Abstract:For the new network communication challenges of efficient data interaction between components in open interactive environments, a novel C2N (computing and control network) was proposed. Aiming at the extreme requirements for efficiency, real-time performance, flexibility, and security, C2N adopts intelligent and simplified designs in protocol architecture, planning, application, and security design, providing high-performance and highly flexible basic network support for strong real-time collaborative fusion among heterogeneous resources. Based on a detailed investigation of relevant research work, key technologies of C2N were discussed, such as data link layer enhancement, remote direct memory access for sensor-controllers, and service-oriented sensing and control middleware. It also introduced the key technology research and test evaluation carried out by the network chip and system team of the National University of Defense Technology, and prospected future challenges and research directions to help China gain leading advantages in high-end equipment systems and innovative ecosystems.

Abstract:To further optimize the hardware offloading of collective communication based on the network interface card in the "Tianhe" network, and to support more types of collective communication algorithms and larger message sizes, the order-preserving triggering mechanism and data buffering method for collective communication hardware offloading was investigated. An order-preserving triggering mechanism for concurrent multitasking was proposed, which meets the desired semantics of collective communication and ensures the reproducibility of floating-point computation results. A dynamic network data buffering method based on Hash tables and pulsed credit flow control was proposed to alleviate the contradiction between limited hardware buffering resources and the high demand for buffering a large amount of network data from concurrent multitasking. Experimental results show that compared with software-based collective communication operations, this method can support the hardware offloading of various algorithms for several typical collective communication operations, with significant performance improvement. Meanwhile, the hardware implementation cost is low, especially with high utilization of buffering resources.

Abstract:An ER-MKKNN (enhanced random mixed kernel K nearest neighbors algorithm) was developed to meet the requirements of base station network traffic prediction in ultra-dense 5G/6G environments. A hybrid kernel function was formed by combining a radial basis function kernel with a white-noise kernel, thereby overcoming the trade-off between nonlinear relationship modeling and noise suppression that plagues single-kernel methods. Dual random subsampling of both samples and features, together with a randomized hyperparameter-interval strategy, was employed to bolster generalization stability in high-dimensional, sparse settings. A dynamic weight-allocation mechanism based on inversion of out-of-bag errors was introduced to improve robustness against abrupt traffic fluctuations. Finally, a multi-level parallel architecture was implemented to deliver a scalable prediction framework for ultra-dense network topologies. Experimental evaluations show that ER-MKKNN outperformed deep-learning models in root mean square error, mean absolute percentage error and mean absolute error, respectively, establishing a new technical pathway for intelligent network operations and maintenance.

Abstract:Particle transport simulations using stochastic methods face significant challenges on conventional von Neumann architectures, particularly due to random branching events and irregular memory access patterns. These limitations stem from the fundamental mismatch between probabilistic algorithms and deterministic computing paradigms. To bridge the gap between architecture and algorithms, a probabilistically tunable true random number generator was developed based on spintronic and ferroelectric devices. The physical randomness of spintronic devices was leveraged to provide a physical random source for the architecture, and the throughput of random bits was enhanced through optimized control logic and writing mechanisms. Next, programmable synapses were designed based on the memristive properties of ferroelectric devices, enabling non-volatile continuous weight storage with tunable probabilities. The experimental results indicate that the proposed approach achieves performance improvements ranging from 171 to 1 028 times compared to a general-purpose CPU when solving a sample transport problem. Furthermore, compared to existing spin-transfer torque magnetic tunnel junction based true random number generators, the developed method not only enables tunable probability random sampling but also achieves a throughput of 303 Mbit/s when generating uniformly distributed random sequences.

