Showing papers by "Jong Wan Hu published in 2021"

Novel application of adaptive swarm intelligence techniques coupled with adaptive network-based fuzzy inference system in predicting photovoltaic power

Abstract: Accurate photovoltaic (PV) power prediction is necessary for future development of the micro-grids projects and the economic dispatch sector. This study investigates the potential of using a novel hybrid approach of adaptive swarm intelligence techniques and adaptive network-based fuzzy inference system (ANFIS) in estimating the PV power of a solar system at different time horizons, from 0 to 24 h. The developed approach is an integration of ANFIS and particle swarm optimization (PSO) with adaptive and time-varying acceleration coefficients, i.e., ANFIS-APSO (ANFIS-PSO with adaptive acceleration coefficients) and ANFIS-IPSO (ANFIS-PSO with time-varying acceleration coefficients), were developed. The performance of the proposed models was compared with other hybrid ANFIS models, namely ANFIS-PSO (ANFIS coupled with PSO), ANFIS-BBO (ANFIS coupled with biogeography-based optimization), ANFIS-GA (ANFIS coupled with genetic algorithm), and ANFIS-GWO (ANFIS coupled with grey wolf optimization). For this purpose, the climatic variables and historical PV power data of a 960 kWP grid-connected PV system in the south of Italy were used to design and evaluate the models. Several statistical analyses were implemented to evaluate the accuracy of the proposed models and assess the impact of variables that affects the PV power values. The experimental results show that the proposed ANFIS-APSO attained the most accurate prediction of the PV power with R2 = 0.835 and 0.657, RMSE = 0.088 kW and 0.081 kW, and MAE = 0.077 kW and 0.079 kW in the testing phase at time horizons 12 h and 24 h, respectively. Based on the obtained results, the newly constructed ANFIS-APSO outperformed the standard ANFIS-PSO model including other hybrid models, and hence very potential to be a new alternative to assist engineers for predicting the PV power of solar systems at short- and long-time horizons.

Reliability Analysis of Pile Foundation Using Soft Computing Techniques: A Comparative Study

Abstract: Uncertainty and variability are inherent to pile design and consequently, there have been considerable researches in quantifying the reliability or probability of failure of structures. This paper aims at examining and comparing the applicability and adaptability of Minimax Probability Machine Regression (MPMR), Emotional Neural Network (ENN), Group Method of Data Handling (GMDH), and Adaptive Neuro-Fuzzy Inference System (ANFIS) in the reliability analysis of pile embedded in cohesionless soil and proposes an AI-based prediction method for bearing capacity of pile foundation. To ascertain the homogeneity and distribution of the datasets, Mann–Whitney U (M–W) and Anderson–Darling (AD) tests are carried out, respectively. The performance of the developed soft computing models is ascertained using various statistical parameters. A comparative study is implemented among reliability indices of the proposed models by employing First Order Second Moment Method (FOSM). The results of FOSM showed that the ANFIS approach outperformed other models for reliability analysis of bearing capacity of pile and ENN is the worst performing model. The value of R2 for all the developed models is close to 1. The best RMSE value is achieved for the training phase of the ANFIS model (0 in training and 2.13 in testing) and the poorest for the ENN (2.03 in training and 31.24 in testing) model. Based on the experimental results of reliability indices, the developed ANFIS model is found to be very close to that computed from the original data.

Experimental investigation of smart shear dampers with re-centering and friction devices

Abstract: Eccentrically braced frames (EBFs) with vertical shear links are lateral load resisting systems having considerable strength and ductility. In this study, an innovative hybrid damper, consisting of four shape memory alloy (SMA) plates, two friction devices, and six polyurethane springs, is proposed and evaluated as a replacement for the vertical shear link. The proposed smart shear dampers are designed to lessen the frequency and severity of deformation and damage to the main structure by earthquakes. Because the proposed smart shear damper is independent of the main structure, it can be repaired rapidly, which lowers the cost of maintenance. Other advantages include ease of assembly and installation. In this study, the seismic performance of the proposed damper is experimentally investigated and evaluated. Quasi-static cyclic loading with displacement control is applied to the side of the damper, and the components of the damper are considered individually. Eight shear dampers, including four SMA plates and four steel plates, are tested under identical loading protocols, and then the effect of each component is measured. The results show that the proposed SMA damper decreases residual displacement by 50%–95% depending on the type of damper system and that the polyurethane springs of the proposed shear damper provide considerable re-centering capability.

