Tingting Xu

With the integration and development of multiple disciplines, as well as a large amount of research on multilevel interconnection networks, wireless sensor networks have become a new access point and have attracted widespread attention worldwide. However, limited by the characteristics of the wireless sensor network itself, the energy problem has repeatedly restricted its function, which needs to be solved urgently. This paper mainly improves the Geographical and Energy-Aware Routing (GEAR) based on cyber-physical systems and energy-aware routing protocols, which reduces the resource consumption of network nodes, achieves network power balance, and further extends the system life cycle. Although the open sharing of the network layer makes CPS more efficient in actual use, it also increases the risks faced by CPS. Among these potential risks, cyberattacks have become the main security problem that CPS must solve with the greatest destructive power. Among them, Denial of Service (DoS) is the simplest and most destructive type of network attack. We can allow the system to reject normal requests for sending and receiving data using the network resources of the communication channel, thereby performing security control. From the perspective of control, this paper studies the security control of CPS in DOS attacks. Firstly, considering the diversity of CPS packet loss factors, assuming that there is an upper limit on the probability characteristics of the total number of packet loss development, the Markov process of inherent packet loss and the Markov process of DoS attack satisfying this constraint are analyzed, and the above two independent packet loss factors are described on this basis. Two independent packet loss factor descriptions are given in the following. In this paper, through the research of wireless sensor networks, it is applied to the cyber-physical system and the cyber-physical system is further improved.

At present, the sample comparison of intelligent electric meters in power grid companies mainly relies on manual inspection. With the development of semiconductor technology and the increasing demand of intelligent electric meters, the disadvantages of this method, such as low detection efficiency, high misjudgment rate, are becoming more prominent. In this paper, a method for automatically detecting and identifying the intelligent electric meter circuit board chip is proposed, and a chip character recognition system based on convolutional neural network (CNN) is designed. The system is mainly divided into two parts: chip positioning and character recognition. The chip is positioned based on the method of layout analysis and edge detection. According to the difference between the characteristics of the chip and the characteristics of the PCB background, preprocess the images, detect the chip identification and obtain multiple candidate regions. Finally, candidate regions are screened based on chip characteristics. The gray-level projection method is used to segment characters. A single character image is obtained by row segmentation and column segmentation. At the same time, the optimization algorithm for character adhesion and fracture problem is proposed to improve the segmentation accuracy. For the character recognition module, build a convolutional neural network to extract character features, and the normalized character is input into the trained neural network for recognition. The recognition accuracy of test sets is high, and the time for recognizing a single character is about 0.35 seconds. Compared with the traditional detection methods, the proposed method has higher detection efficiency and recognition accuracy.