Hybrid Modeling of Non-Linear Mechanical Systems: The Case of a Vehicle Shock Absorber

2011 ◽  
Author(s):  
Antonio Di Dino ◽  
Francesco Biral ◽  
Paolo Bosetti
Keyword(s):  
Neural Network ◽  
Physical Model ◽  
Shock Absorber ◽  
Mechanical Systems ◽  
Hybrid Modeling ◽  
System Control ◽  
Test Case ◽  
The Neural Network ◽  
Non Linear ◽  
Gross Behavior

A large effort in the analysis of a physical system is the development of a model describing its behavior. The non-linear and time variant characteristic of many mechanical systems can be hardly represented by an analytical model without a remarkable increase of its complexity which contrasts with the need to obtain acceptable results in real-time such as in multibody simulations, system control design and Hardware in the loop (HIL) testing. In this context, the use of artificial neural networks are recognized as a powerful modeling tool to produce accurate model with reduced complexity. On the other hand their response to inputs outside the learning range may lead to unrealistic results. This paper presents an hybrid modeling technique, which combines a physical model with a neural network. The physical model describes the gross behavior of the system and the neural network captures the non-linear non-modeled behaviors or the effect of time-varying parameters. It is also proposed a method to limit the outside-range unpredicted responses. A RC car shock absorber is used as test case. Experimental results show that the neural network improves the physical model output capturing nonlinear aspects such as the hysteresis, the fluid leakage and the increase of its temperature.

Photovoltaics Energy Prediction Under Complex Conditions for a Predictive Energy Management System

2015 ◽  
Vol 137 (3) ◽  
Author(s):  
Martin Schmelas ◽  
Thomas Feldmann ◽  
Jesus da Costa Fernandes ◽  
Elmar Bollin
Keyword(s):  
Neural Network ◽  
Physical Model ◽  
Energy Management ◽  
Management System ◽  
Percentage Error ◽  
Positive Energy ◽  
Energy Management System ◽  
Energy Prediction ◽  
The Neural Network ◽  
Accurate Forecast

Solar energy converted and fed to the utility grid by photovoltaic modules has increased significantly over the last few years. This trend is expected to continue. Photovoltaics (PV) energy forecasts are thus becoming more and more important. In this paper, the PV energy forecasts are used for a predictive energy management system (PEMS) in a positive energy building. The publication focuses on the development and comparison of different models for daily PV energy prediction taking into account complex shading, caused for example by trees. Three different forecast methods are compared. These are a physical model with local shading measurements, a multilayer perceptron neural network (MLP), and a combination of the physical model and the neural network. The results show that the combination of the physical model and the neural network provides the most accurate forecast values and can improve adaptability. From April to December, the mean percentage error (MPE) of the MLP with physical information is 11.6%. From December to March, the accuracy of the PV predictions decreases to an MPE of 78.8%. This is caused by poorer irradiation forecasts, but mainly by snow coverage of the PV modules.

A Hybrid Modeling Technique for Partially-Known Systems Using Linear Regression and Neural Network

2009 ◽  
Author(s):  
Andrew J. Joslin ◽  
Chengying Xu
Keyword(s):  
Neural Network ◽  
Linear Regression ◽  
Least Squares ◽  
Process Model ◽  
Modeling Method ◽  
Hybrid Modeling ◽  
Model Description ◽  
Least Squares Regression ◽  
The Neural Network ◽  
Macro Scale

In this paper a hybrid modeling and system identification method, combining linear least squares regression and artificial neural network techniques, is presented to model a type of dynamic systems which have an incomplete analytical model description. This approach in modeling nonlinear, partially-understood systems is particularly useful to the study of manufacturing processes, where the linear regression portion of the hybrid model is established using a known mathematical model for the process and the neural network is constructed using the residuals from the least squares regression, therefore ensuring a more precise process model for the specific machining setup, tooling selection, workpiece properties, etc. In this paper the method is mathematically proven to give regression coefficients close to those which would be found if only a regression had been performed. The modeling method is then simulated for a macro-scale hard turning process, and the result proves the effectiveness of the proposed hybrid modeling method.

scholarly journals Agricultural data prediction by means of neural network

2011 ◽  
Vol 57 (No. 7) ◽  
pp. 356-361 ◽  
Author(s):  
O. Trenz ◽  
J. Šťastný ◽  
V. Konečný
Keyword(s):  
Neural Network ◽  
Linear Regression Models ◽  
Linear Character ◽  
Main Stress ◽  
Data Prediction ◽  
The Neural Network ◽  
Non Linear ◽  
The Individual ◽  
Intelligence Approach ◽  
Artificial Intelligence Approach

The contribution deals with the prediction of crop yield levels, using an artificial intelligence approach, namely a multi-layer neural network model. Subsequently, we are contrasting this approach with several non-linear regression models, the usefulness of which has been tested and published several times in the specialized periodicals. The main stress is placed on judging the accuracy of the individual methods and of the implementation. A neural network simulation device is that which enables the user to set an adequate configuration of the neural network vis á vis the required task. The conclusions can be generalized for other tasks of a similar nature, especially for the tasks of a non-linear character, where the benefits of this method increase.

