Explore the vast range of titles available.

The construction of soft robots’s models and controllers remains a significant challenge. In this paper, we propose a new walking control method for the quadruped soft robot named genetic algorithm-optimized PID. First, we construct the control model correlating valve voltage with leg bending based on the geometrical analysis. This modeling approach leverages the characteristics of novel leg structure and bend sensor, thereby streamlining the control model for locomotion of quadruped soft robotic. Moreover, We apply the genetic algorithm to automatically tune parameters and optimize PID controllers, aiming to enhance control performance. The application of the proposed method to the walking control has been uniquely demonstrated on a real 3D-printed quadruped soft robot. Experimental results indicate that the genetic algorithm-optimized PID controller significantly improves trajectory tracking compared to the Ziegler-Nichols tuning method. This optimization increases the robot’s walking speed from 5 mm/s to 8 mm/s, reduces the error rate by 2.4064%, decreases overshoot by 12.55%, and shortens response time by 0.5 s, substantially enhancing the controller’s overall performance. Additionally, compared to particle swarm optimization, the proposed method further improves performance by reducing the error rate by 0.4079%, overshoot by 8.4%, and response time by 1.0 s.

Accurate trajectory prediction of concealed targets in complex, interference-laden environments present a formidable challenge for millimeter-wave sensor tracking systems. To address this, we propose a state-of-the-art autonomous prediction framework that integrates an Improved Sequential Variational Mode Decomposition (ISVMD) algorithm with an Extreme Learning Machine (ELM), synergistically optimized by the novel Red-billed Blue Magpie Optimizer (RBMO). The ISVMD enhances signal reconstruction by transforming noisy target echo signals into robust feature sequences, effectively mitigating the impacts of environmental disturbances and intentional concealment. Subsequently, the RBMO-optimized ELM leverages these feature sequences to predict the future trajectories of concealed targets with high precision. The RBMO further refines critical parameters within the ISVMD-ELM pipeline, ensuring adaptability and computational efficiency across diverse scenarios. Experimental validation using real-world data demonstrates that the RBMO-ISVMD-ELM approach surpasses state-of-the-art algorithms in both accuracy and robustness when predicting the trajectories of concealed ground targets, achieving optimal performance metrics under demanding conditions.

The Elman neural network has good dynamic properties and strong global stability, being most widely used to deal with nonlinear, dynamic, and complex data. However, as an optimization of the backpropagation (BP) neural network, the Elman model inevitably inherits some of its inherent deficiencies, influencing the recognition precision and operating efficiency. Many improvements have been proposed to resolve these problems, but it has proved difficult to balance the many relevant features such as storage space, algorithm efficiency, recognition precision, etc. Also, it is difficult to obtain a permanent solution from a temporary solution simultaneously. To address this, a genetic algorithm (GA) can be introduced into the Elman algorithm to optimize the connection weights and thresholds, which can prevent the neural network from becoming trapped in local minima and improve the training speed and success rate. The structure of the hidden layer can also be optimized using the GA, which can solve the difficult problem of determining the number of neurons. Most previous studies on such evolutionary Elman algorithms optimized the connection weights or network structure individually, which represents a slight deficiency. We propose herein a novel optimized GA–Elman neural network algorithm where the connection weights are real-encoded, while the neurons of the hidden layer also adopt real-coding but with the addition of binary control genes. In this new algorithm, the connection weights and the number of hidden neurons are optimized using hybrid encoding and evolution simultaneously, greatly improving the performance of the resulting novel GA–Elman algorithm. The results of three experiments show that this new GA–Elman model is superior to the traditional model in terms of all calculated indexes.

Objectives Building upon the minimization random grouping algorithm designed by Pocock and Simon, this study proposes a randomization algorithm based on the minimization of expected balance distribution differences. This approach aims to balance key covariates and other potential confounding factors. Methods A global difference algorithm based on expected balance distribution was proposed upon analysis of the limitations of the local range algorithm used in traditional minimization randomization for imbalance calculation. The study implemented three algorithms using R 4.3.2 and conducted three experiments through Monte Carlo simulations, In Experiment One, the sample size was fixed, while the number of control factors varied. In Experiment Two, the control factors and their levels were fixed, and the sample sizes varied. Imbalance performance was compared the imbalance performance across groups and control factors. Additionally, in Experiment Three, a real-data analysis was conducted to assess the applicability of the new design in clinical trials. Results In Experiment One, the Expected Balance Distribution and Minimized Variations(EBDMV) consistently outperformed the minimum sufficient balance and the traditional minimization method in terms of the sample size difference between the groups (e.g., 0.716 vs. 15.55 vs. 0.574). Additionally, the P -values distribution was more concentrated, approaching 1. When the number of control factors was increased to 10, the minimum P -value of the traditional method was individually less than 0.05, whereas the minimum P -value of the expected balance distribution and minimized variations(EBDMV) remained greater than 0.05, indicating that the latter method exhibited stronger stability and adaptability. In Experiment Two, the EBDMV also demonstrated higher performance in terms of the sample size difference between groups (e.g., 0.708 vs. 7 vs. 0.726). Furthermore, as the sample size increased, the P -value approached 1, demonstrating greater stability. The results of Experiment Three were consistent with the simulated data. The EBDMV method generally outperformed the traditional minimization method in terms of sample size difference between groups (e.g., 1.08 vs. 9.652 vs. 0.968) and exhibited a more centralized distribution of P -values. Conclusions When the number of control factors is high and the sample size is small, the EBDMV method demonstrates significantly superior balance in both inter-group distributions and control factor balance compared to the traditional minimization method.

