Deep Learning of (Periodic) Minimal Coordinates for Multibody Simulations

2020 ◽  
Author(s):  
Andrea Angeli ◽  
Frank Naets ◽  
Wim Desmet
Keyword(s):  
Neural Network ◽  
Differential Algebraic Equations ◽  
Algebraic Equations ◽  
Multibody Model ◽  
Network Training ◽  
The Neural Network ◽  
Continuous Description ◽  
Minimal Coordinates ◽  
Reduced Space ◽  
Multi Body

Abstract Mechanical systems are typically described through multi-body models with redundant coordinates, related by imposed constraints, where the dynamics is expressed with Differential Algebraic Equations. Alternatively, for rigid models, it may be preferable to employ minimal coordinates that do not require additional constraints, thus leading to Ordinary Differential Equations. However, to reduce a general multibody model to minimal coordinates and perform the simulation in the reduced space, the mapping between the minimal coordinates and the full coordinates is required. In this work, it is proposed to approximate such mapping using a neural network. In order to avoid overfitting and guarantee a continuous description of the solution manifold, the multibody dynamics information are included in the neural network training. The particular case where periodic minimal coordinates are required is treated and validated. In general, the methodology can be used when the mapping is unknown such as for spatial mechanisms with closed loops.

Self-validating deep learning of continental hydrology through satellite gravimetry and altimetry

2021 ◽  
Author(s):  
Christopher Irrgang ◽  
Jan Saynisch-Wagner ◽  
Robert Dill ◽  
Eva Boergens ◽  
Maik Thomas
Keyword(s):  
Neural Network ◽  
Satellite Altimetry ◽  
Water Cycle ◽  
Global Water Cycle ◽  
Network Training ◽  
The Neural Network ◽  
Continental Hydrology ◽  
Terrestrial Water ◽  
Combine Machine ◽  
Groundwater Basins

<p>Space-borne observations of terrestrial water storage (TWS) are an essential ingredient for understanding the Earth's global water cycle, its susceptibility to climate change, and for risk assessments of ecosystems, agriculture, and water management. However, the complex distribution of water masses in rivers, lakes, or groundwater basins remains elusive in coarse-resolution gravimetry observations. We combine machine learning, numerical modeling, and satellite altimetry to build and train a downscaling neural network that recovers simulated TWS from synthetic space-borne gravity observations. The neural network is designed to adapt and validate its training progress by considering independent satellite altimetry records. We show that the neural network can accurately derive TWS anomalies in 2019 after being trained over the years 2003 to 2018. Specifically for validated regions in the Amazonas, we highlight that the neural network can outperform the numerical hydrology model used in the network training.</p><p>https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2020GL089258</p>

Research on the Optimized Algorithms on Neural Network

2012 ◽  
Vol 605-607 ◽  
pp. 2175-2178
Author(s):  
Xiao Qin Wu
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Simulated Annealing Algorithm ◽  
Fitness Function ◽  
Strong Stability ◽  
Training Algorithm ◽  
Network Training ◽  
The Neural Network ◽  
Annealing Algorithm ◽  
Proper Operation

In order to overcome the disadvantage of neural networks that their structure and parameters were decided stochastically or by one’s experience, an improved BP neural network training algorithm based on genetic algorithm was proposed.In this paper,genetic algorithms and simulated annealing algorithm that optimizes neural network is proposed which is used to scale the fitness function and select the proper operation according to the expected value in the course of optimization,and the weights and thresholds of the neural network is optimized. This method is applied to the stock prediction system.The experimental results show that the proposed approach have high accuracy,strong stability and improved confidence.

scholarly journals Modeling a Thermochemical Reactor of a Solar Refrigerator by BaCl2-NH3 Sorption Using Artificial Neural Networks and Mathematical Symmetry Groups

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Onesimo Meza-Cruz ◽  
Isaac Pilatowsky ◽  
Agustín Pérez-Ramírez ◽  
Carlos Rivera-Blanco ◽  
Youness El Hamzaoui ◽  
...  
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Neural Networks ◽  
Heating Temperature ◽  
Barium Chloride ◽  
Symmetry Groups ◽  
Solar Cooling ◽  
Network Training ◽  
The Neural Network ◽  
Marquardt Algorithm

The aim of this work is to present a model for heat transfer, desorbed refrigerant, and pressure of an intermittent solar cooling system’s thermochemical reactor based on backpropagation neural networks and mathematical symmetry groups. In order to achieve this, a reactor was designed and built based on the reaction of BaCl2-NH3. Experimental data from this reactor were collected, where barium chloride was used as a solid absorbent and ammonia as a refrigerant. The neural network was trained using the Levenberg–Marquardt algorithm. The correlation coefficient between experimental data and data simulated by the neural network was r = 0.9957. In the neural network’s sensitivity analysis, it was found that the inputs, reactor’s heating temperature and sorption time, influence neural network’s learning by 35% and 20%, respectively. It was also found that, by applying permutations to experimental data and using multibase mathematical symmetry groups, the neural network training algorithm converges faster.

