Recent publications in Engineering

Yang, Zhe, Yang, Kan, Lei, Lei, Zheng, Kan, and Leung, Victor C.M. (2019) Blockchain-based decentralized trust management in vehicular networks. IEEE Internet of Things Journal, 6 (2). pp. 1495-1505.
Vehicular networks enable vehicles to generate and broadcast messages in order to improve traffic safety and efficiency. However, due to the non-trusted environments, it is difficult for vehicles to evaluate the credibilities of received messages. In this paper, we propose a decentralized trust management system in vehicular networks based on blockchain techniques. In this system, vehicles can validate the received messages from neighboring vehicles using Bayesian Inference Model. Based on the validation result, the vehicle will generate a rating for each message source vehicle. With the ratings uploaded from vehicles, Roadside Units (RSUs) calculate the trust value offsets of involved vehicles and pack these data into a "block". Then, each RSU will try to add their "blocks" to the trust blockchain which is maintained by all the RSUs. By employing the joint Proof-of-Work and Proof-of-Stake consensus mechanism, the more total value of offsets (stake) is in the block, the easier RSU can find the nonce for the hash function (proof-of-work). In this way, all RSUs collaboratively maintain an updated, reliable, and consistent trust blockchain. Simulation results reveal that the proposed system is effective and feasible in collecting, calculating, and storing trust values in vehicular networks.

Huo, Shuwei, Zhou, Yuan, Xiang, Wei, and Kung, Sun-Yuan (2019) Semisupervised learning based on a novel iterative optimization model for saliency detection. IEEE Transactions on Neural Networks and Learning Systems, 30 (1). pp. 225-241.
In this paper, we propose a novel iterative optimization model for bottom-up saliency detection. By exploring bottom-up saliency principles and semisupervised learning approaches, we design a high-performance saliency analysis method for wide ranging scenes. The proposed algorithm consists of two stages: 1) we develop a boundary homogeneity model to characterize the general position and the contour of the salient objects and 2) we propose a novel iterative optimization model, termed gradual saliency optimization, for further performance improvement. Our main contribution falls on the second stage, where we propose an iterative framework with self-repairing mechanisms for refining saliency maps. In this framework, we further develop a more comprehensive optimization function applying a novel semisupervised learning scheme to enhance the traditional saliency measure. More elaborately, the iterative method can gradually improve the output in each iteration and finally converge to high-quality saliency maps. Based on our experiments on four different public data sets, it can be demonstrated that our approach significantly outperforms the state-of-the-art methods.

Yuan, Pu, Xiong, Xiong, Lei, Lei, and Zheng, Kan (2019) Design and implementation on Hyperledger-based Emission Trading System. IEEE Access, 7. pp. 6109-6116.
Emission trading policy provides a new approach using economic incentives to control the environmental pollution efficiently. Legal polluters can trade emission permits with each other through a trusted trading system that lacks security and credibility due to its centralization nowadays. Permissioned blockchain utilize a decentralized way to store private data immutably, providing new approaches to solve those defects of the existing centralized systems. In this paper, we propose a Hyperledger-based Emission Trading System (HyperETS) on the permissioned blockchain. Using Hyperledger Fabric as the implementation platform, HyperETS integrates the fine-grained access control, distributed ledger, and consensus protocol, aiming to provide credible trading service for polluters. We achieve the business logic by designing the particular ledger structures and smart contract in blockchain. HyperETS stores all transactions immutably in a chain and makes it easy to share the data between organizations. Finally, several experiments are conducted to evaluate the performances of the proposed demonstration system.

Roy, Dilip Kumar, and Datta, Bithin (2019) Adaptive management of coastal aquifers using entropy-set pair analysis-based three-dimensional sequential monitoring network design. Journal of Hydrologic Engineering, 24 (3). 04018072.
A three-dimensional compliance monitoring network design methodology is presented to develop an adaptive and sequentially modified management policy that intends to improve optimal and justifiable use of groundwater resources in coastal aquifers. In the first step, an ensemble metamodel-based multiobjective prescriptive model is developed using a coupled simulation-optimization approach to derive a set of Pareto optimal groundwater extraction strategies. Prediction uncertainty of metamodels is addressed by utilizing a weighted average ensemble using set pair analysis. In the second step, a monitoring network is designed for evaluating the compliance of the implemented strategies with the prescribed management goals due to possible uncertainties associated with field-scale application of the proposed management policy. Optimal monitoring locations are obtained by maximizing Shannon's entropy between the saltwater concentrations at the selected potential locations. Performance of the proposed three-dimensional sequential compliance monitoring network design is assessed for an illustrative multilayered coastal aquifer study area. The performance evaluations show that sequential improvements of optimal management strategy is possible by using saltwater concentrations measured at the proposed optimal compliance monitoring locations. Therefore, the salinity concentration data collected at the designed compliance monitoring wells can be used to collect feedback information in terms of salinity concentrations. This feedback information can be applied to improve the initially prescribed optimal groundwater extraction patterns while keeping the original management goal intact.

