Data processing: structural design – modeling – simulation – and em – Modeling by mathematical expression
Reexamination Certificate
2000-07-31
2004-06-01
Jones, Hugh (Department: 2123)
Data processing: structural design, modeling, simulation, and em
Modeling by mathematical expression
C703S006000, C703S009000, C239S003000, C700S048000, C706S023000
Reexamination Certificate
active
06745158
ABSTRACT:
BACKGROUND OF THE INVENTION
Field of the Invention
The invention relates to a method for determining a layer thickness distribution to be expected in a paint layer to be produced during paint spraying after inputting specific spraying parameters into an electrostatically based paint spraying device.
A known mode of procedure for an a-priori calculation of the painting result of electrostatically based painting units is based on empirical investigations with the aid of which it is possible to determine poorly founded estimated values and only very simplified mathematical descriptions for the painting result. The extreme simplifications required for this purpose, a few influences on the painting result, such as ambient temperature or the type and shape of the painting booth, also remaining unconsidered, lead to an unsatisfactory accuracy of the calculation.
Another known proposal envisages a complex physical modeling with the aid of which the very complex physical process of painting is to be simulated in accurate detail, and which is to be used to determine the painting result.
However, the complexity of the modeling is disadvantageous. Thus, a satisfactorily accurate simulation of the physical processes during the painting process and, in particular, of their effects on one another is scarcely possible, since stochastically proceeding processes (atomization, etc.) are involved. Moreover, the outlay on modeling and the true computing time of the model are also unacceptably high (days or weeks) even on computer installations currently available.
SUMMARY OF THE INVENTION
It is accordingly an object of the invention to provide a method and a device for determining the layer thickness distribution in a paint layer that overcomes the disadvantages of the prior art methods and devices of this general type, which leads to satisfactorily accurate results in conjunction with a relatively low outlay.
With the foregoing and other objects in view there is provided, in accordance with the invention, a method for determining a layer thickness distribution to be expected in a paint layer produced during paint spraying after inputting specific spraying parameters into an electrostatically based paint spraying device. The method includes providing a data processing device for setting up and using a phenomenological mathematical model of a quasi-stationary three-dimensional spray pattern. An angle of rotation of electrodes of the spraying device and a rate of movement of the spraying device are input directly into the phenomenological mathematical model as fixed input parameters. Real physical input parameters including, a paint volume, directing air data, and a voltage value, whose influence on a spraying result is not accurately known, are fed to an artificial neural network which has previously been trained using real input data including a configuration of the spraying device used, a paint type, operating parameters, and measured values of a test layer thickness distribution. The artificial neural network carries out a conversion of the real physical input parameters into model input parameters. The model input parameters are fed to the phenomenological mathematical model. The spray patterns formed by the phenomenological mathematical model are integrated in a function unit in dependence on movement data of the spraying device which are contained in input parameters to form an overall paint layer. The layer thickness distribution of the overall paint layer is then provided at an output.
In the method according to the invention, it is not the overall physical process of painting, but the painting result, without taking account of the physical processes, which is simulated with the aid of the phenomenological model. The model parameters taken into account in this case, correspond only partially to actual parameters of the painting process. The relationship between the model parameters and the real spraying parameters is produced with the aid of the artificial neural networks that are trained with the aid of real measurements.
The advantage of the method is based on the fact that complex physical modeling of the overall process is avoided. Nevertheless, results attained are realistic and, because of the use of real measured values of a training process of the artificial neural networks, take account of all relationships, that is to say also previously unknown ones.
In accordance with an added feature of the invention, there is the step of training a separate neural network for each desired model parameter. The separate neural network has only a single output and a number of input neurons which correspond to a portion of a totality of available input variables.
In accordance with an additional feature of the invention, there is the step of eliminating a parameter that is acknowledged as irrelevant when a learning process of two neural networks which differ formally only by an input parameter lead to equivalent learning results in conjunction with an otherwise identical learning data record.
In accordance with a concomitant feature of the invention, a data processing configuration is provided for determining a layer thickness distribution to be expected in a paint layer produced during paint spraying after inputting specific spraying parameters into an electrostatically based paint spraying device. The data processing configuration contains a data processing device having means for producing a phenomenological mathematical model, an artificial neural network connected to the means for producing the phenomenological mathematical model, and a functional unit connected to the means for producing the phenomenological mathematical model. The data processing device is programmed to:
set up and use the phenomenological mathematical model of a quasi-stationary three-dimensional spray pattern;
input an angle of rotation of electrodes of the spraying device and a rate of movement of the spraying device directly into the phenomenological mathematical model as fixed input parameters;
feed in real physical input parameters including, a paint volume, directing air data, and a voltage value, whose influence on a spraying result is not accurately known, to the artificial neural network which has previously been trained using real input data including a configuration of the spraying device used, a paint type, operating parameters, and measured values of a test layer thickness distribution, and the artificial neural network carries out a conversion of the real physical input parameters into model input parameters;
feed the model input parameters to the phenomenological mathematical model;
integrate spray patterns formed by the phenomenological mathematical model in the functional unit in dependence on movement data of the spraying device which are contained in input parameters to form an overall paint layer; and
output the layer thickness distribution of the overall paint layer.
Other features which are considered as characteristic for the invention are set forth in the appended claims.
Although the invention is illustrated and described herein as embodied in a method and a device for determining the layer thickness distribution in a paint layer, it is nevertheless not intended to be limited to the details shown, since various modifications and structural changes may be made therein without departing from the spirit of the invention and within the scope and range of equivalents of the claims.
REFERENCES:
patent: 5456548 (1995-10-01), Smyrk et al.
patent: 5649063 (1997-07-01), Bose
patent: 5689415 (1997-11-01), Calotychos et al.
patent: 6507803 (2003-01-01), Eickmeyer et al.
Börner Gunter
Eickmeyer Dietmar
ABB Research LTD
Jones Hugh
LandOfFree
Method and device for determining the layer thickness... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and device for determining the layer thickness..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and device for determining the layer thickness... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3366027