Data-Driven Approach for Rainfall-Runoff Modelling Using Equilibrium Optimizer Coupled Extreme Learning Machine and Deep Neural Network

Abstract: Rainfall-runoff (R-R) modelling is used to study the runoff generation of a catchment. The quantity or rate of change measure of the hydrological variable, called runoff, is important for environmental scientists to accomplish water-related planning and design. This paper proposes (i) an integrated model namely EO-ELM (an integration of equilibrium optimizer (EO) and extreme learning machine (ELM)) and (ii) a deep neural network (DNN) for one day-ahead R-R modelling. The proposed R-R models are validated at two different benchmark stations of the catchments, namely river Teifi at Glanteifi and river Fal at Tregony in the UK. Firstly, a partial autocorrelation function (PACF) is used for optimal number of lag inputs to deploy the proposed models. Six other well-known machine learning models, called ELM, kernel ELM (KELM), and particle swarm optimization-based ELM (PSO-ELM), support vector regression (SVR), artificial neural network (ANN) and gradient boosting machine (GBM) are utilized to validate the two proposed models in terms of prediction efficiency. Furthermore, to increase the performance of the proposed models, paper utilizes a discrete wavelet-based data pre-processing technique is applied in rainfall and runoff data. The performance of wavelet-based EO-ELM and DNN are compared with wavelet-based ELM (WELM), KELM (WKELM), PSO-ELM (WPSO-ELM), SVR (WSVR), ANN (WANN) and GBM (WGBM). An uncertainty analysis and two-tailed t-test are carried out to ensure the trustworthiness and efficacy of the proposed models. The experimental results for two different time series datasets show that the EO-ELM performs better in an optimal number of lags than the others. In the case of wavelet-based daily R-R modelling, proposed models performed better and showed robustness compared to other models used. Therefore, this paper shows the efficient applicability of EO-ELM and DNN in R-R modelling that may be used in the hydrological modelling field.

A novel approach for resilient modulus prediction using extreme learning machine-equilibrium optimiser techniques

Abstract: This study presents a novel hybrid intelligent approach using Extreme Learning Machine (ELM) and Equilibrium Optimiser (EO) (ELM-EO) for predicting resilient modulus, Mr of Unbound Granular Materia...

Structural Retrofitting of Corroded Reinforced Concrete Beams Using Bamboo Fiber Laminate.

Abstract: Corrosion creates a significant degradation mechanism in reinforced concrete (RC) structures, which would require a high cost of maintenance and repair in affected buildings. However, as the cost of repairing corrosion-damaged structures is high, it is therefore pertinent to develop alternative eco-friendly and sustainable methods. In this study, structural retrofitting of corroded reinforced concrete beams was performed using bamboo fiber laminate. Three reinforced normal weight concrete beams were produced, two of which were exposed to laboratory simulated corrosion medium, and the remaining one sample served as control. Upon completion of the corrosion cycle, one of the two corroded beams was retrofitted externally with a prefabricated bamboo fiber laminate by bonding the laminate to the beam surface with the aid of an epoxy resin. The three beams were subjected to loading on a four-point ultimate testing machine, and the loads with corresponding deflections were recorded through the entire load cycle of the beams. Finally, the mass loss of embedded steel reinforcements was determined to measure the effect of corrosion on the beams and the steel. The result showed that corroded beams strengthened with bamboo laminates increase the bearing capacity. Using a single bamboo laminate in the tensile region of the corroded beam increased the ultimate load capacity of the beam up to 21.1% than the corroded beam without retrofit. It was demonstrated in this study that the use of bamboo fiber polymer for strengthening destressed RC beams is a more sustainable approach than the conventional synthetic fibers.

Assessment and prediction of land-use/land-cover change around Blue Nile and White Nile due to flood hazards in Khartoum, Sudan, based on geospatial analysis

Abstract: Rising floodwaters in the Blue Nile (BN) and White Nile (WN) tributaries continually affects people’s lives and the safety of infrastructures in Khartoum, the capital of Sudan. Recently, floods hav...

Improving accuracy of local geoid model using machine learning approaches and residuals of GPS/levelling geoid height

Abstract: This study aims to use GPS/Levelling data and machine learning techniques (MLs) to model a high precision local geoid for Kuwait. To improve the accuracy of a local geoid the global geopotential mo...