Abstract:Combining software defined networking and SR (segment routing) can optimize network performance, but in large-scale dynamic networks, excessive link utilization at key nodes can lead to a surge in queue delays. To address this, a SROD-LC (segment routing optimization algorithm based on deep reinforcement learning and load centrality theory) was proposed. By quantifying the importance of network nodes using load centrality theory, key nodes are identified and their link load states are monitored; utilizing a multi-agent reinforcement learning framework, distributed deep reinforcement learning agents are deployed at key nodes, coordinating routing decisions through a shared reward mechanism to achieve proactive optimization of link loads. At the same time, leveraging the flexibility of SR, segment identifier lists are dynamically adjusted to quickly reroute partial traffic, reducing local link utilization and avoiding potential congestion. Simulation experiments based on real network topologies show that when the proportion of SR key nodes is in the range of 0.3~0.5, the SROD-LC algorithm exhibits significant optimization effects, reducing the networks maximum link utilization by 21%~35% compared to baseline algorithms.

Abstract:Efficient inference deployment of large language models faces severe challenges in resource-constrained scenarios. Although current mainstream inference optimization techniques have improved model inference efficiency to some extent, they still suffer from issues like coarse-grained deployment and poor inference accuracy.Based on the discovery that different operators exhibit varying degrees of GPU affinity, an OATO (operator-aware tensor offloading) approach was proposed. OATO could extract operators′semantic knowledge and used it to design an intelligent scheduling algorithm, which further yielded a globally optimal model-deployment plan. Meanwhile, the OATO approach was integrated into the latest large model inference framework Llama.cpp to implement an operator-aware tensor offloading enhanced inference engine, referred to as OALlama.cpp. Experimental results show that compared with the state-of-the-art inference engines Llama.cpp and FlexGen, OALlama.cpp achieves the best inference performance on three large models. Notably, in the scenario where 75% of the LlaMA3-8B model weights are loaded on the GPU, the first-token generation speed of OALlama.cpp is nearly doubled compared with FlexGen and Llama.cpp.

Abstract:AI chips face on-chip memory limits in deep learning. Current optimization methods focus on static computation graphs, leaving room to improve memory efficiency for dynamic graphs. To overcome this limitation, a memory optimization framework for control-flow computation graphs was developed. The framework realized operator-level memory reuse within subgraphs and further achieved recursive reuse across subgraphs by exploiting control-flow characteristics. In addition, a ping-pong buffering strategy for weight data was introduced to mitigate the memory wall between on-chip and off-chip memory, thereby allowing overlapping of memory access and computation operations within subgraphs. Validation on the domestic LUNA AI chip has demonstrated that the proposed framework improves on-chip memory utilization by 5.9% compared with existing methods. Moreover, the strategy effectively alleviates the memory wall problem by reducing data transfer time between on-chip and off-chip memory, resulting in execution efficiency improvements of up to 29%.

Abstract:To achieve accurate and stable online identification of inductance parameters for PMSM (permanent magnet synchronous motor), an online inductance observation method based on virtual voltage vector excitation and current differential response was proposed, which required no additional test signal injection and was decoupled from rotor position, stator resistance, and permanent magnet flux linkage. By introducing the concept of a virtual voltage vector-oriented coordinate system, it was analytically derived and proven that the d-and q-axis inductances of a PMSM can be observed independently of the angular position in the conventional d-q synchronous reference frame. Building on this, the implementation procedure for extracting virtual voltage vectors and current differential information was discussed in detail, enabling non-intrusive inductance identification without any signal injection. The effectiveness and accuracy of the proposed method were validated by comparison with offline test procedures in IEEE standards.

Abstract:For the common stator winding short circuit and rotor eccentricity faults in surface-mounted permanent magnet synchronous motors, a flexible printed circuit board with small footprint and capable of accommodating a large number of windings was used to fabricate the detection coil, which was then arranged in the stator slots to capture magnetic field information. For the stator winding short circuit fault, a winding short circuit detection method using dual orthogonal phase-locked loop to extract fault characteristic values was proposed. This method can effectively distinguish the short circuit resistance, short circuit winding number, and fault location, and was not affected by the motors speed fluctuations. For the rotor eccentricity fault, a differential bridge structure of the detection coil based on high-frequency injection was proposed for eccentricity detection, and ultimately, a 2% eccentricity detection can be achieved. For the composite fault, a fault discrimination scheme based on convolutional neural networks was introduced, and the performance of different learning methods was compared. The experimental results show that under the composite fault condition, a 98% correct rate of winding short circuit assessment is achieved, and the eccentricity detection error using AlexNet with a training data proportion of 60% is only 5%.

