This paper proposes a neural network predictive control (NNPC) method to address the challenge of controlling the output speed in a fixed displacement motor (FDM) system controlled by an electrohydraulic proportional variable displacement pump (EHP-VDP). The dynamic response of the system is divided into four segments, and mathematical models are derived for each segment. The system is modelled using over 400 input-output data pairs, with 75% of the data used for training and the remaining 25% for validation. The Levenberg-Marquardt algorithm (LMA) is employed to optimise the neural network, achieving optimal validation performance with a mean square error of 0.0029637 after 258 epochs. This real-time optimisation enables the output speed of the system to accurately track the reference speeds. Simulink simulations are conducted over a 25-second duration covering five reference speed intervals, demonstrating reliable tracking performance. The NNPC method shows competitive performance compared with backpropagation-neural network-proportional integral derivative (BP-NN-PID) and proportional integrative derivative (PID) controllers, achieving the root mean square error (RMSE), the mean absolute error (MAE), and the integral squared error (ISE) values of 6.72, 1.00, and 572.89, respectively. These results indicate that the NNPC offers advantages in fast-response scenarios while maintaining acceptable tracking accuracy.
This paper considers a multi-objective optimisation problem focusing on translational parallel manipulators. The proposed approach combines interval analysis with genetic algorithms to optimise the dynamic parameters of parallel manipulators. The objectives are to enhance the robot accuracy, while maximising the tolerance intervals of the parameters. This paper's contribution is to introduce an interval method to estimate the error bounds of a dynamic parallel manipulator within the desired workspace. A genetic algorithm is then applied to improve manipulator accuracy and reduce design costs. The resulting Pareto fronts illustrate the trade-off between each pair of objective functions.
This study examines springback in mild-steel sheet air V-bending through an integrated experimental-numerical-data-driven framework aimed at practical bend design and tool compensation. Bending tests were performed using a modular die set while systematically varying sheet thickness, punch radius, and target bending angle, and repeated measurements were used to ensure reliable springback evaluation. The experimental trends were crosschecked with nonlinear finite element simulations in MSC Marc Mentat (R), providing a physicsbased reference and confirming that the selected parameters govern the springback response over the investigated range. To enable fast prediction without repeated simulations, a feedforward artificial neural network (ANN) was trained on 106 experimental cases to map the forming parameters to springback. Because conventional ANN training can be sensitive to random initialisation and can become trapped in local minima, a genetic algorithm (GA) was employed to optimise the initial weights and biases prior to gradient-based learning. Compared with a standard ANN, the GA-optimised ANN delivered more stable convergence and improved generalisation, increasing test accuracy (R2 from 0.833 to 0.875) and reducing the mean absolute error from 0.195 degrees to 0.075 degrees (61.5% improvement). Overall, the proposed hybrid approach combines experimental reliability, FEM validation, and GA-enhanced learning to provide an efficient and robust springback prediction tool for sheet-metal forming applications.
This study investigates the mechanical performance and microstructural evolution of AA7075 aluminium alloy joints produced using the cold metal transfer process. Owing to its low heat input, cold metal transfer is well suited for welding heat-sensitive precipitation-hardened alloys prone to porosity, hot cracking, and strength loss. Response surface methodology with a central composite design was applied to quantify the effects of welding current (160 to 200 A), welding speed (100 to 140 mm/min), and wire feed speed (1000 to 2000 mm/min) on ultimate tensile strength. The resulting empirical model showed strong statistical significance and close agreement between predicted and experimental values. Microstructural analysis revealed the dissolution of dizinc magnesium precipitate, dendritic solidification, and inter-dendritic segregation in the fusion zone; partial over-ageing in the heat-affected zone; and the retention of the T6 structure in the base metal. Hardness decreased from 164-171 HV0.5 (the base metal) to 147-155 HV0.5 (the heat-affected zone) and 140-145 HV0.5 (the fusion zone). Validation using optimised parameters achieved an ultimate tensile strength of 366 MPa, matching the model prediction. Overall, the study confirms cold metal transfer as an effective technique for producing high-strength AA7075 welds with minimal thermal damage.
This paper presents a novel approach to the integration of biological inspiration into topological optimisation through the specification of input parameters derived from nature. The aim is to create biomimetic designs that may incorporate the multifunctionality inherent in natural systems. The presented methodology for modelling bioinspired structures using topological optimisation provides critical insights into translating natural forms and their load-bearing characteristics into topological optimisation design parameters (design space, boundary conditions, and loads). The proposed BioTop method is a structured framework that guides designers through a design-to-biology approach for conducting truly bioinspired topological optimisation by systematically defining the required inputs. An illustrative case study demonstrates the practical application of the BioTop method and its capacity to create bioinspired topologically optimised structures. While acknowledging current simplifications, this research lays a foundation for future research in bioinspired design by providing a systematic method for using nature as an informed input source for the standard topological optimisation software.
