, which makes the attacker distribute the malware code to the network to destroy the normal operation of the network. In this study, an improved two‐dimensional (2D) cellular automata model and a multi‐player evolutionary game model are proposed to describe the propagation process of malware propagation, aiming at the shortcomings of research on malware propagation in WSN. First, the authors introduce the node diversity model according to the difference between the cluster‐head node and the terminal node in WSN. Then, based on the existing 2D cellular automata malware model, an improved mechanism of epidemiological transmission is improved. To make the model more complete, a multi‐player evolutionary game model is established according to the different attack methods and the different coping strategies adopted by the cluster‐head node and the terminal node in WSN. The replication dynamic equation of the strategy evolution is also given. Simulation results show that the proposed model can accurately describe the propagation behaviour of malware in WSN and provide a basis for security defence research of WSN.