Inam, Mohammad Ilias, Lin, Wenxian, Williamson, N., Armfield, S.W., and He, Yinghe (2019) Characteristics of unsteadiness for transitional plane fountains in linearly stratified fluids. International Communications in Heat and Mass Transfer, 100. pp. 83-97.
When a fountain is injected into a linearly stratified fluid, its behavior will be governed by the stratification of the ambient fluid, represented by the dimensionless temperature stratification parameter (s), in addition to the Reynolds number (Re) and the Froude number (Fr). In this study, a series of three-dimensional direct numerical simulations (DNS) were carried out using ANSYS Fluent for transitional plane fountains in linearly-stratified fluids with Re, Fr and s over the ranges 28 ≤ Re ≤ 300, 3 ≤ Fr ≤ 10, and 0.1 ≤ s ≤ 0.5 to study the effects of these governing parameters on the characteristics of such unsteadiness. Empirical correlations to quantify the effects of Fr, Re and s over the studied ranges on the characteristics of the unsteadiness are also obtained and compared to the relevant scaling relations developed for weak plane fountains.

Amirabdollahian, Mahsa, Datta, Bithin, and Beck, Peter H. (2019) Application of a link simulation optimization model utilizing quantification of hydrogeologic uncertainty to characterize unknown groundwater contaminant sources. Modeling Earth Systems and Environment, 5 (1). pp. 119-131.
In existing groundwater contamination source characterization methodologies, simulation models estimate the contamination concentration in the study area. In order to obtain reliable solutions, it is essential to provide the simulation models with reliable hydrogeological properties. In real-life scenarios often high level of uncertainty and variability is associated with the hydrogeological properties. This study focuses on quantifying the hydrogeological parameter uncertainty to enhance the accuracy of identifying contamination release histories. Tracer experiment results at the Eastlakes Experimental Site, located in Botany Sands Aquifer, in New South Wales, Australia, are utilized to examine the performance and potential applicability of the methodology. In the selected study area, the hydrogeological heterogeneity in the microscopic scale, specifically the hydraulic conductivity, has substantial effect on the transport of pollutants. Among available tracer information, Bromide is studied as a conservative contaminant. Using possible realizations of the flow field, a coefficient of confidence (COC) is calculated for each field monitoring locations and times. Higher COC implies that the result of simulation models at that specific monitoring location and time is more reliable than other contaminant concentration data. Therefore, the optimization model should emphasise matching the corresponding estimated and observed contamination concentrations to accurately identify the contaminant release locations and histories. The linked simulation–optimisation method is utilised to optimally characterise the Bromide sources. Performance evaluation results demonstrate that the proposed methodology recovers pollution source characteristics more accurately compared to the methodology which does not consider the effect of hydrogeological parameter uncertainty.

Xiao, Yu, Wang, Yafeng, and Xiang, Wei (2019) Dimension-deficient channel estimation of hybrid beamforming based on compressive sensing. IEEE Access, 7. pp. 13791-13798.
Due to high hardware costs for digital beamforming, hybrid beamforming (HBF) is widely employed in millimeter-wave (mmWave) communications systems. However, the number of radio frequency chains in the analog part of HBF is far less than that of antennas, which causes a serious dimension-deficient problem. In order to overcome this problem, this paper proposes a compressive sensing algorithm using an adaptive overcomplete dictionary to estimate the sparse channel in the HBF-based mmWave system. The algorithm adaptively generates the dictionary by using the received signal to accurately reconstruct the mmWave channel. The simulation results are presented to demonstrate that the proposed algorithm outperforms its traditional counterparts in terms of the normalized mean square error and the spectral efficiency.

