Search results

Engineering design and operational decisions depend largely on deep understanding of applications that requires assumptions for simplification of the problems in order to find proper solutions. Cutting-edge machine learning algorithms can be used as one of the emerging tools to simplify this process. In this paper, we propose a novel scalable and interpretable machine learning framework to automate this process and fill the current gap.

The essential principles of the proposed pipeline are mainly (1) scalability, (2) interpretibility and (3) robust probabilistic performance across engineering problems. The lack of interpretibility of complex machine learning models prevents their use in various problems including engineering computation assessments. Many consumers of machine learning models would not trust the results if they cannot understand the method. Thus, the SHapley Additive exPlanations (SHAP) approach is employed to interpret the developed machine learning models.

The proposed framework can be applied to a variety of engineering problems including seismic damage assessment of structures. The performance of the proposed framework is investigated using two case studies of failure identification in reinforcement concrete (RC) columns and shear walls. In addition, the reproducibility, reliability and generalizability of the results were validated and the results of the framework were compared to the benchmark studies. The results of the proposed framework outperformed the benchmark results with high statistical significance.

Although, the current study reveals that the geometric input features and reinforcement indices are the most important variables in failure modes detection, better model can be achieved with employing more robust strategies to establish proper database to decrease the errors in some of the failure modes identification.

Recycled waste glasses have been widely used in Portland cement and concrete as aggregate or supplementary cementitious material. Compressive strength is one of the most important properties of concrete containing waste glasses, providing information about the loading capacity, pozzolanic reaction and porosity of the mixture. This study aims to propose highly nonlinear models to predict the compressive strength of concrete containing finely ground glass particles.

A robust machine leaning method called genetic programming is used the build the compressive strength prediction models. The models are developed using a number of test results on 50-mm mortar cubes containing glass powder according to ASTM C109. Parametric and sensitivity analyses are conducted to evaluate the effect of the predictor variables on the compressive strength. Furthermore, a comparative study is performed to benchmark the proposed models against classical regression models.

The derived design equations accurately characterize the compressive strength of concrete with ground glass fillers and remarkably outperform the regression models. A key feature of the proposed models as compared to the previous studies is that they include the simultaneous effect of various parameters such as glass compositions, size distributions, curing age and isothermal temperatures. Parametric and sensitivity analyses indicate that compressive strength is very sensitive to the curing age, curing temperature and particle surface area.

This study presents accurate machine learning models for the prediction of one of the most important mechanical properties of cementitious mixtures modified by waste glass, i.e. compressive strength. In addition, it provides an insight into the effect of several parameters influencing the compressive strength. From a computing perspective, a robust machine learning technique that overcomes the shortcomings of existing soft computing methods is introduced.

Unbonded concrete overlays (UBOLs) are commonly used in pavement rehabilitation. The current models included in the Mechanistic-Empirical Pavement Design Guide cannot properly predict the structural response of UBOLs. In this paper, a multigene genetic programming (MGGP) approach is proposed to derive new prediction models for the UBOLs response to temperature loading.

MGGP is a promising variant of evolutionary computation capable of developing highly nonlinear explicit models for characterizing complex engineering problems. The proposed UBOL response models are formulated in terms of several influencing parameters including joint spacing, radius of relative stiffness, temperature gradient and adjusted load/pavement weight ratio. Furthermore, linear regression models are developed to benchmark the MGGP models.

The derived design equations accurately characterize the UBOLs response under temperature loading and remarkably outperform the regression models. The conducted parametric analysis implies the efficiency of the MGGP-based model in capturing the underlying physical behavior of the UBOLs response to temperature loading. Based on the results, the proposed models can be reliably deployed for design purposes.

A challenge in the design of UBOLs is that their interlayer effects have not been directly considered in previous design procedures. To achieve better performance predictions, it is necessary to capture the effect of the interlayer in the design process. This study addresses this important issue via developing new models that can efficiently account for the effects of interlayer on the stress and deflections. In addition, it provides an insight into the effect of several parameters influencing the deflections of the UBOLs. From a computing perspective, a powerful evolutionary computation technique is introduced that overcomes the shortcomings of existing machine learning methods.