Experimental study on the optimized design of butterfly-shaped dampers

Abstract: Structural fuses are manufactured from oriented steel plates for use in seismic protective systems to withstand significant lateral shear loads. These systems are designed and detailed for concentrating the damage and excessive inelastic deformations in the desired location along the length of the fuse to prevent the crack propagation and structural issues for the surrounding elements. Among a number of structural systems with engineered - cut-outs, a recently developed butterfly-shaped structural fuses are proposed to better align the bending strength along the length of the fuse with the demand moment, enhancing controlled yielding features over the brittle behavior. Previously, the design methodologies were developed purely based on the flexural stresses' or shear stresses' behavior leading to underestimate or overestimate the structural capacity of the fuses. The aim of this study is to optimize the design methodologies for commonly used butterfly-shaped dampers through experimental investigations considering the stresses are not uniformly distributed stresses along the length of the fuse system. The effect of shear and flexural stresses on the behavior of butterfly-shaped are initially formulated based on the Von-Mises criterion, and the optimized geometry is specified. Subsequently, experimental tests are developed for evaluating the optimized design concepts for butterfly-shaped dampers considering the uniform stress distribution and efficient use of steel. It is shown that butterfly-shaped dampers are capable of full cyclic hysteric behavior without any major signs of strength or stiffness degradations.

Predictive modeling of the compressive strength of bacteria-incorporated geopolymer concrete using a gene expression programming approach

Abstract: The performance of gene expression programming (GEP) in predicting the compressive strength of bacteriaincorporated geopolymer concrete (GPC) was examined in this study. Ground-granulated blast-furnace slag (GGBS), new bacterial strains, fly ash (FA), silica fume (SF), metakaolin (MK), and manufactured sand were used as ingredients in the concrete mixture. For the geopolymer preparation, an 8 M sodium hydroxide (NaOH) solution was used, and the ambient curing temperature (28oC) was maintained for all mixtures. The ratio of sodium silicate (Na2SiO3) to NaOH was 2.33, and the ratio of alkaline liquid to binder was 0.35. Based on experimental data collected from the literature, an evolutionary-based algorithm (GEP) was proposed to develop new predictive models for estimating the compressive strength of GPC containing bacteria. Data were classified into training and testing sets to obtain a closed-form solution using GEP. Independent variables for the model were the constituent materials of GPC, such as FA, MK, SF, and Bacillus bacteria. A total of six GEP formulations were developed for predicting the compressive strength of bacteria-incorporated GPC obtained at 1, 3, 7, 28, 56, and 90 days of curing. 80% and 20% of the data were used for training and testing the models, respectively. R2 values in the range of 0.9747 and 0.9950 (including train and test dataset) were obtained for the concrete samples, which showed that GEP can be used to predict the compressive strength of GPC containing bacteria with minimal error. Moreover, the GEP models were in good agreement with the experimental datasets and were robust and reliable. The models developed could serve as a tool for concrete constructors using geopolymers within the framework of this research.

Hybrid-ANFIS approaches for compressive strength prediction of cementitious mortar and paste employing magnetic water

Abstract: The compressive strength is an important mechanical feature of concrete that is needed in construction design. Thus, a lot of investigations were carried out to predict the compressive strength of various concretes. However, the prediction models for the compressive strength of cement mortar or paste that include magnetic water (MW) and granulated blast-furnace slag (GBFS) are still limited. The current study has developed hybrid algorithms based on adaptive neuro-fuzzy inference system (ANFIS) for modeling the compressive strength of cement mortar and paste that made with MW and GBFS as a novel mixture content. A total of 144 experimental sets of concrete-compressive strength tests for each cement mortar and paste were collected to train and validate the proposed methods, in which the cycles number of water magnetization, cement, GBFS, superplasticizer contents and curing time are set as the input data while the compressive strength value is set as the output. The developed hybrid algorithms of ANFIS optimized by firefly algorithm (FA), Improved Particle Swarm Optimization (IPSO) and biogeographybased optimization (BBO) algorithms for predicting the compressive strength of the mortar and paste. The proposed models and relevance vector machine (RVM) approach were evaluated and compared. The results showed that the ANFIS-FA outperforms other models for modeling the compressive strength of cement mortar and paste. The adjusted-coefficient of determination and root mean square error values of cement mortar models (96.20%, 92.33%, 92.36% and 89.41%) and (2.17 MPa, 3.10 MPa, 3.18 MPa and 3.06 MPa) and of cement paste models (96.92%, 80.91%, 92.19% and 88.18%) and (2.45 MPa, 5.80 MPa, 4.39 MPa and 5.20 MPa) were determined for ANFIS-FA, ANFIS-IPSO, ANFIS-BBO and RVM models, respectively, which indicate that the ANFIS-FA is a suitable model for estimating the compressive strength of cement mortar and paste that include MW. Moreover, the sensitivity of MW and GBFS is shown high for modeling the compressive strength of cement mortar.