Numerical oil spill models, which predict the transport and behavior of oil spills, are an essential tool for risk assessment and clean-up during an actual accident. The existing numerical oil spill models are mainly applied to large-scale oil spills, while few models on small-scale oil spills exist. Therefore, this study focuses on the prediction model of small-scale oil spills. Oil diffusion experiments in seawater using different oil types, including heavy oil, light oil, and gasoline, at different addition amounts under various kinds of wind were carried out, and these diffusion processes were recorded by a camera. The experimental images were processed to obtain the spread oil film area. The oil film edge processing based on genetic algorithm (GA) and back propagation artificial neural network optimized by a particle swarm optimization (PSO-BP) is proposed. Numerical prediction models were then constructed using the BP artificial neural network, the genetic algorithm-optimized back propagation neural network (GA-BP), and the PSO-BP. Among the three methods, the PSO-BP has the fastest convergence speed and the highest stability, which can usually achieve the goal. The PSO-BP reduces the possibility of the BP-ANN and the GA-BP falling into a local optimum instead of reaching global optimization. The prediction performance evaluation data are R2 = 1 and MSE = 3.58e−9 – 8.87e−8. Results show that the GA and the PSO-BP provide a new approach to small-scale oil spill prediction.

A rolling bearing early fault diagnosis method is proposed in this paper, which is derived from a refined composite multi-scale approximate entropy (RCMAE) and improved coyote optimization algorithm based probabilistic neural network (ICOA-PNN) algorithm. Rolling bearing early fault diagnosis is a time-sensitive task, which is significant to ensure the reliability and safety of mechanical fault system. At the same time, the early fault features are masked by strong background noise, which also brings difficulties to fault diagnosis. So, we firstly utilize the composite ensemble intrinsic time-scale decomposition with adaptive noise method (CEITDAN) to decompose the signal at different scales, and then the refined composite multi-scale approximate entropy of the first signal component is calculated to analyze the complexity of describing the vibration signal. Afterwards, in order to obtain higher recognition accuracy, the improved coyote optimization algorithm based probabilistic neural network classifiers is employed for pattern recognition. Finally, the feasibility and effectiveness of this method are verified by rolling bearing early fault diagnosis experiment.

Predicting groundwater levels is critical for ensuring sustainable use of an aquifer’s limited groundwater reserves and developing a useful groundwater abstraction management strategy. The purpose of this study was to assess the predictive accuracy and estimation capability of various models based on the Adaptive Neuro Fuzzy Inference System (ANFIS). These models included Differential Evolution-ANFIS (DE-ANFIS), Particle Swarm Optimization-ANFIS (PSO-ANFIS), and traditional Hybrid Algorithm tuned ANFIS (HA-ANFIS) for the one- and multi-week forward forecast of groundwater levels at three observation wells. Model-independent partial autocorrelation functions followed by frequentist lasso regression-based feature selection approaches were used to recognize appropriate input variables for the prediction models. The performances of the ANFIS models were evaluated using various statistical performance evaluation indexes. The results revealed that the optimized ANFIS models performed equally well in predicting one-week-ahead groundwater levels at the observation wells when a set of various performance evaluation indexes were used. For improving prediction accuracy, a weighted-average ensemble of ANFIS models was proposed, in which weights for the individual ANFIS models were calculated using a Multiple Objective Genetic Algorithm (MOGA). The MOGA accounts for a set of benefits (higher values indicate better model performance) and cost (smaller values indicate better model performance) performance indexes calculated on the test dataset. Grey relational analysis was used to select the best solution from a set of feasible solutions produced by a MOGA. A MOGA-based individual model ranking revealed the superiority of DE-ANFIS (weight = 0.827), HA-ANFIS (weight = 0.524), and HA-ANFIS (weight = 0.697) at observation wells GT8194046, GT8194048, and GT8194049, respectively. Shannon’s entropy-based decision theory was utilized to rank the ensemble and individual ANFIS models using a set of performance indexes. The ranking result indicated that the ensemble model outperformed all individual models at all observation wells (ranking value = 0.987, 0.985, and 0.995 at observation wells GT8194046, GT8194048, and GT8194049, respectively). The worst performers were PSO-ANFIS (ranking value = 0.845), PSO-ANFIS (ranking value = 0.819), and DE-ANFIS (ranking value = 0.900) at observation wells GT8194046, GT8194048, and GT8194049, respectively. The generalization capability of the proposed ensemble modelling approach was evaluated for forecasting 2-, 4-, 6-, and 8-weeks ahead groundwater levels using data from GT8194046. The evaluation results confirmed the useability of the ensemble modelling for forecasting groundwater levels at higher forecasting horizons. The study demonstrated that the ensemble approach may be successfully used to predict multi-week-ahead groundwater levels, utilizing previous lagged groundwater levels as inputs.

