scholarly journals Hybrid Krill Herd-ANN Model for Prediction Strength and Stiffness of Bolted Connections

Buildings ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 229
Author(s):  
Iman Faridmehr ◽  
Mehdi Nikoo ◽  
Mohammad Hajmohammadian Baghban ◽  
Raffaele Pucinotti
Keyword(s):  
Correlation Coefficient ◽  
Predictive Accuracy ◽  
Supply And Demand ◽  
Steel Structures ◽  
Ann Model ◽  
Krill Herd Algorithm ◽  
Seat Angle ◽  
Taylor Diagram ◽  
Krill Herd ◽  
Strength And Stiffness

The behavior of beam-to-column connections significantly influences the stability, strength, and stiffness of steel structures. This is particularly important in extreme non-elastic responses, i.e., earthquakes, and sudden column removal, as the fluctuation in strength and stiffness affects both supply and demand. Accordingly, it is essential to accurately estimate the strength and stiffness of connections in the analysis of and design procedures for steel structures. Beginning with the state-of-the-art, the capacity of three available component-based mechanical models to estimate the complex mechanical properties of top- and seat-angle connections with double-web angles (TSACWs), with variable parameters, were investigated. Subsequently, a novel hybrid krill herd algorithm-artificial neural network (KHA-ANN) model was proposed to acquire an informational model from the available experimental dataset. Using several statistical metrics, including the corresponding coefficient of variation (CoV), correlation coefficient (R), and the correlation coefficient provided by the Taylor diagram, this study revealed that the krill herd-ANN model achieved the most reliable predictive accuracy for the strength and stiffness of top- and seat-angle connections with double web angles.

scholarly journals Krill Herd Algorithm for Signal Optimization of Cooperative Control With Traffic Supply and Demand

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 10776-10786 ◽  
Author(s):  
Li Zhihui ◽  
Cao Qian ◽  
Zhao Yonghua ◽  
Tao Pengfei ◽  
Zhuo Rui
Keyword(s):  
Cooperative Control ◽  
Supply And Demand ◽  
Signal Optimization ◽  
Krill Herd Algorithm ◽  
Krill Herd

scholarly journals HKF-SVR Optimized by Krill Herd Algorithm for Coaxial Bearings Performance Degradation Prediction

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 660 ◽  
Author(s):  
Fang Liu ◽  
Liubin Li ◽  
Yongbin Liu ◽  
Zheng Cao ◽  
Hui Yang ◽  
...  
Keyword(s):  
Kernel Method ◽  
Back Propagation ◽  
Vibration Signal ◽  
Back Propagation Neural Network ◽  
Industrial Applications ◽  
Performance Degradation ◽  
Support Vector ◽  
Krill Herd Algorithm ◽  
Krill Herd ◽  
Learning Machine

In real industrial applications, bearings in pairs or even more are often mounted on the same shaft. So the collected vibration signal is actually a mixed signal from multiple bearings. In this study, a method based on Hybrid Kernel Function-Support Vector Regression (HKF–SVR) whose parameters are optimized by Krill Herd (KH) algorithm was introduced for bearing performance degradation prediction in this situation. First, multi-domain statistical features are extracted from the bearing vibration signals and then fused into sensitive features using Kernel Joint Approximate Diagonalization of Eigen-matrices (KJADE) algorithm which is developed recently by our group. Due to the nonlinear mapping capability of the kernel method and the blind source separation ability of the JADE algorithm, the KJADE could extract latent source features that accurately reflecting the performance degradation from the mixed vibration signal. Then, the between-class and within-class scatters (SS) of the health-stage data sample and the current monitored data sample is calculated as the performance degradation index. Second, the parameters of the HKF–SVR are optimized by the KH (Krill Herd) algorithm to obtain the optimal performance degradation prediction model. Finally, the performance degradation trend of the bearing is predicted using the optimized HKF–SVR. Compared with the traditional methods of Back Propagation Neural Network (BPNN), Extreme Learning Machine (ELM) and traditional SVR, the results show that the proposed method has a better performance. The proposed method has a good application prospect in life prediction of coaxial bearings.

scholarly journals Using Long Term Simulations to Understand Heat Transfer Processes during Steady Flow Conditions in Combined Sewers

Water ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 570
Author(s):  
Mohamad Abdel-Aal ◽  
Simon Tait ◽  
Mostafa Mohamed ◽  
Alma Schellart
Keyword(s):  
Heat Transfer ◽  
Heat Recovery ◽  
Predictive Accuracy ◽  
Flow Conditions ◽  
Empirical Relationships ◽  
Taylor Diagram ◽  
Physical Phenomena ◽  
The Heat Transfer Coefficient ◽  
Empirical Approaches

This paper describes a new heat transfer parameterisation between wastewater and in-sewer air based on understanding the physical phenomena observed in free surface wastewater and in-sewer air. Long-term wastewater and in-sewer air temperature data were collected and studied to indicate the importance of considering the heat exchange with in-sewer air and the relevant seasonal changes. The new parameterisation was based on the physical flow condition variations. Accurate modelling of wastewater temperature in linked combined sewers is needed to assess the feasibility of in-sewer heat recovery. Historically, the heat transfer coefficient between wastewater and in-sewer air has been estimated using simple empirical relationships. The newly developed parameterisation was implemented and validated using independent long-term flow and temperature datasets. Predictive accuracy of wastewater temperatures was investigated using a Taylor diagram, where absolute errors and correlations between modelled and observed values were plotted for different site sizes and seasons. The newly developed coefficient improved wastewater temperature modelling accuracy, compared with the older empirical approaches, which resulted in predicting more potential for heat recovery from large sewer networks. For individual locations, the RMSE between observed and predicted temperatures ranged between 0.15 and 0.5 °C with an overall average of 0.27 °C. Previous studies showed higher RMSE ranges, e.g., between 0.12 and 7.8 °C, with overall averages of 0.35, 0.42 and 2 °C. The new coefficient has also provided stable values at various seasons and minimised the number of required model inputs.

Robust, interpretable and high quality fuzzy rule discovery using krill herd algorithm

2016 ◽  
Vol 30 (3) ◽  
pp. 1601-1612 ◽  
Author(s):  
Ali Mohammadi Shanghooshabad ◽  
Mohammad Saniee Abadeh
Keyword(s):  
Fuzzy Rule ◽  
Rule Discovery ◽  
High Quality ◽  
Krill Herd Algorithm ◽  
Krill Herd
Sign in / Sign up

Export Citation Format

Share Document