The wheel-legged biped robot is a typical ground-based mobile robot that can combine the high velocity and high efciency pertaining to wheeled motion and the strong, obstacle-crossing performance associated with legged motion. These robots have gradually exhibited satisfactory application potential in various harsh scenarios such as rubble rescue, military operations, and wilderness exploration. Wheel-legged biped robots are divided into four categories according to the open–close chain structure forms and operation task modes, and the latest technology research status is summarized in this paper. The hardware control system, control method, and application are analyzed, and the dynamic balance control for the two-wheel, biomimetic jumping control for the legs and whole-body control for integrating the wheels and legs are analyzed. In summary, it is observed that the current research exhibits problems, such as the insufcient application of novel materials and a rigid–fexible coupling design; the limited application of the advanced, intelligent control methods; the inadequate understanding of the bionic jumping mechanisms in robot legs; and the insufcient coordination ability of the multi-modal motion, which do not exhibit practical application for the wheel-legged biped robots. Finally, this study discusses the key research directions and development trends for the wheel-legged biped robots.

Biological water striders have advantages such as fexible movement, low disturbance to the water surface, and low noise. Researchers have developed a large number of biomimetic water strider robots based on their movement mechanism, which have broad application prospects in water quality testing, water surface reconnaissance, and search. This article mainly reviews the research progress of biomimetic water strider robots. First, the biological and kinematic characteristics of water striders are outlined, and some mechanical parameters of biological water striders are summarized. The basic equations of water strider movement are then described. Next, an overview is given of the past and current work on skating and jumping movements of biomimetic water strider robots based on surface tension and water pressure dominance. Based on the current research status of biomimetic water strider robots, the shortcomings of current research on biomimetic water striders are summarized, and the future development of biomimetic water strider robots is discussed. This article provides new insights for the design of biomimetic water strider robots.

Cartilage regeneration and repair are considered clinical challenges since cartilage has limited capability for reconstruction. Although tissue-engineered materials have the ability to repair cartilage, they have weak mechanical characteristics and cannot resist long-term overload. On the other hand, surgery to replace the joint is frequently done to treat signifcant cartilage deterioration these days. However, the materials that are being used for replacement have high friction coefcients, lack shock absorption functions, and lack cushioning. Further research on natural articular cartilage structure and function may lead to bionic hydrogels, which have suitable physicochemical and biological characteristics (e.g., tribological and mechanical properties and the ability to support loadbearing capability), but need improvements. Based on their tribological and mechanical characteristics, the current review highlights the most recent advancements of bionic hydrogels used for articular cartilage, highlighting both the feld's recent progress and its potential for future research. For this reason, frstly, some important property improvement methods of bionic hydrogels are discussed and then, the recent fndings of various research on the making of those bionic materials are provided and compared. It seems that by using some modifcations such as product design, surface treatments, animal tests, controlling the isoelectric point of hydrogels, and computer simulation, the intended mechanical and tribological characteristics of natural articular cartilage may be attained by the bionic hydrogels.

Tissue engineering is nowadays an emerging approach that aims to replace or regenerate diseased or damaged organs with engineered constructs. Considering the key role of growth factors (GFs) in the tissue regeneration process, these biomolecules are considered an important part of the tissue engineering process, so the presence of growth factors in engineered scafolds can accelerate tissue regeneration by infuencing the behavior of cells. Platelet-rich plasma (PRP), as an autologous source of a variety of growth factors, is considered a therapeutic agent for the treatment of degenerative diseases. Regarding its ability to promote the healing process and tissue regeneration, PRP therapy has attracted great attention in bone and cartilage tissue engineering. Incorporating PRP and its derivatives into engineered scafolds not only bioactivates the scafold, but the scafold matrix also acts as a sustained and localized growth factor release system. In addition, the presence of a scafold can promote the bioactivity of GFs by providing an environment that facilitates their interaction, leading to enhanced efects compared to their free form. This review presents a brief overview of PRP's role in bone and cartilage tissue regeneration with the main focus on scafold-mediated PRP delivery. In addition, the classifcation of platelet-rich products, current extraction techniques, terminology, and scafold bioactivation methods are presented to provide a better understanding of the basics and the key aspects that may afect the efectiveness of therapy in bone and cartilage tissue engineering.