Xie, Huiqiang, Xu, Weiyang, Xiang, Wei, Li, Bing, and Wang, Rui (2019) Performance of ED-based non-coherent massive SIMO systems in correlated Rayleigh fading. IEEE Access, 7. pp. 14058-14069.
In recent studies, a simple non-coherent communications' scheme based on energy detection is proposed for massive single-input multiple-output systems, where transmit symbols are decoded by averaging the received signal energy across all antennas. In this paper, we investigate the effect of correlated Rayleigh fading on the performance of the aforementioned systems. Specifically, we derive the analytical expressions of the symbol error rate, achievable rate, and outage probability. Furthermore, the asymptotic behaviors of these expressions in regimes of large numbers of receive antennas, high channel correlation, and high signal-to-noise ratio are investigated. The analytical results demonstrate the adverse impact of channel correlation on the error probability, which can be attributed to the fact that channel correlation reduces the degrees of freedom. Our analysis also shows that channel correlation poses little influence on the achievable rate. Besides, an upper bound of the achievable rate is given when the number of receive antennas goes to infinity. Finally, the numerical results are presented to verify our analysis.

Heidarpur, Moslem, Ahmadi, Arash, Ahmadi, Majid, and Rahimiazghadi, Mostafa (2019) CORDIC-SNN: on-FPGA STDP learning with Izhikevich neurons. IEEE Transactions on Circuits and Systems I: Regular Papers. (In Press)
This paper proposes a neuromorphic platform for on-FPGA online spike timing dependant plasticity (STDP) learning, based on the COordinate Rotation DIgital Computer (CORDIC) algorithms. The implemented platform comprises two main components. First, the Izhikevich neuron model is modified for implementation using the CORDIC algorithm, simulated to ensure the model accuracy, described as hardware, and implemented on FPGA. Second, the STDP learning algorithm is adapted and optimized using the CORDIC method, synthesized for hardware, and implemented to perform on-FPGA online learning on a network of CORDIC Izhikevich neurons to demonstrate competitive Hebbian learning. The implementation results are compared with the original model and state-of-the-art to verify accuracy, effectiveness, and higher speed of the system. These comparisons confirm that the proposed neuromorphic system offers better performance and higher accuracy while being straightforward to implement and suitable to scale.

Zhou, Yuan, Huo, Shuwei, Xiang, Wei, Hou, Chunping, and Kung, Sun-Yuan (2019) Semi-supervised salient object detection using a linear feedback control system model. IEEE Transactions on Cybernetics, 49 (4). pp. 1173-1185.
To overcome the challenging problems in saliency detection, we propose a novel semi-supervised classifier which makes good use of a linear feedback control system (LFCS) model by establishing a relationship between control states and salient object detection. First, we develop a boundary homogeneity model to estimate the initial saliency and background likelihoods, which are regarded as the labeled samples in our semi-supervised learning procedure. Then in order to allocate an optimized saliency value to each superpixel, we present an iterative semi-supervised learning framework which integrates multiple saliency cues and image features using an LFCS model. Via an innovative iteration method, the system gradually converges an optimized stable state, which is associating with an accurate saliency map. This paper also covers comprehensive simulation study based on public datasets, which demonstrates the superiority of the proposed approach.

Yang, Zhe, Zhang, Kuan, Lei, Lei, and Zheng, Kan (2019) A novel classifier exploiting mobility behaviors for Sybil detection in connected vehicle systems. IEEE Internet of Things Journal, 6 (2). pp. 2626-2636.
A Sybil attacker is able to obtain more than one identities and disguise as multiple vehicles in order to interfere the normal operations of the Connected Vehicle System (CVS). In this paper, we propose a novel classifier to detect Sybil attackers according to their mobility behaviors. Specifically, three levels of Sybil attackers are first defined according to their attack abilities. Through analyzing the mobility behaviors of vehicles, a learning-based model is used in the Central Server (CS) to extract mobility features and distinguish Sybil attackers from benign vehicles. Three classification algorithms are tested and compared, i.e., the Naive Bayes, Decision Tree, and Support Vector Machine. Furthermore, location certificates issued by Base Stations are used to resist location forgery by attackers. Based on the location certificates, the CS is able to evaluate the credibilities of uploaded locations using the Subjective Logic theory. In addition, we develop an edge betweenness-based community detection algorithm to handle the collusion among multiple Sybil attackers. Simulations are conducted based on a real-world vehicle trajectory dataset, which indicate that the proposed scheme is effective to resist Sybil attackers in CVS.

