Method for monitoring a machining process in a machine tool, and monitoring device and computer program for same

Abstract

In a method for monitoring a machining process in a machine tool, values of a measured variable are received, said values having been determined during a machining stroke in the machining of a workpiece. At least one test value based on the values of the measured variable is compared with a tolerance limit (U i, L i). The tolerance limit is automatically determined by performing a statistical analysis of a plurality of reference values (R į) determined by measurements taken during the machining of a plurality of previous workpieces, each reference value being based on one or more values of the measured variable obtained during the machining of one of the previous workpieces.

Description

[0001]TITLE METHOD FOR MONITORING A MACHINING PROCESS IN A MACHINE TOOL TECHNICAL FIELD The present invention relates to a method for monitoring a machining process in a machine tool. The machine tool can be a gear cutting machine for machining toothed workpieces, in particular a gear grinding machine. PRIOR ART When machining workpieces in a machine tool, manufacturing deviations naturally occur. These deviations manifest themselves in deviations between the actually manufactured geometry of the workpieces and a predetermined target geometry. The manufacturing deviations can be caused by deviations from the intended process during the machining process. Process deviations can arise, among other things, from incorrect operation, malfunctions, or wear of the various components of the machine tool.For time and cost reasons, machined workpieces can usually only be randomly inspected for machining errors. For example, if the machining process involves generating grinding, which is used to fine-machine gears, the gear inspection of a single workpiece typically takes significantly longer than the actual machining. Individual inspection of each workpiece would therefore not be cost-effective. Machining errors are therefore often only detected after the workpiece has been installed in a gearbox, during a so-called end-of-line (EOL) inspection. At this stage, a defective workpiece entails significant cost consequences. It is therefore desirable to detect process deviations as early as possible during machining ("online") or at least immediately afterward ("inline"), in order to be able to reject defectively manufactured workpieces in a timely manner and intervene in the process to correct them.For this purpose, it is known to continuously determine measured values ​​on the machine tool and compare these measured values ​​with tolerance limits. The measured values ​​can be, for example, the power consumption of a tool or workpiece spindle or a signal from a vibration sensor. If the tolerance range limited by the tolerance limits is exceeded, this indicates a process deviation. In this case, the workpiece currently being machined can be rejected as defective and, if necessary, the process can be regulated. Setting the tolerance limits is a very demanding task that requires a great deal of expert knowledge. Furthermore, setting the tolerance limits is an iterative process that is prone to errors. WO2022100972A2 proposes measuring two machine parameters when grinding a gear using a grinding tool.If at least one of the machine parameters exceeds or falls below a specified value within a tolerance band, a signal is output. At least one of the machine parameters contains periodic signal components. These signal components are broken down into their individual frequency components using frequency analysis, and the frequency components are compared based on their frequency and / or amplitude. Individual limit values ​​can be defined for each frequency component. Defining individual tolerance limits for the individual frequency components requires a particularly high level of expert knowledge. For example, the operator who sets the tolerance limits must be able to classify the significance of the individual frequency components for possible machining errors. Machine tool operators often lack this expert knowledge. Due to the large number of frequency components, defining such limit values ​​is also extremely time-consuming.The unavoidable process variation further complicates this task. A complete picture of the variation of all frequency components often only emerges after several thousand workpieces have been manufactured. In practice, the limit values ​​are therefore often set incorrectly. For example, limit values ​​are set too wide, so that inadmissible process deviations are not even detected, or they are set too narrow, so that workpieces are rejected as defective even though they actually meet the manufacturing accuracy requirements. WO2021048027A1 discloses a method for monitoring a machining process in which a plurality of measured values ​​are recorded while a tool is in machining engagement with a workpiece, including values ​​of a power indicator that indicates the current power consumption of the tool spindle during machining.A normalization operation is applied to at least some of these measured values ​​or to values ​​of a variable derived from the measured values ​​in order to obtain normalized values. The normalization operation depends on at least one of the following parameters: geometric parameters of the tool, geometric parameters of the workpiece, and setting parameters of the machine tool. This makes it possible to compare measured values ​​obtained with different process parameters. This document also proposes subjecting the measured values ​​to a frequency analysis. The document does not address the definition of tolerance limits. WO 2020 / 193228 A1 discloses a method for automatic process monitoring during the continuous generating grinding of pre-toothed workpieces, which enables early detection of grinding wheel chipping. At least one measured variable is monitored during the machining of workpieces.From this, a warning indicator for grinding wheel chipping is determined. If the warning indicator indicates grinding wheel chipping, the grinding wheel is automatically inspected for grinding wheel chipping. This document also does not deal with the definition of tolerance limits. Against the backdrop of ever-increasing demands on machining quality and a correspondingly decreasing error tolerance, methods are desired that can accurately detect even the smallest deviations or irregularities in the machining process. For example, in generating grinding, it is desirable not only to detect entire grinding wheel chippings, but also to obtain indications of microcracks in the grinding wheel. Therefore, methods for automatic process monitoring are needed that can detect process deviations in a more objective and reliable manner than previous methods.DESCRIPTION OF THE INVENTION In a first aspect, it is an object of the present invention to provide a method for monitoring a machining process in a machine tool, which enables objective and reliable detection of process deviations without requiring special expert knowledge for defining tolerance limits. This object is achieved by a method according to claim 1. Further embodiments are specified in the dependent claims. Thus, a method for monitoring a machining process in a machine tool is proposed, in which a workpiece is machined with a tool in one or more machining strokes, comprising the following steps: receiving values ​​of a measured variable(s) determined by measurements on the machine tool during the machining stroke; and comparing at least one test value based on the values ​​of the measured variable with a tolerance limit.According to the invention, the tolerance limit is determined by performing a statistical analysis of a plurality of reference values ​​determined by measurements during the machining of a plurality of previous workpieces, wherein each reference value is based on one or more values ​​of the measured quantity determined during the machining of one of the previous workpieces, and wherein, during the statistical analysis of the reference values, a measure of dispersion for the reference values ​​is determined and the tolerance limit is set based on the measure of dispersion. In the proposed method, a large number of reference values ​​are available, which were obtained during previous machining processes by measurements on other workpieces, preferably on the same machine. The reference values ​​can be stored in a database and read from the database as part of the method.The term "reference values" is not intended to suggest that these values ​​are particularly reliable. Rather, this term is used merely to logically differentiate the data obtained in earlier machining processes from the current values ​​of the measured variable obtained during the machining process to be monitored, or the test values ​​obtained from them. A key idea of ​​the present invention is to make values ​​of the same measured variable during earlier machining processes usable for the assessment of the current machining process by calculating the tolerance limits for the current machining process based on a statistical analysis of reference values ​​based on these earlier values. This is based on the assumption that, in practice, the vast majority of the earlier measured values ​​orthe resulting reference values ​​were determined in machining processes for which no inadmissible process deviations existed. Only a few machining processes will be "bad" processes in practice, since such "bad" processes are usually quickly identified through manufacturing deviations, and corrective measures are taken. In practice, a certain portion of all workpieces is usually measured after the machining process (e.g., every hundredth workpiece), so that after a certain number of workpieces, an inadmissible process deviation would become noticeable through a manufacturing deviation of the workpieces in question. If the workpieces are geared, for example, the workpieces are also usually installed in gearboxes after the machining process, and at least some of the finished gearboxes are tested in a so-called EOL test bench (EOL = End of Line).Here, too, workpieces with unacceptable manufacturing deviations would be quickly identified, particularly due to disturbing noise in the gearbox. Reference values ​​obtained during the machining of workpieces with manufacturing deviations can subsequently be marked accordingly in the database and thus excluded from the determination of tolerance limits or even specifically taken into account when determining tolerance limits. Statistically averaged across many machining processes, the reference values ​​therefore essentially represent a "good" machining process, i.e., a machining process without unacceptable process deviations, and the statistical distribution of the reference values ​​represents the typical distribution to be expected in a "good" machining process. This knowledge is exploited to automatically determine the tolerance limits.As a result, tolerance limits are automatically determined based on objective criteria, without the operator requiring in-depth knowledge of the machining process. The tolerance limits determined in this way can be utilized in two ways within the machining process. Firstly, the machining process can be directly controlled by comparing the test value with the tolerance limit. In particular, the machining process can be interrupted or automatically modified if the