scholarly journals An Application of Neural Network Technique to Correct the Dome Temperature Effects on Pyrgeometer Measurements

2006 ◽  
Vol 23 (1) ◽  
pp. 80-89 ◽  
Author(s):  
Amauri P. Oliveira ◽  
Jacyra Soares ◽  
Marija Z. Božnar ◽  
Primož Mlakar ◽  
João F. Escobedo
Keyword(s):  
Neural Network ◽  
Temperature Effects ◽  
Longwave Radiation ◽  
Global Solar Radiation ◽  
Time Of Day ◽  
Network Training ◽  
The Neural Network ◽  
Neural Network Algorithm ◽  
Using Data ◽  
The City

Abstract This work describes an application of a multilayer perceptron neural network technique to correct dome emission effects on longwave atmospheric radiation measurements carried out using an Eppley Precision Infrared Radiometer (PIR) pyrgeometer. It is shown that approximately 7-month-long measurements of dome and case temperatures and meteorological variables available in regular surface stations (global solar radiation, air temperature, and air relative humidity) are enough to train the neural network algorithm and correct the observed longwave radiation for dome temperature effects in surface stations with climates similar to that of the city of São Paulo, Brazil. The network was trained using data from 15 October 2003 to 7 January 2004 and verified using data, not present during the network-training period, from 8 January to 30 April 2004. The longwave radiation values generated by the neural network technique were very similar to the values obtained by Fairall et al., assumed here as the reference approach to correct dome emission effects in PIR pyrgeometers. Compared to the empirical approach the neural network technique is less limited to sensor type and time of day (allows nighttime corrections).

On the Use of the HHT Method in the Context of Index 3 Differential Algebraic Equations of Multibody Dynamics

2005 ◽  
Author(s):  
Dan Negrut ◽  
Rajiv Rampalli ◽  
Gisli Ottarsson ◽  
Anthony Sajdak
Keyword(s):  
Differential Algebraic Equations ◽  
Algebraic Equations ◽  
Body System ◽  
Vehicle Model ◽  
Good Efficiency ◽  
Numerical Integrator ◽  
Starting Point ◽  
Implementation Aspects ◽  
Multi Body ◽  
Simulation Package

The paper presents theoretical and implementation aspects related to a new numerical integrator available in the 2005 version of the MSC.ADAMS/Solver C++. The starting point for the new integrator is the Hilber-Hughes-Taylor method (HHT, also known as α-method) that has been widely used in the finite element community for more than two decades. The method implemented is tailored to answer the challenges posed by the numerical solution of index 3 Differential Algebraic Equations that govern the time evolution of a multi-body system. The proposed integrator was tested with more than 1,600 models prior to its release in the 2005 version of the simulation package MSC.ADAMS. In this paper an all-terrain-vehicle model with flexible chassis is used to prove the good efficiency and accuracy of the method.

Ride Dynamics of a Flexible Multibody Model of an Urban Bus

2007 ◽  
Author(s):  
G. Georgiou ◽  
A. Badarlis ◽  
S. Natsiavas
Keyword(s):  
Degrees Of Freedom ◽  
Ride Comfort ◽  
Equations Of Motion ◽  
Differential Algebraic Equations ◽  
Accurate Information ◽  
Algebraic Equations ◽  
Multibody Model ◽  
Road Excitation ◽  
Urban Bus ◽  
Stiffness And Damping

Dynamic response of a large order mechanical model of an urban bus is investigated. The emphasis is first put on developing a quite complete model, which can be utilized in order to extract sufficiently reliable and accurate information related to its dynamics in a fast way. Since some of the components of the bus undergo large rigid body rotation, in addition to motion resulting from their deformability, a multibody dynamics framework is adopted. This implies that the resulting equations of motion appear in the form of a strongly nonlinear set of differential-algebraic equations, which are difficult to handle even numerically. In fact, the modeling becomes more involved because all the significant nonlinearities appearing in the interconnections of the structural components and especially in the front and rear suspension subsystems of the bus are taken into account. In order to alleviate some of these complexities, the number of degrees of freedom of each component, associated with its deformability, is reduced drastically by applying an appropriate coordinate condensation methodology. Finally, this model is employed and numerical results are obtained for motions resulting from typical road excitation. In particular, selected response quantities related to ride comfort are examined for characteristic combinations of the bus suspension stiffness and damping parameters.

Sign in / Sign up

Export Citation Format

Share Document