The purpose of this paper is to develop new constitutive models to predict the soil deformation moduli using multi expression programming (MEP). The soil deformation parameters formulated are secant (Es) and reloading (Er) moduli.

MEP is a new branch of classical genetic programming. The models obtained using this method are developed upon a series of plate load tests conducted on different soil types. The best models are selected after developing and controlling several models with different combinations of the influencing parameters. The validation of the models is verified using several statistical criteria. For more verification, sensitivity and parametric analyses are carried out.

The results indicate that the proposed models give precise estimations of the soil deformation moduli. The Es prediction model provides considerably better results than the model developed for Er. The Es formulation outperforms several empirical models found in the literature. The validation phases confirm the efficiency of the models for their general application to the soil moduli estimation. In general, the derived models are suitable for fine‐grained soils.

These equations may be used by designers to check the general validity of the laboratory and field test results or to control the solutions developed by more in‐depth deterministic analyses.

The complexity of analysis of geotechnical behavior is due to multivariable dependencies of soil and rock responses. In order to cope with this complex behavior, traditional forms of engineering design solutions are reasonably simplified. Incorporating simplifying assumptions into the development of the traditional models may lead to very large errors. The purpose of this paper is to illustrate capabilities of promising variants of genetic programming (GP), namely linear genetic programming (LGP), gene expression programming (GEP), and multi‐expression programming (MEP) by applying them to the formulation of several complex geotechnical engineering problems.

LGP, GEP, and MEP are new variants of GP that make a clear distinction between the genotype and the phenotype of an individual. Compared with the traditional GP, the LGP, GEP, and MEP techniques are more compatible with computer architectures. This results in a significant speedup in their execution. These methods have a great ability to directly capture the knowledge contained in the experimental data without making assumptions about the underlying rules governing the system. This is one of their major advantages over most of the traditional constitutive modeling methods.

In order to demonstrate the simulation capabilities of LGP, GEP, and MEP, they were applied to the prediction of: relative crest settlement of concrete‐faced rockfill dams; slope stability; settlement around tunnels; and soil liquefaction. The results are compared with those obtained by other models presented in the literature and found to be more accurate. LGP has the best overall behavior for the analysis of the considered problems in comparison with GEP and MEP. The simple and straightforward constitutive models developed using LGP, GEP and MEP provide valuable analysis tools accessible to practicing engineers.

The LGP, GEP, and MEP approaches overcome the shortcomings of different methods previously presented in the literature for the analysis of geotechnical engineering systems. Contrary to artificial neural networks and many other soft computing tools, LGP, GEP, and MEP provide prediction equations that can readily be used for routine design practice. The constitutive models derived using these methods can efficiently be incorporated into the finite element or finite difference analyses as material models. They may also be used as a quick check on solutions developed by more time consuming and in‐depth deterministic analyses.

To improve the performance of the krill herd (KH) algorithm, in this paper, a series of chaotic particle-swarm krill herd (CPKH) algorithms are proposed for solving optimization tasks within limited time requirements. The paper aims to discuss these issues.

In CPKH, chaos sequence is introduced into the KH algorithm so as to further enhance its global search ability.

This new method can accelerate the global convergence speed while preserving the strong robustness of the basic KH.

Here, 32 different benchmarks and a gear train design problem are applied to tune the three main movements of the krill in CPKH method. It has been demonstrated that, in most cases, CPKH with an appropriate chaotic map performs superiorly to, or at least highly competitively with, the standard KH and other population-based optimization methods.

Meta-heuristic algorithms are efficient in achieving the optimal solution for engineering problems. Hybridization of different algorithms may enhance the quality of the solutions and improve the efficiency of the algorithms. The purpose of this paper is to propose a novel, robust hybrid meta-heuristic optimization approach by adding differential evolution (DE) mutation operator to the accelerated particle swarm optimization (APSO) algorithm to solve numerical optimization problems.

