Diagnostic systems, diagnostic methods, and diagnostic programs

Abstract

To obtain a diagnostic system that can achieve highly accurate machining diagnosis even when the changes in the feature quantities of machining data calculated from machining data are small in cutting processes. [Solution] The diagnostic system 1 includes a machining data acquisition unit 10 that acquires multiple machining data from a machine tool 2 for multiple machining operations performed under the same machining conditions from past machining operations to the present machining operation; a feature quantity calculation unit 13 that calculates feature quantities from the machining data; a change trend calculation unit 15 that calculates the change trend of the feature quantities; and a machining diagnostic unit 17 that performs machining diagnostics based on the change trend.

Description

Technical Field

[0001] The present disclosure relates to a diagnostic system, a diagnostic method, and a diagnostic program for diagnosing machining by a machine tool.

[0002] When a machine tool processes a workpiece with a tool, the machining state of the workpiece by the tool changes due to factors such as the state of the tool and the state of the workpiece. If machining is performed in an abnormal machining state, a desired machined product cannot be obtained. Also, if tool replacement is performed in a normal machining state, the manufacturing cost of the machined product increases. Therefore, it is desired that machining diagnosis in a machine tool be accurately executed.

[0003] The machining diagnosis device described in Patent Document 1 extracts and cleans machining data in a cutting machining section from machining data such as current values, calculates a feature amount from the extracted and cleaned machining data, and executes machining diagnosis based on the calculated feature amount.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the technique of Patent Document 1 described above, for example, with respect to machining data, a feature amount is calculated while including both those resulting from machining processing and those resulting from external factors other than machining processing such as temperature changes of the machine tool. Therefore, when the change in the feature amount of the machining data calculated from the machining data in cutting machining is small, the accuracy of machining diagnosis decreases.

[0006] This disclosure is made in view of the above, and aims to provide a diagnostic system that can achieve highly accurate machining diagnosis even when the change in the feature quantities of machining data calculated from machining data in cutting processes is small. [Means for solving the problem]

[0007] To solve the above-mentioned problems and achieve the objective, the diagnostic system of this disclosure includes a machining data acquisition unit that acquires multiple machining data from a machine tool for multiple machining operations performed under the same machining conditions from past machining operations to the present machining operation; a feature quantity calculation unit that calculates feature quantities from the machining data; a change trend calculation unit that calculates the change trend of the feature quantities; and a machining diagnostic unit that performs machining diagnostics based on the change trend. [Effects of the Invention]

[0008] The diagnostic system described herein has the effect of achieving highly accurate machining diagnosis even when the changes in the feature quantities of machining data calculated from machining data are small during cutting processes. [Brief explanation of the drawing]

[0009] [Figure 1] Diagram showing the configuration of the diagnostic system according to the embodiment. [Figure 2] A diagram illustrating the waveform of processing data acquired by the diagnostic system according to the embodiment. [Figure 3] A diagram illustrating the cutting section and correction section extracted from the machining data by the diagnostic system according to the embodiment. [Figure 4] A flowchart showing the processing procedure of the diagnostic system according to the embodiment. [Figure 5] This figure illustrates the process by which the diagnostic system according to the embodiment calculates real features using the integrated values ​​of processed data. [Figure 6] A diagram illustrating the process by which the diagnostic system according to the embodiment determines the machining state and tool wear state based on feature quantities. [Figure 7] This figure illustrates a first processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of changes in real feature quantities. [Figure 8] This figure illustrates a second processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of changes in real feature quantities. [Figure 9] This figure illustrates a third processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of changes in real feature quantities. [Figure 10] This figure illustrates a fourth processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of changes in real feature quantities. [Figure 11] This figure illustrates a fifth processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of changes in real feature quantities. [Figure 12] This figure illustrates a sixth processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of changes in real feature quantities. [Figure 13] This figure illustrates a first processing example in which the diagnostic system according to the embodiment determines the processing state based on real features. [Figure 14] This figure illustrates a second processing example in which the diagnostic system according to the embodiment determines the processing state based on real features. [Figure 15] This figure illustrates a third processing example in which the diagnostic system according to the embodiment determines the processing state based on real features. [Figure 16] This figure illustrates an example of the changes in the actual feature quantities calculated by the diagnostic system according to the embodiment when a tool deteriorates. [Figure 17] This figure illustrates the process by which the diagnostic system according to the embodiment determines the processing state in the second processing example with respect to the graph shown in Figure 16. [Figure 18] This figure illustrates the first example of a process in which the diagnostic system according to the embodiment determines the processing state in the third processing example with respect to the graph shown in Figure 16. [Figure 19]FIG. for explaining a second example of a process for determining a machining state in a third process example with respect to the graph shown in FIG. 16 in the diagnostic system according to the embodiment [Figure 20] FIG. for explaining spindle load data used by the diagnostic system of the comparative example [Figure 21] FIG. for explaining the feature amount used by the diagnostic system of the comparative example [Figure 22] FIG. for explaining the replacement timing of a tool when the diagnostic system according to the embodiment determines the wear state of the tool [Figure 23] FIG. showing a configuration example of a processing circuit when the processing circuit included in the diagnostic system according to the embodiment is realized by a processor and a memory [Figure 24] FIG. showing a configuration example of a processing circuit when the processing circuit included in the diagnostic system according to the embodiment is configured by dedicated hardware MODE FOR CARRYING OUT THE INVENTION