comparison indicates an unacceptable process deviation. Secondly, the tolerance limits themselves also provide a valuable interpretation aid for the operator. Based on the tolerance limits, the operator can distinguish "good" from "bad" test values. This allows them to objectively assess the quality of a current machining process.Ideally, this enables the operator to draw direct conclusions about the cause of identified manufacturing deviations. The steps of receiving measured values ​​and comparing the test values ​​based on them with the tolerance limit are preferably carried out repetitively, i.e. these steps are preferably repeated continuously during a machining operation. The reference values ​​can be stored in a database. The method can then involve retrieving the reference values ​​to be statistically analyzed from the database. The measured values ​​of the current machining process can themselves be made usable for subsequent machining processes. For this purpose, a new reference value can be calculated based on these measured values, and the database can be updated by saving the new reference value in the database.By continuously adding new reference values ​​to the database, the method becomes self-learning to a certain extent and constantly improves itself through the ever-increasing number of reference values. In particular, in the method according to the invention, each reference value can correspond to a test value that was determined for a previous workpiece based on measured values ​​taken during the machining of the previous workpiece, i.e. the reference values ​​are formed directly from test values ​​of previous workpieces. However, it is also conceivable that the reference values ​​were derived in a different way from the measured values ​​of previous machining processes. In particular, the test values ​​that are compared with the tolerance limits can be the actual measured values, and several measured values ​​determined one after the other can be compared with one and the same tolerance limit.The reference values ​​from which this tolerance limit is determined can, however, be formed by an average value (or another position parameter), maximum value, minimum value or other value that characterizes the previous machining process. It is sufficient if these reference values ​​are saved in the database. This requires less storage space in the database than if all previous measured values ​​were saved in the database and called up each time the tolerance limits are calculated. Reference values ​​for each combination of workpiece geometry and tool type can be stored in separate areas of the database, i.e. the reference values ​​in a certain area of ​​the database are always specific to a certain workpiece geometry and a certain tool type. For each of these areas of the database, additional information about the workpiece geometry and the type of tool can then be stored in the database.If necessary, the reference values ​​can also be specific to a particular tool geometry. With dressable tools, the tool becomes smaller after each dressing process. In this case, it is conceivable to store the reference values ​​obtained from machining operations that took place after a specific dressing process in a separate area of ​​the database. In this case, information about the tool dimensions resulting from this dressing process can also be stored in the database. The tolerance limits can then be redefined after each dressing process, whereby only those reference values ​​determined after dressing using a tool with the same or similar tool dimensions are used to calculate the tolerance limits."Similar" tool dimensions are understood to mean dimensions that lie within a predetermined range around the current dimensions of the tool. However, it is also conceivable to take the decreasing tool dimensions into account by performing a standardization operation, as described below. A combination of both measures is also possible. As already mentioned, the workpiece can be, for example, a toothed workpiece, in particular a gear, specifically a spur gear, a bevel gear, or any other rotationally symmetrical workpiece with a regular sequence of teeth and tooth spaces. The machining process can, in particular, be a grinding process, specifically a gear grinding process such as generating or profile grinding. However, the invention is not limited to the machining of toothed workpieces or to grinding processes.For example, the invention can also be used in gear machining, including hobbing, gear skiving, or gear honing. The machining process can also be a dressing process, in which the tool is a dressing tool (in particular a rotating dressing wheel or a rotating dressing gear) and the workpiece is a grinding tool (in particular a grinding worm or a profile grinding wheel). The measured variable can vary over time, so that in the method according to the invention, time-dependent values ​​of the measured variable are received for a plurality of points in time during a machining stroke. These time-dependent values ​​can then be processed in various ways. In a first, particularly simple variant, a time-independent test value is calculated from the time-dependent values ​​of the measured variable, which represents the values ​​of the measured variable over the entire machining stroke.Each reference value is also time-independent and is based on time-dependent values ​​of the measured quantity over a machining stroke during the machining of one of the previous workpieces. Through the statistical analysis of the time-independent reference values, at least one time-independent tolerance limit is determined, and the time-independent test value is compared with the at least one time-independent tolerance limit. In a second, more complex variant, a plurality of time intervals of the machining stroke are specified, whereby the time intervals can all have the same length or different lengths and do not necessarily have to be immediately adjacent to one another. For each of the time intervals, at least one associated test value is determined, which is based on the values ​​of the measured quantity determined during machining in the respective time interval.The test value can, for example, be the value of the measured variable in the middle of the time interval in question, a mean value (or another position parameter in the sense of descriptive statistics) of the measured variable in the time interval in question, or any other value that characterizes the behavior of the measured variable in the time interval in question. For each of the time intervals, at least one tolerance limit is determined. This is done on the basis of reference values ​​that are specific to the time interval in question, i.e. each of the reference values ​​is based on time-dependent values ​​of the measured variable during the machining of one of the earlier workpieces in the time interval in question. The at least one test value for each of the time intervals is then compared with the at least one tolerance limit for the time interval in question.In a further variant, a frequency analysis of the time-dependent values ​​of the measured variable is carried out in order to determine a plurality of frequency components of the measured variable. A plurality of frequency intervals is specified, whereby the frequency intervals can all have the same size or different sizes and do not necessarily have to be directly adjacent to one another. For each of the frequency intervals, at least one associated test value is determined which is based on the frequency components in the respective frequency interval. The test value can be, for example, a selected frequency component in the respective frequency interval, the maximum or integral of the frequency components in the respective frequency interval, or any other value that characterizes the frequency content of the measured variable in the respective frequency interval. For each of the frequency intervals, at least one tolerance limit is determined.This is done on the basis of reference values ​​that are each specific for the respective frequency interval, i.e. each reference value is based on frequency components in the respective frequency interval that were determined by a frequency analysis of time-dependent values ​​of the measured variable during the machining of one of the previous workpieces. The at least one test value for each of the frequency intervals is then compared with the at least one tolerance limit for the respective frequency interval. In some embodiments, the workpiece is machined consecutively in at least two machining strokes. It is then advantageous if the tolerance limit is specific for the respective machining stroke, i.e. if individually different tolerance limits are determined for each machining stroke. The reference values ​​are preferably based on measured values ​​that were determined during the machining of previous workpieces in the same machining stroke on the same machine tool.However, it is also conceivable to use reference values ​​that were determined during the machining of previous workpieces in other machining strokes and / or on other, similar machine tools. The statistical analysis of the reference values ​​can be carried out in various ways. The measure of dispersion can, for example, be a standard deviation or the size of a value interval in which a predetermined proportion of all reference values ​​lies (e.g., the interquartile range). In some embodiments, the tolerance limit can then be defined relative to a position parameter of the reference values ​​(e.g., relative to the arithmetic mean or the median) as a multiple of the standard deviation or as a multiple of the size of the said value interval. In other embodiments, a boundary of the said value interval can directly form the tolerance limit, e.g., the boundary of the value interval in which the lower 99% or 99.9% of all values ​​lie.In order to reduce the sensitivity of the method to peculiarities of a specific statistical analysis method, it can be provided that the tolerance limit is determined by combining at least two statistical analysis methods. Alternatively or additionally, it can be provided that the at least one value of the measured variable or the test value derived therefrom is compared with at least two tolerance limits that were determined using different statistical analysis methods. The time-dependent measured variable can, for example, be at least one of the following variables or be derived from at least one of the following variables: a power indicator that is a measure of the instantaneous power consumption of a tool spindle or workpiece spindle of the machine tool; or a vibration indicator that was determined using at least one vibration sensor and represents vibrations of the machine tool.In order to reduce the dependence of the test value on process parameters such as tool diameter, workpiece diameter and module or infeed, it can be provided that a standardization operation is carried out when determining the test value in order to standardize the test value. The standardization operation depends on at least one process parameter, wherein the process parameter is at least one geometric parameter of the tool, at least one geometric parameter of the workpiece and / or at least one setting parameter of the machine tool. The standardization operation is carried out in such a way that the standardized test value depends less strongly on the at least one process