scholarly journals Placement and sizing of EESS bundled with uncertainty modeling by two-stage stochastic search based on improved shark smell optimization algorithm in micro-grids

2021 ◽  
Vol 7 ◽  
pp. 4792-4808
Author(s):  
Ye-fei Tian ◽  
Rui-jin Liao ◽  
Saeid Gholami Farkoush
Atmosphere ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 64
Author(s):  
Feng Jiang ◽  
Yaqian Qiao ◽  
Xuchu Jiang ◽  
Tianhai Tian

The randomness, nonstationarity and irregularity of air pollutant data bring difficulties to forecasting. To improve the forecast accuracy, we propose a novel hybrid approach based on two-stage decomposition embedded sample entropy, group teaching optimization algorithm (GTOA), and extreme learning machine (ELM) to forecast the concentration of particulate matter (PM10 and PM2.5). First, the improvement complementary ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is employed to decompose the concentration data of PM10 and PM2.5 into a set of intrinsic mode functions (IMFs) with different frequencies. In addition, wavelet transform (WT) is utilized to decompose the IMFs with high frequency based on sample entropy values. Then the GTOA algorithm is used to optimize ELM. Furthermore, the GTOA-ELM is utilized to predict all the subseries. The final forecast result is obtained by ensemble of the forecast results of all subseries. To further prove the predictable performance of the hybrid approach on air pollutants, the hourly concentration data of PM2.5 and PM10 are used to make one-step-, two-step- and three-step-ahead predictions. The empirical results demonstrate that the hybrid ICEEMDAN-WT-GTOA-ELM approach has superior forecasting performance and stability over other methods. This novel method also provides an effective and efficient approach to make predictions for nonlinear, nonstationary and irregular data.


Author(s):  
Minshui Huang ◽  
Xihao Cheng ◽  
Zhigang Zhu ◽  
Jin Luo ◽  
Jianfeng Gu

A novel two-stage method is proposed to properly identify the location and severity of damage in plate structures. In the first stage, a superposition of modal flexibility curvature (SMFC) is adopted to locate the damage accurately, and the identification index of modal flexibility matrix is improved. The low-order modal parameters are used and a new column matrix is formed based on the modal flexibility matrix before and after the structure is damaged. The difference of modal flexibility matrix is obtained, which is used as a damage identification index. Meanwhile, based on SMFC, a method of weakening the “vicinity effect” is proposed to eliminate the impact of the surrounding elements to the damaged elements when damage identification is carried out for the plate-type structure. In the second stage, the objective function based on the flexibility matrix is constructed, and according to the damage location identified in the first stage, the actual damage severity is determined by the enhanced whale optimization algorithm (EWOA). In addition, the effects of 3% and 10% noise on damage location and severity estimation are also studied. By taking a simply supported beam and a four-side simply supported plate as examples, the results show that the method can accurately estimate the damage location and quantify the damage severity without noise. When considering noise, the increase of noise level will not affect the assessment of damage location, but the error of quantifying damage severity will increase. In addition, damage identification of a steel-concrete composite bridge (I-40 Bridge) under four damage cases is carried out, and the results show that the modified method can evaluate the damage location and quantify 5%–92% of the damage severity.


2017 ◽  
Vol 14 (8) ◽  
pp. 694-702 ◽  
Author(s):  
Mingxuan Mao ◽  
Li Zhang ◽  
Qichang Duan ◽  
O.J.K Oghorada ◽  
Pan Duan ◽  
...  

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 15611-15631
Author(s):  
Wen-Jun Li ◽  
Yu-Ting Wang ◽  
Lei Nie ◽  
Yinghui Wu ◽  
Liu Peng

Sign in / Sign up

Export Citation Format

Share Document