Deep learning based load and position identification of complex structure

Feng, Tao; Duan, Andongzhe; Guo, Liang; Gao, Hongli; Chen, Tao; Yu, Yaoxiang

doi:10.1109/iciea51954.2021.9516129

Cited by 4 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VSRPM is a more efficient method among the MOFM. The artificial intelligence dynamic load positioning method employs decision tree models, convolutional neural network models, and bidirectional long short-term memory models based on deep learning, etc., to simulate the dynamic behavior of the structure and the relationship between response data through a large dataset, thereby achieving the positioning and identification of dynamic loads [26][27][28][29].…”

Section: Introductionmentioning

confidence: 99%

A Non-Global Traversal Method for Dynamic Load Rapid Localization and Identification

Li,

Zhang,

Jiang

2024

Aerospace

View full text Add to dashboard Cite

Dynamic load localization and identification technology is very important in the structural design and optimization of aircraft. This paper proposes a non-global traversal method (NTM) for the fast positioning and recognition of dynamic loads on continuous beams. This method separates the load’s position and amplitude information in the modal space. Then, it constructs an interpolation function about position information, and converts load positioning to solving the zero point of the interpolation function. After determining the position of the dynamic load, the amplitude of the dynamic load is recognized. This method does not need to traverse all the position points globally, thereby greatly improving the efficiency of load positioning. Numerical simulations and experiments show that compared with the original variable separation fast positioning method (VSRPM), this method improves the calculation efficiency by more than 80% while maintaining the same recognition accuracy. NTM is a new method of great application value.

show abstract

Section: Introductionmentioning

confidence: 99%

A Non-Global Traversal Method for Dynamic Load Rapid Localization and Identification

Li,

Zhang,

Jiang

2024

Aerospace

View full text Add to dashboard Cite

show abstract

“…In 2021, XIA Peng et al [22] combined the "memory" characteristics of time-delay neural networks, the theory of causal finite impulse response (FIR) systems, and the solution principle of vibration response, and proposed a time-domain dynamic model using timedelay neural networks load reverse sequence identification method. T. Feng et al [23] proposed a deep learning-based identification method to identify the static load amplitude and position of the bulkhead plate. Wang, L.J.…”

Section: Introductionmentioning

confidence: 99%

Impact Load Identification Algorithm of Helicopter Weapon Pylon Based on Time-Domain Response Signal

Gao

Chen

et al. 2022

Aerospace

View full text Add to dashboard Cite

Accurately identifying the peak value of impact load acting on the helicopter structure during weapon launch is of great significance to the design and finalization of weapon pylons. Firstly, a method of standardized preprocessing load signal is proposed by analyzing the vibration response and the characteristics of the impact load. Then, the test model of the weapon pylon is designed, and the position of the strain gauge is determined; the static load calibration test and the ground impact test are carried out on the test model. Next, the time-domain response measured by the strain gauge is filtered and de-noised. Impact load is processed by a standardized method. The response and load are used to train BP neural network and the mapping relationship between response and load is established. The impact load generated by a specific weapon is statistically processed to obtain the normalized average load time history, and the identified standard load is converted back to the original load pattern. Finally, the network that meets the error requirements is tested. Both the standardized pattern and the original pattern have high identification accuracy, which shows that an effective load identification model can be established based on the time-domain response signal and the standardized processed load signal.

show abstract

Deep recurrent-convolutional neural network learning and physics Kalman filtering comparison in dynamic load identification

Impraimakis

2024

Structural Health Monitoring

View full text Add to dashboard Cite

The dynamic structural load identification capabilities of the gated recurrent unit, long short-term memory, and convolutional neural networks are examined herein. The examination is on realistic small dataset training conditions and on a comparative view to the physics-based residual Kalman filter (RKF). The dynamic load identification suffers from the uncertainty related to obtaining poor predictions when in civil engineering applications only a low number of tests are performed or are available, or when the structural model is unidentifiable. In considering the methods, first, a simulated structure is investigated under a shaker excitation at the top floor. Second, a building in California is investigated under seismic base excitation, which results in loading for all degrees of freedom. Finally, the International Association for Structural Control-American Society of Civil Engineers (IASC-ASCE) structural health monitoring benchmark problem is examined for impact and instant loading conditions. Importantly, the methods are shown to outperform each other on different loading scenarios, while the RKF is shown to outperform the networks in physically parametrized identifiable cases.

show abstract

Deep learning based load and position identification of complex structure

Cited by 4 publications

References 20 publications

A Non-Global Traversal Method for Dynamic Load Rapid Localization and Identification

A Non-Global Traversal Method for Dynamic Load Rapid Localization and Identification

Impact Load Identification Algorithm of Helicopter Weapon Pylon Based on Time-Domain Response Signal

Deep recurrent-convolutional neural network learning and physics Kalman filtering comparison in dynamic load identification

Contact Info

Product

Resources

About