parameter than without the standardization operation. Such a standardization operation is particularly valuable if the measured variable is a measure of the power consumption of the tool spindle or workpiece spindle.As soon as at least one of the mentioned process parameters changes, the normalization operation is preferably recalculated. The recalculation of the normalization operation can in particular comprise the application of a model that describes an expected dependence of the reference values ​​on the process parameters, in particular a model of a process force or process power. For further considerations regarding the normalization operation, reference is made to the publication WO2021048027A1, the content of which is incorporated in its entirety by reference into the present disclosure. The method can comprise the output of user information to a user of the machine tool, wherein the user information is based on the comparison of the at least one test value with the tolerance limit. For example, the result of the comparison can be displayed visually, e.g.on a display of a machine control system of the machine tool or on a display of a mobile device, for example a laptop or tablet computer, whereby the mobile device does not necessarily have to be located at the same time as the machine tool, and / or an acoustic output can be provided. A visual output can be provided, for example, graphically. Of course, there are countless other ways of outputting user information. Alternatively or additionally, the method can comprise influencing the machining process depending on the result of the comparison of the test value with the tolerance limit. In particular, it can be provided that the machining process is stopped if the comparison shows that an inadmissible process deviation exists, or that a workpiece during the machining of which an inadmissible process deviation was detected is automatically rejected.Based on the comparison of at least one test value with the tolerance limit, a numerical process deviation indicator can be determined. In the simplest case, the process deviation indicator is a Boolean variable, which indicates, through one of its two possible values, that an impermissible process deviation exists (e.g., TRUE = impermissible process deviation, FALSE = no impermissible process deviation). However, the process deviation indicator can also be a more complex indicator, for example, an array of Boolean, integer, or real-valued variables, where each of these variables specifies the degree of deviation of a test value from the assigned tolerance limit. The process deviation indicator or user information based on it can be output. The method can also provide for the automatic checking of the machine status.This can be done ad hoc whenever an inadmissible process deviation is detected, or the machine status check can be performed at regular intervals, e.g., during machining breaks, independently of the actual monitoring of the machining process. To check the machine status, the method can comprise: performing a machine test cycle in which at least some of the machine axes are specifically actuated and status data associated with this actuation are determined by measurements; and performing a status diagnosis in which the status data are compared with at least one reference status variable in order to determine at least one machine status indicator. A fault source indicator containing information about the type of fault source for an inadmissible process deviation is determined from the process deviation indicator and the machine status indicator.The method does not necessarily have to include performing the machine test cycle and the condition diagnosis. It can also be provided that a machine condition indicator determined in a previous condition diagnosis is read from a database. For example, the error source indicator can indicate which machine axis is affected and / or whether it is likely a machine error (e.g., due to a malfunctioning machine axis), a process error (e.g., due to incorrect clamping of the workpiece), or an operator error. The machine condition can be checked using a method as described in application CH 070373 / 2021 dated October 11, 2021 (patent no. CH 718264) by the applicant of the present application. The content of application CH 070373 / 2021 and patent no. CH718264 is incorporated in its entirety into the present disclosure by reference.The identification of a source of error indicator is also advantageous if the tolerance limit on the basis of which the process deviation indicator was determined was set by a method other than a statistical analysis of reference values. In particular, the identification of the source of error indicator is also advantageous if the tolerance limit was previously set manually. In any case, the source of error indicator represents a very powerful interpretation aid with which an operator can quickly identify a suspected source of error even without in-depth specialist knowledge. The strength of this approach lies in the fact that it combines information from two very different sources: on the one hand, from monitoring a machining process (i.e., process diagnostics) and, on the other hand, from checking the machine status (i.e., status diagnostics).This combination of information provides clues that a process diagnosis alone or a condition diagnosis alone could not provide. Only by relating the process diagnosis and the condition diagnosis to one another do new insights emerge that make it easier for the operator to identify a source of error. In a further aspect, the present invention provides a monitoring device for monitoring a machining process in a machine tool in which a workpiece is machined with a tool. The monitoring device is configured to carry out the method described above. For this purpose, the monitoring device can have a computer that is configured to carry out the method. The computer can be implemented locally at a single physical location, distributed across multiple physical locations, or in the cloud.The computer may comprise a non-volatile memory device in which a computer program is stored which, when executed, causes the computer to carry out said method. The monitoring device may comprise one or more of the following devices, wherein these devices may be implemented by the computer program executed by said computer: ^ a database interface configured to read the reference values ​​from a database and, if necessary, to transmit new reference values ​​to the database; ^ a limit determination device configured to carry out the statistical analysis of the reference values ​​in order to determine the tolerance limit; ^ a measured value interface configured to receive the values ​​of the measured variable, e.g.by reading the values ​​of the measured variable from a memory device of a machine control system or by directly reading a detector for determining the measured variable; ^ a test value determination device configured to determine a test value based on the values ​​of the measured variable; ^ a comparison device configured to compare the test value with the tolerance limit; and ^ a user interface configured to output user information, e.g., in the form of a process deviation indicator or a fault source indicator. These devices can be implemented in different physical units. For example, the calculation of the tolerance limit can be performed in the cloud, i.e., the database interface and the limit determination device can be implemented by a service in the cloud.The reception of measured values, the determination of the test value, the comparison with the tolerance limit, and the output of user information can, however, take place locally in a machine control system of the machine tool. A data interface can then be used for data exchange between the service in the cloud and the machine, via which, in particular, the tolerance limit can be transmitted to the machine and via which the measured values ​​and / or reference values ​​are transmitted back to the database interface. This data interface can be implemented wirelessly or wired. The monitoring device can also have a user interface configured to change at least one parameter used by the computer to automatically set the tolerance limit, e.g., a factor by which a fluctuation in the reference values ​​is multiplied when setting the tolerance limit.The user interface can also be configured to change an automatically defined tolerance limit. The user interface can be implemented, for example, locally on a control panel of the machine tool or decentrally on a mobile device such as a laptop or tablet computer, e.g., via a touchscreen. The present invention also provides a machine tool comprising a monitoring device of the aforementioned type.The machine tool can also have at least one of the following devices: ^ a tool spindle for rotating a tool about a tool spindle axis; ^ a workpiece spindle for rotating a workpiece about a workpiece spindle axis; ^ a movement apparatus designed to move the tool spindle and the workpiece spindle relative to one another in order to execute a machining stroke; ^ at least one detector for determining values ​​of a measured variable during the machining stroke. The detector can in particular be a power detector for determining a measure of the power consumption of the tool spindle or workpiece spindle or a vibration detector for determining a measure of vibrations of the machine tool.In a further aspect, the invention provides a computer program comprising instructions which, when executed by a computer of a monitoring device, in particular the monitoring device defined above, cause this computer to carry out the method described above. The computer program can be stored on a non-volatile storage medium. The above statements regarding the method according to the invention also apply mutatis mutandis to the device according to the invention and the computer program according to the invention. BRIEF DESCRIPTION OF THE DRAWINGS Preferred embodiments of the invention are described below with reference to the drawings, which serve merely as an explanation and are not to be interpreted in a restrictive manner. The drawings show: Fig. 1 a schematic view of a generating grinding machine; Fig.Fig. 2 is a schematic diagram to explain the temporal progression of a measured variable during a machining stroke; Fig. 3 is a diagram illustrating a statistical distribution of the maximum of a measured variable for a multitude of machining operations on different workpieces on the same generating grinding machine; Fig. 4 is a diagram illustrating a possible statistical distribution of reference values ​​for a multitude of machining operations on different workpieces on the same generating grinding machine; Fig. 5 is a diagram illustrating another statistical distribution of reference values ​​for a multitude of machining operations on different workpieces on the same generating grinding machine; Fig. 6 is a diagram illustrating the temporal progression of a measured variable over a machining stroke and its evaluation in the time domain; Fig. 7 is a spectrum obtained by a frequency analysis of the temporal progression of a measured variable; Fig.8 shows a diagram illustrating the comparison of test values ​​obtained from frequency components of a measured variable with frequency-dependent tolerance limits; Fig. 9 shows a sketch of a network with several similar generating grinding machines that communicate with a