Monitoring a multi-axis machine by means of interpretable time series classification
Patent Information
- Application Number
- EP2023726104
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2022-05-31
- Filing Date
- 2023-05-11
- Publication Date
- 2025-04-09
AI Technical Summary
Multi-axis machines face challenges in error detection and prevention due to the lack of effective monitoring and evaluation methods, leading to potential deviations from desired trajectories and equipment wear, which are not efficiently identified or addressed.
A method utilizing interpretable time series classification with machine learning algorithms, specifically convolutional neural networks, to acquire and analyze data time series from multi-axis machines, determining classification values and issuing warnings or all-clears based on learned warning and all-clear ranges, while providing transparent contributions of channels and time intervals to classification results.
This approach enhances the accuracy and speed of error detection and prevention, allowing for timely identification and remediation of issues, improving the robustness and reliability of multi-axis machine operations by providing interpretable results and reducing the reliance on 'black box' algorithms.
Smart Images
Figure 1.1
Abstract
Description
[0001] Description
[0002] Monitoring a multi-axis machine using interpretable time series classification
[0003] The present invention relates to a method for evaluating and / or monitoring a process and / or a multi-axis machine, a system for operating and / or monitoring a multi-axis machine and a computer program or computer program product.
[0004] The object of the present invention is to improve a process, in particular a process of a multi-axis machine, and further in particular to reduce and / or avoid errors in the process, in particular error states in the multi-axis machine.
[0005] This object is achieved by a method having the features of claim 1. Claims 10 and 11 protect a system for operating and / or monitoring a multi-axis machine, or a computer program or computer program product, respectively, in particular for implementing a method described herein. The subclaims relate to advantageous developments.
[0006] According to one embodiment of the present invention, a method for evaluating and / or monitoring a processor and / or for monitoring a multi-axis machine comprises acquiring at least one data time series. In one embodiment, the at least one data time series comprises at least one channel, wherein the channel describes at least one parameter of the process and / or the multi-axis machine, in particular over a (predetermined) time interval. In one embodiment, the data time series is caused by the process. In one embodiment, the method comprises determining an interpretable result by means of a machine learning algorithm based on the at least one data time series. In one embodiment, the result describes a classification value of a state in the process and / or a state of the multi-axis machine.In one embodiment, determining the interpretable result further comprises issuing a warning if the classification value of the state in the process and / or the state of the multi-axis machine is or is assigned to a value of an error class that lies in a, in particular predetermined and / or learned, warning range or corresponds to a warning range and / or issuing an all-clear signal if the classification value of the state in the process and / or the state of the multi-axis machine is or is assigned to a value that lies in a, in particular predetermined and / or learned, all-clear range or corresponds to an all-clear range.
[0007] A "channel" is preferably understood herein as a data channel, and a data time series is preferably understood as data from at least one data channel recorded over time. In one embodiment, a channel provides data of the process and / or the multi-axis machine, in particular position data, acceleration data, current data, temperature data, and / or status messages. In one embodiment, the data can be recorded in a file, diagram, or the like, for example, in a KRC Diag, a similar data set or diagram, or the like.
[0008] An "interpretable result" is preferably understood herein as a result that is readable and understandable by a user, in particular as a result that allows the user to draw direct conclusions about the (existing) channels, further in particular about a point in time and / or a period within the at least one channel and / or across all existing channels. A "result" is preferably understood herein as a classification of the at least one data time series, in particular all existing data time series, in particular individually and / or as a whole.
[0009] A "warning range" is preferably understood herein as a predetermined range, in particular a value range, which is in particular adaptable or can be adapted, in particular dynamically, in particular by the machine learning algorithm. An "all-clear range" is preferably understood herein as a predetermined range, in particular a value range, which is in particular tangible or can be adapted, in particular dynamically, in particular by the machine learning algorithm. If a value of a state of the process and / or the state of the multi-axis machine in one embodiment falls within a warning range or an all-clear range, a message, in particular a warning or an all-clear signal, is issued accordingly.In one embodiment, a classification in an error class may assume discrete values, in particular multi-level or otherwise discretized, in particular into binary values such as “okay (IO)” or “not okay (NIO)”, alternatively continuous values, or the like.