To reduce the material consumption of the telescopic boom of forklift trucks, a multilevel optimisation lightweight design approach for the boom is proposed. Based on actual loading conditions, a mechanical model of the boom cross-section is established, and the design is optimised through topology optimisation. By analysing the impact of element size, volume fraction, and threshold values on the performance of the telescopic boom's cross-section, the optimal topology of its configuration is obtained. The parametric model of the boom is reconstructed based on the topology optimisation result. With the minimisation of the boom mass as the objective, and both stress and deformation as constraints, the cross-sectional parameters of the boom are optimised. The design variables are sampled by the Optimal Space-Filling (OSF) design method, and the Kriging surrogate model is used to construct a high-precision model, thereby enhancing computational efficiency and ensuring accuracy. The Multi-Objective Genetic Algorithm (MOGA) is used to solve the optimisation model and identify the optimal solution. Upon validation, the optimised boom not only reduces the mass by 8.44%, but also improves its torsional stiffness, effectively reduces the material usage, and has important guiding significance for the lightweight design of telescopic booms.
This study presents the characterisation of microelectrode array (MEA) chips with 3D microtopography using scanning electron microscopy (SEM) and energy-dispersive X-ray spectroscopy (EDS). The aim was to evaluate the uniformity of the composition across four microtopographic zones and between individual chips, as well as to assess surface coverage following the drying of Neurobasal-A (NB-A) culture medium. The atomic fractions of the chip elements were expressed by the titanium ratio (Ti_index) on three chips. The residue coverage of the chip surface with dried NB-A droplets on a four-chip sample (3 or 30 mu L; two chips per volume) was expressed by NaCl_index (Na and Cl relative to chip-related elements). A twofactor ANOVA test showed a tendency for the Ti_index to vary across zones rather than between chips, implying a high-quality manufacturing process. The NaCl_index increased with the volume of the culture medium without a noticeable effect across zones, indicating that the dried medium may mask the microstructures of the chip surface.
Shot peening was applied to quenched and highly tempered C55 structural steel as a pretreatment to titanium coating cold spray deposition with the aim of improving the coating's adhesion during cyclic loading. Applying titanium cold spray directly onto the steel surface caused significant plastic deformation of the substrate, resulting in the creation of discontinuities on the coating/substrate interface. When shot peening was applied prior to the cold spraying, the work-hardened surface layer served as a more suitable substrate, avoiding the creation of major interface discontinuities. Fatigue resistance of the shot-peened specimens was improved by up to 20% and no coating delamination was observed in the regions of fatigue crack initiation and propagation.
The aim of this paper is to present the possibilities of using Artificial Neural Networks (ANNs) for the smart management of energy storage in systems with a high share of renewable energy sources. The overall method consists of two separate parts. First, optimal energy flows are simulated in EnergyPLAN, where the management of the energy system, including five energy storage systems, is optimised for daily and seasonal management. EnergyPLAN here represents an expert system from which the ANN model learns optimal energy system management. The outputs are then used in the second part which is training, validating, and testing ANNs in PyTorch for the reproduction of energy storage management with respect to the same set of input data. Input variables are related to intermittent, but predictable, supply from the wind and solar insolation, seasonal demand for grid gas, district heating demand, as well as electricity demand for BEVs. Output variables are the charge and discharge signals of all five energy storage systems, as well as the control variables of other components of the energy system. Several configurations of ANNs were tested, showing that ANNs can obtain statistically significant results, achieving an overall R2 score of 0.8 in the prediction of energy flows in all five storage systems. The results show that better performance is achieved if residual connection blocks are included in the ANN architecture and better agreement if physical constraints are integrated in the model training loss.
This paper presents an analytical calculation method for high-speed helical gear multitooth impact excitation based on energy conservation considering the temperature effect. Firstly, considering the tooth surface contact temperature factor, the position of the meshing point of a gear tooth is determined. Then, the meshing impact excitation of the first pair of helical gears, considering the temperature effect, is obtained. Secondly, based on the principle of conservation of energy, the amount of change in the meshing speed of tooth pairs II and III, induced by the meshing impact excitation outside the line, is determined, and an analytical model for the impact of tooth pairs II and III is established; the model will obtain the impact excitation of tooth pairs II and III. Then, the evolution law of multi-tooth impact excitation induced by the meshing impact excitation is explained. Finally, the influence of gear impact on the time-varying friction excitation and the tooth surface load is studied. The proposed calculation method can accurately and quickly calculate the multi-tooth impact excitation of a high-speed helical gear pair and provide theoretical support for the prediction of the impact and contact state of a gear system in engineering practice.