database via a service server; Fig. 10A shows a flow chart for determining a tolerance limit from reference values; Fig. 10B shows a flow chart for monitoring a machining process using the tolerance limit; Fig. 10C shows a flow chart for determining an error source indicator; Fig. 10D shows a flow chart for updating the database with new reference values; Fig. 11 shows a schematic example of a user interface for modifying the automatically calculated tolerance limits; and Fig. 12 shows a schematic example of a user interface for outputting information about the machining process. DESCRIPTION OF PREFERRED EMBODIMENTS Exemplary structure of a generating grinding machine In Fig.Figure 1 shows a generating grinding machine 1 as an example of a machine tool, which will also be referred to as "machine" below. The machine 1 has a machine bed 11 on which a tool carrier 12 is guided for displacement along a radial feed direction X. The tool carrier 12 carries an axial slide 13, which is guided for displacement relative to the tool carrier 12 along a feed direction Z. A grinding head 14 is mounted on the axial slide 13. The grinding head 14 can be pivoted about a pivot axis running parallel to the X direction (the so-called A axis) to adapt to the helix angle of the gear to be machined. The grinding head 14, in turn, carries a shift slide on which a tool spindle 15 can be shifted relative to the grinding head 14 along a shift direction Y. A helically profiled grinding wheel (grinding worm) 16 is clamped on the tool spindle 15.The grinding worm 16 is driven by the tool spindle 15 to rotate about a tool axis B. The machine bed 11 further supports a pivotable workpiece carrier 20 in the form of a turret, which can be pivoted about a pivot axis C3 between at least three positions. Two identical workpiece spindles are mounted diametrically opposite one another on the workpiece carrier 20, of which only one workpiece spindle 21 with the associated tailstock 22 is visible in Fig. 1. A workpiece can be clamped onto each of the workpiece spindles and driven to rotate about a workpiece axis C1 or C2. The workpiece spindle 21 visible in Fig. 1 is in a machining position in which a workpiece 23 clamped thereon can be machined with the grinding worm 16. The other spindle, offset by 180° and shown in Fig.A workpiece spindle (not visible) is located in a workpiece change position, where a finished workpiece can be removed from this spindle and a new blank can be clamped. A dressing device 30 is mounted offset by 90° to the workpiece spindles. The machine 1 thus has a multitude of moving components such as slides or spindles, which are controlled by corresponding drives. These drives are often referred to in the technical world as "NC axes," "machine axes," or simply "axes." This term sometimes also includes the components driven by the drives, such as slides or spindles. The machine 1 also has a multitude of sensors. For example, only two sensors 18 and 19 are schematically indicated in Fig. 1. Sensor 18 is a vibration sensor for detecting vibrations in the housing of the grinding spindle 15.Sensor 19 is a position sensor for detecting the position of the axial slide 13 relative to the tool carrier 12 along the Z-direction. In addition, the machine 1 comprises a plurality of additional sensors. These sensors include, in particular, additional position sensors for detecting the actual position of a linear axis, angle sensors for detecting the rotational position of a rotary axis, current sensors for detecting the drive current of a respective axis, and additional vibration sensors for detecting vibrations of a respective driven component. All driven axes of the machine 1 are digitally controlled by a machine control system 40. The machine control system 40 comprises several axis modules 41, a control computer 42, and an operator panel 43.The control computer 42 receives operator commands from the control panel 43 as well as sensor signals from various sensors of the machine 1 and calculates control commands for the axis modules 41 from these. It also outputs operating parameters to the control panel 43 for display. The axis modules 41 each provide control signals for one machine axis at their outputs. A monitoring device 44 is connected to the control computer 42. The monitoring device 44 can be a separate hardware unit assigned to the machine 1. It can be connected to the control computer 42 via a known interface, e.g., via the well-known Profinet standard, or via a network, e.g., via the Internet. It can be physically part of the machine 1 or it can be physically located remotely from the machine 1. During machine operation, the monitoring device 44 receives a variety of different measurement data from the control computer 42.The measurement data received by the control computer includes sensor data acquired directly by the control computer 42 and data that the control computer 42 reads from the axis modules 41, e.g., data describing the target positions of the various machine axes and the target current consumption in the axis modules. The monitoring device 44 can optionally have its own analog and / or digital sensor inputs in order to directly receive sensor data from additional sensors as measurement data. The additional sensors are typically sensors that are not directly required for controlling the actual machining process, e.g., acceleration sensors to detect vibrations, or temperature sensors. The monitoring device 44 can alternatively also be implemented as a software component of the machine control system 40, which, for example,executed on a processor of the control computer 42, or it can be embodied as a software component of the service server 45, described in more detail below. Fig. 1 accordingly shows a processor 451 and a memory device 452 of the service server 45. The monitoring device 44 communicates directly or via the Internet and a web server 47 with the service server 45. The service server 45, in turn, communicates with a database server 46 with a database DB. These servers can be located remotely from the machine 1. The servers do not need to be a single physical unit. In particular, the servers can be implemented as virtual units in the so-called "cloud." The service server 45 communicates via the web server 47 with a mobile terminal 48. The terminal 48 can, in particular, execute a web browser with which the received data and its evaluation are visualized.The end device does not need to meet any special computing power requirements. For example, the end device could be a desktop computer, a notebook computer, a tablet computer, a mobile phone, etc. Machining a batch of workpieces For the sake of completeness, the following describes how workpieces are typically machined using machine 1. To machine an as yet unmachined workpiece (blank), the workpiece is clamped by an automatic workpiece changer on the workpiece spindle that is in the workpiece change position. The workpiece change takes place in parallel with the machining of another workpiece on the other workpiece spindle that is in the machining position.Once the new workpiece to be machined is clamped and machining of the other workpiece is complete, the workpiece carrier 20 is pivoted 180° around the C3 axis so that the spindle with the new workpiece to be machined moves into the machining position. Before and / or during the pivoting process, a centering operation is performed using the associated centering probe. For this purpose, the workpiece spindle 21 is rotated, and the position of the tooth gaps of the workpiece 23 is measured using the centering probe 24. The rolling angle is determined on this basis. Once the workpiece spindle, which carries the workpiece 23 to be machined, has reached the machining position, the workpiece 23 is brought into collision-free engagement with the grinding worm 16 by moving the tool carrier 12 along the X axis. The workpiece 23 is now machined by the grinding worm 16 in rolling engagement.This is achieved through one or more machining strokes, for example one or more roughing strokes followed by one or more finishing strokes. Optionally, one or more polishing strokes can follow. During each machining stroke, the grinding worm 16 is continuously advanced along the Z-axis relative to the workpiece 23 at a constant or variable radial X-feed (so-called axial stroke). At the same time, the tool spindle 15 is slowly and continuously shifted along the shift axis Y in order to continuously use unused areas of the grinding worm 16 during machining (so-called shift movement). A so-called shift jump can occur between two machining strokes, which means that an area of ​​the grinding worm is used in the next machining stroke that is not immediately adjacent to the previous area. Typically, the radial X-feed differs from machining stroke to machining stroke.This also means that the machining forces differ between the individual machining strokes. At the same time as the workpiece is being machined, the finished workpiece is removed from the other workpiece spindle, and another blank is clamped onto this spindle. If, after machining a certain number of workpieces, the use of the grinding worm 16 has progressed so far that the grinding worm is too blunt and / or the flank geometry is too inaccurate, the grinding worm is dressed. For this purpose, the workpiece carrier 20 is pivoted by ±90° so that the dressing device 30 reaches a position in which it is opposite the grinding worm 16. The grinding worm 16 is now dressed with the dressing tool 33. Monitoring a measured variable Fig. 2 shows a highly schematic representation of the temporal progression of a time-dependent measured variable ^(^) during a machining stroke lasting approximately 2 seconds in arbitrary units (au).The measured variable can, for example, be the current consumption of the tool spindle 15 or the signal from the vibration sensor 18. The exact temporal progression of the measured variable over a machining stroke depends heavily on the type of measured variable; in this respect, Fig. 2 is to be understood only as an example. The measured variable is digitally recorded by the monitoring device 44. For this purpose, the measured variable is sampled in a known manner with a predetermined sampling frequency and digitized using an analog-to-digital converter (ADC). This results in a sequence of discrete sampled values ​​of the measured variable for successive points in time. These digitized values ​​of the measured variable are referred to below as measured values. In the example in Fig. 2, these measured values ​​are subject to fluctuations over time. Over a machining stroke, the measured values ​​reach a maximum value ^. ^^^ and a minimum value ^ ^^^The arithmetic mean of the measured values ​​over the machining stroke is ^ ^^^ . The sizes ^ ^^^ , ^ ^^^ and ^ ^^^are examples of time-independent test values ​​derived from values ​​of a time-dependent measured quantity. Instead or in addition, other time-independent values ​​can also be determined as test values, e.g., a measure of the fluctuation of the measured values ​​during the machining stroke. As explained in more detail below, separate test values ​​can also be determined for different time intervals of the machining stroke, or the test values ​​can be determined from frequency components determined by a frequency analysis of the temporal progression of the measured values. A test value determined in this way will generally vary from workpiece to workpiece. This is