Soft robotic crawlers have limited payload capacity and crawling speed. This study proposes a high-performance inchwormlike modular robotic crawler based on fuidic prestressed composite (FPC) actuators. The FPC actuator is precurved and a pneumatic source is used to fatten it, requiring no energy cost to maintain the equilibrium curved shape. Pressurizing and depressurizing the actuators generate alternating stretching and bending motions of the actuators, achieving the crawling motion of the robotic crawler. Multi-modal locomotion (crawling, turning, and pipe climbing) is achieved by modular reconfguration and gait design. An analytical kinematic model is proposed to characterize the quasi-static curvature and step size of a single-module crawler. Multiple confgurations of robotic crawlers are fabricated to demonstrate the crawling ability of the proposed design. A set of systematic experiments are set up and conducted to understand how crawler responses vary as a function of FPC prestrains, input pressures, and actuation frequencies. As per the experiments, the maximum carrying load ratio (carrying load divided by robot weight) is found to be 22.32, and the highest crawling velocity is 3.02 body length (BL) per second (392 mm/s). Multi-modal capabilities are demonstrated by reconfguring three soft crawlers, including a matrix crawler robot crawling in amphibious environments, and an inching crawler turning at an angular velocity of 2? /s, as well as earthworm-like crawling robots climbing a 20?  inclination slope and pipe.

Geckos can efciently navigate complex terrains due to their multi-level adhesive system that is present on their toes. The setae are responsible for the gecko’s extraordinary adhesion and have garnered wide attention from the scientifc community. The majority of the reported works in the literature that have dealt with the peeling models mainly focus on the gecko hierarchical adhesive system, with limited attention given to investigating the infuence of gecko toe structure on the detachment. Along these lines, to gain a deeper understanding of the rapid and efortless detachment abilities of gecko toes, the peeling behavior of gecko toes on vertical surfaces was primarily investigated in this work. More specifcally, the detachment time of a single toe on a smooth acrylic plate was measured to be 0.41±0.21 s. Moreover, it was observed that the toe assumed a "U"- shaped structure upon complete detachment. Additionally, Finite Element Analysis (FEA) models for three diferent types of gecko toes were developed to simulate both the displacement-peel and the moment-peel modes. Increasing the segmentation of the adhesive layer led to a gradual decrease in the resultant force, as well as the normal and tangential components. Lastly, a gecko-inspired toe model was constructed and powered by Shape Memory Alloy (SMA). A systematic comparison between the vertical drag separation and the outward fip separation was also conducted. From our analysis, it was clearly demonstrated that outward peel separation signifcantly necessitated the reduction of the peeling force, thus confrming the advantageous nature of the outward motion in gecko toe detachment. Our data not only contribute to a deeper understanding of the gecko detachment behavior but also ofer valuable insights for the advancement of the wall-climbing robot feet.

Bionic manta underwater vehicles will play an essential role in future oceans and can perform tasks, such as long-duration reconnaissance and exploration, due to their efcient propulsion. The manta wings’ deformation is evident during the swimming process. To improve the propulsion performance of the unmanned submersible, the study of the deformation into the bionic pectoral fn is necessary. In this research, we designed and fabricated a fexible bionic pectoral fn, which is based on the Fin Ray? efect with active and passive deformation (APD) capability. The APD fn was actively controlled by two servo motors and could be passively deformed to variable degrees. The APD fn was moved at 0.5 Hz beat frequency, and the propulsive performance was experimentally verifed of the bionic pectoral fns equipped with diferent extents of deformation. These results showed that the pectoral fn with active–passive deformed capabilities could achieve similar natural biological deformation in the wingspan direction. The average thrust (T) under the optimal wingspan deformation is 61.5% higher than the traditional passive deformed pectoral fns. The obtained results shed light on the design and optimization of the bionic pectoral fns to improve the propulsive performance of unmanned underwater vehicles (UUV).

