ID	原文	译文
3953	针对由 2 个稀疏均匀矩形阵列（URA）构成的互质面阵（CPPA），提出了一种基于张量代数的阵列信号处理方法，以提高阵列自由度。	For the co-prime planar array (CPPA) consisting of two sparse uniform rectangular array (URA), a new pro-cessing method based on tensor algebra was proposed to enhance the degrees of freedom (DoF).
3954	首先，对 CPPA 中的 2 个 URA 进行拆分，将这 2 个 URA 的接收信号表示成 2 个张量；	By dividing each URAinto some overlapping subarrays, the received signals of two URAs were expressed as two tensors.
3955	然后将其互相关结果处理成一个虚拟阵列的接收信号张量。	And then thecross-correlation between such two tensors was processed into a received signal tensor of the virtual array.
3956	分析表明，所提方法可将一个具有22 1 L  个物理阵元的 CPPA 转换成一个具有4( 1)16L 个阵元的虚拟稀疏非均匀面阵。	Analysis show that by the new method, the CPPA with22 1 L  physical elements can be transformed into a virtual sparse non-uniformplanar array with4( 1)16L elements.
3957	针对该虚拟面阵，给出了利用张量分解从其接收信号张量中估计入射信号二维波达角的方法，以避免二维谱峰搜索。	For the virtual array, the tensor decomposition-based approach for estimating thetwo-dimensional (2-D) direction of arrival (DoA) of the incident signal is also proposed, which means 2-D spectral peaksearching is avoided.
3958	与文献报道的互质面阵信号处理方法相比，所提方法将阵列自由度从2L 提升至4( 1)116L  ，并具有更好的信号波达角估计性能及较低的计算复杂度，仿真结果证明了所提方法的有效性。	Compared with the co-prime planar signal processing methods reported in the literature, the pro-posed method can increase the DoF from2L to4( 1)116L  , and has the better performance of the 2-D DoA estimationand lower computational complexity. Simulation results demonstrate the efficiency of the proposed method.
3959	针对异构无线网络故障检测与诊断过程中，如何基于小数据量样本进行准确的故障检测与诊断模型的训练的问题，提出了基于生成对抗网络的异构无线网络故障检测与诊断算法。	Aiming at the problem that in the process of network fault detection and diagnosis, how to train the precisefault diagnosis and detection model based on small data volume, a fault diagnosis and detection algorithm based on gen-erative adversarial networks (GAN) for heterogeneous wireless networks was proposed.
3960	首先，分析了异构无线网络环境下的常见网络故障来源，通过 GAN 算法，在小数据量的网络故障样本的基础上，得到大量可靠数据集。	Firstly, the common networkfault sources in heterogeneous wireless network environment was analyzed, and a large number of reliable data sets wasobtained based on a small amount of network fault samples through GAN algorithm.
3961	然后，基于这些数据，利用极端梯度提升算法选择故障检测阶段输入参数的最优特征组合，并完成故障检测与诊断。	Then, the extreme gradient boosting(XGBoost) algorithm was used to select the optimal feature combination of input parameters in the fault detection stageand completed fault diagnosis and detection based on these data.
3962	仿真结果表明，所提算法可以实现对异构无线网络更加准确而高效的故障检测与诊断，准确率可达 98.18%。	Simulation results show that the algorithm can achieve more accurate and efficient fault detection and diagnosis for heterogeneous wireless networks, with an accuracy of 98.18%.