Hou, Lu, Lei, Lei, Zheng, Kan, and Wang, Xianbin (2019) A Q-learning based proactive caching strategy for non-safety related services in vehicular networks. IEEE Internet of Things Journal, 6 (3). pp. 4512-4520.
Content caching has brought huge potential for the provisioning of non-safety related infotainment services in future vehicular networks. Assisted by multi-access edge computing, roadside units (RSUs) could become cache-capable and offer fast caching services to moving vehicles for content providers. On the other hand, deep learning makes it possible to accurately estimate the behavior of vehicles, which enables effective proactive caching strategies. However, caching services considering both the mobility of vehicles and storage could incur increased latency and considerable cost due to the cache size needed in RSUs. In this paper, we model such a problem using Markov decision processes, and propose a heuristic Q-learning solution together with vehicle movement predictions based on a long short-term memory network. The optimal caching strategy which minimizes the latency of caching services can be derived by our heuristic εn-greedy training processes. Numerical results demonstrate that our proposed strategy can achieve better performance compared with several baselines under different prediction accuracies.

Lei, Lei, Xu, Huijuan, Xiong, Xiong, Zheng, Kan, and Xiang, Wei (2019) Joint computation offloading and multi-user scheduling using approximate dynamic programming in NB-IoT edge computing system. IEEE Internet of Things Journal, 6 (3). pp. 5345-5362.
The Internet of Things (IoT) connects a huge number of resource-constraint IoT devices to the Internet, which generate massive amount of data that can be offloaded to the cloud for computation. As some of the applications may require very low latency, the emerging mobile edge computing (MEC) architecture offers cloud services by deploying MEC servers at the mobile base stations (BSs). The IoT devices can transmit the offloaded data to the BS for computation at the MEC server. Narrowband Internet of Things (NB-IoT) is a new cellular technology for the transmission of IoT data to the BS. In this paper, we propose a joint computation offloading and multi-user scheduling algorithm in NB-IoT edge computing system that minimizes the long-term average weighted sum of delay and power consumption under stochastic traffic arrival. We formulate the dynamic optimization problem into an infinite-horizon average-reward continuous-time Markov decision process (CTMDP) model. In order to deal with the curse-of-dimensionality problem, we use the approximate dynamic programming techniques, i.e., the linear value-function approximation and TD learning with post-decision state and semi-gradient descent method, to derive a simple algorithm for the solution of the CTMDP model. The proposed algorithm is semi-distributed, where the offloading algorithm is performed locally at the IoT devices, while the scheduling algorithm is auction-based where the IoT devices submit bids to the BS to make the scheduling decision centrally. Simulation results show that the proposed algorithm provides significant performance improvement over the two baseline algorithms and the MUMTO algorithm which is designed based on the deterministic task model.

Wang, Xiao, Zhang, Dingdong, Jin, Hui, Poliquit, Beta Zenia, Philippa, Bronson, Nagiri, Ravi Chandra Raju, Subbiah, Jegadesan, Jones, David J., Ren, Wencai, Du, Jinhong, Burn, Paul L., and Yu, Junsheng (2019) Graphene‐based transparent conducting electrodes for high efficiency flexible organic photovoltaics: elucidating the source of the power losses. Solar RRL. 1900042. (In Press)
Solution processed flexible organic solar cells (OSCs) are of interest due to their potential use as environmentally friendly, shapeable, or wearable energy. Such flexible devices require compatible transparent conducting electrodes (TCEs). The use of three‐layer graphene as a useful TCE for flexible OSCs is reported. The conformal coating of the graphene‐based TCE with good retention of performance was achieved using a bulk heterojunction (BHJ) active layer comprised of the non‐polymeric molecular (5Z,5′Z)‐5,5′‐[(5‴,5‴‴′‐{4,8‐bis[5‐(2‐ethylhexyl)‐4‐n‐hexylthiophen‐2‐yl]benzo[1,2‐b:4,5‐b′]dithiophene‐2,6‐diyl}bis{3′,3″,3‴‐tri‐n‐hexyl‐[2,2′:5′,2″:5″,2‴‐quaterthiophene]‐5‴,5‐diyl})bis(methanylylidene)]bis[3‐n‐hexyl‐2‐thioxothiazolidin‐4‐one] (BQR) donor and [6,6]‐phenyl‐C71‐butyric acid methyl ester (PC71BM) as the acceptor. This material combination enables thick BHJ junctions to be used so that the roughness of the graphene surface did not lead to shorted devices. The best graphene/poly(ethylene terephthalate) (PET) devices (PET/graphene/molybdenum oxide/BHJ/calcium/aluminum) show a photoconversion efficiency (PCE) of 5.8%, which while excellent was lower than that of a similar device architecture that used ITO/glass as the anode. The power losses of the graphene/PET‐based cells mainly resulted from absorption losses caused by the optical profile distribution in the device and the relatively high sheet resistance of the anode, leading to an 18% decrease in the short‐circuit current and lower fill factor, respectively.