scholarly journals Testing the Reliability of Interpretable Neural Networks in Geoscience Using the Madden-Julian Oscillation

2020 ◽  
Author(s):  
Benjamin A. Toms ◽  
Karthik Kashinath ◽  
Da Yang ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Test Case ◽  
Madden Julian Oscillation ◽  
State Variables ◽  
Current State ◽  
The Neural Network ◽  
Geophysical Phenomenon ◽  
The Neural Networks ◽  
Atmospheric State

Abstract. We test the reliability of two neural network interpretation techniques, backward optimization and layerwise relevance propagation, within geoscientific applications by applying them to a commonly studied geophysical phenomenon, the Madden-Julian Oscillation. The Madden-Julian Oscillation is a multi-scale pattern within the tropical atmosphere that has been extensively studied over the past decades, which makes it an ideal test case to ensure the interpretability methods can recover the current state of knowledge regarding its spatial structure. The neural networks can, indeed, reproduce the current state of knowledge and can also provide new insights into the seasonality of the Madden-Julian Oscillation and its relationships with atmospheric state variables. The neural network identifies the phase of the Madden-Julian Oscillation twice as accurately as linear regression, which means that nonlinearities used by the neural network are important to the structure of the Madden-Julian Oscillation. Interpretations of the neural network show that it accurately captures the spatial structures of the Madden-Julian Oscillation, suggest that the nonlinearities of the Madden-Julian Oscillation are manifested through the uniqueness of each event, and offer physically meaningful insights into its relationship with atmospheric state variables. We also use the interpretations to identify the seasonality of the MJO, and find that the conventionally defined extended seasons should be shifted later by one month. More generally, this study suggests that neural networks can be reliably interpreted for geoscientific applications and may thereby serve as a dependable method for testing geoscientific hypotheses.

Modelling of a Novel Gas Strut Using Neural Networks

2004 ◽  
Author(s):  
B. Gao ◽  
J. Darling ◽  
D. G. Tilley ◽  
R. A. Williams ◽  
A. Bean ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Mathematical Model ◽  
Least Square ◽  
Operation Conditions ◽  
The Neural Network ◽  
Wide Range ◽  
Non Linear ◽  
Vehicle Suspension System ◽  
And Control

The strut is one of the most important components in a vehicle suspension system. Since it is highly non-linear it is difficult to predict its performance characteristics using a physical mathematical model. However, neural networks have been successfully used as universal ‘black-box’ models in the identification and control of non-linear systems. This approach has been used to model a novel gas strut and the neural network was trained with experimental data obtained in the laboratory from simulated road profiles. The results obtained from the neural network demonstrated good agreement with the experimental results over a wide range of operation conditions. In contrast a linearised mathematical model using least square estimates of system parameters was shown to perform badly due to the highly non-linear nature of the system. A quarter car mathematical model was developed to predict strut behavior. It was shown that the two models produced different predictions of ride performance and it was argued that the neural network was preferable as it included the effects of non-linearities. Although the neural network model does not provide a good understanding of the physical behavior of the strut it is a useful tool for assessing vehicle ride and NVH performance due to its good computational efficiency and accuracy.

Estimation of Crop LAI Based on the Neural Network Trained from Physical Model

2010 ◽  
Vol 12 (3) ◽  
pp. 426-435 ◽  
Author(s):  
Yang LIU ◽  
Ronggao LIU ◽  
Siliang LIU ◽  
Jiyuan LIU ◽  
Zhongxin CHEN ◽  
...  
Keyword(s):  
Neural Network ◽  
Physical Model ◽  
The Neural Network

Modelling methane-air turbulent diffusion flame in a gas turbine combustor with artifical neural network

2009 ◽  
Vol 113 (1146) ◽  
pp. 541-547
Author(s):  
N. S. Mehdizadeh ◽  
P. Sinaei
Keyword(s):  
Neural Network ◽  
Gas Turbine ◽  
Network Architecture ◽  
Turbulent Flame ◽  
Ann Model ◽  
Turbulent Diffusion Flame ◽  
Air Jet ◽  
The Neural Network ◽  
Non Linear ◽  
Non Linear System

Abstract The present paper reports a way of using an artificial neural network (ANN) for modelling methane-air jet diffusion turbulent flame characteristics, such as temperature and chemical species mass fractions in a gas turbine combustion chamber. Since the neural network needs sets of examples to adapt its synaptic weights in the training phase, we used pre-assumed probability density function (PDF) method and considered chemical equilibrium chemistry model to compute the flame characteristics for generating the examples of input-output data sets. In this approach, flow and mixing field results are presented with a non-linear first order k-ε model. The turbulence model is applied in combination with preassumed β-PDF modelling for turbulence-chemistry interaction. The training algorithm for the neural network is based on a back-propagation supervised learning procedure, and the feed-forward multilayer network is incorporated as neural network architecture. The ability of ANN model to represent a highly non-linear system, such as a turbulent non-premixed flame is illustrated, and it can be summarized that the results of modelling of the combustion characteristics using ANN model are satisfactory, and the CPU-time and memory savings encouraging.

Sign in / Sign up

Export Citation Format

Share Document