illustrated in Fig. 3. A consecutive workpiece number ^ is plotted along the horizontal axis, and the corresponding test value ^ along the vertical axis. ^ (^). The check value ^ ^ (^) is used for each workpiece with an upper tolerance limit ^ ^and a lower tolerance limit ^ ^ compared. In this example, the check value ^ ^ (^) for almost all workpieces in the tolerance band between these two tolerance limits, with the exception of the values ​​for workpieces with workpiece numbers ^ = 34 and ^ = 44. These deviations from the tolerance band indicate unacceptable process deviations during the machining of these workpieces. The corresponding workpieces can be removed from the process, and measures can be taken to return the process to within the tolerance limits. Automatic definition of tolerance limits The tolerance limits ^ ^ , are automatically determined through a statistical analysis of a large number of values ​​of a reference quantity (reference values). These reference values ​​were determined through measurements taken during the machining of a large number of previous workpieces. Each reference value is based on values ​​of the measured quantity that were determined during a previous machining operation on one of the previous workpieces in the same machining stroke on the same machine. In particular, the test value ^ can be used as the reference value. ^which was determined during the relevant machining stroke when machining the respective previous workpiece. This is based on the consideration that, on average, over a large number of machining operations on many workpieces, the vast majority of the machining operations will not exhibit any unacceptable process deviations, because otherwise the unacceptable process deviations would be detected sooner or later based on manufacturing deviations on the workpieces machined in this way. If the number of workpieces for which the reference values ​​were determined is sufficiently large (e.g., greater than 1,000 or even greater than 10,000), the distribution of the reference values ​​across all the workpieces therefore corresponds to a good approximation of the distribution to be expected for a flawless manufacturing process.Through a statistical analysis of these values, tolerance limits can be automatically determined based on objective criteria. This is illustrated by an example in Fig. 4, which shows an empirical frequency distribution of values ​​of a reference quantity (reference values) ^. ^ in arbitrary units (au). On the horizontal axis are the reference values ​​^ ^ The relative frequency for equally sized value intervals ("bins") is plotted on the vertical axis as a bar chart. In the present case, this frequency distribution corresponds approximately to a Gaussian normal distribution, whose density function is also plotted with a dotted line in Fig. 4. For this frequency distribution, the arithmetic mean the reference values ​​and the empirical variance (defined as the mean square deviation of the reference values ​​from the arithmetic mean and the empirical standard deviation (defined as the square root of the empirical variance). The tolerance limits can now be automatically determined based on these statistical quantities. For example, in this example, the upper tolerance limit is defined as ^ ^ = ^ ^ + ^ ^ ^ ^ set, the lower tolerance limit as ^ ^ = − ^ ^ ^ ^ . The factor ^ ^ a freely selectable positive real number that indicates by how many standard deviations the tolerance limits deviate from the mean are removed. Based on the well-known 6σ concept (which is normally used for a different purpose), for example, ^ ^ = 6. Depending on the customer's tolerance sensitivity, another factor ^ ^ be selected. The factor ^ ^can optionally be specified by the operator. In the example in Fig.4, the values ​​of the reference size ^ ^ nearly normally distributed. However, in many cases this is not the case. For example, Fig. 5 shows an empirical frequency distribution of reference values ​​^ ^which deviates strongly from a normal distribution. For example, the frequency distribution in Fig. 5 is bimodal and strongly asymmetric. Such a distribution is only inadequately characterized by the arithmetic mean and standard deviation. In such cases, other statistical analysis methods may be more promising. Two such methods are explained below. Instead of the arithmetic mean, for example, the median ^(0.5) (i.e., the ^- quantile ^(^) for ^ = 50%) of the reference values ​​can be calculated as a more robust form of a location parameter. Instead of the standard deviation, which can be strongly influenced by individual "outliers," the interquartile range (IQR) of the reference values ​​can be calculated as a more robust measure of fluctuation. This is the value interval in which the middle 50% of all values ​​of the reference values ​​lie, or in other words, the distance ^(0.75) − ^(0.25) between the ^-quantiles of the frequency distribution for ^ = 75% and ^ = 25% (also referred to as the upper and lower quartiles). The term "^-quantile" is understood in the same way as is usual in descriptive statistics for sample quantiles, namely as the smallest value below which a given proportion ^ of all values ​​in the sample lies, where ^ is a real number between 0 and 1 and is referred to as the undershoot proportion. Accordingly, the tolerance limits can be set using ^-quantiles of the distribution of the reference values. In particular, the tolerance limits can be set using the median and the interquartile range. For example, the upper and lower tolerance limits can be set as follows: where the factor ^ is again a freely selectable positive real number. An alternative definition can be made using the median and its distance from the upper and lower quantiles as follows: ^ ^= ^(0.5) + ^ ^ ^^ ( 0.75 ) − ^ ( 0.5 ) ^, ^ ^ = ^(0.5 − ^ ^ ^ ^ ( 0.5 ) − ^ ( 0.25 )^ , Another determination can be made based solely on the upper and lower quartiles as follows: In this case, no position parameter such as the median is required. In an even simpler embodiment, a predefined quantile of the frequency distribution of the reference values ​​can be used directly as the tolerance limit. For example, the 99% quantile ^(0.99) (often referred to as the "last percentile") can be defined as the upper tolerance limit and the 1% quantile ^(0.01) (the "first percentile") as the lower tolerance limit. In this case, the percentage of undershoot ^, by which the corresponding quantile is determined, can be specified by the operator. When determining a tolerance limit, several statistical methods can also be combined. For example, the upper tolerance limit can be defined as a weighted average of the upper tolerance limits calculated using two different methods.Alternatively, two or more upper and / or lower tolerance limits can be defined for a test value, with the tolerance limits determined using different statistical methods. For example, the test value can be compared with a first upper tolerance limit, which is defined as ^. ^ = was calculated, and on the other hand compared with a second upper tolerance limit, which is known as ^ ^ = ^(0.75) + ^ ^ ^ ^ ( 0.75 ) − ^ ( 0.25 )^was calculated. If just one of these two upper tolerance limits is exceeded, it can be concluded that there is an inadmissible process deviation. Implementation with database The reference values ​​can be determined in advance and stored in the database 46. The automatic setting of the tolerance limits is then carried out by the monitoring device 44 by accessing the database 46, reading the reference values ​​from this database and statistically analyzing them. After the successful machining of a workpiece, the monitoring device 44 can calculate a new value of the reference quantity from the measured values ​​for this workpiece and save it in the database 46. In this way, the database is continuously supplemented with new reference values, which are then available for setting the tolerance limits for subsequent workpieces. This makes the monitoring device self-learning to a certain extent. Time-varying tolerance limits In the example in Fig.3, a time-independent test value was determined for a time-dependent measured variable, and this test value was compared with an upper and lower tolerance limit. Instead of or in addition, it is also possible to compare test values ​​that were specifically determined for certain time intervals during a machining stroke with tolerance limits. These tolerance limits can themselves be time-dependent, i.e. different tolerance limits can be provided for different time intervals. This is illustrated in Fig. 6. This shows a solid line showing the curve of a time-dependent measured variable ^(^) for a specific workpiece (in this example, the workpiece with the workpiece number ^ = 12). In this example, the measured variable initially increases during a machining stroke, then reaches a plateau, and then falls again.Such a curve can be observed, for example, in the power consumption of the tool spindle when the tool first gradually engages the workpiece, machines the workpiece in full engagement, and then gradually disengages. Typically, this curve is superimposed with a noise component, which, however, has not been shown in Fig. 6 for reasons of clarity. Also illustrated in Fig. 6 are the upper and lower tolerance limits ^. ^ and ^ ^ , which were each defined separately for a plurality of time intervals ^. In the present example, there are a total of 8 such time intervals with assigned upper and lower tolerance limits. During the machining stroke, the measured variable ^(^) is digitally recorded, and test values ​​^ derived from the measured variable values ^are continuously compared with these tolerance limits in order to detect unacceptable process deviations. In the example shown in Fig. 6, the test value ^ ^ simply the respective value of the measured quantity ^(^) in the middle of the respective time interval. The circles in Fig. 6 illustrate the fluctuations of the test values ​​^ ^ in the intervals ^ from workpiece to workpiece. In the present example, these values ​​lie mostly between the assigned tolerance limits ^ ^ and ^ ^ . Only for one of the workpieces (here the workpiece with the workpiece number ^ = 87) the value of the measured quantity ^(^) exceeds the upper tolerance limit ^ during the time interval ^ = 2 ^The dashed line shows the complete curve of the measured variable ^(^) for this workpiece. This shows that the measured variable has increased unexpectedly rapidly. Exceeding the upper tolerance limit indicates an unacceptable process deviation. Accordingly, the workpiece in question can be rejected and examined more closely or discarded. If necessary, the machine condition can be examined, or the process can be adjusted. The tolerance limits ^ ^ and ^ ^can in turn be determined automatically through a statistical analysis. For this purpose, values ​​of the measured quantity ^(^) are used, which were determined in previous processing steps. For each time interval ^, a characteristic value of the measured quantity ^(^) is determined as a reference quantity, for example the mean value of the digitized values ​​of the measured quantity ^(^) during this time interval or the value of the measured quantity ^(^) in the middle of the time interval. The distribution of these reference values ​​is then statistically analyzed in a similar manner as described above in connection with Figures 3-5. In particular, statistical parameters can again be