Abstract:To address the challenges of intelligent diagnosis for open-circuit faults in power electronic inverters, such as the lack of actual fault samples and the issue of varying characteristic adaptability, a set of optimization methods was proposed from two key intelligent elements: data and algorithm, to support the practical applications of intelligent diagnosis for open-circuit faults in power electronic inverters. For the data element, a fault sample amplification method based on inverters′ characteristics was proposed, which finds out the minimum number of practical samples required for model training. For the algorithm element, an attention-enhanced method and a frequency points adaptive training method for the diagnosis model were proposed, which significantly improve model training effectiveness and diagnosis accuracy under wide-frequency inverter operation. The effectiveness of the proposed optimization methods for the intelligent elements was validated by experiments.

Abstract:An adaptive active disturbance rejection control strategy integrating DRL (deep reinforcement learning) with enhanced PSO (particle swarm optimization) was presented, aiming to improve the speed and thrust control performance of PMSLMs (permanent magnet synchronous linear motors). A mathematical model of the motor was established to analyze its dynamic characteristics, followed by the design of a DRLPSO control framework. This framework leveraged reward mechanisms in reinforcement learning to interact with the environment, dynamically optimized ADRC (active disturbance rejection controller) parameters to accommodate varying operating conditions and external disturbances. The modified PSO algorithm incorporated partitioned inertia weights and cyclically utilized historical global optimal data to iteratively update control policies, refining neural network weights and thereby enhancing search efficiency and optimization accuracy. Experimental results show that the proposed DRLPSO-ADRC method achieves significantly higher tracking precision in position and velocity, along with improved system stability and resistance to thrust disturbances, compared to conventional PSO-ADRC algorithms. These findings validate the effectiveness of the innovative control strategy.

Abstract:Modular multilevel converters exhibit significant capacitor voltage ripple under low-speed, high-torque operating conditions. Existing high-frequency injection suppression schemes increase device current stress and losses while introducing overmodulation risk, and their parameter optimization lacks full operational-condition adaptability. To resolve this issue, a high-frequency injection parameter adaptive optimization strategy considering multiple constraints was proposed. Based on system characteristics and a steady-state model, a variable-step gradient descent algorithm was employed offline to generate a minimum injection-amplitude base parameter reference table that satisfies both capacitor voltage ripple and modulation wave constraints. Subsequently, an online adaptive correction mechanism was designed. Injection parameters were dynamically adjusted in real-time according to acquired capacitor voltage ripple and modulation information, compensating for model deviations and operational variations, forming a coordinated architecture of offline global optimization and online local refinement. Simulation and experimental results show that the proposed strategy maintains the capacitor voltage ripple suppression effect while significantly reducing high-frequency circulating currents, demonstrating dynamic tracking capability for the optimal objective.

Abstract:To improve the design performance of long-range guided rockets, a multidisciplinary parametric model of long-range guided rockets was first established to achieve high-precision performance simulation of guided rockets. A sequence approximation optimization method based on an improved augmented radial basis function was proposed, which enhanced the generalization ability of the augmented radial basis function model through anisotropic techniques. Recursive evolution experimental design and fast cross-validation were used to improve the efficiency of approximation modeling, and an imprecise search strategy was applied for sequence sampling. The effectiveness of the proposed optimization method was verified through numerical examples. A sequence approximate optimization design of the long-range guided rocket was carried out, and the maximum range increase by 16.7% compared to before optimization while satisfying design constraints.