In high-elevation or high-latitude permafrost areas, persistent subzero temperatures significantly impact the freeze–thaw durability of concrete structures. Traditional methods for studying the frost resistance of concrete in permafrost regions do not provide a complete picture for predicting properties, and new approaches are needed using, for example, machine learning algorithms. This study utilizes four machine learning models—Support Vector Machine (SVM), extreme learning machine (ELM), long short-term memory (LSTM), and radial basis function neural network (RBFNN)—to predict freeze–thaw damage factors in concrete under low and subzero temperature conservation conditions. Building on the prediction results, the optimal model is refined to develop a new machine learning model: the Sparrow Search Algorithm-optimized Extreme Learning Machine (SSA-ELM). Furthermore, the SHapley Additive exPlanations (SHAP) value analysis method is employed to interpret this model, clarifying the relationship between factors affecting the freezing resistance of concrete and freeze–thaw damage factors. In conclusion, the empirical formula for concrete freeze–thaw damage is compared and validated against the prediction results from the SSA-ELM model. The study results indicate that the SSA-ELM model offers the most accurate predictions for concrete freeze–thaw resistance compared to the SVM, ELM, LSTM, and RBFNN models. SHAP value analysis quantitatively confirms that the number of freeze–thaw cycles is the most significant input parameter affecting the freeze–thaw damage coefficient of concrete. Comparative analysis shows that the accuracy of the SSA-ELMDE prediction set is improved by 15.46%, 9.19%, 21.79%, and 11.76%, respectively, compared with the prediction results of SVM, ELM, LSTM, and RBF. This parameter positively influences the prediction results for the freeze–thaw damage coefficient. Curing humidity has the least influence on the freeze–thaw damage factor of concrete. Comparing the prediction results with empirical formulas shows that the machine learning model provides more accurate predictions. This introduces a new approach for predicting the extent of freeze–thaw damage to concrete under low and subzero temperature conservation conditions.

The door lock is one of the elevator fault prone parts, and the fault may further lead to personal injury accidents. In the process of elevator operation, the door lock acts frequently, resulting in a large amount of operation data. Using big data method, the fault prediction of elevator door lock could be realized, so as to prevent and reduce accidents. BP (Back Propagation) neural network algorithm and GA-BP (Genetic Algorithm) were used as door lock fault prediction algorithms, but there were some defects in performance. BP algorithm was easy to fall into local minima and the convergence speed was uncertain, while GA-BP algorithm would reduce the genetic diversity of the population. In this paper, we use MPGA (Multiple Population Genetic Algorithm) to improve the initial weight threshold of BP algorithm, adjust the neural network, and establish a door lock fault prediction model. The simulation results show that MPGA-BP model greatly improves the generalization ability and prediction accuracy of BP neural network, compared with traditional BP and GA-BP model.

Bright-field and phase-contrast imaging represent two of the most essential modes for target recognition and feature extraction, offering broad applicability in fields such as biomedicine and autonomous driving. In this work, we propose a cascaded Moiré metasurfaces system with a large interlayer spacing, which enables switchable bright-field and phase-contrast imaging at a wavelength of 532 nm by adjusting the illumination conditions between coherent and incoherent light sources. By employing an optimized phase-iterative algorithm, the stringent spacing requirement of conventional cascaded Moiré metasurfaces is relaxed from the subwavelength scale (∼100 nm) to beyond 1 mm, while maintaining robust imaging performance under spacing deviations of ±0.1 mm. Through controlled relative rotation of the two metasurfaces by an angle , the system dynamically switches between a focused solid Airy disk ( = 0°) and vortex beams with tunable topological charges ranging from −5 to +5 ( = ±20° to ±100°). The design achieves a focusing efficiency of 82 % and vortex beam purities up to 99 %. Owing to its versatile switching capability, the system supports multi-order edge extraction for both phase-type and amplitude-type objects, reaching a spatial frequency of 228 lp/mm. This approach overcomes the limitation of existing edge-detection metasurfaces, which operate only under either coherent or incoherent illumination. Our findings provide a new technical pathway toward compact, multifunctional, and integrated imaging devices.