determined for these reference values, in particular a position parameter and a measure of dispersion, and from these, the tolerance limits can be calculated. In this way, a separate upper tolerance limit ^ is determined for each of the time intervals ^ ^ and a separate lower tolerance limit ^^determined. In a further development, it is also conceivable that a test value is determined for each time interval, which characterizes the behavior of the measured variable ^(^) in this time interval in a way other than just by a current value in the middle of the time interval. For example, an average of the measured values ​​can be determined for each time interval as the test value, or a regression analysis of the measured values ​​can be carried out in order to determine a test value that characterizes the temporal change of the measured values ​​in the respective interval. For example, a gradient of the measured values ​​in the respective time interval can be determined as the test value. Tolerance limits can then be automatically determined for this test value by statistically analyzing the correspondingly calculated test values ​​during the machining of previous workpieces as reference values.Frequency-dependent tolerance limits For a time-dependent measured variable, the comparison with tolerance limits can be made in the frequency domain as well as in the time domain. For this purpose, a frequency analysis of the digitized time-dependent values ​​of the measured variable is first performed in order to determine a large number of frequency components of the measured variable. This can be done by applying a suitable transformation to the time-dependent values ​​of the measured variable, in particular a discrete Fourier transform (DFT), which can specifically be implemented as a fast Fourier transform (FFT). However, other methods can also be used to perform a frequency analysis, for example a wavelet analysis. The result of such a frequency analysis is schematically illustrated in Fig. 7. Fig. 7 shows a spectrum of a measured variable in the form of a large number of frequency components (spectral values) ^(^) as a function of the frequency ^.The spectrum was obtained by filtering and DFT of a time-dependent measurement variable. Several peaks, indicated by circles, are visible in the spectrum. The frequency components in the range of these peaks are of particular interest for the subsequent analysis. Various frequency intervals are now specified for this spectrum. For each of the frequency intervals, at least one test value is compared with one or more frequency-dependent tolerance limits. This is illustrated in Fig. 8. In this figure, an upper tolerance limit ^ is specified for each of the frequency intervals ^. ^ (solid line) and a lower tolerance limit ^ ^(dashed line). In addition, for each frequency interval, several test values ​​are shown as circles. These were determined from the frequency components of the measured quantity in the respective frequency interval based on measurements on different workpieces. The respective test value can be, for example, the integral or the maximum of the frequency components in the respective frequency interval. The frequency intervals can, for example, be chosen to be so narrow that there is exactly one peak in each frequency interval, and the intensity of the respective peak can serve as the test value. The assigned tolerance limits then define the permissible range within which the intensity may vary. The intensity of the peak can, for example, be determined by integrating the spectrum in the respective frequency interval or as the maximum value of the frequency components in the respective frequency interval.However, the frequency intervals can also be selected to be wider, so that several peaks are located in one frequency interval. The test value can therefore also be defined more complexly. The frequency intervals do not necessarily have to be directly adjacent to one another. For example, it is possible to compare only the intensities of selected peaks with tolerance limits, e.g. peaks at certain multiples of the workpiece or tool speed. The intensities of peaks at certain multiples of these frequencies thus allow direct conclusions to be drawn about certain types of process deviations, as will be discussed in more detail below. In the example in Fig. 8, the integral of the frequency components in the relevant frequency interval was selected as the test value for each frequency interval. In the present example, most of the test values ​​are in the range between the assigned tolerance limits.Only the test value for the workpiece with the workpiece number ^ = 27 for the frequency interval ^ = 6 falls below the lower tolerance limit ^. ^ , and the test value for the workpiece with workpiece number ^ = 51 for the frequency interval ^ = 14 exceeds the upper tolerance limit ^ ^^ . This again indicates certain process deviations. Under certain circumstances, the frequency interval in which the deviation occurs may even allow direct conclusions to be drawn about the nature of the process deviation. Each upper and / or lower tolerance limit ^ ^ or ^ ^can in turn be determined by a statistical analysis of reference values ​​that were determined for previous machining operations. For example, the relevant test value for the relevant frequency interval that was determined for a previous workpiece can serve as a reference value. The comparison with the tolerance limits can be carried out repetitively (cyclically) for each machining operation by continually determining new test values ​​and comparing them with the tolerance limits. For example, a frequency analysis can be carried out continuously during machining and the resulting frequency components or the test values ​​obtained from it can be continuously compared with the tolerance limits. Normalization operation One difficulty of process monitoring, particularly in gear machining, is the fact that the monitored measured variables depend in a highly complex way on a large number of geometric properties of the tool (in the case of a grinding worm, for example, the diameter of the tool).B. diameter, module, number of threads, lead angle, etc.), geometric properties of the workpiece (e.g. module, number of teeth, helix angle, etc.) and setting parameters on the machine (e.g. radial infeed, axial feed, speeds of the tool and workpiece spindles, etc.). Due to these diverse, complex dependencies, it is extremely challenging to draw direct conclusions about specific process deviations and the resulting machining errors from the monitored measured variables. Secondly, it is extremely difficult to compare the measured variables from different machining processes. An additional challenge arises when using dressable tools. Dressing changes the diameter of the tool during the machining of a series of workpieces, and with it the machining conditions.As a result, the monitored measured values ​​from different dressing cycles are not directly comparable, even within the same series of workpieces, even if all other conditions remain the same. To compensate for differences in the machining conditions of different workpieces, a standardization operation is applied to the measured values ​​or the test values ​​determined from them. The standardization operation takes into account the influence of one or more process parameters on the measured values ​​or test values, in particular the influence of geometric parameters of the finishing tool (especially its dimensions, specifically its outer diameter), geometric parameters of the workpiece, and / or setting parameters of the finishing machine (especially radial infeed, axial feed, and speeds of the tool and workpiece spindles).The resulting standardized test values ​​are thus independent of, or at least significantly less dependent on, the specified process parameters than without standardization. Thanks to the standardization operation, the standardized values ​​are comparable between different machining operations even if these process parameters differ. In particular, this can eliminate the need to define tolerance limits that depend on the process parameters. The standardization operation is preferably based on a model that describes an expected dependence of the measured variable on the specified parameters. If the measured variable is a performance indicator, the model preferably describes the dependence of the process performance (i.e., the mechanical or electrical power required for the machining process being performed) on the specified parameters.The process performance model can, in particular, be based on a force model that describes the expected dependence of the cutting force acting at the point of contact between the finishing tool and the workpiece on geometric parameters of the finishing tool, geometric parameters of the workpiece, and setting parameters of the finishing machine. The process performance model can also take into account the length of a lever arm acting between the tool axis and a contact point between the finishing tool and the workpiece. The lever arm length can, in particular, be approximated by the outer diameter of the finishing tool. Furthermore, the process performance model can take into account the speed of the tool spindle. The normalization operation can, for example, comprise multiplying the recorded measured values ​​or variables derived therefrom by a normalization factor.However, more complex standardization operations are also conceivable. If the measured values ​​include the values ​​of a performance indicator, the standardization factor can in particular be an inverse performance variable calculated using the process performance model for the specific machining situation at hand, or a variable derived therefrom. The standardization operation is preferably applied directly to the recorded values ​​of the measured variable, if necessary after filtering. The standardization operation is advantageously carried out in real time, i.e. while the machining process is still in progress, in particular while the respective workpiece is being machined, i.e. while the tool is still in machining engagement with the workpiece. This means that standardized values ​​are available directly during the machining process and can be used in real time to monitor the machining process.The normalization operation can be recalculated each time at least one of the process parameters changes. Recalculating the normalization operation preferably involves applying the aforementioned model to the changed process parameters. For further considerations regarding the normalization operation, reference is made to publication WO2021048027A1, the content of which is incorporated in its entirety by reference into the present disclosure. Performing a Condition Diagnosis in the Presence of Inadmissible Process Deviations If a process deviation is detected, it may be useful to investigate the cause of the process deviation. For this purpose, an automatic diagnosis of the machine condition can be performed, or existing data determined during such a diagnosis can be used.To diagnose the machine condition, a test cycle is carried out in which at least some of the machine axes are specifically actuated and status data associated with this actuation is determined through measurements. Based on this status data, a status diagnosis can then be carried out in which the status data is compared with at least one reference status variable in order to