Abstract:To meet the requirements of lightweight and low error sensitivity in the optimization design of stiffened panels, the optimization design of stiffened panels was carried out considering the twist angle error of stringers. The finite element model of post-buckling instability of stiffened panels under axial compression was established, and the sensitivity of the load-carrying capacity to the twist angle error on stringers and the distribution position of the torsional stringer was analyzed. On this basis, a sequential approximate optimization method based on surrogate model was proposed by using parallel sequential sampling strategy, and the lightweight design of stiffened panel was carried out under the influence of twist angle error of stringers. The optimized results show that, compared with the optimization design scheme without error influence, the optimization scheme considering the twist angle error of stringers has lower sensitivity to the twist angle error when the weight is reduced by more than 32%, which can effectively improve the reliability and engineering application value of the optimized structure.

Abstract:Thermally-induced oscillatory rarefied gas flow inside a two-dimensional rectangular cavity was investigated. The effects of the Knudsen numbers and the oscillation frequency of lid temperature on the flow parameters were analyzed. The Shakhov model equation was solved numerically based on the mesoscopic approach in the near-wall region, and the macroscopic approach was adopted in the bulk flow region to reduce the computational cost. To close the numerical iteration procedure, the velocity distribution functions, served as the pseudo boundary between macroscopic and mesoscopic methods, were reconstructed using the high-order Hermite polynomials. Numerical simulations demonstrate that the temperature profile at the central vertical of the cavity predicted by the hybrid method is in good agreement with results from the mesoscopic method, with maximum error 0.23%. Besides, the computational memory cost can be saved up to about 69.91%. The hybrid approach is able to capture the nonlinear phenomenon in the thermally-induced oscillatory rarefied gas flow under high Kn numbers, where the horizontal velocity no longer obeys the law of periodic oscillating cosine function, and the rise time of the horizontal velocity is much longer than the fall time. The thickness of the viscous penetration layer and the disturbed region increases as the Kn number increases, and decreases as the St number increases.

Abstract:In monocular vision-guided high-precision inter-platform pose measurement, existing methods require an accurate 3D model of the target platform and are unable to eliminate the impact of 3D model errors on pose measurement. To address this issue, iterative optimization was performed on the 3D model of the target platform and pose, and a new monocular vision measurement method was proposed. Specifically, the target platforms 3D model was modeled using a set of sparse 3D keypoints. By leveraging multi-view geometric constraint information in sequential images, the sparse 3D keypoint set of the target and 6D pose were treated as parameters to be solved. An objective function was established to minimize object-space residuals, and through solving this optimization problem, iterative optimization of the sparse 3D keypoint set and pose was achieved. Additionally, a sliding window combined with a keyframe selection strategy was adopted to realize real-time and online high-precision monocular vision measurement. Experimental results demonstrate that, through iterative optimization of the sparse 3D keypoint set and pose, the proposed method achieves real-time, online high-precision monocular pose measurement under the condition of an inaccurate 3D model of target platform, while simultaneously improving the accuracy of the targets 3D model.

Abstract:The StS (state-to-state) model and MT(multi-temperature) model were used to numerically simulate and analyze the high-temperature air flow of 11 chemical species behind normal shock waves. The StS model resolved vibrational levels of neutral molecules and electronic levels of neutral atoms; the MT model distinguished the translational-rotational temperature, vibrational temperatures of neutral molecules, and the electron temperature. Simulation results for velocities ranging from 5 km/s to 11 km/s before the shock front demonstrate that immediately behind the shock wave, due to the dissociation and ionization reactions, the higher vibrational levels of molecules and the higher excited electronic levels of atoms are underpopulated relative to the Boltzmann distribution at the corresponding temperatures. Compared to the StS model, the MT model shows that the excitation of vibrational and electronic energies and the attainment of thermal equilibrium in different energy modes occur later, while chemical reactions also take place later but reach chemical equilibrium earlier. The MT model underpredicts vibrational energy loss from chemical reactions while overpredicting electronic energy loss due to electron-impact ionization. Moreover, obtained derived vibrational temperatures of molecules and electron temperature fail to accurately characterize the nonequilibrium population distributions of particle energy levels.