[0010] A "state of a multi-axis machine" is preferably to be understood herein as a predetermined parameter, in particular as a predetermined parameter that is of interest when operating a multi-axis machine, in particular with regard to possible sources of error, or as a state that is classified by the machine learning algorithm on the basis of training (data) as, in particular probably, critical for operating and / or continuing to operate the multi-axis machine and / or continuing the process and / or achieving goals with the process, in particular quality goals.
[0011] In one embodiment, the result of issuing a warning can indicate an error in the process and / or an error in the robot, or can detect a corresponding error, or can be detected with the result. In one embodiment, an error in the process can be, in particular, a deviation from the desired trajectory, the desired process result, a faulty assembly operation, or the like. In one embodiment, an error in the multi-axis machine, in particular a robot, can be wear on at least one gear, a bearing, a joint, or the like, in particular wear on at least one part of the multi-axis machine or, in particular, the robot.
[0012] Advantageously, in one embodiment, a user can understand the contribution of individual existing channels and points in time, in particular time intervals, to the result or classification. In one embodiment, the result can, in particular, increase the transparency of the algorithms used and, furthermore, establish or increase the trust of users. In one embodiment, the result can reveal potential for improvement, in particular for the process and / or the multi-axis machine. In one embodiment, the method can, in particular, create an opportunity to review and / or improve black-box algorithms (beyond their classification statistics).
[0013] In one embodiment, the invention is based on the approach that machine learning algorithms, in particular neural networks, when the last activation is omitted, can be represented for constant inputs x as a weighted sum (with weights w) of these inputs - SummeJ (w_i x_i) + B = y -, where y is the output before the last activation function (in particular sigmoid and / or softmax) with respect to a class and B is a constant bias term. "y" can (therefore) be interpreted in one embodiment as a classification value. In particular, with high values of y compared to other error classes, a high probability of this error class can be inferred or determined based on the classification value. SummeJ (wj x ) + B describes in one embodiment mathematically exactly what contribution the input makes to the classification value.
[0014] Furthermore, in one embodiment, the invention is based on the approach that it can be shown that the weights wj each represent the derivatives dy / dxj. In particular, inputs are multiplied by associated gradients in order to determine contributions of these inputs, in particular channels and times. Advantageously, in one embodiment, the exact mathematical relationship between the contributions and the classification value can be determined: (SumJ (dy / dxj * xj) + B = y), which in particular increases interpretability. In one embodiment, the averaging of the gradients can advantageously be omitted and, in particular, negative contributions can be taken into account, in particular in comparison with Gradient-weighted Class Activation Mapping (Grad-CAM), which is used for the classification of images and is only applicable to a limited extent or not at all to data time series, in particular from processes and / or multi-axis machines.Grad-CAM is not suitable for the method described here, particularly because Grad-CAM calculates an activation score for each time interval and channel, which measures the contribution to the classification and, in particular, assigns a higher activation score to a higher contribution of that channel to the classification. Therefore, Grad-CAM would require a previously defined threshold for automated testing of an activation score, which does not exist, or at least is not guaranteed to exist, particularly in processes, especially those involving multi-axis machines, and furthermore, in robotic processes. Therefore, Grad-CAM cannot provide a reliable basis for identifying important channels, as the scores can only be understood in relation to the other channels and to the data time series of the entire dataset.
[0015] With regard to the uncertainty factor B, which can be different for each input and thus can make a comparison of the contributions more difficult, the invention is further based in one embodiment on providing a machine learning algorithm, in particular a convolutional neural network, with K layers, which evaluates the data time series channels separately in the first k (with 1 < k < K) layers, in particular of the neural network, and then combines these results in layers k+1 to K and evaluates them together. In other words, in one embodiment, the inputs xk in layer k can still be assigned to the individual channels and time intervals.
[0016] Given that no bias terms need to be used in layers k+1 to K (convolutions without bias terms and no batch normalization) to achieve a classification accuracy, in particular a required or predetermined one, a representation SumJ (xk_i wk_i) = y without a bias term can be used (in one embodiment) for the second part of the neural network. The summands bk_i = xk_i wk_i describe (in one embodiment) the contribution of individual channels to the classification value at different time intervals; in particular, there is no influence on the classification value outside of these summands. This results (in one embodiment) in the contributions still being different for each data time series, but the variance is advantageously reduced by eliminating the bias term. The weights wkj are (in one embodiment) given by the gradients dy / dxk_i.
[0017] In other words, in one embodiment, the invention is based on the calculation of the contribution of a channel per data time series and a comparison of the contributions of the channels, in particular across the data set, and in particular with the aid of probability distributions, wherein similar patterns may occur in particular in different channels, which should be interpreted differently or are evaluated differently using the method described herein.
