Multi-objective mixture design and optimisation of steel fiber reinforced UHPC using machine learning algorithms and metaheuristics

Ultra-high-performance concrete (UHPC) is a recent class of concrete with improved durability, rheological and mechanical and durability properties compared to traditional concrete. The production cost of UHPC is considerably high due to a large amount of cement used, and also the high price of other required constituents such as quartz powder, silica fume, fibres and superplasticisers. To achieve specific requirements such as desired production cost, strength and flowability, the proportions of UHPC’s constituents must be well adjusted. The traditional mixture design of concrete requires cumbersome, costly and extensive experimental program. Therefore, mathematical optimisation, design of experiments (DOE) and statistical mixture design (SMD) methods have been used in recent years, particularly for meeting multiple objectives. In traditional methods, simple regression models such as multiple linear regression models are used as objective functions according to the requirements. Once the model is constructed, mathematical programming and simplex algorithms are usually used to find optimal solutions. However, a more flexible procedure enabling the use of high accuracy nonlinear models and defining different scenarios for multi-objective mixture design is required, particularly when it comes to data which are not well structured to fit simple regression models such as multiple linear regression. This paper aims to demonstrate a procedure integrating machine learning (ML) algorithms such as Artificial Neural Networks (ANNs) and Gaussian Process Regression (GPR) to develop high-accuracy models, and a metaheuristic optimisation algorithm called Particle Swarm Optimisation (PSO) algorithm for multi-objective mixture design and optimisation of UHPC reinforced with steel fibers. A reliable experimental dataset is used to develop the models and to justify the final results. The comparison of the obtained results with the experimental results validates the capability of the proposed procedure for multi-objective mixture design and optimisation of steel fiber reinforced UHPC. The proposed procedure not only reduces the efforts in the experimental design of UHPC but also leads to the optimal mixtures when the designer faces strength-flowability-cost paradoxes.

     

Analytical Solution for Wave Propagation Due to Pop-Out Phenomenon in Solid Expandable Tubular Technology

Solid expandable tubular technology has gained wide acceptance in the petroleum industry due to its operationally simplified and cost-effective solution in well drilling. The down-hole hydraulic expansion results in forward motion of a mandrel until it pops out of the tubular. The pop-out phenomenon, which occurs at the end of the tubular expansion process, leads to a sudden release of stored energy within a fluid-tubular system, causing unnecessary vibration. These vibrations can become severe and may cause permanent damage to the tubular. Hence, a complete understanding of the dynamics of the fluid-tubular system is essential to avoid premature failure.

This paper focuses on the development of a mathematical model describing the dynamics of a fluid-tubular system due to pop-out phenomenon. The coupling between tubular, fluids, and formation is incorporated. An analytical solution for the propagation of displacement, stress, and pressure waves, originating due to the excitation caused by pop-out, is obtained. The model also identifies the potential failure locations along the tubular. The coupling effect is more prominent if the tubular material is elastic as compared to elastic-perfectly plastic material. A sensitivity analysis showed that the coupling effects vanish with increase in tubular stiffness and reach an asymptotic value with an increase in formation stiffness. The quantification of coupling effects is important in order to see the effects of pressure waves on the other subsystems present down hole.     

Limit analysis for the seismic stability of three-dimensional rock slopes using the generalized Hoek-Brown criterion

The parameters that influence slope stability and their criteria of failure are fairly understood but over-conservative design approaches are often preferred, which can result in excessive overburden removal that may jeopardize profitability in the context of open pit mining. Numerical methods such as finite element and discrete element modelling are instrumental to identify specific zones of stability, but they remain approximate and do not pinpoint the critical factors that influence stability without extensive parametric studies. A large number of degrees of freedom and input parameters may make the outcome of numerical modelling insufficient compared to analytical solutions. Existing analytical approaches have not tackled the stability of slopes using non-linear plasticity criteria and three-dimensional failure mechanisms. This paper bridges this gap by using the yield design theory and the Hoek-Brown criterion. Moreover, the proposed model includes the effect of seismic forces, which are not always taken into account in slope stability analyses. The results are presented in the form of rigorous mathematical expressions and stability charts involving the loading conditions and the rock mass properties emanating from the plasticity criterion.     

Analytical Solution for Wave Propagation Due to Pop-Out Phenomenon in Solid Expandable Tubular Technology

Abstract

Solid expandable tubular technology has gained wide acceptance in the petroleum industry due to its operationally simplified and cost-effective solution in well drilling. The down-hole hydraulic expansion results in forward motion of a mandrel until it pops out of the tubular. The pop-out phenomenon, which occurs at the end of the tubular expansion process, leads to a sudden release of stored energy within a fluid-tubular system, causing unnecessary vibration. These vibrations can become severe and may cause permanent damage to the tubular. Hence, a complete understanding of the dynamics of the fluid-tubular system is essential to avoid premature failure.

