Current Issue : July-September Volume : 2025 Issue Number : 3 Articles : 5 Articles
Reservoir rule curves (RCs) are crucial for guiding operators on the optimal water release based on the available water at the start of each month. In the absence of RCs, simulation and optimization techniques can be effectively employed to develop these curves. This study evaluates the performance of various optimization techniques for deriving optimal reservoir RCs for the Zarrineh Rud reservoir using soft computing (SC) algorithms. The algorithms investigated include the genetic algorithm (GA), particle swarm optimization (PSO), and gravitational search algorithm (GSA). To this end, monthly demand and discharge data from 1987 to 2018 were collected. Historical RCs were first simulated using the sequent peak algorithm (SPA), and optimal RCs were subsequently derived through the GA–SPA, PSO–SPA, and GSA–SPA algorithms to minimize water shortages. The results indicated that the GSA–SPA generally improved the time-based (αt) and volume-based (αv) reliability indices by 3 and 2%, respectively, compared to the historical SPA (SPA-Hist). Additionally, simulations with the GSA–SPA significantly reduced the mean annual shortage and total shortage by approximately 8% compared to SPA-Hist. The PSO–SPA ranked second, with a 7.4 and 6.8% reduction in mean annual shortage and total shortage, respectively....
Soft robots have shown great application potential in human–computer interaction, scientific exploration, and biomedical fields. However, they generally face issues like poor load capacity. Inspired by the propagation and movement mechanisms of ocean waves, this study proposes a novel type of pneumatically driven crawling soft robot. An automated pneumatic drive system was first constructed for driving and controlling the crawling soft robot, and then the soft robot body was made using additive manufacturing and silicone molding. Experimental testing of the robot’s performance revealed that it can move efficiently on surfaces with varying friction coefficients and has a strong load-bearing capacity. This work is expected to provide a reference for the design of other soft robots....
With the rapid development of artificial intelligence, automated artifact recognition technology has gradually replaced the traditional manual quality evaluation method. The existing samples of CT images containing artifacts are small, and the relationships between the images are of great significance. In this study, firstly, a method for CT image artifact recognition was developed by transforming the problem into a node classification framework. Secondly, the characteristics of this complex network and the features of the CT image texture were extracted. Finally, the combination of the complex network’s characteristics and CT image texture features was viewed as node attribution; the relationship between different nodes was analyzed using a graph attention network; and classification was carried out. The integration of multi-order neighbor features in the MNFF-GNN model improves the representation of motion artifact regions, targeting the limitations of traditional methods and convolutional neural networks (CNNs). The model demonstrates potential as a clinical tool, particularly in resource-constrained settings, by effectively identifying artifacts even with limited data, with an accuracy of 90.9%, which is an improvement of 9.73%. This innovative approach leverages graph neural networks (GNNs), which are particularly effective at capturing both local and global relationships within graph-structured data....
Laser-directed energy deposition technology (LDED), a method for repairing worn agricultural machinery parts, is valued for its flexibility, efficiency, and economy. To improve the comprehensive quality of the parts repair layer and reduce the processing energy consumption and time, it is necessary to explore the influence law of process parameters and multi-objective optimization experiments. We used L9 (33) orthogonal experiments to evaluate the effects of laser power, scanning speed, and powder feed rate on repair quality. Variance analysis assessed factor level impacts and a multi-objective optimization model was constructed and optimized using a genetic algorithm (GA). Then, a preferred algorithm is proposed to optimize and obtain the optimal process level. The results show that the cladding efficiency increases at first and then decreases with the increase in laser power, decreases with the increase in scanning speed, and increases with the increase in powder feed rate. The dilution rate decreases at first and then increases with the increase in laser power, increases with the increase in scanning speed, and decreases with the increase in powder feed rate. In addition, it is also affected by the interaction between scanning speed and powder feed rate. Taking the maximum cladding efficiency and the minimum dilution rate as the optimization objectives, the verification test was carried out with the process parameters of laser power 1684.7370 W, scanning speed 3.0175 mm s−1, and powder feed rate 1.5901 r min−1. The error rates of cladding efficiency and dilution rate were 3.98% and 4.89%, respectively, which confirmed the method’s effectiveness. The research results can provide a reference for the repair of worn parts of agricultural machinery, which is not only cost-effective but saves time, as well. The free formability of the LDED process also allows it to add special functions to simple damaged castings and forging parts during the repair process to improve their performance....
Rutting is a crucial concern impacting asphalt concrete pavements’ stability and long-term performance, negatively affecting vehicle drivers’ comfort and safety. This research aims to evaluate the permanent deformation of pavement under different traffic and environmental conditions using an Artificial Neural Network (ANN) prediction model. The model was built based on the outcomes of an experimental uniaxial repeated loading test of 306 cylindrical specimens. Twelve independent variables representing the materials’ properties, mix design parameters, loading settings, and environmental conditions were implemented in the model, resulting in a total of 3214 data points. The network accomplished high prediction accuracy with an R2 of 0.93 and a mean squared error (MSE) of 0.0039. Results based on the sensitivity analysis and variable importance techniques showed that the percentage of aggregate passing the 4.75 mm sieve and the (rice) theoretical maximum specific gravity (Gmm) were the most significant factors in predicting axial permanent strain (εp). Furthermore, the connection weight method highlighted input variables’ distinct positive and negative impacts on permanent deformation....
Loading....