The innovative technologies for the hardware construction of VR stereo vision systems are summarized and an innovative method for AI-generated VR vision of digital models in MBSE system engineering is proposed. By carefully selecting hardware such as large-screen displays, small-pitch LED displays, and active stereo display devices, the study innovatively realizes a VR visual hardware system that integrates high-resolution, multi-channel stereo synchronization, and multi-channel stereo stitching, all while incorporating functions for scientific research demonstrations, validation, and conference discussions. Furthermore, through data-driven Al algorithms, it accurately and efficiently generates VR vision for various types of digital models in MBSE system engineering. Technical references for the software and hardware construction of VR systems for other users are provided.

In order to realize the unsupported launch of a medium-sized launch vehicle, a movable deflector scheme is adopted. Deflector has gone through a complete development process such as scheme design, gas flow field simulation analysis, metal matrix production, ablation test, heat protection cap production, etc., and has finally been successfully applied in the unsupported launch of medium-sized liquid launch vehicles.

In the view of the difficulty of digital coordination of coordination hole of the carrier rocket part, the influencing factors of digital coordination processing are analyzed and the main reasons are determined, and the influence of measurement error and positioning on the machining accuracy is analyzed through comparative test and theoretical analysis. On this basis, the digital coordinated machining control scheme is put forward, and the typical part is taken as the object to carry out coordinated hole test, the test results show that the digital quantity coordination machining hole position accuracy meets the requirements of assembly coordination, and the test coordination with the tooling platform, laying the foundation for the engineering application of the end-frame digital quantity coordinated machining.

With the rapid development of commercial aerospace, traditional measurement and control resources are unable to meet the demand for high-density and rapid launch of commercial rockets. There is a shortage of measurement and control resources in the aviation area, and space-based measurement and control resources based on Tianlian satellites are not suitable for commercial space launch modes. The performance indicators of civil and commercial communication satellites are investigated, and the Ku frequency band space-based measurement technology based on APSTAR-6D satellite is studied. A space-based measurement and control system implementation scheme has been proposed by combining link calculations with satellite performance. Finally, it provides new measurement and control resources for commercial space rocket launches, and the measurement and control can cover the needs of typical SSO orbit launch vehicles.

With the continuous development of science and technology, space launch has entered a new stage of development, and the research of space launch mission planning technology has been deepened. The current progress and advanced technology of space launch mission planning are mainly discussed, including the mission planning stage, process and significance, and the analysis of the current difficult problems is focused. The relevant opinions and suggestions are put forward. The future development trend is looked forward to, and finally the improved particle swarm algorithm is adopted to simulate and analyze the launch selection, and the experimental results show that the adopted algorithm effectively solves the problem, and is able to provide a plan with low launch cost and high launch success rate at the same time.

The hypersonic vehicle needs to separate from the booster stage in an environment with low altitude and high dynamic pressure. The current prediction of separation and attitude control based on limit deviation method is not real enough and the design is heavily redundant. For inserted separation with long stroke and small gap, the collision detection of two stages cannot be carried out during the attitude control design process. To solve the above problems, a coupling calculating method of separation and attitude control is proposed, which introduces the attitude control model into separation dynamic model. Design redundancy is reduced and the level of refine is improved. Also, collision detection can be realized in the whole process, providing support for ensuring the safety of the separation and attitude control process. The method provides a basis for the time to start attitude control of the upper stage, and has guiding significance for optimization design of separation time sequence.

Iron loss occupies a large proportion of the losses of in-wheel motor for special vehicle, which directly affects the efficiency and temperature rise of the drive system. In order to accurately calculate the iron loss, time-stepping finite element analysis is adopted to analyze the flux density waveforms at different regions of the stator core by taking the in-wheel motor with rated power of ${70}\mathrm{\;{kW}}$ for example. Harmonic analysis of radial and tangential flux density waveforms at different regions of the stator core is carried out. The impact of rotating magnetic field and harmonic component on the stator iron loss is further studied. Three different iron loss calculation methods are adopted to calculate the stator iron loss after the flux density waveforms and harmonic analysis are carried out. The stator iron loss values separated from the efficiency and loss test of the in-wheel motor are compared with the calculation values of different calculation methods. The results show that the calculation method in consideration of the effect of rotating magnetic field and harmonic component has the highest accuracy and its calculation result is the closest to the test result, which verifies the validity of the calculation method.

Along with the surge of radio application, electronic communication in interference environments has become increasingly important. The spectrum sensing technique matters in surmounting the frequency conflict of radio. However, the complex environment hinders the efficient feature extraction from the received spectrum signal and reduces the signal practicality. Recently, the artificial intelligence has been widespread in communication field and crucially influenced the electronic countermeasures. Consequently, based on the deep learning, this work proposes a spectrum sensing method to mix DenseNet and MLP-Mixer. Firstly, the model processes and transforms the spectrum signal data to feature images by Deepinsight Net and the generative adversarial networks renew an image. After obtaining the feature image, aspectrum sensing method integrating DenseNet and MLP-Mixer is used in order to sense the channel occupancy of primary user. Compared with the existing model through ablation experiments, the proposed method improves the detection probability of spectrum sensing better.

Aiming at the rotor axis of PIGA with a zero bias, the transverse acceleration will be coupled to the direction of the input axis to form a cross-coupling error. For the decoupled nonlinear PIGA output expression, the influence of a time-varying input acceleration and the transverse acceleration which is applied to the output are considered, the computing method of PIGA’s output analytic expression relying on the base acceleration of three orthogonal direction and angles of outer axis and rotor shaft as input information is given. On this basis, the model parameters are calibrated by recursive iteration method, in addition to which, the output value compensation method of gyro accelerometer is given. By comparing the error results before and after parameter compensation, the input acceleration error is reduced from ${0.05}\mathrm{\;g}$ to ${0.002}\mathrm{\;g}$, which verifies the effectiveness of the cross coupling error compensation in the output model in the way of improving the measurement accuracy.

An improved ACO is proposed for two-dimensional path planning of flight vehicles to solve the problems such as slow convergence speed, easy to fall in stagnation and zigzag path with large angles in basic ACO. First, the improved algorithm optimizes extend method to accelerate convergence. Then, a new pheromone strategy is put forward to increase the utilization of pheromone information while preventing ant from falling into stagnation. At last, local optimization method is introduced to reduce the twists and turns in the searched path. According to the simulation results, the improved ACO has superiority in convergence, iteration number and quality of path. The result proves that the improved algorithm can increase the rate of convergence and path quality compared with basic ACO.