[0018] In one embodiment, determining an interpretable result further comprises determining a probability with which the state of the process and / or the state of the multi-axis machine corresponds to a value of an error class that lies in a warning range or corresponds to a warning range, in particular for the at least one channel and / or for a time interval of the process.
[0019] Advantageously, in one embodiment per data time series and / or across the entire data set, interpretable, in particular quantitative, statements on the contribution of the at least one channel, in particular on the contribution of the existing channels, can be achieved, in particular by means of the method.
[0020] After one execution, probability distributions of the contributions of each error class, particularly the existing one, are calculated, particularly across a training dataset. The contributions bk_i are collected in one execution in layer k of the network and can be assigned to individual channels and / or time intervals there.
[0021] The invention is further based in one embodiment on the approach that all contributions are included as summands in the classification value, therefore one can or are in one embodiment subsets of contributions combined as desired by forming the sum over the subset, in particular over the entire contribution of a channel (sum over all time intervals of this channel), over the entire contribution of a time interval (sum over all channels in this time interval), the contribution of all channels that monitor a Cartesian coordinate, in particular of the multi-axis machine, and / or combinations of (pre)determined time intervals and / or channels.
[0022] Subsets can preferably be understood here as the sum of the contributions of a channel over time. Based on the label for a data time series, the contributions of a subset are then classified into error classes, such as IO and NIO, in one embodiment. For each error class, probability distributions are then calculated or determined in one embodiment, in particular by evaluating the subset across all n time series, in particular from the training data set, with a result that describes a total of n values distributed across different error classes. In one embodiment, the values of a class are then each converted into a probability distribution.
[0023] In one embodiment, determining an interpretable result comprises determining an average distance of different error classes with respect to a classification value.
[0024] In one embodiment, this advantageously allows a generally valid statement to be made about the process, in particular about the entirety of the data time series, in particular in the form of: "The average distance of channel X corresponds to one-third of the average distance between OK and NIO samples in the classification value" or the like. Furthermore, in a further development, a statement can advantageously be mathematically correctly aggregated for any time intervals and channels and in particular a statement can be determined in the form of: "In channel X and Y, an error probability of 95% results for this time series in seconds 5 to 10", "The distances of the aggregated channels X, Y, and Z correspond to 98% of the average distance between OK and NIO samples in the classification value" or the like.
[0025] In one embodiment, the method comprises determining a probability distribution for each error class, in particular for each existing error class, for a contribution of the at least one channel to the classification value. In one embodiment, a kernel density estimation (Gaussian kernel density estimation) and / or histograms can be used for the probability distribution. In one embodiment, other representations of probability distributions can be used to replace the kernel density estimation and / or histograms.
[0026] In one embodiment, the method further comprises normalizing the probability distribution of the values of the error class and determining a probability with which a classification value is assigned to a warning area or an all-clear area, in particular is assigned based on the probability distribution.
[0027] In one embodiment, this can advantageously be used, in particular by means of a normalization of the probability distribution, to assign a probability of belonging to a specific, in particular existing, error class to a, in particular given, contribution of the at least one channel.
[0028] In one embodiment, this advantageously makes it possible to make a statement such as, in particular, "A contribution of zero in a channel has a probability of 2% in the OK distribution and a probability of 10% in the NIO distribution, and when normalized, an NIO sample is assumed for the channel with 83%" (here, for example, for the case of an OK / NIO classification) or the like. Advantageously, in one embodiment, the probability distributions, in particular probabilities, can be used to determine an interpretable statement regarding contributions from different channels to a classification value or a classification into a warning range or an all-clear range; in particular, a confidence level can be determined with which an algorithm assumes an assignment to an error class.
[0029] According to one embodiment, the method further comprises determining a Wasserstein distance for different error classes. Alternatively or additionally, in one embodiment, an average distance between the (different error classes) or a corresponding distance can be determined using an intersection-over-unit metric, or if a corresponding distance is determined, particularly if the probability distributions are disjoint, in one embodiment the classification can be performed based on these distributions with at least essentially 100% accuracy.