Abstract:To investigate the effect of interlaminar properties on the tensile properties of fiber hybrid composites, two kinds of epoxy resins with different toughness, 7901 and 9A16, were used as the matrix. Interlayer carbon/glass hybrid composites with different numbers of carbon fiber layers were designed and manufactured. The effects of mode Ⅱ interlaminar fracture toughness (G_ⅡC) on the failure mode and mechanical properties of carbon/glass hybrid composites were investigated through both theoretical and experimental investigation. The results show that, the higher mode Ⅱ interlaminar fracture toughness is, the more the carbon layer tends to fail in fragmentation, achieving a higher critical thickness for fragmentation, which is beneficial for achieving pseudo-ductility. In addition, the GⅡC on the modulus and strength of hybrid composites is marginal, as the variation is within 5%. However, the GⅡC demonstrates a significant impact on the pseudo-ductility strain, which is decreased by 40.7% when the GⅡC is increased from 1.75 N/mm to 2.08 N/mm.

Abstract:Power semiconductor modules are the core energy conversion units in power converters. By optimizing their design, the power density can be significantly enhanced. However, current design methods lack systematic summaries. To address this, a systematic summary across four levels(material, chip, packaging and drive) was presented. This included utilizing wide bandgap materials, enhancing chip structure, adopting advanced packaging and improving gate drive design. The underlying principles behind these methods for increasing power density were summarized, and classified and compared the existing research on improving the power density of converters based on power semiconductor module design. The primary challenges in current research were combed, and the future development trend was forecasted.

Abstract:The issues of small UAV (unmanned aerial vehicle) target size, limited pixel coverage in images, weak texture detail information, and the difficulty in effectively extracting infrared UAV target features, which lead to low detection accuracy, were addressed by proposing a multi-scale learning-based target detection algorithm. A multi-scale feature fusion structure was constructed in the neck network of the model, and a multi-scale feature learning module was introduced. Features from both deep and shallow networks were cascaded to capture target features at multiple scales, enriching the semantic and feature information of the feature map, which significantly improved the detection accuracy of small UAV targets. During training, SIoU was used in place of CIoU loss, minimizing the network models loss and enhancing the regression accuracy. Experimental results demonstrate that, compared to other infrared small target detection algorithms and mainstream methods, the proposed approach effectively improves the detection accuracy of UAV targets and meet the detection accuracy requirements for UAV target detection in practical applications.

Abstract:Semantic segmentation of building facades from 3D mesh data is essential for scene understanding but often relies on costly fine-grained annotations. In response to this issue, a semi-supervised learning approach was proposed, introducing a semi-supervised semantic segmentation method based on contrastive learning SS_CC(semi-supervised semantic segmentation based on contrastive learning and consistency regularization) to segment building facades in 3D mesh data. In the SS_CC method, the enhanced contrastive learning module exploited the class separability between positive and negative samples to more effectively utilize class-specific feature information. Additionally, the proposed feature-space consistency regularization loss improved the discriminative capability of the extracted building facade features by leveraging global feature representations. Experimental results show that the proposed SS_CC method outperforms some mainstream methods in F1 score and mIoU, and has relatively better segmentation performance on building walls and windows.

Abstract:To investigate the generation mechanism and variation patterns of the ship corrosion electric field under navigation conditions, the galvanic corrosion cathode of the ship propeller was equated to a rotating disk, and an equivalent model of the corrosion electric field of the rotating disk under turbulent medium conditions was established. Combining the boundary layer theory in fluid mechanics and electrochemical corrosion related theories, the boundary layer flow state and corrosion current density on the surface of a disk under laminar and turbulent medium flow conditions were calculated, and differentiation treatment on the disk was performed. The multiple point charge superposition method was used to calculate the corrosion electric field of a rotating disk under the control of oxygen mass transfer in a flowing medium. The variation law of corrosion electric field on rotating disks at different speeds was studied and experimentally verified. The results indicate that as the rotational speed of the disk increases, the corrosion electric field gradually increases. When the flow state of the medium on the surface of the disk gradually transitions from laminar to turbulent, the corrosion electric field modulus increases significantly.