Lizards use the synergy between their feet and tail to climb on slopes and vertical terrains. They use their soft adhesive feet with millions of small hairs to increase their contact area with the terrain surface and press their tails against the terrain to actively maintain stability during climbing. Inspired by this, we propose a bio-inspired climbing robot based on a new approach wherein the synergy between soft feet and an active tail with a soft adhesive tip allows the robot to climb stably on even and uneven terrains at diferent slope angles. We evaluate and compare the climbing performance of the robot on three diferent terrains (hard, soft, and fufy) at diferent slope angles. Various robot confgurations are employed, including those with standard hard feet and soft feet in combination with an active tail—with and without a soft tip. The experimental results show that the robot having soft feet and a tail with the soft tip achieves the best climbing performance on all terrains, with maximum climbing slopes of 40?, 45?, and 50? on fufy, soft, and hard terrains, respectively. Its payload capacity depends on the type of terrain and the inclination angle. Moreover, our robot performs multi-terrain transitions (climbing from horizontal to sloped terrains) on three diferent terrains of a slope. This approach can allow a climbing robot to walk and climb on diferent terrains, extending the operational range of the robot to areas with complex terrains and slopes, e.g., in inspection, exploration, and construction.

The robotic airship is one of the most unique and promising green aircraft, however, as a “lighter-than-air aircraft” and “thermal aircraft”, its long-endurance fight has great difculties in decreasing drag and controlling buoyancy and pressure under thermal efects. In this work, we reported a robotic airship inspired by the Physalia physalis, imitating its morphology, physiological structure, and biological behaviors. The hull is designed by imitating the morphology of the Physalia physalis, and the gasbags including a helium balloon, two ballonets, and a thermoregulation gasbag are designed by imitating the physiological structure and biological behaviors of the pneumatophore, bladder, and gland of the Physalia physalis, respectively. Experimental results show that the bionic airship has an increase of about 40% in lift-to-drag and decreases the pressure in helium balloon by 47.5% under thermal efects, and has better aerodynamic performances and thermoregulation performances than conventional airships.

Inspired by the way sea turtles rely on the Earth’s magnetic feld for navigation and locomotion, a novel magnetic soft robotic turtle with programmable magnetization has been developed and investigated to achieve biomimetic locomotion patterns such as straight-line swimming and turning swimming. The soft robotic turtle (12.50 mm in length and 0.24 g in weight) is integrated with an Ecofex-based torso and four magnetically programmed acrylic elastomer VHB-based limbs containing samarium-iron–nitrogen particles, and was able to carry a load more than twice its own weight. Similar to the limb locomotion characteristics of sea turtles, the magnetic torque causes the four limbs to mimic sinusoidal bending deformation under the infuence of an external magnetic feld, so that the turtle swims continuously forward. Signifcantly, when the bending deformation magnitudes of its left and right limbs difer, the soft robotic turtle switches from straight-line to turning swimming at 6.334 rad/s. Furthermore, the tracking swimming activities of the soft robotic turtle along specifc planned paths, such as square-shaped, S-shaped, and double U-shaped maze, is anticipated to be utilized for special detection and targeted drug delivery, among other applications owing to its superior remote directional control ability.

Bionic hands are promising devices for assisting individuals with hand disabilities in rehabilitation robotics. Controlled primarily by bioelectrical signals such as myoelectricity and EEG, these hands can compensate for lost hand functions. However, developing model-based controllers for bionic hands is challenging and time-consuming due to varying control parameters and unknown application environments. To address these challenges, we propose a model-free approach using reinforcement learning (RL) for designing bionic hand controllers. Our method involves mimicking real human hand motion with the bionic hand and employing a human hand motion decomposition technique to learn complex motions from simpler ones. This approach signifcantly reduces the training time required. By utilizing real human hand motion data, we design a multidimensional sampling proximal policy optimization (PPO) algorithm that enables efcient motion control of the bionic hand. To validate the efectiveness of our approach, we compare it against advanced baseline methods. The results demonstrate the quick learning capabilities and high control success rate of our method.