[0030] Advantageously, in one embodiment, this makes it possible to determine how far apart contributions of an error class, in particular between IO and NIO or warning range and all-clear range, are, in particular on average. In one embodiment, this makes it possible to determine the importance of subsets of contributions. In other words, in one embodiment, the determined distance can advantageously be used as a measure of the importance of a subset of contributions to a classification value. According to one embodiment, the machine learning algorithm comprises, in particular is, a convolutional neural network or is configured as a convolutional neural network. Advantageously, in one embodiment, this makes it possible for the algorithm to operate more efficiently or to evaluate and / or monitor a process described herein more efficiently.
[0031] According to one embodiment, the machine learning algorithm, in particular if the machine learning algorithm comprises a convolutional neural network, in particular, has as a last layer a max-pooling layer, in particular over the time dimension.
[0032] This makes it possible in one embodiment for each input, in particular input, of this pooling layer to correspond to the classification value for the associated point in time, in particular if the maximum value is greater than zero, the data time series is classified as NIO, and respectively, in particular if the maximum value is less than zero, the data time series is classified as IO. In other words, this makes it possible in one embodiment for areas in which an NIO event has occurred or occurred, or in particular is to be expected, to be marked with a value above zero, or (time) areas that were not or are not responsible for the NIO classification to be marked as IO. Advantageously, this makes it possible in one embodiment for the accuracy of localizing important time intervals, in particular for classification, in a data time series to be increased.is thereby increased, in particular in comparison to convolutional neural networks with a differently configured last layer. Furthermore, in one embodiment, this makes it possible for the contributions determined or calculated per time point and channel to be assigned to the probability distributions for IO and / or NIO based on the classification values per time point. In particular, this makes it possible to subsequently classify the contribution and / or contributions of a new data time series for each time interval. Advantageously, in one embodiment, this makes it possible for a statement such as "In channel X, an error probability of 5% results in seconds 5 to 10, and in seconds 20 to 25, this is 95%" or the like to be determined or can be determined as an interpretable result, in particular to be determined.According to one embodiment, the method further comprises evaluating and / or monitoring a process and / or a multi-axis machine. Advantageously, in one embodiment, this makes it possible for the process to be carried out more quickly and / or more precisely, in particular for errors in the process to be noticed more quickly and, in particular, for errors in the process to be rectified and, in particular, for them to be predicted by means of the machine learning algorithm. Advantageously, in one embodiment, this makes it possible for wear on the multi-axis machine to be localized more quickly and / or more precisely, in particular for an erroneous execution of a process by the multi-axis machine to be determined and, in particular, for them to be predicted by means of the machine learning algorithm.
[0033] According to one embodiment, the method comprises a step of evaluating and / or monitoring the process and / or the multi-axis machine. Furthermore, in one embodiment, the method comprises issuing a warning, stopping and / or changing the process, in particular a request for maintenance of the machine and / or performing a maintenance step, in particular a (re)calibration, in particular of the machine and / or the means for acquiring the at least one data time series. Furthermore, in one embodiment, the method comprises repeating the process, in particular in a modified form.
[0034] This can make it possible in one embodiment that the process and / or the multi-axis machine is less susceptible to errors, in particular is more robust against errors
[0035] After an execution, the machine learning algorithm or another algorithm is configured to predict the error class, in particular a classification value, of a data time series from the calculated contributions, in particular they can be trained or are trained to do so.
[0036] According to one embodiment, the process is a process that is executed or can be executed by at least one multi-axis machine, in particular at least one robot. In one embodiment, the multi-axis machine is a robot. According to one embodiment of the present invention, a system for operating and / or monitoring at least one multi-axis machine, in particular at least one robot, which is configured to carry out a method according to one of the preceding claims, is provided. In one embodiment, the system comprises at least one multi-axis machine and / or at least one robot.
[0037] In one embodiment, the system comprises means for acquiring at least one time series of data. Furthermore, in one embodiment, the system comprises means for determining an interpretable result using a machine learning algorithm, in particular based on the at least one time series of data. In one embodiment, the means for acquiring at least one time series of data is at least one sensor or is designed as a sensor.
[0038] Furthermore, in one embodiment, the system comprises means for determining a probability with which the classification value of the state of the process and / or the state of the multi-axis machine corresponds to a value of an error class that lies in a warning range or corresponds to a warning range, in particular for the at least one channel and / or for a time interval of the process.
[0039] In one embodiment, the system comprises means for determining an average distance of different error classes with respect to a classification value.
[0040] In one embodiment, the system comprises means for determining a probability distribution per, in particular existing, error class for a contribution of the at least one channel to the classification value.
