We propose a learning algorithm for discovering unknown parameterized dynamical systems by using observational data of the state variables. Our method is built upon and extends recent work systems, in particular those deep neural network (DNN). DNN structure, largely based residual (ResNet), to not only learn form governing equation but also take into account random effect embedded system, which generated parameters. Once model successfully constructed, it able produce system prediction over...

Electric Vertical Take-off and Landing vehicles (eVTOLs) are driving Advanced Air Mobility (AAM) toward transforming urban transportation by extending travel from congested ground networks to low-altitude airspace. This transition promises reduce traffic congestion significantly shorten commute times. To ensure aviation safety, eVTOLs must fly within prescribed flight corridors. These corridors managed ground-based Traffic Control (ATCo) stations, which oversee air-ground communication...

Structural damage identification based on metaheuristic algorithms is an important part of structural health monitoring with great potential. However, the intelligent probably have flaws slow convergence speed and low calculation accuracy, which need to be improved address engineering optimization problems. In this paper, black widow (BWO) algorithm used for identification. addition, a multistrategy fusion–improved BWO (IBWO) proposed by introducing tent chaotic mapping, golden sine...

Structural damage identification (SDI) serves as an indirect approach that has the potential to meet real‐time monitoring of structures. However, accuracy and efficiency some methods need be improved, especially when there are uncertain interfering factors or noise. This paper presents a new optimization algorithm improved objective function for inverse problems SDI, offering effective solution bridge under noise interference incomplete modal data. In this study, by hybridizing whale sand...

This article introduces and evaluates the piecewise polynomial truncated singular value decomposition algorithm toward an effective use for moving force identification. Suffering from numerical non-uniqueness noise disturbance, identification is known to be associated with ill-posedness. An important method solving this problem algorithm, but small values removed by may contain some useful information. The extracts responses superposes it into solution of decomposition, which can in In...

In this study, a modified truncated singular value decomposition (MTSVD) method is proposed for the identification of dynamic moving forces on simply-supported beams. By regularizing (TSVD) method, MTSVD focuses overcoming ill-posed problems that intrinsically exist in force identification. Two regularization parameters, namely, matrix and truncating point are most important parameters affecting performance method. The accuracy efficiency shown by comparing results with conventional...

Swarm intelligence algorithms and finite element model update technology are important issues in the field of structural damage detection. However, complexity engineering models normally leads to low computational efficiency large detection errors To solve these problems, a simulated annealing-artificial hummingbird algorithm (SA-AHA) is proposed based on artificial (AHA). The Sobol sequence used improve identification by optimizing initial population distribution AHA. Then, annealing...

Damage detection of structures based on swarm intelligence optimization algorithms is an effective method for structural damage and key parts the field health monitoring. Based chimp algorithm (ChOA) whale algorithm, this paper proposes a novel hybrid whale-chimp (W-ChOA) detection. To improve identification accuracy ChOA, Sobol sequence adopted in population initialization stage to make evenly fill entire solution space. In addition, local search ability traditional bubble-net hunting...

Reliable bond of steel fiber in concrete is a key problem relating to the reinforcing effect on matrix and for guide significance optimal design geometry mechanical properties fiber. In this paper, basis multi-indices evaluation single hooked-end fiber, indices synergistic different deformed fibers are proposed. The pull-out tests were carried out embedded mortar wet-sieved from self-compacting SFRC with manufactured sand. Fourteen types used, including six hooked-end, two crimped, four...

This paper studied two-stage permutation flow shop problems with batch processing machines, considering different job sizes and arbitrary arrival times, the optimisation objective of minimising makespan. The quantum-inspired ant colony (QIACO) algorithm was proposed to solve problem. In QIACO algorithm, ants are divided into two groups: one group selects largest in terms size as initial for each other smallest batch. Each has its own pheromone matrix. computational experiment, our novel...

The high surface accuracy design of a cable-net antenna structure under the disturbance extremely harsh space environment requires to have good in-orbit adjustment ability for accuracy. A shape memory (SMC) is proposed in this paper and believed be able improve antenna. Firstly, incremental stiffness equation one-dimensional bar element alloy (SMA) express relationship between force, temperature deformation was effectively constructed. Secondly, finite model SMC incorporated SMA established....

The studies on inverse problems exist extensively in aerospace, mechanical, identification, detection, scanning imaging and other fields. Its ill-posed characteristics often lead to large oscillations the solution of problem. In this study, truncated generalized singular value decomposition (TGSVD) method is introduced identify two kinds moving forces, single multi-axial forces. truncating point most influential regularization parameter TGSVD, which initially selected by classic selection...