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.

     

EBSD investigation of the effect of the solidification rate on the nucleation behavior of eutectic components in a hypoeutectic Al-Si-Cu alloy

This article represents a study of the influence of the solidification rate on the crystallographic orientation of eutectic components with respect to the primary ??-Al in the tested hypoeutectic alloy. Electron backscattering diffraction (EBSD) patterns were produced from the Al-Si cast specimens that were solidified with different cooling rates and prepared via ion etch polishing as a complementary method after mechanical polishing. The results indicated a strong orientation relationship between the primary ??-Al and eutectic Al phase at all cooling rates. It was also found that the silicon eutectic flakes were heterogeneously nucleated in the interdendritic eutectic liquid. The increase of the cooling rate from 2 to 80 mm/min was found to be effective in lowering the intensity of the relationship between the primary ??-Al and eutectic Al phases, and changing the misorientation angle clustering between the primary ??-Al and eutectic Si phases in the interval from 41?C60° to lower angle intervals.     

Dynamic behavioral modeling of nonlinear circuits using a novel recurrent neural network technique

In this paper, a new method called local-global feedback recurrent neural network (LGFRNN) is proposed for dynamic behavioral modeling of nonlinear circuits. The structure of the proposed method is based on recurrent neural network and constructed by time-delayed local and global feedbacks. Adding time-delayed feedbacks has a great impact on the learning capability of previous neural network-based methods. Moreover, time-delayed local feedbacks alleviate the problem of slow convergency of the conventional neural network-based methods in the training phase. The proposed LGFRNN can be trained only by having sampled input-output waveforms of the original circuit without knowing the internal details of the circuit. A training algorithm based on real-time recurrent learning (RTRL) is used to train LGFRNN. After the training phase, the proposed LGFRNN provides accurate macromodel of a nonlinear circuit. The proposed method is more accurate compared with the conventional neural-based models (which do not benefit from time-delayed local-global feedbacks) and also significantly reduces the training time of the conventional models. Moreover, proposed LGFRNN is faster than the existing models in simulation tools. The validity of the proposed method is verified by time-domain modeling of three nonlinear devices including commercial TI's SN74AHCT540 device, five-stage complementary metal-oxide-semiconductor (CMOS) receiver, and commercial TI's LM324 power amplifier.     

Thermally reused solar energy harvesting using current mirror cells

This paper implements a simultaneous solar and thermal energy harvesting system, as a hybrid energy harvesting (HEH) system, to convert ambient light into electrical energy through photovoltaic (PV) cells and heat absorbed in the body of PV cells. Indeed, a solar panel equipped with serially connected thermoelectric generators not only converts the incoming light into electricity but also takes advantage of heat emanating from the light. In a conventional HEH system, the diode block is used to provide the path for the input source with the highest value. In this scheme, at each time, only one source can be handled to generate its output, while other sources are blocked. To handle this challenge of combining resources in HEH systems, this paper proposes a method for collecting all incoming energies and conveying its summation to the load via the current mirror cells in an approach similar to the maximum power point tracking. This technique is implemented using off-the-shelf components. The measurement results show that the proposed method is a realistic approach for supplying electrical energy to wireless sensor nodes and low-power electronics.