深圳大学学报理工版

王武亮,江辉.基于多任务贝叶斯压缩感知的电能质量信号重构[J].深圳大学学报理工版,2021,38(1):77-84.[doi:10.3724/SP.J.1249.2021.01077]
WANG Wuliang and JIANG Hui.Power quality signal reconstruction based on multitask Bayesian compressive sensing[J].Journal of Shenzhen University Science and Engineering,2021,38(1):77-84.[doi:10.3724/SP.J.1249.2021.01077]

点击复制

基于多任务贝叶斯压缩感知的电能质量信号重构

王武亮,江辉

深圳大学物理与光电工程学院,广东深圳 518060

关键词：信息处理技术; 压缩感知; 电能质量; 多任务贝叶斯; 信号重构

Power quality signal reconstruction based on multitask Bayesian compressive sensing

WANG Wuliang and JIANG Hui

College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China

Keywords： information processing technology; compressive sensing; power quality; multitask Bayesian; signal reconstruction

DOI: 10.3724/SP.J.1249.2021.01077

备注

摘要

全文

图/表

参考文献

压缩感知技术突破奈奎斯特采样定理限制,能够有效降低数据的存储和传输成本,只需较少的样本就能对电能质量信号进行重构,对电能质量的检测分析具有重要意义.针对电能质量信号,提出一种基于多任务贝叶斯压缩感知理论的电能质量信号压缩重构算法,该算法选择快速傅里叶变换基作为稀疏基对电能质量信号进行稀疏处理,将所得稀疏向量的实部和虚部构成两个压缩重构任务; 利用超参数估计的共享机制,考虑两个任务间数据的内在相关性,对电能质量信号进行重构.仿真结果表明,该算法在压缩重构含复杂扰动的电能质量信号时,其抗噪性能和重构精度均优于正交匹配追踪算法和贝叶斯压缩感知算法,更加适用于含有复杂扰动的电能质量信号的压缩重构.

Compressed sensing technology breaks through the limitation of Nyquist sampling theorem, and can effectively reduce the cost of data storage and transmission. Only a few samples are needed to reconstruct the power quality signal by using the compressed sensing technology, which is of great significance for the detection and analysis of power quality. We propose an algorithm based on multitask Bayesian compressed sensing(MT-BCS)theory for power quality signals compression and reconstruction in this paper. The power quality signals are changed to sparse vectors by taking the fast Fourier transform basis as the sparse basis. The real and imaginary parts of sparse vectors are then treated as two compression and reconstruction tasks. Considering the internal correlation of data corresponding to these two tasks, the power quality signal is reconstructed using the sharing mechanism of hyperparameter estimation. The simulation results show that the algorithm is superior to the orthogonal matching pursuit algorithm and the Bayesian compressed sensing algorithm in anti-noise performance and reconstruction accuracy, and is more suitable for compressing and reconstructing power quality signals with complex disturbance.

引言
1 MT-BCS
2 基于MT-BCS的电能质量信号重构
3 仿真与结果分析
4 结语

[1] CANDÈS E J, ROMBERG J K, TAO T. Stable signal recovery from incomplete and inaccurate measurements[J]. Communications on Pure and Applied Mathematics, 2006, 59(8): 1207-1223.
[2] CANDES E J, TAO T. Near-optimal signal recovery from random projections: universal encoding strategies?[J]. IEEE Transactions on Information Theory, 2006, 52(12): 5406-5425.
[3] DONOHO D L. Compressed sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306.
[4] WANG Xu, TIAN Lijun, GAO Yunxing, et al. Analysis of power quality disturbance signal based on improved compressed sensing reconstruction algorithm[C]// IEEE Transportation Electrification Conference and Expo, Asia-Pacific(ITEC Asia-Pacific). Harbin, China: IEEE, 2017: 1-5.
[5] 童新,卿朝进,夏凌,等.基于稀疏度特征的短时电能质量扰动信号重构方法[J].电测与仪表,2018,55(20):114-121.
[6] 刘国海,丁灵卫,沈跃, 等.广义正交匹配追踪电能质量信号重构方法[J].电测与仪表,2019,56(10):69-74.
[7] 刘嫣,汤伟,刘宝泉.基于压缩感知的电能质量扰动数据稀疏分析与改进重构算法[J].电工技术学报,2018(1):3461-3470.
[8] 张锐, 吴庭宇. 基于压缩感知的电能质量压缩采样重构算法[J]. 数据采集与处理, 2019, 34(2):214-222.
[9] BISHOP C M, TIPPING M E. Variational relevance vector machines[C]// Proceedings of the 16th Conference in Uncertainty in Artificial Intelligence. San Francisco, USA:[s. n.], 2000: 46-53.
[10] TIPPING M E. Sparse Bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research, 2001, 1(3): 211-244.
[11] WIPF D P, RAO B D. Sparse Bayesian learning for basis selection[J]. IEEE Transactions on Signal Processing, 2004, 52(8): 2153-2164.
[12] JI Shihao, XUE Ya, CARIN L. Bayesian compressive sensing[J]. IEEE Transactions on Signal Processing, 2008, 56(6): 2346-2356.
[13] JI Shihao, DUNSON D, CARIN L. Multitask compressive sensing[J]. IEEE Transactions on Signal Processing, 2009, 57(1): 92-106.