The Atmospheric Diving Suit (ADS) depth movement control have some problems caused by model uncertainty, unknown disturbance. To address these problems, this paper introduces a sliding mode backstepping and time-varying observer disturbance observer with adaptive law. The time-varying disturbance observer can track disturbance on ADS move, and the adaptive sliding mode backstepping controller controls the vertical movement of ADS, thus the tracking error can be controlled to approximately zero. In the paper, to test the controller's stability and proving the controller can track the error caused by model uncertainty and disturbance, the Lyapunov method is used. Simulation proves the controller's performance in overcoming uncertainties and disturbances with good robustness, stability and error-tracking convergence.
The floating cranes used to install large wind turbines are at risk of instability and collision because of the dynamic and changing sea conditions. Ship-motion measurement and prediction of heave is applied for wave compensation, but a high prediction accuracy is difficult because of measurement drift and phase advance. To address this issue, a ship heave motion measurement and prediction scheme based on unscented Kalman filter, phase space reconstruction and long short-term memory (LSTM) is proposed. First, the Stewart platform is used to simulate ship motions, and data are collected by inertial sensors and are processed by unscented Kalman filter. Second, the mutual information is applied to calculate the delay of the ship-motion time series, and the Cao method is used to obtain the embedding dimension, then phase space reconstruction is carried out. Third, the reconstructed data are trained by the multidimensional LSTM to predict extremely short-term ship motions. Simulation results showed that the proposed method provides better measurement and better prediction accuracy, especially under more complex sea conditions.
With the rapid development of 5G technology, industry users in the process of accelerating to the digital intelligent transformation of the network coverage quality, delay, uplink capacity and stability and other performance has an urgent need. 5G private network has technical characteristics such as open network architecture, virtual intelligent orchestration of network elements, and air interface capabilities. It can provide a dedicated network with differential performance, autonomy and control, agility and security on the basis of meeting the requirements of network performance indicators. In this paper, we discuss an area restriction technology based on tracking area code (TAC) control policy for 5G private network. Based on the design of 5G private network architecture and TAC control policy, we focus on proposing the related 5G private network area restriction technology. This scheme can provide a unified data interaction channel for all kinds of wireless intelligent devices, and continuously integrate all kinds of sensing terminals with sensing and monitoring capabilities into all aspects of the industrial production process. Finally, a typical application scenario is presented to demonstrate the effectiveness and safety of the proposed scheme.
The experimental and numerical research, based on a large-bore marine single-cylinder engine, on the influence of the number of nozzle holes on the engine performance was carried out. Two injectors, which have identical structural parameters except the nozzle hole number, were investigated in the experiment. The pressure difference between inlet and exhaust was altered for studying the effect of the number of injector holes on the performance and emission of the diesel engine under different conditions. The experimental results show that the fuel consumption, NOx emission, and SOOT emission of the 8-hole injector are lower than those of the 7-hole injector under the same pressure-difference boundary and same maximum combustion pressure, in which the fuel consumption is reduced by 2-7g/kWh, NOX emission and SOOT emission are reduced by 50-100ppm and 0.2-0.4FSN respectively. The CFD calculation was carried out to explain the experimental results. The simulation shows that the flow rate of the injector with 7 holes is smaller, and the center of combustion is far away from the top dead center, which results in increased fuel consumption. The single-hole fuel jet of the 7-hole injector has larger momentum because of the longer injection duration. After hitting the wall, the fuel jet develops along the wall and in the opposite direction of the injection, and the interference of the fuel jet itself and adjacent jets is strengthened, resulting in more high-temperature zones, and thus the increase of NOx. The strengthened interference of the fuel jet itself and adjacent jets results in high fuel concentration zones, which leads to higher SOOT formation rate and lower SOOT oxidation rate, so that SOOT emission is increased. The experimental and numerical research conducted in this paper can provide guidance for further energy conservation and emission reduction of large-bore marine diesel engines.
This study aims to enhance the accuracy and generalization of motor imagery-based brain-computer interface (MI-BCI) systems using a novel frequency-based graph convolutional neural network technique called Chebyshev Graph Neural Networks (ChebGNNs). The study involves acquiring a substantial amount of motor imagery EEG signals and merging them with an open-source dataset to create a heterogeneous dataset. The study shows that ChebGNNs significantly improve the training and classification performance of the MI-BCI model. ChebGNNs outperform conventional frequency-based and time-domain techniques, achieving an average accuracy of 91.09%, 90.27%, and 89.24% on various datasets. The study demonstrates the promising potential of graph convolutional neural networks in improving the accuracy and generalization of MI-BCI systems. This enables a more effective capture of correlation information and local characteristics in signals, thereby enhancing the overall performance of the system.