determine at least one machine status indicator. From the process deviation indicator and the machine status indicator, an error source indicator can then be determined, which indicates, for example, whether a machine error, a pre-processing error, or an operating error has occurred. For example, in gear machining, a detected process deviation may be that the intensity of the frequency component of the drive power of the tool spindle at the speed of the workpiece spindle exceeds an upper tolerance limit.This process deviation can have various causes. One cause could be an inadmissible total pitch error of the workpiece blank due to faulty pre-machining. However, the process deviation can also be the result of an imbalance caused by faulty workpiece clamping or the result of a faulty workpiece spindle. To investigate the cause of this process deviation, a diagnosis of the workpiece spindle can be carried out with the workpiece clamped on it, but without machining with the tool. If this does not reveal any abnormalities, this allows the conclusion that the process deviation was the result of a pre-machining error on the workpiece. Otherwise, a condition diagnosis of the workpiece spindle can follow without the workpiece clamped on it. If this does not reveal any abnormalities, this allows the conclusion that the process deviation was the result of a clamping error on the workpiece.Otherwise, it can be concluded that the process deviation was caused by a faulty workpiece spindle. In this way, the operator, even without in-depth specialist knowledge, receives direct information that allows him or her to make a differentiated assessment of the machining process and the machine condition. This procedure is also advantageous if the tolerance limits were defined in a different way than described above, for example, if the tolerance limits were defined purely manually. Implementation in the Cloud The calculation and monitoring of the tolerance limits can be carried out locally in a monitoring device that is directly assigned to the machine tool. However, it is also conceivable to carry out at least some of these processes in the cloud. An example is illustrated in Fig. 9.The machine 1 to be monitored and a plurality of other machines 2, 3, ..., N are connected to a service server 45 and a database 46 via a web server 47. The service server 45 and the database 46 are located in the cloud. Each of these machines has a monitoring device that continuously transmits certain data to the database 46 during operation of the respective machine. This data includes, in particular, a unique machine identifier, a timestamp, and a plurality of test values, as described above. The data can optionally also include further data, for example data on measurements taken on the workpieces following production, e.g., indicators of the achieved workpiece quality. This data is stored in the database DB.As a result, over time the database contains a very large amount of process data that was acquired for several machines in many different machining operations. This data can be used for future machining processes. For example, the stored test values ​​can be used as reference values ​​when determining tolerance limits for future machining processes. The monitoring results can be accessed and visualized remotely from any location. This is done by the web server 47, which communicates with the decentralized mobile device 48, e.g. a tablet computer. Flowcharts Figures 10A to 10D show flowcharts that briefly summarize the method described above. Figure 10A illustrates steps for determining a tolerance limit. In step 101, a monitoring device reads reference values ​​from a database.In step 102, the monitoring device carries out a statistical analysis of the reference values ​​and thus determines a tolerance limit. In step 103, the monitoring device saves the tolerance limit in a memory device of the monitoring device so that this tolerance limit can be accessed later. Fig. 10B illustrates steps for determining a deviation indicator. In step 111, values ​​of a measurand are determined by measurements. In step 112, the monitoring device receives these measured values. In optional step 113, the monitoring device determines associated process parameters, e.g. by reading them from a machine control system, and applies a normalization operation that takes these process parameters into account. In optional step 114, the monitoring device carries out a frequency analysis. In step 115, the monitoring device calculates the (optionally normalized) measured values ​​orwhose frequency components a test value. In step 116, the monitoring device compares the test value with the previously determined tolerance limit and thereby determines a deviation indicator. In step 117, the monitoring device outputs the deviation indicator to the machine control or to a user interface. Steps 111-117 are repeated cyclically during the machining of a workpiece. Fig. 10C illustrates steps for determining a fault source indicator. In step 121, the monitoring device executes a test cycle. In step 122, the monitoring device performs a condition diagnosis based on the measurement results of the test cycle in order to determine a machine condition indicator. Alternatively, the monitoring device reads a machine condition indicator, which was already determined in a previous condition diagnosis, from a database.In step 123, the monitoring device compares the machine condition indicator with the previously determined process deviation indicator. In step 124, the monitoring device outputs the error source indicator. Fig. 10D illustrates how the measured values ​​determined during monitoring of a current machining process can be used to determine and save new reference variables. In step 131, a machining process is monitored. This occurs as shown in Fig. 10B. During this machining process, values ​​of a measured variable (measured values) are continuously determined. A new reference value is calculated from the measured values ​​in step 132. In step 133, this reference value is saved in the database from which the previous reference values ​​were read in Fig. 10A. In this way, the database is supplemented with new reference values ​​for each machining process.User Interface The monitoring device 44 may provide a user interface that allows a user to set one or more parameters that the monitoring device requires to perform the automatic setting of the tolerance limits, for example the parameter ^ mentioned above. ^ or a specific undershoot value ^, for which the corresponding ^-quantile of the distribution of the reference values ​​should serve as the tolerance limit. The user interface can also allow the user to manually change the automatically calculated tolerance limits. Fig. 11 illustrates a highly simplified user interface in a highly schematic manner. For each frequency interval, the operator can enter the factor ^ in a box 201. ^The resulting tolerance limits are displayed graphically to the operator. By dragging an arrow 202, the operator can manually change each tolerance limit. The monitoring device 44 can also provide a user interface that enables the output of user information based on the comparison of the test values ​​with the tolerance limits. Figure 12 illustrates such a user interface in a highly simplified and highly schematic form. The user interface illustrated here displays the quality of the current machining process and the status of the machine tool for two machines, "A" and "B," respectively.This display is based on a traffic light system: A machining process in which all test values ​​are at least within the tolerance limits is represented by a green traffic light, a process with inadmissible process deviations by a red traffic light, and a process in which test values ​​are very close to the tolerance limits by a yellow traffic light. The machine status is also displayed in a similar way. In the example in Fig. 12, traffic light 212 for the machining process on machine A is green, and the traffic light for the machine status of machine A is also green. The user can therefore see at a glance that everything is OK on machine A. Traffic light 214 for the machining process on machine B, on the other hand, is red, meaning that an inadmissible process deviation has been detected in this machining process. Traffic light 215 for the machine status of machine B is yellow, meaningAt least one axis of machine B has been identified as critical during machine diagnostics. In the present example, it is assumed that this is the C1 axis (i.e., one of the two workpiece spindles). For example, the process deviation indicator may show that frequency components of the drive power of the tool spindle or a vibration signal from the vibration sensor 18 at the speed of the workpiece spindle and its multiples are outside the tolerance limits, and the condition diagnostics may have shown that increased vibrations occur when the workpiece spindle is operated, even when no workpiece is clamped on the workpiece spindle. As explained above, this together indicates a faulty C1 axis. The comparison of the process deviation indicator and the machine condition indicator therefore shows that the C1 axis is highly likely responsible for the detected process deviation, i.e.The comparison identified a fault source indicator that points to the C1 axis as the source of the error. Accordingly, the user interface issues a warning to the user, "Attention: Check C1 axis!" The user then has the opportunity to investigate this warning in detail. For example, the user interface can provide a graphical representation of a comparison of test values ​​with the corresponding tolerance limits in a manner similar to Fig. 3, 6, or 8, making it easy to identify which frequency components exceed the corresponding tolerance limits and to what extent. The user interfaces can be implemented, for example, in the control panel 43 or in the mobile device 48. Of course, countless other implementations of such user interfaces are also possible.Modifications The invention is not limited to the exemplary embodiments described above, and many modifications are possible without departing from the scope of the invention as defined in the claims. In particular, statistical methods other than those described above can also be used to determine the tolerance limits. This also includes machine learning algorithms. The training data set for such a machine learning algorithm can, for example, be the reference values ​​together with an associated quality indicator, wherein the quality indicator provides a measure of the quality of the machining process with which the respective reference value was obtained. The quality indicator can, for example, be determined subsequently by (tactile or non-contact) measurements on the workpiece for whose machining the reference values ​​were obtained.Alternatively, the quality indicator can be determined through measurements in an EOL test bench. After specifying a desired machining quality, a machine learning algorithm trained in this way can, for example, automatically determine tolerance limits, compliance with which is expected to lead to the desired machining quality. While the invention has been explained using the generating grinding of gears, the invention is also applicable to other types of gear machining, such as hobbing, skiving, gear honing, profile grinding, etc. The invention is also applicable to methods for machining workpieces other than gears.