Sanderson, Stephen, Philippa, Bronson, Vamvounis, George, Burn, Paul L., and White, Ronald D. (2019) Understanding charge transport in Ir(ppy)₃:CBP OLED films. Journal of Chemical Physics, 150 (9). 094110.
Ir(ppy)₃:CBP blends have been widely studied as the emissive layer in organic light emitting diodes (OLEDs), yet crucial questions about charge transport within the layer remain unaddressed. Recent molecular dynamics simulations show that the Ir(ppy)₃ molecules are not isolated from each other, but at concentrations of as low as 5 wt. % can be part of connected pathways. Such connectivity raises the question of how the iridium(iii) complexes contribute to long-range charge transport in the blend. We implement a kinetic Monte Carlo transport model to probe the guest concentration dependence of charge mobility and show that distinct minima appear at approximately 10 wt. % Ir(ppy)₃ due to an increased number of trap states that can include interconnected complexes within the blend film. The depth of the minima is shown to be dependent on the electric field and to vary between electrons and holes due to their different trapping depths arising from the different ionization potentials and electron affinities of the guest and host molecules. Typical guest-host OLEDs use a guest concentration below 10 wt. % to avoid triplet-triplet annihilation, so these results suggest that optimal device performance is achieved when there is significant charge trapping on the iridium(iii) complex guest molecules and minimum interactions of the emissive chromophores that can lead to triplet-triplet annihilation.

Al-Juboori, Muqdad, and Datta, Bithin (2019) Minimum cost design of hydraulic water retaining structure by using coupled simulation optimization approach. KSCE Journal of Civil Engineering, 23 (3). pp. 1095-1107.
A linked Simulation-Optimization (S-O) model was developed to find the optimum design of Hydraulic Water Retaining Structure (HWRS) constructed on permeable soils. The nonlinear relationship between seepage design variables can accurately and solely simulated by numerical methods. To increase the computational efficiency of the S-O model, the seepage numerical model was replaced by approximation simulator based on the Support Vector Machine (SVM) surrogate models. The surrogate models incorporated and highlighted the effects of hydraulic conductivity (k) and anisotropy ratio (k(y)/k(x)) on the optimum design of HWRS. The results revealed that reducing k and (k(y)/k(x)) values augments the optimum cost. The most effective seepage controller variables were the depth and inclination angle of the last cut-off. Increasing these variables effectively reduced the exit gradient value to the allowable limits. Also, the first and second last aprons (b(9), b(10)) were important to provide a sufficient cross section for HWRS to increase the stability of the HWRS against the overturning, flotation, sliding, etc. The evaluation of S-O technique demonstrated a good agreement between the predicted and simulated seepage characteristics of the optimum HWRS design. Hence, the S-O methodology is applicable to obtain an optimal and minimum cost HWRS design.

Lal, Alvin, and Datta, Bithin (2019) Multi-objective groundwater management strategy under uncertainties for sustainable control of saltwater intrusion: solution for an island country in the South Pacific. Journal of Environmental Management, 234. pp. 115-130.
To date, simulation-optimization (S/O) based groundwater management models have delivered optimal saltwater intrusion management strategies for coastal aquifer systems. At times, however, uncertainties in the numerical simulation model due to uncertain aquifer parameters are not incorporated into the management model. The present study explicitly incorporated aquifer parameter uncertainty into a multi-objective management model for the optimal design of groundwater pumping strategies from the unconfined Bonriki aquifer situated in a small Pacific island country. The objective of the multi-objective management model was to maximise pumping from production wells and minimize pumping from the barrier wells (hydraulic barriers) to ensure that the water quality at different monitoring locations (MLs) were within pre-specified sustainable limits. To achieve the targeted management goal, a coupled flow and transport numerical simulation model of the Bonriki aquifer was developed using the FEMWATER numerical code. The developed three-dimensional numerical model was calibrated and validated using limited available hydrological data. To achieve computational efficiency and feasibility of the management model, the numerical simulation model in the S/O model was replaced with ensembles of Support Vector Machine Regression (SVMR) surrogate models. Each SVMR standalone surrogate model in the ensemble was constructed using datasets from different numerical simulation models with different hydraulic conductivity and porosity values. These ensemble SVMR models were coupled to the multi-objective genetic algorithm optimization model to solve the Bonriki aquifer management problem. The executed optimization model presented a Pareto-front with 600 non-dominated optimal trade-off pumping solutions. The reliability of the management model established after validation of the optimal solution results suggests that the implemented constraints of the optimization problem were satisfied, i.e., the salinity concentrations at respective MLs were within the pre-specified limits. Overall, the results from this study indicated that the developed management model has the potential to address groundwater salinity problems in small island countries.