[0041] In one embodiment, the system comprises means for normalizing the probability distribution of the values of the error class and determining a probability, in particular with which a classification value is assigned to a warning zone or a clear zone, in particular based on the probability distribution. In one embodiment, the system comprises means for determining an average distance for different error classes.
[0042] In one embodiment, the system comprises means for evaluating and / or monitoring the process and / or the multi-axis machine and, in particular, if a warning is issued when determining the result, stopping and / or changing the process and / or servicing the multi-axis machine, in particular repeating the process, further in particular in a modified form.
[0043] A system and / or means within the meaning of the present invention can be designed in hardware and / or software, in particular at least one, in particular digital, processing unit, in particular a microprocessor unit (CPU), graphics card (GPU) or the like, preferably connected to a memory and / or bus system for data or signals, and / or one or more programs or program modules. The processing unit can be designed to execute instructions implemented as a program stored in a memory system, to detect input signals from a data bus, and / or to output signals to a data bus. A memory system can have one or more, in particular different, storage media, in particular optical, magnetic, solid-state, and / or other non-volatile media. The program can be designed in such a way that it embodies the methods described here orcapable of carrying out such a method, so that the processing unit can carry out the steps of such methods and thus in particular operate or monitor the machine.
[0044] In one embodiment, a computer program product can comprise, in particular be, a storage medium, in particular a computer-readable and / or non-volatile one, for storing a program or instructions or with a program or instructions stored thereon. In one embodiment, execution of this program or these instructions by a system or a controller, in particular a computer or an arrangement of multiple computers, causes the system or the controller, in particular the computer(s), to carry out a method described here or one or more of its steps, or the program or the instructions are configured to do so.
[0045] In one embodiment, one or more, in particular all, steps of the method are carried out completely or partially automatically, in particular by the controller or its means.
[0046] In one embodiment, the system comprises at least one, in particular multi-axis machine and / or at least one robot.
[0047] Further advantages and features emerge from the subclaims and the exemplary embodiments. The following shows, partly schematically:
[0048] Fig. 1 : a multi-axis machine which is monitored, in particular controlled, by means of a method according to an embodiment of the present invention;
[0049] Fig. 2: the schematic structure of a neural network according to an embodiment of the present invention; and
[0050] Fig. 3 schematically shows a method according to an embodiment of the present invention.
[0051] Fig. 1 shows a multi-axis machine 1 which is monitored, in particular controlled, by means of a method 100. The multi-axis machine 1 in Figure 1 is shown as a robot by way of example. The robot has, by way of example, means 2 for capturing S10 at least one data time series Zi. Figure 1 schematically shows, by way of example, various means for capturing the at least one data time series Zi, in particular state sensors 2.1, which preferably detect or can detect a state of at least part of the multi-axis machine 1 or are in particular configured to do so; in particular force and / or torque sensors 2.2 or the like, which preferably detect or can detect a force and / or torque or the like or are configured to do so, and position sensors 2.3, which detect or can detect a position or pose or its time derivatives, in particular speed and / or acceleration.are configured for this purpose, in particular over time. The recorded data time series Zi are transferred to means S20 for determining an interpretable result, in particular transmitted via data communication, and in particular retrieved by them.
[0052] Figure 2 schematically shows an artificial neural network with various layers and inputs x1 to xn, which feed into layers 1 to k, represented here by a dashed line or three dots. K1 to Kn represent the channels present in the at least one data time series, which are (initially) evaluated separately. These are followed by convolutional layers from k + 1 to k + 2 and k + 2 to K -1 with an (intermediate) result M1 and M2, which are applied as described herein, without bias terms and / or batch norm layer. y represents an output, which describes, preferably and / or advantageously enables, an interpretable result. This result is provided after layer K.
[0053] Figure 3 schematically shows a method 100 for evaluating and / or checking a process and / or for evaluating and / or checking a multi-axis machine 1, in particular for controlling the process and / or the machine. The method has, by way of example, several method steps, wherein the acquisition of at least one data time series Zi is represented by S10. Furthermore, Figure 3 shows the determination of an interpretable result by S20. If the result describes a value that lies within a warning range, a warning is issued. If the result describes a value that lies within a clear range, an all-clear signal is issued. This is represented in each case by S30. S40 schematically represents the evaluation and / or monitoring, in particular control, of the process and / or the multi-axis machine.The method can preferably be repeated, as shown by the dashed arrow in Figure 3, in particular with a modified process, a recalibrated multi-axis machine and / or a serviced multi-axis machine, or the like.