Inspired by the fast, agile movements of insects, we present a 1.9 g, 4.5 cm in length, piezoelectrically driven, quadrupedal microrobot. This microrobot uses a novel spatial parallel mechanism as its hip joint, which consists of two spatially orthogonal slider-crank linkages. This mechanism maps two inputs of two independent actuators to the decoupled swing and lift outputs of a leg, and each leg can produce the closed trajectories in the sagittal plane necessary for robot motion. Moreover, the kinematics of the transmission are analyzed, and the parameters of the fexure hinges are designed based on geometrical constraints and yield conditions. The hip joints, legs and exoskeletons are integrated into a fve-layer standard laminate for monolithic fabrication which is composed of two layers of carbon fber, two layers of acrylic adhesive and a polyimide flm. The measured output force (15.97 mN) of each leg is enough to carry half of the robot’s weight, which is necessary for the robot to move successfully. It has been proven that the robot can successfully perform forward and turning motions. Compared to the microrobot fabricated with discrete components, the monolithically fabricated microrobot is more capable of maintaining the original direction of locomotion when driven by a forward signal and has a greater speed, whose maximum speed is 25.05 cm/s.

Continuum manipulators (CM) are soft and fexible manipulators with large numbers of degrees of freedom and can perform complex tasks in an unstructured environment. However, their deformability and compliance can deviate distal tip under uncertain external interactions. To address this challenge, a novel tension-based control scheme has been proposed to modulate the stifness of a tendon-driven CM, reducing the tip position errors caused by uncertain external forces. To minimize the tip position error, a virtual spring is positioned between the deviated and the desired tip positions. The proposed algorithm corrects the manipulator deviated tip position, improving tension distribution and stifness profle, resulting in higher stifness and better performance. The corresponding task space stifness and condition numbers are also computed under diferent cases, indicating the efectiveness of the tension control scheme in modulating the manipulator's stifness. Experimental validation conducted on an in-house developed prototype confrms the practical feasibility of the proposed approach.

Brain-controlled technology is the key technology in biological control, and the corresponding relationship between animal brain nuclei and motor behavior is the core. The purpose of this study was to explore the motor nuclei of the medulla oblongata in carp. The carps were subjected to electrical stimulation and chemical stimulation experiments, respectively, in the water-free state, and the efective chemical stimulation sites were injected with the pontamine sky blue solution. The brain tissue sections were obtained by parafn tissue section technology and the neutral red staining method. By comparing the positions of the brain nuclei shown in earlier studies, the motor nerve nuclei in the medulla oblongata were identifed. The brain electrode was implanted into the motor nucleus of the medulla oblongata, and the underwater control experiment and behavioral tests were carried out with diferent electrical stimulation parameters. The results showed that the abducens nucleus (NVI) was the motor nucleus that controls the ipsilateral steering, and the facial nucleus (NVII) was the motor nucleus that controls the forward movement. By adjusting the stimulation voltage and the stimulation pulse number, the carp can be stably controlled to achieve a left–right steering motion of 30°–180° and a forward motion of more than 80 cm/s. This study indicated that the quantitative control of the steering and forward behavior of the carp can be achieved by electrical stimulation of the NVI and NVII, which provided a certain experimental basis for the accurate control of the carp robot.

