METHOD FOR MONITORING AND/OR PREDECTING MACHINING PROCESSES AND/OR MACHNINING OUTCOMES

Abstract

Method for monitoring and/or predicting machining processes and/or machining outcomes in mechanical workpiece machining carried out by a workpiece processing machine operable by specifiable operating parameters and having at least one machining tool. The monitoring and/or predicting occurs via a computer program product evaluation algorithm executed on a computer on the basis of training data sets. The training data sets include, as training data, adjustment data relating to adjustment of operating parameters of the workpiece processing machine for carrying out a machining process to be monitored and/or predicted. The training data sets further include outcome data of workpieces finished in a machining process to be monitored and/or predicted, and state data of the processing machine, determined by sensor, during a machining process to be monitored and/or predicted. In use, capture of outcome data by prediction made on the basis of machine-learned knowledge is avoided or reduced.

Claims

1. A method for monitoring or predicting machining processes or machining outcomes in mechanical workpiece machining carried out by means of a workpiece processing machine operable by specifiable operating parameters and having at least one machining tool, the monitoring or predicting occurring by means of an evaluation algorithm; wherein the evaluation algorithm is obtained by means of a computer program product executed on a computer on the basis of training data sets; wherein the training data sets comprise the following data as training data: adjustment data relating to the adjustment of operating parameters of the workpiece processing machine for carrying out a machining process to be monitored or predicted; outcome data of workpieces finished in the machining process to be monitored or predicted; and state data of the processing machine, determined by sensor, during the machining process to be monitored or predicted.

2. The method according to claim 1, wherein in a first step, training data sets are generated and, in a second step, the training data sets or the evaluation algorithm obtained on the basis of the training data sets are transmitted to an evaluation device.

3. The method according to claim 1, wherein the training data at least partially comprise adjustment data, outcome data or state data actually obtained from earlier machining processes which were actually carried out.

4. The method according to claim 1, wherein the evaluation algorithm is generated on the basis of the training data sets and with recourse to guided learning, in which expert knowledge about machining processes and the behavior of state data, adjustment data and outcome data and their mutual influence is incorporated into an initial setup of the specifications for the evaluation algorithm.

5. The method according to claim 1, wherein the training data comprise adjustment data, outcome data or state data obtained, at least in part, from simulated machining processes.

6. The method according to claim 1, wherein the evaluation algorithm is generated on the basis of the training data sets and using an approximation method.

7. The method according to claim 1, wherein the evaluation algorithm is generated on the basis of the training data sets and with recourse to monitored learning or reinforcement learning.

8. The method according to claim 1, wherein the adjustment data comprise data on the type or state of the machining tool of the processing machine, data on the adjusted speeds of workpiece or tool spindles of the processing machine, data on an adjusted coolant entry into a machining region or data on feed rates of workpiece or tool holders.

9. The method according to claim 1, wherein the outcome data comprise data on a surface condition of the finished workpiece or on dimensional accuracy of the machining outcomes achieved in relation to an outcome specification.

10. The method according to claim 1, wherein the state data comprise data on the forces and torques acting on the workpiece or tool during the machining process, data relating to a motor current consumption by drive motors of the processing machine, temperature data relating to the workpiece, tool or further components of the processing machine, data determined on a coolant entry into a machining region, data on a volume or shape of the material removed during the machining process or data relating to a state of a tool detected during machining.

11. The method according to claim 1, wherein the adjustment data, outcome data or state data determined for the machining process carried out are used as training data in order to supplement or replace the training data sets in order to adapt the evaluation algorithm.

12. The method according to claim 1, wherein the outcomes obtained with the evaluation algorithm in relation to a prediction of the outcome data obtained are used for monitoring machining outcomes, with regard to quality control.

13. The method according to claim 1, wherein the results obtained with the evaluation algorithm in relation to monitoring the machining process are used to identify an error in the workpiece processing machine, tool wear or tool damage or to identify an error in the machining.

14. The method according to claim 1, wherein the evaluation by means of the evaluation algorithm takes place in situ during the machining process.

15. The method according to claim 14, wherein the results of the evaluation are supplied to a controller of the workpiece processing machine in order to adapt reference variables for the machining process.

16. The method according to claim 1, wherein the evaluation is carried out by means of the evaluation algorithm after the machining process.

17. The method according to claim 1, wherein training data sets obtained or adapted during operation of a plurality of workpiece processing machines are transmitted to a central memory and in that meta-training data records are determined from the individual training data records by linking.

18. The method according to claim 17, wherein the meta-training data sets are supplied to a meta-data evaluation algorithm for a comparative evaluation.

19. Use of predictions obtained by means of a method according to claim 1 about a machining outcome of a first machining process as an input variable for a subsequent machining process to be carried out on a workpiece machined in the first machining process.

20. The method according to claim 6, wherein the approximation method comprises one or more of deep learning, convolutional neural network (CNN), recursive nets (RNN), stochastic machine, random forest or a support vector machine.

Description

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0024] The method according to the invention and the associated procedure are explained in more detail below with reference to the accompanying drawings. In the drawings:

[0025] FIG. 1 is, in the form of a diagram, an illustration of the learning process for obtaining the evaluation algorithm on the basis of training data sets and using artificial intelligence (AI), and

[0026] FIG. 2 is, in the form of a diagram, an illustration of the use of the evaluation algorithm obtained by means of the learning process for predicting machining outcomes.

DESCRIPTION

[0027] The drawings show the procedure according to the method according to the invention and the use of the evaluation algorithm obtained by means of a machine learning process on the basis of the use of artificial intelligence (AI) for predicting machining outcomes in mechanical workpiece machining carried out by means of a workpiece processing machine, in particular material-removing processing, preferably metal cutting, illustrated by examples.

[0028] Firstly, as shown in FIG. 1, machine learning and the creation of an evaluation algorithm are carried out as part of a training phase. This is carried out using a computer program product executed on a computer. The computer program product is given correlated data as training data sets consisting of adjustment data; these are the basic adjustments of the processing machine (also called system variables here) and data relating to the adjustments of the processing machine in the process (also called manipulated variables here), state data; these are data recorded during the process flow and relating to the process flow, such as recorded mechanical loads, such as the forces and moments acting on the tool and/or workpiece, for example, a temperature of the tool and/or workpiece, recorded vibrations or the like, and outcome data; these are, for example, data on the machining outcome on the workpiece, such as data on the dimensional and geometrical accuracy or surface quality, as well as data on a state of the tool after the process, such as wear, cutting edge sharpness and the like. The training data sets comprise such adjustment data, state data and outcome data pertaining to a machining process that has been carried out. These training data sets are evaluated using AI and form the basis of machine learning, which ultimately forms and refines an evaluation algorithm for predicting and/or evaluating machining outcomes. In the process, the system for machine learning is also given further specifications from existing expert knowledge, which takes into account already known relationships between values of individual training data or tendencies in the training data. This is how guided learning takes place.

[0029] The training data and training data sets entered in this learning phase can be obtained from machining processes actually carried out or obtained by means of simulation.

[0030] After completion of the learning phase run through by means of AI, e.g. after training using training data sets for 100 different machining processes, the evaluation algorithm obtained in this way can then be used as knowledge, so-called AI knowledge, in order to make a prediction of the outcome data. This is shown in FIG. 2.