Control device and machine learning device

Abstract

The present invention provides a control device and a machine learning device, wherein the machine learning device provided in the control device can determine parameters of the PID control, and the parameters of the PID control can extend the life of the tool without increasing the cycle time to a required degree or more. The machine learning includes a state observation unit that observes, as state variables representing a current state of an environment, PID control parameter data indicating the a parameter of the PID control during machining, machining condition data indicating a machiningcondition of the machining, and machining environment data relating to a machining environment of the machining, a determination data acquisition unit that acquires, as determination data, tool lifedetermination data indicating an appropriateness determination result relating to depletion of the life of a tool during the machining, and cycle time determination data indicating an appropriatenessdetermination result relating to the cycle time of the machining, and a learning unit that learns the machining condition and the machining environment of the machining, and the parameter of the PID control in association with each other.

Description

technical field [0001] The invention relates to a control device and a machine learning device. Background technique [0002] As a prior art for machining related to machine tools, there is a technology of intelligent adaptive control in which feedrate override is controlled by PID control in which the spindle load is set as an input value (for example, JP-A-09-500331 ). By using this technique, such as Figure 8 As shown, in the part where the load is low, the overrun is increased and the cycle time is shortened, and in the part where the load is high, the overrun is reduced to prevent tool damage and overheating. The output of the PID control can generally be calculated by Equation 1. In addition, in Equation 1, the time when PID control starts is t 0 . [0003] [Formula 1] [0004] [0005] O(t): output value [0006] e L (t): The difference between the target of the control object and the current (time t) value [0007] K p : The gain of the proportional term...

AI Technical Summary

Problems solved by technology

However, it is impossible to understand the impact of parameter changes on the tool life unless the tool is actually used until the life of the tool

On the other hand, in order to optimize the parameters of the PID control, it is necessary to repeat the work of setting the parameters based on experience by a skilled operator, and try to actually perform machining using the set parameters, and observe the results. Further adjustment of the parameters becomes a burden on the operator.

In addition, the combination of these two problems will cause a problem that it takes a corresponding amount of time until the relationship between the parameters of the PID control and the tool life can be grasped.

Images