Abstract:In order to improve the sensitivity of time-frequency system integrity monitoring, a time-frequency system integrity monitoring method based on robust Kalman filter was proposed. In this method, a robust Kalman filter model was constructed using the historical measurement data of time difference, the time difference prediction bias and the frequency bias were estimated in real time, and the consistency detection was carried out separately, so that the integrity monitoring was realized. The model and method were verified through measured data and simulation analysis, and the results show that: this method can effectively detect and identify single faults of phase jump and frequency jump, and alarm the user; in a single fault scenario, compared with the traditional integrity monitoring method, the detection sensitivity is increased by about 25.0%; in a multi-fault scenario, the method can effectively detect faults, but there is a problem of insufficient fault identification, and the detection sensitivity is reduced by about 26.2% compared to a single fault, but it is still better than the traditional method.

Abstract:To investigate the process fluctuation influence on SRAM(static random-access memory) single event upset in sub-20 nm FinFET(fin field-effect transistor) process, a high precision three dimensional technology computer-aid design model based on commercial process fluctuations was established, then simulated to find the FinFET SRAM single event upset threshold under different process corners. The simulation results show that the FinFET SRAM upset threshold has less variation induced by process corner fluctuation. Meanwhile, the sensitive positions of SRAM are on the N-complementary metal oxide semiconductor. Then, to understand the the impact of specific process parameter fluctuations on the single event upset threshold, the process fluctuation factor impact on single event upset was discussed, including fin width, fin height, the oxide thickness and the work function fluctuation. The simulation results show that the first two factors did not affect the upset threshold, while the latter two factors caused slight fluctuations in the upset threshold. Significant reduction in the impact of process fluctuations on FinFET SRAM single event upset threshold is firstly found, which is of great significance for the development of highly consistent radiation hardened aerospace integrated circuits.

Abstract:For high-order continuous linear multi-agent systems, a minimum-energy formation design method with sampled-data communication was proposed. Based on local neighboring information of multi-agent systems at sampling time, a time-varying formation cooperative control protocol with global control energy consumption being considered was presented. By the state-space decomposition method, the time-varying formation problem of multi-agent systems was transformed into the stability problem of decomposed non-consensus subsystems. A formation feasible condition was constructed, and sufficient conditions for the design of time-varying formation under minimum-energy constraints were obtained by the generalized eigenvalue approach, which ensured that the time-varying formation of multi-agent systems could be realized under minimum-energy constraints. Theoretical results were verified by a numerical simulation, and simulation results show that the formation control method with minimum-energy constraints can effectively reduce the global control energy consumption of time-varying formation of multi-agent systems with sampled-data communication.

Abstract:The PHM index is directly affected the design of PHM and the availability of equipment. In response to the shortage of theoretical and implementable methods, a graded demonstration method was introduced, outlining a progression from comprehensive efficiency indicators to PHM comprehensive indicators and then to PHM capability indicators. The availability was selected as the comprehensive efficiency indicator, and the health evaluation rate was defined as the PHM comprehensive indicator. The relationship between availability and health evaluation rate was derived. The optimal health evaluation rate was obtained by maximizing the availability. It was deduced that the health evaluation rate was equal to the product of fault coverage and evaluation accuracy, where depend on the number of sensors and the accuracy of diagnostic/prognostic methods, respectively. This conclusion can guide PHM design. The effectiveness and practicality of this method were verified by cases.

Abstract:In view of the contradiction between the need of the electromagnetic sled for real-time accurate position and speed information and the limitation or high cost of traditional position and speed measurement methods, a new measurement system based on vernier caliper structure was proposed and designed. The principle of high precision positioning and the corresponding position analysis method was expounded, and the position prediction algorithm and Kalman filter algorithm were designed to improve the accuracy and real-time performance. The hardware circuit and software program were designed to realize the function, and a synchronous belt guide rail experimental platform was built to verify the designed system. The test results show that the system can achieve millimeter-level positioning accuracy, and performs well in terms of real-time capability, accuracy and engineering application. The positioning and speed measurement system was applied to the electromagnetic levitation propulsion platform.