Wibowo, David, Zhao, Chun-Xia, and He, Yinghe (2019) Fluid properties and hydrodynamics of microfluidic systems. In: Santos, Hélder A., Liu, Dongfei, and Zhang, Hongbo, (eds.) Microfluidics for Pharmaceutical Applications: from nano/micro systems fabrication to controlled drug delivery. Elsevier, Oxford, United Kingdom, pp. 37-77.
Microfluidics has been an active research field and an indispensable tool for quantitative analyses of chemicals and biological specimens for decades. Its widespread application stems from its ability to accurately handle small quantities of samples and its well-controlled environments. Further developments of microfluidics require a fundamental understanding of fluid dynamics and associated phenomena. This chapter provides some basic descriptions of fluid properties and principles that govern the flows inside the channels of a microfluidic device. It also examines relevant dimensionless numbers used for the understanding of the flow and the design and scale-up of microfluidic devices. The chapter concludes with suggestions on key areas of importance for future research in microfluidics.

Al-Juboori, Muqdad, and Datta, Bithin (2019) Optimum design of hydraulic water retaining structures incorporating uncertainty in estimating heterogeneous hydraulic conductivity utilizing stochastic ensemble surrogate models within a multi-objective multi-realisation optimisation model. Journal of Computational Design and Engineering, 6 (3). pp. 296-315.
In order to find optimum and reliable designs for hydraulic water retaining structures (HWRSs), a reliability based optimum design (RBOD) model was used to quantify uncertainty in estimates of seepage characteristics due to uncertainty in heterogeneous hydraulic conductivity (HHC). This included incorporating reliability measures into minimum-cost HWRS designs and utilising a multi-realisation optimisation technique based on various stochastic ensemble surrogate models. To improve the efficiency of the RBOD model and the direct search optimisation solver, a multi-objective multi-realisation optimisation (MOMRO) model was employed. Some of the stochastic optimisation constraints could be formulated as a second objective function to be minimised in the MOMRO model. This can significantly improve the search efficiency of the multi-objective non-dominated sorting genetic algorithm-II (NSGA-II) that was used, and help determine more feasible candidate solutions in the search space. Gaussian process regression was used to develop the surrogate models,which were trained on numerous datasets created from numerical seepage simulations. The effect of uncertainty was also considered for other HWRS safety factors and conditions such as overturning, flotation, sliding and eccentric loading. The results demonstrate that uncertainty in HHC estimates significantly impacts optimum HWRS design. Therefore, deterministic optimum solutions that are created based on expected values of hydraulic conductivity are not adequate for reliable HWRS design. The developed MOMRO model, which was based on an ensemble approach, addresses some of the uncertainty in HHC values that affects HWRS design. Also, the MOMRO technique improves the efficiency of the optimisation search process and facilitates a direct search process to provide many optimum alternatives.

Al-Juboori, Muqdad, and Datta, Bithin (2019) Performance evaluation of a genetic algorithm-based linked simulation-optimization model for optimal hydraulic seepage-related design of concrete gravity dams. Journal of Applied Water Engineering and Research, 7 (3). pp. 173-197.
Concrete gravity dams (CGD) are classified as a strategic and essential structures in water resources management. Precise seepage analysis, construction cost and safety are the most important factors in the design and construction of CGD. The analytical solution and empirical seepage analysis methods under hydraulic structure are not sufficient or precise enough to provide an ideal solution for complex projects. This study concentrated on developing accurate surrogate models utilizing the Artificial Neural Network (ANN) technique, which are trained based on numerical simulated data sets generated by the seepage modelling software (SEEPW/Geo-Studio). The developed surrogate models are linked with the Genetic Algorithm (GA) optimization solver to optimize the hydraulic design considering the design safety factors and minimum construction cost of CGD. The performance of the linked simulation-optimization (S-O) model is evaluated for different design scenarios. The evaluation results demonstrate the potential applicability of the methodology for efficient, safe, and economical hydraulic design CGD on permeable soils.

 Find more publications @ JCU Research Online