Autonomous navigation is a fundamental problem in robotics. Traditional methods generally build point cloud map or dense feature map in perceptual space; due to lack of cognition and memory formation mechanism, traditional methods exist poor robustness and low cognitive ability. As a new navigation technology that draws inspiration from mammal’s navigation, bionic navigation method can map perceptual information into cognitive space, and have strong autonomy and environment adaptability. To improve the robot’s autonomous navigation ability, this paper proposes a cognitive map-based hierarchical navigation method. First, the mammals’ navigation-related grid cells and head direction cells are modeled to provide the robots with location cognition. And then a global path planning strategy based on cognitive map is proposed, which can anticipate one preferred global path to the target with high efciency and short distance. Moreover, a hierarchical motion controlling method is proposed, with which the target navigation can be divided into several sub-target navigation, and the mobile robot can reach to these sub-targets with high confdence level. Finally, some experiments are implemented, the results show that the proposed path planning method can avoid passing through obstacles and obtain one preferred global path to the target with high efciency, and the time cost does not increase extremely with the increase of experience nodes number. The motion controlling results show that the mobile robot can arrive at the target successfully only depending on its self-motion information, which is an efective attempt and refects strong bionic properties.

In previous studies, Periaqueductal Gray (PAG) stimulation was used to stop ratbots from moving. Due to the homology between the PAG and the intercollicular nucleus, which has been used for forward movement in birds, we investigated the possibility of PAG application to induce forward locomotion for the frst time. Using a corridor maze, the traveled distances via PAG electrical stimulation were examined in nine Wistar male rats during three sessions. A custom-designed stimulator was developed to apply the stimulation. The results showed reductions in responses to stimulation over time. Accordingly, the traveled distances had negative slopes during the consecutive trials (in 8 out of the 9 rats), and the slope mean was signifcantly diferent from zero. There was a strong correlation between the stimulation parameters (electric Charge per Phase (CPP) and the Number of Pulses (NP)) and the observed slopes. The negative Movement Slopes (MS) were highly correlated with the CPP and the NP, as the Pearson's linear correlation coefcients were ? 0.87 and ? 0.79, respectively. The MS-CPP coefcients of determination (R-squared) were also between 0.76 and 0.95. In addition, the MS-NP coefcients of determination were between 0.63 and 0.87. Thus, it is concluded that the electrical stimulation parameters infuence the behavioral outcomes directly. Furthermore, the PAG area may be considered a suitable candidate for forward locomotion control in the future if the area is harnessed efectively to prevent undesirable chaotic behaviors.

To reveal the resonance suppression mechanism of the blood circulation in dragonfy wings, a numerical modeling method of dragonfy wings based on Voronoi diagrams is proposed, and the changes in mass, aerodynamic damping, and natural frequencies caused by blood circulation in veins are investigated. The equivalent mass of blood, boundary conditions, and aerodynamic damping are calculated theoretically. Modal analysis and harmonic response analysis of wing models with different blood circulation paths are performed using the fnite-element method (FEM). The vibration reduction ratio δ is introduced to compare the damping efciency of diferent mass regions. Finally, a natural frequency testing device is constructed to measure the natural frequencies of dragonfy wings. The results indicate that the shape, mass, and natural frequencies of the dragonfy wing model constructed by numerical method agree well with reality. The mass distribution on the wing can be altered by blood circulation, thereby adjusting the natural frequencies and achieving resonance suppression. The highest δ of 1.013 is observed in the C region when blood circulates solely in secondary veins, but it is still lower than the δ of 1.017 when blood circulates in complete veins. The aerodynamic damping ratio (1.19–1.79%) should not be neglected in the vibration analysis of the beating wing.

Total shoulder arthroplasty is a standard restorative procedure practiced by orthopedists to diagnose shoulder arthritis in which a prosthesis replaces the whole joint or a part of the joint. It is often challenging for doctors to identify the exact model and manufacturer of the prosthesis when it is unknown. This paper proposes a transfer learning-based class imbalance-aware prosthesis detection method to detect the implant’s manufacturer automatically from shoulder X-ray images. The framework of the method proposes a novel training approach and a new set of batch-normalization, dropout, and fully convolutional layers in the head network. It employs cyclical learning rates and weighting-based loss calculation mechanism. These modifcations aid in faster convergence, avoid local-minima stagnation, and remove the training bias caused by imbalanced dataset. The proposed method is evaluated using seven well-known pre-trained models of VGGNet, ResNet, and DenseNet families. Experimentation is performed on a shoulder implant benchmark dataset consisting of 597 shoulder X-ray images. The proposed method improves the classifcation performance of all pre-trained models by 10–12%. The DenseNet-201-based variant has achieved the highest classifcation accuracy of 89.5%, which is 10% higher than existing methods. Further, to validate and generalize the proposed method, the existing baseline dataset is supplemented to six classes, including samples of two more implant manufacturers. Experimental results have shown average accuracy of 86.7% for the extended dataset and show the preeminence of the proposed method.

