Output device, control device, and method for outputting evaluation functions and machine learning results
A technology of machine learning and evaluation function, which is applied in machine learning, neural learning methods, adaptive control, etc., and can solve problems such as the inability to know the learning effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 approach
[0073] figure 1 It is a block diagram showing a configuration example of the control device according to the first embodiment of the present invention. figure 1 The shown control device 10 has a machine learning device 100 , an output device 200 , a servo control device 300 , and a servo motor 400 . The control device 10 drives machine tools, robots, industrial machines, and the like. The control device 10 may be provided separately from the machine tool, robot, or industrial machine, or may be included in the machine tool, robot, or industrial machine.
[0074] The servo control device 300 outputs a torque command based on control commands such as a position command and a speed command, and controls the rotation of the servo motor 400 . The servo control device 300 has, for example, structural elements such as a velocity feedforward processing unit represented by a transfer function including coefficients machine-learned by the machine learning device 100 . The components ...
specific example 1
[0133] (Concrete example 1: an example of a plurality of evaluation functions having different values of a plurality of weighting coefficients)
[0134] image 3 It is a diagram showing an example of a display screen displaying a plurality of evaluation functions set by weighting coefficients and a graph obtained by superimposing time responses of positional deviations based on parameters learned using these evaluation functions.
[0135] In this specific example, the operation when the output device 200 outputs an evaluation function (hereinafter referred to as "evaluation function of weights W1 to W3") and a graph will be described. Coefficients α, β, and γ set weight values W1 to W3, and in this graph, the three positional deviation times obtained by driving the servo control device 300 based on the parameters learned using the evaluation functions of these weights W1 to W3 respectively Responses are superimposed. In addition, the number of evaluation functions is not...
specific example 2
[0174] (Concrete example 2: Example of multiple evaluation functions with different weight sum types)
[0175]In the specific example 1, an example in which an evaluation function is selected from a plurality of evaluation functions set by a plurality of weighting coefficients or a weighting coefficient is corrected is described. The specific example 2 is for explaining an example of selecting an evaluation function from two evaluation functions having different weight sum types.
[0176] In concrete example 2, use Figure 4 The operation when the output device 200 displays the following screens side by side: a screen showing the evaluation function of Mathematical Formula 2 and a graph illustrating the time response of positional deviation obtained from parameters learned using the evaluation function, and a screen showing Mathematical Formula 3 will be described. An evaluation function and a screen illustrating a time-response graph of a positional deviation acquired from p...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More