The paper presents a case study on additive manufacturing, focusing on metal threedimensional (3D) printing technology, to produce intricate components and assemblies required for constructing a demonstration model of the Wankel engine. After creating a digital 3D model, Studio SystemTM was used to print 3D physical parts. For the metal 3D printing process, 17-4 PH stainless steel, a high-performance material provided by Desktop Metal, was selected. The 3D printing process, which involves printing, debinding, and sintering, was photo documented. The Wankel engine was assembled using sintered 3D-printed parts, and the porosity of the material was tested by injecting fuel. The results demonstrated that the material used for the engine model was fuel-tight, thus validating the precision and effectiveness of the metal 3D printing process in producing highly complex operational parts.
Swarms of Unmanned Aerial Vehicles (UAVs) have been widely used in various applications mainly for surveillance and crowd-sensing. A swarm setup is an environment where multiple UAVs coordinate together to execute a specific mission. Such a swarm of UAVs is a useful entity to access areas where human penetration is impossible. To facilitate the need for automation among swarms of UAVs, a Deep Q-Learning based Dynamic Swarm Pattern Formation (DSPF) model is proposed. The proposed Speed Control based Reinforcement Learning (SC-RL) algorithm enhances the DSPF model to achieve pattern formation in an automated manner. The SC-RL algorithm strives to switch patterns efficiently by avoiding inter-UAV collisions and also keeps optimal trajectory intact throughout its pattern switching mechanism. To speed up the pattern building process and enable parallelised coordinate computation, a Decentralised Coordinate Computation (DCC) algorithm is implemented. The Servo Interrupt based Pattern Switch (SIPS) control also gives the DSPF model the ability to change patterns dynamically, which allows it to be adjusted to a variety of situations. By increasing the pattern formation time and distance covered by about 95.68% and 66.67%, respectively, simulations conducted for 100 UAVs demonstrate the viability of the suggested DSPF model in a crowded, collision-prone environment.
This study investigates the effect of tip-mounted store mass on the flutter behaviour of an F-16 fighter jet model wing using wind tunnel testing and numerical analysis. A 1/8-scale polycarbonate wing was tested with six external store configurations of identical geometry but different masses, representing varying inertia through aluminium and steel materials. Experiments were conducted in the Ankara Wind Tunnel, while numerical analyses were performed in ZAERO (R) using modal data obtained from finite-element models. Seven configurations, including a clean wing baseline, were evaluated with stores mounted on F-16 under-wing stations. A comparison of ZAERO's g-method and k-method showed that the kmethod exhibits closer agreement with experimental results. The findings reveal that increasing store mass leads to a pronounced reduction in flutter frequency and flutter speed, and this trend becomes increasingly non-linear for heavier configurations. These results underscore the dominant role of tip-mounted inertia in subsonic flutter behaviour and demonstrate that simplified flat-plate wing models can reliably capture mass-driven aeroelastic trends.
To improve the energy utilisation efficiency and driving range of electric vehicles, this paper proposes two strategies: a brake energy recovery control strategy and an electric braking force optimisation algorithm based on electro-mechanical brakes (EMBs). First, a three-stage control system for the EMBs is designed using an active disturbance rejection control (ADRC) algorithm. Next, a brake force distribution strategy that uses a safety zone rule to dynamically adjust the brake force distribution according to real-time operating conditions is proposed based on the ideal brake force distribution curve and the ECE regulation line. This ensures effective braking performance. Then, the whale optimisation algorithm (WOA) is introduced with improvements to its adaptive inertia weight and nonlinear convergence factor to optimise the motor torque control and improve the braking energy recovery efficiency. Finally, co-simulations were performed in MATLAB/Simulink and AVL Cruise for two typical conditions: the worldwide harmonised light vehicle test cycle (WLTC) and China light-duty vehicle test cycle (CLTC). The simulation results show that the three-stage control system designed with the ADRC algorithm outperforms the standard EHB system and that the optimised motor braking force using the improved WOA can recover more energy during braking.
Plasma spray welding is widely used in surface engineering and remanufacturing. To improve the efficiency of energy utilisation during the spray welding process and the performance of repaired parts, plasma spray welding parameters are optimised from three aspects, namely the efficiency of energy utilisation, the Vickers hardness of the repaired layer, and the residual stress on the boundary of the heat-affected zone on the workpiece surface. Based on the central composite design method, experiments were conducted to analyse the relationship between specific energy, Vickers hardness, residual stress, and process parameters. The objective functions of the energy efficiency, the Vickers hardness, and the residual stress during plasma spray welding were established by using the response surface methodology. A multi-objective optimisation model has been established based on the improved energy efficiency and process performance. Finally, the relationship between the energy efficiency and the repair process performance was discussed.