[0054] Although exemplary embodiments have been explained in the preceding description, it should be noted that numerous modifications are possible. Furthermore, it should be noted that the exemplary embodiments are merely examples and are not intended to limit the scope of protection, applications, or structure in any way. Rather, the preceding description provides the skilled person with a guide for implementing at least one exemplary embodiment, whereby various modifications, particularly with regard to the function and arrangement of the described components, can be made without departing from the scope of protection as it results from the claims and equivalent combinations of features.
[0055] List of reference symbols
[0056] 1 multi-axis machine
[0057] 2 Means for collecting data time series
[0058] 2.1 , 2.2, 2.3 exemplary means for capturing data time series, in particular
[0059] Sensors
[0060] 10 systems
[0061] 100 procedures
[0062] S10 Collecting at least one data time series
[0063] S20 Determining an interpretable result
[0064] S30 Issuing a warning or all-clear
[0065] S40 Evaluation and / or monitoring, in particular control of the multi-axis machine x1 ... xn inputs
[0066] K1 ... Kn channels
[0067] M1 Intermediate result of the first convolutional layers
[0068] M2 Intermediate result of the second convolutional layers y Output / interpretable result
Claims
Claims Method (100) for evaluating and / or monitoring a process and / or a multi-axis machine (1), wherein the method comprises: Acquisition (S10) of at least one data time series (Zi), wherein the at least one data time series (Zi) comprises at least one channel (K1 , Kn) that describes at least one parameter of the process and / or the multi-axis machine (1), and wherein the data time series (Zi) is caused by the process; Determining (S20) an interpretable result using a machine learning algorithm based on the at least one data time series (Zi), wherein the result describes a classification value of a state in the process and / or a state of the multi-axis machine (1); wherein, when determining the result, a warning is issued (S30) if the classification value of the state in the process and / or the state of the multi-axis machine (1) is assigned a value of a fault class that lies within or corresponds to a warning range, and an all-clear is issued (S30) if the classification value of the state in the process and / or the state of the multi-axis machine (1) is assigned a value of a fault class that lies within or corresponds to an all-clear range. Method (100) according to the preceding claim, characterized in that determining an interpretable result further comprises: Determining a probability with which the classification value of the state of the process and / or the state of the multi-axis machine (1) corresponds to a value of a fault class that lies within or corresponds to a warning range, in particular for the at least one channel (K1, Kn) and / or for a time interval of the process. Method (100) according to one of the preceding claims, characterized in that determining an interpretable result further comprises: Determining the average distance between different error classes in relation to a classification value.
4. Method (100) according to one of the preceding claims, characterized in that the method (100) further comprises a Determine a probability distribution for each error class for a contribution of at least one channel (K1 , Kn) to the classification value.
5. Method (100) according to the preceding claim, characterized in that the method (100) further comprises a Normalizing the probability distribution of the error class values and determining a probability with which a classification value is assigned to a warning area or an all-clear area, in particular, is assigned based on the probability distribution.
6. Method (100) according to one of the preceding claims, characterized in that the method (100) further comprises: Determining an average distance, in particular a Wasserstein distance, alternatively using an intersection-over-unit metric, for different error classes.
7. Method (100) according to one of the preceding claims, characterized in that the machine learning algorithm is an artificial neural network, in particular a Convolutional Neural Network.
8. Method (100) according to the preceding claim, characterized in that the Convolutional Neural Network has a Max-Pooling layer as the last layer, in particular a Max-Pooling layer over the time dimension.
9. Method (100) according to one of the preceding claims, characterized in that the method (100) further comprises: Evaluating and / or monitoring the process and / or the multi-axis machine (1) and in particular when a warning is issued when determining the result, stopping and / or changing the process and / or maintaining the multi-axis machine (1), in particular repeating, further in particular in a modified form, the process.
10. System (10) for operating and / or monitoring a multi-axis machine (1), in particular a multi-axis machine (1) configured to carry out a method (100) according to one of the preceding claims.
11. Computer program or computer program product, wherein the A computer program or computer program product, in particular stored on a computer-readable and / or non-volatile storage medium, contains instructions which, when executed by one or more computers or a system (10) according to claim 10, cause the computer(s) or system (10) to perform a method (100) according to any one of claims 1 to 9.