The produced water from the oilfeld was purifed with flter material and then injected back into the ground. The serpentine flter material was easy to harden with the increase in fltration amount, which afected the water quality. A superhydrophilic/ underwater oleophobic serpentine flter material was successfully prepared by a simple method of coating modifcation, which exhibited long-lasting fltration of oily water, good fltration and anti-fouling properties, and resistance to harden. The flm-forming material of the superhydrophilic/underwater oleophobic coating was composed of SiO2 particles with small size, which could completely and evenly cover the flter particle. The weight loss was only 7.6% after mechanical stirring for 90 min. Compared with the original flter material, the superhydrophilic/underwater oleophobic serpentine flter material showed a better anti-fouling ability and resistance to harden. The fltration of crude oil emulsion and oil slick sewage showed a better backwashing performance. After 35 cycles of continuous fltration of suspended solids in wastewater, the backwashing rate reached 78.4%. The results provided an efective method for the fltration of oily wastewater in the oilfeld.

Engineered cardiac constructs (ECC) aid in the progression of regenerative medicine, disease modeling and targeted drug delivery to adjust and aim the release of remedial combination as well as decrease the side efects of drugs. In this research, polycaprolactone/gold nanoparticles (PCL/GNPs) three-dimensional (3D) composite scafolds were manufactured by 3D printing using the fused deposition modeling (FDM) method and then coated with gelatin/spironolactone (GEL/SPL). Scanning electron microscopy (SEM) and Fourier transform-infrared spectroscopy (FTIR–ATR) were applied to characterize the samples. Furthermore, drug release, biodegradation, behavior of the myoblasts (H9C2) cell line, and cytotoxicity of the 3D scafolds were evaluated. The microstructural observation of the scafolds reported interconnected pores with 150–300 μm in diameter. The 3D scafolds were degraded signifcantly after 28 days of immersion in stimulated body fuid (SBF), with the maximum rate of GEL- coated 3D scafolds. SPL release from cross-linked GEL coating demonstrated the excess of drug release over time, and according to the control release systems, the drug delivery systems (DDS) went into balance after the 14th day. In addition, cell culture study showed that with the addition of GNPs, the proliferation of (H9C2) was enhanced, and with GEL/SPL coating the cell attachment and viability were improved signifcantly. These fndings suggested that PCL/ GNPs 3D scafolds coated with GEL/SPL can be an appropriate choice for myocardial tissue engineering.

Basalt fber reinforcement in polymer matrix composites is becoming more and more popular because of its environmental friendliness and mechanical qualities that are comparable to those of synthetic fbers. Basalt fber strengthened vinyl ester matrix polymeric composite with fller addition of nano- and micro-sized silicon carbide (SiC) element spanning from 2 weight percent to 10 weight percent was studied for its mechanical and wear properties. The application of Artifcial Neural Network (ANN) to correlate the fller addition composition for optimum mechanical properties is required due to the non-linear mechanical and tribological features of composites. The stufng blend and composition of the composite are optimized using the hybrid model and Genetic Algorithm (GA) to maximize the mechanical and wear-resistant properties. The predicted and tested ANN–GA optimal values obtained for the composite combination had a tensile, fexural, impact resilience, hardness and wear properties of 202.93 MPa, 501.67 MPa, 3.460 J/s, 43 HV and 0.196 g, respectively, for its optimum combination of fller and reinforcement. It can be noted that the nano-sized SiC fller particle enhances most of the properties of the composite which diversifes its applications. The predicted mechanical and wear values of the developed ANN–GA model were in closer agreement with the experimental values which validate the model.