Currently, deformation modelling of a riveted assembly of aircraft thin-walled parts typically assumes that the riveted surfaces of thin-walled parts are smooth. However, in engineering practice, the riveted surfaces of thin-walled parts are not smooth. Therefore, in this study, the relationships among the pressing riveting force, the fractal characteristics of the riveting surface, and the riveting deformation are precisely quantified and a new modelling method for predicting the deformation of the riveted assembly of thin-walled components is proposed based on the spring damping method. The method enhances the prediction accuracy of the riveting deformation of aircraft thin-walled components. Through the analysis of the riveted assembly of thin-walled components, the pressing riveting force of the standard pier head is obtained. By examining the microscopic features of the riveting surface, a fractal model capable of capturing the surface complexity at the microscopic scale is established, revealing the geometric and topological properties of the surface. The structural function method is employed to derive the fractal parameters of the equivalent riveting surface topography that characterise the surface roughness. A micro-asperity contact model considering the interactions between micro-asperities is established to simulate the actual contact conditions. By extending the size distribution function of the micro-asperity contact area, a normal contact stiffness and damping model describing the mechanical response of the surface under normal loading is established, incorporating the elastic and dissipative properties of the contact interface. Spring elements representing normal contact stiffness and damping are arranged on the riveting surface to establish a simulation model for the riveted assembly of thin-walled components based on the spring damping method. Simulation and experimental results indicate that, compared with the smooth surface model, the spring damping method model reduces the two indicators of overall relative error by 16% each, and the local relative error of each measuring point by over 8%, thus significantly improving the prediction accuracy. This study integrates the fractal contact theory with the spring damping equivalent method to quantify the influence mechanism of the microscopic topography of the riveting surface on macroscopic deformation, breaking through the limitations of the traditional smooth surface assumption.
Mathematical modelling of production systems is a central task of production system engineering, especially when considering the competitiveness and effectiveness of production companies aiming at quality management and customer-oriented production. Two different approaches to the modelling of a Bernoulli production line with product quality inspection and rework stations are presented in this study. In the first case, analytical modelling is introduced based on Markov chains and the formulation of constitutive transition matrices. In the second case, an approximative approach is presented by employing the finite state method and formulating new finite state elements. The validation of the approximative approach is performed based on theoretical production lines, and the main findings are employed in a shipyard's plate prefabrication line. The issues of computing requirements and quality-quantity coupling are also discussed, indicating the need for further research in the context of improvability analyses and the design of production systems.
To investigate the impact of installation errors on the meshing performance of variable hyperbolic circular arc tooth trace (VH-CATT) cylindrical gear transmission systems, this study examines the time-varying meshing stiffness characteristics under the influence of such errors. First, based on the VH-CATT cylindrical gear forming principle, a precise three-dimensional model was established after deriving tooth surface equations. Second, the tooth face load and meshing stiffness of VH-CATT cylindrical gears were calculated using tooth contact analysis (TCA) and load tooth contact analysis (LTCA) models. Finally, the effects of different mounting errors on the meshing stiffness of VH-CATT cylindrical gears were examined. The study conclusively shows that the centre distance installation error, the axial installation error, and the rotational installation error around the gears' centre line direction (for the y-axis) exert a pronounced effect on both the single-tooth stiffness and the meshing stiffness characteristics of VH-CATT cylindrical gears. The rotational installation error around the normal direction of the gear centre line (for the x-axis) notably affects the single-tooth stiffness characteristics of the VH-CATT cylindrical gears, yet it exhibits limited sensitivity towards the meshing stiffness characteristics. These findings provide a technical basis for reducing vibration and noise, improving load carrying capacity, and optimising the tooth surface design of VH-CATT cylindrical gears.
The Bao-Wierzbicki (B-W) criterion more accurately describes the fracture characteristics of steel under different stress states and provides a more precise prediction of the fracture of duplex steels. Taking DP780 as a research object, the relationship between stress triaxiality and fracture strain in the fracture region of dual-phase steel at different temperatures was investigated by uniaxial tensile, shear, and Nakazima tests combined with numerical simulations. A stress triaxiality-based fracture model (B-W fracture criterion) at different temperatures was obtained and its temperature dependence was studied. Finally, the reliability of the criterion was verified using the stretch-bending tests of U-shape parts. The fracture criterion can be employed to forecast the emergence of fractures in automotive components during the stamping processes. This enables designers to undertake virtual simulations of operational conditions, thereby facilitating the selection of optimal process parameters during production.
