Page 130 - 2022年第53卷第3期

Comprehensive assessment method of water security in Yellow River Basin
based on fuzzy logic

2
1
1
3
1
SHANG Wenxiu ，SHANG Yi ，YAN Dengming ，WU Tianzhi ，PENG Shaoming ，ZHOU Xiangnan 1
（1. Yellow River Engineering Consulting Co.，Ltd.，Zhengzhou 450003，China；
2. North China University of Water Resources and Electric Power，Zhengzhou 450045，China；
3. Luoyang Water Resources Surveying & Designing Co.，Ltd.，Luoyang 471000，China）
Abstract： Water security assessment is important to understand and promote basin water security scientifi⁃
cally. This paper developed a Yellow River Basin water security assessment index system with consideration
of water supply，economy，ecology，environment and disaster control，This paper built a fuzzy logic assess⁃
ment model incorporating influence relationship among indicators，and developed sensitivity analysis method
and water security promotion direction diagnosis method. The results show that the influence relationship
among indicators can increase the impact of single indicator on assessment result，therefore，the sensitivity
of the fuzzy logic assessment model to single indicator alteration is 1.69 times of the sensitivity of the
weighted summation method in this paper. Yellow River Basin water security was basically safe. For provinc⁃
es in the Yellow River Basin， the water security was basically safe in Qinghai， Gansu， Shannxi and
Henan，whereas the water security was in critical state in Ningxia，Inner Mongolia，Shanxi and Shandong.
The water ecological security is the main constraint of the Yellow River Basin water security. Increasing wa⁃
ter ecological security is the best water security promotion direction for the Yellow River Basin，Qinghai，
Gansu，Shannxi and Henan. The results reveal that fuzzy logic has advantages in dealing with multiple indi⁃
cators，non-liner and complex problems，and provides a new way to diagnose water security promotion direc⁃
tion.
Keywords： fuzzy logic； water security； influence relationship of indicators； sensitivity； promotion direction
diagnosis；Yellow River Basin
（责任编辑：于福亮）

（上接第 368 页）

Fault diagnosis of hydropower units based on time-shifted
multiscale attention entropy and random forest

CHEN Fei，WANG Bin，LIU Ting，ZHANG Wenjing，GAO Yuanchen，CHEN Diyi
（College of Water Resources and Architectural Engineering， Northwest A&F University， Yangling 712100，China）

Abstract： In view of the fact that traditional diagnosis methods can not accurately identify faults in high
noise environment， a fault diagnosis method for hydropower units with good anti-disturbance performance
and high recognition rate is proposed in this paper. First，based on the fractal theory，a time-shifted multi⁃
scale attention entropy （TSMATE） is proposed to measure signal complexity. Second， principal component
analysis （PCA） is used to reduce the dimension of TSMATE and overcome the problem of feature redundan⁃
cy. Finally，the reduced dimension features are input into the random forests （RF） model for diagnosis. By
adding noise with different signal-to-noise ratio to the vibration signals， the anti-noise performance of the
proposed model under different noise intensity is investigated. The simulation results show that TS⁃
MATE-PCA-RF achieves diagnosis rates of 98.06% ， 98.89% ， 99.17% and 99.17% under the interference
of four different signal-to-noise ratios of 0 dB，1 dB，2 dB and 3 dB，which verifies the good anti-noise
performance of the proposed model. This study provides a new means for fault diagnosis of hydropower gen⁃
erating units.
Keywords： time-shifted multiscale attention entropy； random forest； principal component analysis； hydro⁃
power generating unit；fault diagnosis

（责任编辑：王 婧）

— 378 —