Millet bran possesses good fuel quality and can be successfully used as a professional feedstock for producing solid biofuel. In this paper, a framework for developing an Artificial Neural Network (ANN) to estimate the performance of millet bran briquettes is presented by using experimental data to train, test, and validate the ANN. With the capacity of the developed multi-layer ANN, the effects of moisture content, temperature, and applied pressure on the density, durability, and impact resistance are predicted. Different cases considering three parameters as inputs to the ANN, namely, moisture content, temperature, and applied pressure were analyzed. The outputs of the ANN are the density, durability, and impact resistance for each of the input parameters separately. By comparing with the experimental values, it is shown that the ANN-based method can predict the data well with a Mean Square Error (MSE) value ~ 0.2%. Further, Multiple Linear Regression (MLR) model is used to check the efficiency of ANN prediction from which it is shown that the proposed ANN-based method provides useful guidance for the prediction of the physical parameters efficiently, with the least deviation and high accuracy.
The lateraltorsional buckling (LTB) performance assessment of laminated glass (LG) beams is a remarkably critical issue becauseamong othersit can involve major consequences in terms of structural safety. Knowledge of LTB load-bearing capacity (in terms of critical buckling load Fcr and corresponding lateral displacement dLT), in this regard, is, thus, a primary step for more elaborated design considerations. The present study examines how machine learning (ML) techniques can be used to predict the response of laterally unrestrained LG beams in LTB. The potential and accuracy of artificial neural networks (ANN), based on ML methods, are addressed based on validation toward literature data. In particular, to detect the best-performing data-driven ML model, the load-bearing capacity of LG beams (i.e., Fcr and dLT) is set as output response, while geometric properties (length, width, thickness) and material features (for glass and interlayers) are used as input variables. A major advantage is taken from a literature database of 540 experiments and simulations carried out on two-ply LG beams in LTB setup. To determine the best-performing ANN model, different strategies are considered and compared. Additionally, the Bayesian regularization backpropagation (trainbr) algorithm is used to optimize the inputoutput relationship accuracy. The suitability of present modeling strategy for LG beams in LTB is quantitatively discussed based on error and performance trends.
Inspired by nature, biomimetic surfaces have shown remarkable potential in enhancing capillary-driven flow through hierarchical microscale and nanoscale structures. However, the Lucas–Washburn equation falls short in accurately describing flow behavior within hierarchical microchannels, which consist of interconnected major and minor channels. This study employs numerical simulations using the Volume of Fluid method in OpenFOAM to investigate capillary-driven flow in closed hierarchical microchannels with an optimal aspect ratio of 2 in the major channels. Our results indicate that the Lucas–Washburn equation is not applicable to the flow within closed hierarchical microchannel. The ribs of minor channels lead to meniscus elongation, which may potentially enhance liquid transport. An aspect ratio of 10 in the minor channels increases imbibition rates, achieving up to a 12% improvement over nonhierarchical channels. Furthermore, increasing the number of minor channels or ribs at a constant hydraulic diameter further augments imbibition rates in both major and minor channels. These findings provide critical insights into hierarchical channel flow dynamics and offer valuable guidance for the design of efficient capillary-based microfluidic systems.
Based on the idea of the decoupling combustion technology and considering the effect of the high temperature on the coking and slagging, a fusion decoupling combustion technical scheme is proposed. The technical scheme divides the continuous combustion process into the fusion gasification stage and gasified gas combustion stage. During the fusion gasification stage, the air required for the gasification reaction is preheated to keep the temperature in the gasification zone above the ash fusion temperature. Then, the high-temperature gas flows into the combustion zone. Meanwhile, the flue gas and the air required for the combustion are introduced, thereby ensuring the burnout of combustible components and decreasing the NOx emission. Corresponding process model is established on the Aspen Plus platform. Through comparison with experimental data, the rationality of the modelling method is verified. And the simulation results show that in the scheme, the mass fraction of carbon in raw biomass could be converted completely. With the increase of ER from 0.33 to 0.47, LHV of product gas decreases from 5.5 MJ/Nm3 to 1.5 MJ/Nm3. The rising preheating temperature could decrease the content of H2 and increase the content of CO, which leads to that the LHV keeps the same, thereby that the effect of preheating temperature on the combustion zone could be ignored. The relationship between preheating temperature and the ratio of Air1 plays a decisive role in the implementation of the scheme. When the ratio of Air1 is equal to 0.47, the NOx emission is lower than 70 mg/m3. GRAPHICAL ABSTRACT