Claims

PATENT CLAIMS 1. Method for monitoring a machining process in a machine tool (1), in which a workpiece (23) is machined with a tool (16) in one or more machining strokes, comprising the following steps: receiving values ​​of a measured variable (^(^)), wherein the values ​​of the measured variable (^(^)) were determined by measurements on the machine tool during the machining stroke; and comparing at least one test value (^ ^ , ^ ^ ) with a tolerance limit (^ ^ , characterized in that the tolerance limit (^ ^ , ^ ^ ) is determined by performing a statistical analysis of a large number of reference values ​​(^ ^ ) which were determined by measurements during the machining of a large number of previous workpieces, each reference value (^ ^) is based on one or more values ​​of the measured quantity (^(^)) determined during the machining of one of the previous workpieces, and wherein the statistical analysis of the reference values ​​(^ ^ ) a measure of dispersion (^ ^ ; IQR) for the reference values ​​(^ ^ ) is determined and the tolerance limit (^ ^ , ^ ^ ) based on the measure of dispersion (^ ^ ; IQR).

2. Method according to claim 1, wherein the reference values ​​(^ ^ ) are stored in a database (46) and the method comprises retrieving the reference values ​​(^ ^ ) from the database (46).

3. The method according to claim 2, wherein the method comprises: calculating a new reference value (^ ^ ) based on one or more of the values ​​of the measured quantity (^(^)), and updating the database by entering the new reference value (^ ^) is stored in the database (46).

4. Method according to one of the preceding claims, wherein each reference value (^ ^ ) a check value (^ ^ , ^ ^ ) determined for a previous workpiece.

5. Method according to one of the preceding claims, where time-dependent values ​​of the measured quantity (^(^)) are received for a plurality of times during a machining stroke, where the test value (^ ^ , ^ ^ ) is time-independent and is calculated from the time-dependent values ​​of the measured quantity (^(^)), where each reference value (^ ^ ) is time-independent and is based on time-dependent values ​​of the measured quantity (^(^)) during a machining stroke when machining one of the previous workpieces, whereby the statistical analysis of the time-independent reference values ​​(^ ^ ) at least one time-independent tolerance limit (^ ^ , ^ ^) is determined, and the time-independent test value (^ ^ , ^ ^ ) with at least one time-independent tolerance limit (^ ^ , ^ ^ ) is compared.

6. Method according to one of claims 1-4, wherein time-dependent values ​​of the measured variable (^(^)) are received for a plurality of times during the machining stroke, wherein a plurality of time intervals of the machining stroke are predetermined, wherein for each of the time intervals at least one associated test value (^ ^ ) which is based on the values ​​of the measured quantity (^(^)) in the time interval concerned, with at least one tolerance limit (^ ^ , ^ ^ ), where each reference value (^ ^) is specific to one of the time intervals and is based on time-dependent values ​​of the measured quantity (^(^)) during the machining of one of the previous workpieces in the time interval in question, and wherein for each of the time intervals the at least one test value (^ ^ ) with at least one tolerance limit (^ ^ , ^ ^ ) for the respective time interval.

7. Method according to claim one of claims 1-4, wherein time-dependent values ​​of the measured variable (^(^)) are received for a plurality of times during the machining stroke, wherein a frequency analysis of the time-dependent values ​​of the measured variable (^(^)) is carried out in order to determine a plurality of frequency components (^ ( ^ ) ) of the measured quantity (^(^)), wherein a plurality of frequency intervals are specified, wherein for each of the frequency intervals at least one assigned test value (^ ^ ) is determined based on the frequency components (^ ( ^) ) in the relevant frequency interval, where for each of the frequency intervals at least one tolerance limit (^ ^ , ^ ^ ), where each reference value (^ ^ ) is specific to one of the frequency intervals and is based on frequency components in the frequency interval in question which were determined by a frequency analysis of time-dependent values ​​of the measured quantity (^(^)) during the machining of one of the previous workpieces, and wherein for each of the frequency intervals the at least one test value (^ ^ ) with at least one tolerance limit (^ ^ , ^ ^ ) for the respective frequency interval.

8. Method according to one of the preceding claims, wherein the workpiece (23) is machined in at least two machining strokes, and wherein the tolerance limit (^ ^ , ^ ^) is specific to the respective machining stroke.

9. Method according to one of the preceding claims, wherein the scatter measure (^ ^ ; IQR) a standard deviation or a size of a value interval in which a given proportion of all reference values ​​(^ ^ ) is, and where the tolerance limit (^ ^ , ^ ^ ) optionally relative to a position parameter ^(0.5)) of the reference values ​​(^ ^ ) is defined as a multiple of the standard deviation or the size of the value interval.

10. Method according to one of the preceding claims, wherein the measure of dispersion (^ ^; IQR) is a value interval in which a predetermined proportion of all reference values ​​lies, and wherein a boundary of said value interval forms the tolerance limit.

11. Method according to one of the preceding claims, wherein the tolerance limit is determined by combining at least two statistical analysis methods, or wherein the at least one value of the measured variable or the test value derived therefrom is compared with at least two tolerance limits that were determined by different statistical analysis methods.

12. Method according to one of the preceding claims, wherein the measured variable (^(^)) is at least one of the following variables or is derived from at least one of the following variables: a power indicator, which is a measure of the instantaneous power consumption of a tool spindle (15) or workpiece spindle (21) of the machine tool (1); or a vibration indicator, which was determined with at least one vibration sensor (18) and represents vibrations of the machine tool (1).

13. The method according to one of the preceding claims, wherein the method further comprises: performing a normalization operation to determine the at least one test value (^ ^ , to standardize, wherein the standardization operation depends on at least one process parameter, wherein the at least one process parameter is selected from geometric parameters of the tool (16), geometric parameters of the workpiece (23) and setting parameters of the machine tool (1), such that the standardized test value (^ ^ , depends less strongly on the at least one process parameter than without the normalization operation.

14. The method according to claim 13, comprising: changing at least one of the process parameters; and recalculating the normalization operation with respect to the process parameters after the change, wherein the recalculation of the normalization operation comprises, in particular, the application of a model that describes an expected dependence of the measured variable (^(^)) on the process parameters, in particular a model of a process force or process performance.

15. The method according to one of the preceding claims, wherein the method comprises: outputting information based on the comparison of the at least one test value (^ ^ , ^ ^ ) with the tolerance limit (^ ^ , ^ ^ ) is based; and / or influencing the machining process depending on a result of the comparison of the test value (^ ^ , with the tolerance limit (^ ^ , ^^ ).

16. The method according to any one of the preceding claims, wherein the method further comprises: determining a process deviation indicator based on the comparison of the at least one test value (^ ^ , with the tolerance limit (^ ^ , ^ ^ ); and Optionally, outputting the process deviation indicator or information based on the process deviation indicator.

17. The method according to claim 16, wherein the method further comprises: reading in a machine condition indicator determined by a condition diagnosis of the machine tool, wherein, during the condition diagnosis, condition data was compared with at least one reference condition variable to determine at least one machine condition indicator, and wherein the condition data was determined by measurements in a machine test cycle in which at least some of the machine axes were specifically actuated and condition data associated with this actuation were determined by measurements; and determining an error source indicator from the process deviation indicator and the machine condition indicator, wherein the error source indicator contains information about the type of error source for an inadmissible process deviation. 18.Method for monitoring a machining process in a machine tool (1), in which a workpiece (23) is machined with a tool (16) in one or more machining strokes, comprising the following steps: receiving values ​​of a measured variable (^(^)), wherein the values ​​of the measured variable (^(^)) were determined by measurements on the machine tool during the machining stroke; and comparing at least one test value (^) based on the values ​​of the measured variable (^(^)). ^ , ^ ^ ) with a tolerance limit (^ ^ , Determining a process deviation indicator based on the comparison of at least one test value (^ ^ , ^ ^ ) with the tolerance limit (^ ^ , ^ ^); reading in a machine condition indicator that was determined by a condition diagnosis of the machine tool, wherein during the condition diagnosis, condition data were compared with at least one reference condition variable in order to determine at least one machine condition indicator, and wherein the condition data were determined by measurements in a machine test cycle in which at least some of the machine axes were specifically actuated and condition data associated with this actuation were determined by measurements; and determining an error source indicator from the process deviation indicator and the machine condition indicator, wherein the error source indicator contains information about the type of error source for an inadmissible process deviation.

19. The method according to claim 17 or 18, comprising: outputting information based on the error source indicator.

20. Monitoring device for monitoring a machining process in a machine tool (1), in which a workpiece (23) is machined with a tool (16), characterized in that the monitoring device is configured to carry out the method of one of the preceding claims.

21. Monitoring device according to claim 20, comprising a user interface configured to allow a user to change at least one parameter used by the computer for automatically setting the tolerance limit and / or to change an automatically set tolerance limit.

22. Monitoring device according to claim 20, comprising a user interface configured to output information based on the comparison of the at least one test value (^ ^ , ^ ^) with the tolerance limit (^ ^ , ^ ^ ) is based.

23. A computer program comprising instructions which, when executed by a computer, cause the computer to carry out the method of any one of claims 1-19.

Images