This paper comprehensively analyzes the Manta Ray Foraging Optimization (MRFO) algorithm and its integration into diverse academic felds. Introduced in 2020, the MRFO stands as a novel metaheuristic algorithm, drawing inspiration from manta rays’ unique foraging behaviors—specifcally cyclone, chain, and somersault foraging. These biologically inspired strategies allow for efective solutions to intricate physical challenges. With its potent exploitation and exploration capabilities, MRFO has emerged as a promising solution for complex optimization problems. Its utility and benefts have found traction in numerous academic sectors. Since its inception in 2020, a plethora of MRFO-based research has been featured in esteemed international journals such as IEEE, Wiley, Elsevier, Springer, MDPI, Hindawi, and Taylor & Francis, as well as at international conference proceedings. This paper consolidates the available literature on MRFO applications, covering various adaptations like hybridized, improved, and other MRFO variants, alongside optimization challenges. Research trends indicate that 12%, 31%, 8%, and 49% of MRFO studies are distributed across these four categories respectively.

In this work, a three dimensional (3D) convolutional neural network (CNN) model based on image slices of various normal and pathological vocal folds is proposed for accurate and efcient prediction of glottal fows. The 3D CNN model is composed of the feature extraction block and regression block. The feature extraction block is capable of learning low dimensional features from the high dimensional image data of the glottal shape, and the regression block is employed to fatten the output from the feature extraction block and obtain the desired glottal fow data. The input image data is the condensed set of 2D image slices captured in the axial plane of the 3D vocal folds, where these glottal shapes are synthesized based on the equations of normal vibration modes. The output fow data is the corresponding fow rate, averaged glottal pressure and nodal pressure distributions over the glottal surface. The 3D CNN model is built to establish the mapping between the input image data and output fow data. The ground-truth fow variables of each glottal shape in the training and test datasets are obtained by a high-fdelity sharp-interface immersed-boundary solver. The proposed model is trained to predict the concerned fow variables for glottal shapes in the test set. The present 3D CNN model is more efcient than traditional Computational Fluid Dynamics (CFD) models while the accuracy can still be retained, and more powerful than previous data-driven prediction models because more details of the glottal fow can be provided. The prediction performance of the trained 3D CNN model in accuracy and efciency indicates that this model could be promising for future clinical applications.

Parkinson’s disease is a neurodegenerative disorder that inficts irreversible damage on humans. Some experimental data regarding Parkinson’s patients are redundant and irrelevant, posing signifcant challenges for disease detection. Therefore, there is a need to devise an efective method for the selective extraction of disease-specifc information, ensuring both accuracy and the utilization of fewer features. In this paper, a Binary Hybrid Artifcial Hummingbird and Flower Pollination Algorithm (FPA), called BFAHA, is proposed to solve the problem of Parkinson’s disease diagnosis based on speech signals. First, combining FPA with Artifcial Hummingbird Algorithm (AHA) can take advantage of the strong global exploration ability possessed by FPA to improve the disadvantages of AHA, such as premature convergence and easy falling into local optimum. Second, the Hemming distance is used to determine the diference between the other individuals in the population and the optimal individual after each iteration, if the diference is too signifcant, the cross-mutation strategy in the genetic algorithm (GA) is used to induce the population individuals to keep approaching the optimal individual in the random search process to speed up fnding the optimal solution. Finally, an S-shaped function converts the improved algorithm into a binary version to suit the characteristics of the feature selection (FS) tasks. In this paper, 10 high-dimensional datasets from UCI and the ASU are used to test the performance of BFAHA and apply it to Parkinson’s disease diagnosis. Compared with other state-of-the-art algorithms, BFAHA shows excellent competitiveness in both the test datasets and the classifcation problem, indicating that the algorithm proposed in this study has apparent advantages in the feld of feature selection.