The improvement includes the addition of DE mutation operator to the APSO updating equations so as to speed up convergence.

A new optimization method is proposed by introducing DE-type mutation into APSO, and the hybrid algorithm is called differential evolution accelerated particle swarm optimization (DPSO). The difference between DPSO and APSO is that the mutation operator is employed to fine-tune the newly generated solution for each particle, rather than random walks used in APSO.

A novel hybrid method is proposed and used to optimize 51 functions. It is compared with other methods to show its effectiveness. The effect of the DPSO parameters on convergence and performance is also studied and analyzed by detailed parameter sensitivity studies.

While regular price discount (RPD) promotions remain popular, marketers have also introduced gambled price discounts (GPDs) in recent years. There is a need to understand the performance and limitation of the relatively novel GPD, because the importance of pricing and the surprise element inherent in GPD could cause the promotions to backfire when inappropriately applied. This study compared the performance of GPD and RPD via consumers' perception of their attractiveness through quality cues of product types (experience and search goods) and word-of-mouth (WOM) content (affective and cognitive).

Analysis of variance (ANOVA) was applied on a 2 (product type: experience goods [hotel rooms] vs. search goods [printers]) × 2 (word-of-mouth type: affective vs. cognitive) × 2 (price promotion type: GPD vs. RPD) between-subjects scenario experimental design (resulting in eight conditions).

Analysis of the 600 returns revealed that RPD does well for both search and experience goods, but GPD is more attractive for the marketing of experience goods. GPD works better with cognitive than with affective WOM.

GPD is a relatively new domain in marketing research. This study contributes to GPD literature and behavioral pricing literature. The study also adds to a better understanding of the dynamics, usefulness and limitations of GPD by considering the roles played by surprise element inherent in GPD and comparing it with RPD.

Drawing on knowledge-based view, social exchange theory and leader-member exchange, this study examines how exploitative leadership (EL) influences knowledge management (KM), its processes, and further investigates the moderating role of organisational citizenship behaviours (OCB) on the relationship between EL and KM.

Using a quantitative approach, survey data were collected from 356 faculty members in Iraqi public universities, and the direct and moderating relationships were assessed through Hierarchical regression by PROCESS v.3.3 macros in SPSS.

The study found a significant negative impact of EL on KM, including its processes, especially on knowledge utilisation. The assessment also revealed that OCB has a significant moderating impact on EL, particularly its effect on knowledge creation.

The empirical insights of the study are valuable and precious for policymakers, managers and academics in education sectors of developing countries, to enrich their managerial and scientific performance through addressing EL behaviours while considering the moderating effect of OCB.

The relevance of the study stems from the scarcity of research on EL, while studies on the negative behaviours of leaders as a predictor of KM process failures are significantly limited. Additionally, studies on the moderating impact of OCB on the linkage between EL and KM processes remain limited. This study is one of the earliest studies that investigate these inter-relationships amongst EL, OCB and KM processes.

The purpose of this paper is to forecast wind power generation in an area through different methods, and then, recommend the most suitable one using some performance criteria.

The Box–Jenkins modeling and the Neural network modeling approaches are applied to perform forecasting for the last 12 months.

The results indicated that among the tested artificial neural network (ANN) model and its improved model, artificial neural network-genetic algorithm (ANN-GA) with RMSE of 0.4213 and R2 of 0.9212 gains the best performance in prediction of wind power generation values. Finally, a comparison between ANN-GA and ARIMA method confirmed a far superior power generation prediction performance for ARIMA with RMSE of 0.3443 and R2 of 0.9480.

Performance of the ARIMA method is evaluated in comparison to several types of ANN models including ANN, and its improved model using GA as ANN-GA and particle swarm optimization (PSO) as ANN-PSO.