This paper presents the design and innovation of fuzzy control algorithms in an underwater weed localization system, which aims to achieve accurate underwater weed identification and localization by integrating sensor arrays, data processing centers, fuzzy logic controllers, and actuation units. The system model combines optical imaging, acoustic sensing, and underwater robot dynamics control and employs a deep fuzzification layer with reinforcement learning algorithms to optimize the fuzzy inference process, as well as particle swarm optimization techniques to dynamically adjust the fuzzy parameters. The experimental evaluation utilizes a comprehensive dataset to verify the localization accuracy and robustness of the system in complex underwater environments. Through model training and environmental impact testing, the system demonstrates excellent performance and adaptability, providing an advanced technical solution for underwater ecological management and aquatic environment monitoring.

In recent years, many low-orbit satellites have been widely used in the field of scientific research and national defense in China. In order to meet the demand of high-precision satellite orbit in China’s space, surveying and mapping, and other related fields, navigation satellites are of great significance. The UKF (unscented Kalman filter) method is applied to space targets’ spaceborne GPS autonomous orbit determination. In this paper, the UKF algorithm based on UT transformation is mainly introduced. In view of the situation that the system noise variance matrix is unknown or the dynamic model is not accurate, an adaptive UKF filtering algorithm is proposed. Simulation experiments are carried out with CHAMP satellite GPS data, and the results show that the filtering accuracy and stability are improved, which proves the algorithm’s effectiveness. The experimental results show that the Helmert variance component estimation considering the dynamics model can solve the problem of reasonable weight determination of BDS/GPS observations and effectively weaken the influence of coarse error and improve the accuracy of orbit determination. The accuracy of autonomous orbit determination by spaceborne BDS/GPS is 1.19 m and 2.35 mm/s, respectively.

With the high attention to the safety of rail transit operation, the rail driver as the main body of the rail transit system, the driver has a crucial impact on the safety of operation. In order to study the influencing factors of illegal driving of rail drivers, 301 rail drivers in a city subway company in China were investigated by questionnaire. And the use of SPSS 25.0 data analysis software for the driver's age, driving age and other basic situation descriptive analysis and correlation analysis, to explore the relationship between human biological rhythm theory and the driver 's illegal driving, to determine the scope of the critical day of serious illegal driving, is conducive to the scientific arrangement of the driver 's driving work, provides a reference for the safe operation of rail transit.

Considering that the global navigation satellite system (GNSS) has the influence of positioning and atmospheric signals from time to time in meteorology, errors caused by moisture, and so on in the effect of the propagation path, these factors have led to the influence of various indexes of meteorological factors. In this study, a meteorological prediction algorithm based on the CNSS and particle swarm optimization is proposed. Aiming at the phenomenon that the particle swarm optimization (PSO) algorithm is prone to slow convergence speed and low optimization accuracy and there is a local optimal but cannot achieve the global optimal, an adaptive Kent chaotic map PSO algorithm is proposed. Through the comprehensive analysis of the meteorological input indicators in the GNSS, a noncurrent weight evaluation system is proposed. Under different evaluation systems, the PSO algorithm is applied, and PCA weight can obtain the best prediction effect. Then, the GA model, PSO model, and ADPSO model are used to predict PM2.5 index in meteorology. The results show that the proposed ADPSO algorithm has a good performance in RMSE, MAE, and R 2 model evaluation.

The BeiDou Satellite Navigation System of China can provide users with high precision, as well as all-weather and real-time positioning and navigation information. It can be widely used in many applications. However, new challenges appear with the expansion of the 5G communication system. To eradicate or weaken the influence of various errors in BeiDou positioning, a BeiDou satellite positioning algorithm based on GPRS technology is proposed. According to the principles of the BeiDou Satellite navigation system, the navigation and positioning data are obtained and useful information are extracted and sent to the communication network through the wireless module. The error is corrected by establishing a real-time kinematic (RTK) mathematical model, and the pseudorange is calculated by carrier phase to further eliminate the relativistic and multipath errors. Based on the results of error elimination, the BeiDou satellite positioning algorithm is improved and the positioning error is corrected. The experimental results show that the positioning accuracy and efficiency of the algorithm can meet the actual needs of real-time dynamic positioning systems.

Given the problem that the existing method of station distributing the pseudosatellite system cannot ensure both its coverage and position in a situation of signal occlusion, it proposed a new stationary layout method with an elite strategy for a ground-based pseudosatellite positioning system based on the elite strategy of the nondominant genetic rankings (NSGA-II). The geometrical design of the pseudosatellite system is calculated by visual domain analysis and precision factors for the signal coverage age and base station. To optimize the algorithm, the NSGA-II algorithm is used. An earth pseudosatellite positioning system method of stationary distribution is obtained that simultaneously optimizes signal coverage and positioning accuracy. The algorithm is better distributed and has a certain superintendence compared with the traditional genetic algorithm.

In order to overcome the problems of the traditional algorithm, such as the time-consuming execution of acquisition instructions, low signal tracking accuracy, and low signal capture accuracy, a global satellite positioning receiver acquisition and tracking algorithm based on UWB technology is designed in this study. On the basis of expounding the pulse generation method and working principle in UWB technology, this paper analyzes in detail the characteristics of UWB technology, such as antimultipath, low power consumption, and strong penetration. Then, on the basis of window function filtering, in the process of three-dimensional search of global satellite positioning signal, firstly, the satellite signal entering the GPS software receiver is processed by RF front-end mixing and AD sampling, and then, the signal tracking and navigation message solving are completed according to the relationship between the influence factor and Doppler frequency offset. The experimental results show that the execution time of the acquisition instruction of the proposed algorithm varies between 1129 ms and 1617 ms; the signal tracking accuracy ranges between 0.931 and 0.951, and the signal capture accuracy ranges between 93.3% and 95.6%, which proves that the proposed algorithm has achieved the design expectation.

Two obstacles lie in the traditional Signal Strength Fingerprint Positioning method. Initially, the algorithm cannot converge quickly and accurately due to massive data generated by large indoor environment. Secondly, it is difficult to determine a specific floor in a building using the received Signal Strength(RSS). This article proposes a method, which uses convolutional neural network (CNN) to classify the floor and location of Bluetooth RSS as well as magnetic field data to calculate the final coordinates, could apply Fingerprint Positioning into indoor environment with large areas and multiply floors. The method involves converting the collected Bluetooth RSS into the fingerprint image required for calculation and establishing the CNN for classification training. Subsequently, the real-time Bluetooth RSS are imported into the CNN to classify the floor and determine the transmitters location. Additionally, the observers coordinates are matched using the magnetic field data. Our experiments suggested that the proposed method can classify floors and transmitters locations with predictable bunds of 0.9667 and 0.9333, respectively. At the same time, the average positioning error is less than 1.2 m, which is 43.32% and 44.67% higher than the traditional Bluetooth and magnetic field fingerprint positioning. The accuracy of dynamic positioning is also within 1.55 meters.