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.

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.

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.

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 network′s maximum link utilization by 21%~35% compared to baseline algorithms.

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 G_ⅡC on the modulus and strength of hybrid composites is marginal, as the variation is within 5%.However, the G_ⅡCdemonstrates a significant impact on the pseudo-ductility strain, which is decreased by 40.7% when the G_ⅡC is increased from 1.75 N/mm to 2.08 N/mm.

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.

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.

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.

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 nonvolatile continuous weight storage with tunable probabilities.The experimental results indicate that the proposed approach achieves performance improvements ranging from 171 to 1028 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.

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%.