This paper focuses on the development of a mathematical model describing the dynamics of a fluid-tubular system due to pop-out phenomenon. The coupling between tubular, fluids, and formation is incorporated. An analytical solution for the propagation of displacement, stress, and pressure waves, originating due to the excitation caused by pop-out, is obtained. The model also identifies the potential failure locations along the tubular. The coupling effect is more prominent if the tubular material is elastic as compared to elastic-perfectly plastic material. A sensitivity analysis showed that the coupling effects vanish with increase in tubular stiffness and reach an asymptotic value with an increase in formation stiffness. The quantification of coupling effects is important in order to see the effects of pressure waves on the other subsystems present down hole.     

Digital bread crumb: Creation and application

Bread is a foam and the softness of breads is an important quality attribute. For many non-food foams, digital environments have been implemented which can be used to characterize the structure to optimize products for specific functionalities. For breads, structure based models that incorporate pore structure, which is comprised of the pore distribution and overall porosity, with solid matrix properties are lacking. For the first time, such structure based models have been stochastically, or randomly, generated for a range of breads using previously published X-ray microtomography data (Wang et al., 2011). The Weibull probability distribution has been used to characterize closed pore distributions, stochastic probability theory has been used to obtain representative porosities, and digital bread crumb models which incorporate pore structure have been created. Digital bread crumbs have been compared against real world samples via visual texture and small strain compression experiments. Digital bread crumbs exhibited similarities to real products in terms of cell wall thicknesses as seen from surface appearance. Results from digital compression experiments using finite element analysis showed differences in Young’s moduli between breads can be attributed to both differences in pore distribution as well as porosity.     

A discrete element study of settlement in vibrated granular layers: role of contact loss and acceleration

This paper deals with the vibration of granular materials due to cyclic external excitation. It highlights the effect of the acceleration on the settlement speed and proves the existence of a relationship between settlement and loss of contacts in partially confined granular materials under vibration. The numerical simulations are carried out using the Molecular Dynamics method, where the discrete elements consist of polygonal grains. The data analyses are conducted based on multivariate autoregressive models to describe the settlement and permanent contacts number with respect to the number of loading cycles.     

Analytical model for the expansion of tubes under tension

This paper focuses on the expansion of metallic tubes subjected to large radial and circumferential plastic deformations. This process can be achieved by driving rigid conical mandrels of various diameters through them either mechanically or hydraulically in order to obtain desirable expansion ratios. A mathematical model was developed to predict the stress field in the expanded zone, the drawing force required for expansion, and the resulting dissipated energy from which optimum mandrel shapes were obtained. A finite element analysis was used to validate the theoretical results. A good agreement was obtained in terms of drawing force and dissipated energy for different geometric constraints and friction coefficients. The study showed that the optimum mandrel angle ranges between 22 and 25 degrees for low friction and increases non-linearly when friction increases.     

Simulation of Solid Tubular Expansion in Well Drilling Using Finite Element Method

Solid expandable tubular is an emerging and promising technology in petroleum industry. It consists of increasing the diameter of a tubular by hydraulically pushing or mechanically pulling a conical mandrel through it. In this paper, a dy namic explicit finite element analysis (FEA) has been used to study the solid tubular expansion using ABAQUS, a commercial FEA software package. The required drawing force for tubular expansion was estimated for different mandrel shapes, friction coefficients, and expansion ratios. The drawing force increases with the increase in friction coefficient and expansion ratio. It was also found that the material velocities increase on the front of the mandrel but decrease to zero in the post expansion section. Moreover, the plastic deformation shows a reduction of thickness with friction coefficient and expansion ratio. Simulation results also revealed that contact occurs at the two ends of the conical mandrel tubular interface and that the contact stress increases with friction coefficient reaches to maximum value at an expansion ratio of 20%.     

Design of T-shaped tube hydroforming using finite element and artificial neural network modeling

Journal of Mechanical Science and Technology - Tube hydroforming (THF) is a frequently used manufacturing method in the industry, especially on automotive and aircraft industries. Compared with...     

The prediction of ultimate pure bending moment of concrete-filled steel tubes by adaptive neuro-fuzzy inference system (ANFIS)

In this study, different modelling techniques such as multiple regression and adaptive neuro-fuzzy inference system (ANFIS) are used for predicting the ultimate pure bending of concrete-filled steel tubes (CFTs). The behaviour of CFT under pure bending is complex and highly nonlinear; therefore, forward modelling techniques can have considerable limitations in practical situations where fast and reliable solutions are required. Linear multiple regression (LMR), nonlinear multiple regression (NLMR) and ANFIS models were trained and checked using a large database that was constructed and populated from the literature. The database comprises 72 pure bending tests conducted on fabricated and cold-formed tubes filled with concrete. Out of 72 tests, 48 tests were conducted by the second author. Input variables for the models are the same with those used by existing codes and practices such as the tube thickness, tube outside diameter, steel yield strength, strength of concrete and shear span. A practical application example, showing the translation of constructed ANFIS model into design equations suitable for hand calculations, was provided. A sensitivity analysis was conducted on ANFIS and multiple regression models. It was found that the ANFIS model is more sensitive to change in input variables than LMR and NLMR models. Predictions from ANFIS models were compared with those obtained from LMR, NLMR, existing theory and a number of available codes and standards. The results indicate that the ANFIS model is capable of predicting the ultimate pure bending of CFT with a high degree of accuracy and outperforms other common methods.