Prediction of Boundary Shear Stress Distribution in Converging Compound Channel Using Gene Expression Programming

The computation of the boundary shear stress distribution in an open channel flow is required for a variety of applications, including the flow resistance relationship and the construction of stable channels. The river breaches the main channel and spills across the floodplain during overbank flow conditions on both sides. Due to the momentum shift between the primary channel and adjacent floodplains, the flow structure in such compound channels becomes complicated. This has a profound impact on the shear stress distribution in the floodplain and main channel subsections. In addition, agriculture and development activities have occurred in floodplain parts of a river system. As a consequence, the geometry of the floodplain changes over the length of the flow, resulting in a converging compound channel. Traditional formulas, which rely heavily on empirical approaches, are ineffective in predicting shear force distribution with high precision. As a result, innovative and precise approaches are still in great demand. The boundary shear force carried by floodplains is estimated by gene expression programming (GEP) in this paper. In terms of non-dimensional geometric and flow variables, a novel equation is constructed to forecast boundary shear force distribution. The proposed GEP-based method is found to be best when compared to conventional methods. The findings indicate that the predicted percentage shear force carried by floodplains determined using GEP is in good agreement with the experimental data compared to the conventional formulas (R2 = 0.96 and RMSE = 3.395 for the training data and R2 = 0.95 and RMSE = 4.022 for the testing data).

MACHINE LEARNING FOR THE DEVELOPMENT OF DATA DRIVEN TURBULENCE CLOSURES IN COOLANT SYSTEMS

This work shows the application of Gene Expression Programming to augment RANS turbulence closure modelling, for flows through complex geometry designed for additive manufacturing. Specifically, for the design of optimised internal cooling channels in turbine blades. One of the challenges in internal cooling design is the heat transfer accuracy of the RANS formulation in comparison to higher fidelity methods, which are still not used in design on account of their computational cost. However, high fidelity data can be extremely valuable for improving current lower fidelity models and this work shows the application of data driven approaches to develop turbulence closures for an internally ribbed duct. Different approaches are compared and the results of the improved model are illustrated; first on the same geometry, and then for an unseen predictive case. The work shows the potential of using data driven models for accurate heat transfer predictions even in non-conventional configurations and indicates the ability of closures learnt from complex flow cases to adapt successfully to unseen test cases.

Prediction and Analysis of PDC Bit Wear in Conglomerate Layer with Machine Learning and Finite-Element Method

Polycrystalline diamond compact (PDC) bits experience a serious wear problem in drilling tight gravel layers. To achieve efficient drilling and prolong the bit service life, a simplified model of a PDC bit with double cutting teeth was established by using finite-element numerical simulation technology, and the rock-breaking process of PDC bit cutting teeth was simulated using the Archard wear principle. The numerical simulation results of the wear loss of the PDC bit cutting teeth, such as the caster angle, temperature, linear velocity, and bit pressure, as well as previous experimental research results, were combined into a training dataset. Then, machine learning methods for equal-probability gene expression programming (EP-GEP) were used. Based on the accuracy of the training set, the effectiveness of this method in predicting the wear of PDC bits was demonstrated by verifying the dataset. Finally, a prediction dataset was established by a Latin hypercube experiment and finite-element numerical simulation. Through comparison with the EP-GEP prediction results, it was verified that the prediction accuracy of this method meets actual engineering needs. The results of the sensitivity analysis method for the gray correlation degree show that the degree of influence of bit wear is in the order of temperature, back dip angle of the PDC cutter, linear speed, and bit pressure. These results demonstrate that when an actual PDC bit is drilling hard strata such as a conglomerate layer, after the local high temperature is generated in the formation cut by the bit, appropriate cooling measures should be taken to increase the bit pressure and reduce the rotating speed appropriately. Doing so can effectively reduce the wear of the bit and prolong its service life. This study provides guidance for predicting the wear of a PDC bit when drilling in conglomerate, adjusting drilling parameters reasonably, and prolonging the service life of the bit.

Rice (Oryza sativa L.) Growth Modeling Based on Growth Degree Day (GDD) and Artificial Intelligence Algorithms

Rice (Oryza sativa L.) growth prediction is key for precise rice production. However, the traditional linear rice growth forecasting model is ineffective under rapidly changing climate conditions. Here we show that growth rate (Gr) can be well-predicted by artificial intelligence (AI)-based artificial neural networks (ANN) and gene-expression programming (GEP), with accumulated air temperatures based on growth degree day (GDD). In total, 10,246 Gr from 95 cultivations were obtained with three cultivars, TK9, TNG71, and KH147, in Central and Southern Taiwan. The model performance was evaluated by the Pearson correlation coefficient (r), root mean square error (RMSE), and relative RMSE (r-RMSE) in the whole growth period (lifecycle), as well as the average and specific key stages (transplanting, 50% initial tillering, panicle initiation, 50% heading, and physiological maturity). The results in lifecycle Gr modeling showed that ANN and GEP models had comparable r (0.9893), but the GEP model had the lowest RMSE (3.83 days) and r-RMSE (7.24%). In stage average and specific key stages, each model has its own best-fit growth period. Overall, GEP model is recommended for rice growth prediction considering the model performance, applicability, and routine farming work. This study may lead to smart rice production due to the enhanced capacity to predict rice growth in the field.

Experimental study on flow over arced-plan porous weirs

Unlike conventional impermeable weirs, porous weirs without clogging the flow and passage of aquatic life with increased aeration and aerobic reactions with minimal negative effects on the environment are known as environmentally friendly structures. This study experimentally investigates the hydraulic performance of Arced-Plan Porous Weirs (APPWs) in different hydraulic and geometric conditions. For this purpose, four different porous and two solid weirs were examined. Experiments were conducted in a horizontal laboratory flume with length, width, and height of 20, 0.6, and 0.5 m, respectively, for a wide range of flow rates, particle sizes, and three arc lengths. Results showed that increasing filling material sizes increases the free discharge coefficient and reduces the submerged Discharge Reduction Factor (DRF). It was also concluded that the weirs’ effective length significantly impacts the free discharge coefficient and has no significant effect on the threshold submergence index and submerged DRF. Unlike solid weirs, the threshold submergence of porous weirs occurs at a downstream depth lower than the weir's height. Finally, according to the dimensional analysis and Gene-Expression Programming (GEP) approach, three relations were extracted to calculate the free discharge coefficient, threshold submergence index, and submerged discharge reduction factor for APPWs.