Extracting photovoltaic (PV) model parameters based on the measured voltage and current information is crucial in the simulation and management of PV systems. To accurately and reliably extract the unknown parameters of diferent PV models, this paper proposes an improved multi-verse optimizer that integrates an iterative chaos map and the Nelder–Mead simplex method, INMVO. Quantitative experiments verifed that the proposed INMVO fueled by both mechanisms has more afuent populations and a more reasonable balance between exploration and exploitation. Further, to verify the feasibility and competitiveness of the proposal, this paper employed INMVO to extract the unknown parameters on single-diode, double-diode, three-diode, and PV module four well-known PV models, and the high-performance techniques are selected for comparison. In addition, the Wilcoxon signed-rank and Friedman tests were employed to test the experimental results statistically. Various evaluation metrics, such as root means square error, relative error, absolute error, and statistical test, demonstrate that the proposed INMVO works efectively and accurately to extract the unknown parameters on diferent PV models compared to other techniques. In addition, the capability of INMVO to stably and accurately extract unknown parameters was also verifed on three commercial PV modules under diferent irradiance and temperatures. In conclusion, the proposal in this paper can be implemented as an advanced and reliable tool for extracting the unknown parameters of diferent PV models. Note that the source code of INMVO is available at https://github.com/woniuzuioupao/INMVO.

In recent years, with the increasing demand for social production, engineering design problems have gradually become more and more complex. Many novel and well-performing meta-heuristic algorithms have been studied and developed to cope with this problem. Among them, the Spherical Evolutionary Algorithm (SE) is one of the classical representative methods that proposed in recent years with admirable optimization performance. However, it tends to stagnate prematurely to local optima in solving some specifc problems. Therefore, this paper proposes an SE variant integrating the Cross-search Mutation (CSM) and Gaussian Backbone Strategy (GBS), called CGSE. In this study, the CSM can enhance its social learning ability, which strengthens the utilization rate of SE on efective information; the GBS cooperates with the original rules of SE to further improve the convergence efect of SE. To objectively demonstrate the core advantages of CGSE, this paper designs a series of global optimization experiments based on IEEE CEC2017, and CGSE is used to solve six engineering design problems with constraints. The fnal experimental results fully showcase that, compared with the existing well-known methods, CGSE has a very signifcant competitive advantage in global tasks and has certain practical value in real applications. Therefore, the proposed CGSE is a promising and frst-rate algorithm with good potential strength in the feld of engineering design.

Nowadays, optimization techniques are required in various engineering domains to fnd optimal solutions for complex problems. As a result, there is a growing tendency among scientists to enhance existing nature-inspired algorithms using various evolutionary strategies and to develop new nature-inspired optimization methods that can properly explore the feature space. The recently designed nature-inspired meta-heuristic, named the Golden Jackal Optimization (GJO), was inspired by the collaborative hunting actions of the golden jackal in nature to solve various challenging problems. However, like other approaches, the GJO has the limitations of poor exploitation ability, the ease of getting stuck in a local optimal region, and an improper balancing of exploration and exploitation. To overcome these limitations, this paper proposes an improved GJO algorithm based on multi-strategy mixing (LGJO). First, using a chaotic mapping strategy to initialize the population instead of using random parameters, this algorithm can generate initial solutions with good diversity in the search space. Second, a dynamic inertia weight based on cosine variation is proposed to make the search process more realistic and efectively balance the algorithm's global and local search capabilities. Finally, a position update strategy based on Gaussian mutation was introduced, fully utilizing the guidance role of the optimal individual to improve population diversity, efectively exploring unknown regions, and avoiding the algorithm falling into local optima. To evaluate the proposed algorithm, 23 mathematical benchmark functions, CEC-2019 and CEC2021 tests are employed. The results are compared to high-quality, well-known optimization methods. The results of the proposed method are compared from diferent points of view, including the quality of the results, convergence behavior, and robustness. The superiority and high-quality performance of the proposed method are demonstrated by comparing the results. Furthermore, to demonstrate its applicability, it is employed to solve four constrained industrial applications. The outcomes of the experiment reveal that the proposed algorithm can solve challenging, constrained problems and is very competitive compared with other optimization algorithms. This article provides a new approach to solving real-world optimization problems.