[0010] Hereinafter, a diagnostic system, a diagnostic method, and a diagnostic program according to an embodiment of the present disclosure will be described in detail based on the drawings.

[0011] Embodiment FIG. 1 is a diagram showing the configuration of a diagnostic system according to an embodiment. The diagnostic system 1 is a system that diagnoses machining by a machine tool 2. The machining diagnosis executed by the diagnostic system 1 includes diagnosis of the wear state of a tool, diagnosis of whether or not the machining state is abnormal, diagnosis of signs of abnormality of the machine tool 2, and the like.

[0012] The machine tool 2 cuts a workpiece (not shown), which is a work piece, with a tool. The machine tool 2 is a machine that performs machining such as cutting, cutting, and polishing on a workpiece that is a machining object, and is, for example, a milling machine, a lathe, a ball grinder, or the like. The diagnostic system 1 diagnoses the cutting process by the machine tool 2 and outputs the diagnosis result to the machine tool 2.

[0013] The diagnostic system 1 comprises a processing data acquisition unit 10, an interval extraction unit 11, a feature calculation unit 13, a corrected feature calculation unit 14, a change trend calculation unit 15, a learning unit 16, a processing diagnostic unit 17, and a diagnostic result output unit 18. The diagnostic system 1 also comprises a trend data storage unit 22 and a diagnostic model storage unit 23. The interval extraction unit 11 includes a corrected interval extraction unit 12A and a cutting processing interval extraction unit 12B.

[0014] The machining data acquisition unit 10 acquires machining data, machining information used to identify the type of machining (machining conditions), and control information (including machining methods, etc.) from the machine tool 2 via CNC (Computer Numerical Control). Alternatively, the machining data acquisition unit 10 may acquire machining data and machining information directly from the machine tool 2.

[0015] The machining data for one machining process (the process of cutting out one product) includes machining data for the approach section where the tool approaches the workpiece, machining data for the cutting section where the tool cuts the workpiece (cutting section), and machining data for the retraction section where the tool moves away from the workpiece (tool retraction section). The cutting section is the first section, and the approach section or retraction section is the second section.

[0016] The machining data in the cutting section is the machining data to be diagnosed. The machining data in the approach section and the retraction section are the machining data used to correct the machining data in the cutting section. Thus, the cutting section is the section to be diagnosed (diagnostic section), and the approach section and retraction section are the sections used to correct the machining data in the cutting section (correction sections). The correction section is the section other than the cutting section.

[0017] Here, we will explain the machining data, cutting section, and correction section. Figure 2 is a diagram illustrating the waveform of the machining data acquired by the diagnostic system according to the embodiment. Figure 3 is a diagram illustrating the cutting section and correction section extracted from the machining data by the diagnostic system according to the embodiment.

[0018] In the graphs shown in Figures 2 and 3, the horizontal axis represents time, and the vertical axis represents the cutting load (spindle load in Figures 2 and 3). The spindle load corresponds to a physical quantity (such as the motor drive current value) included in the machining data. Figure 2 shows the waveform of the spindle speed Rm along with the waveform of the spindle load Wm. In Figure 3, the diagnostic system 1 extracts the waveform of the spindle load Wm from the machining data waveform shown in Figure 2, and shows the cutting section, correction section (approach section, retraction section), etc., within the waveform Wm.

[0019] When machining begins, the tool starts rotating, and the spindle speed increases to the target speed (actual machining speed). In other words, the tool's rotation accelerates, and the rotational speed increases to the target speed (actual machining speed). The period from when the tool starts rotating until the rotational speed reaches the target speed is the acceleration section IN1.

[0020] When the spindle starts rotating, acceleration torque is generated, and the spindle load corresponding to the motor drive current value increases. As the spindle rotation approaches the target rotational speed, the spindle load decreases and stabilizes. The spindle load at this stable state is the spindle load required to maintain rotation, and this section is the approach section. In other words, the section from when the spindle rotational speed reaches the rotational speed during actual machining until the tool contacts the workpiece is the approach section IN2.

[0021] Machine tool 2 brings the tool closer to the workpiece and begins actual machining when the tool makes contact with the workpiece. When the tool begins cutting the workpiece, cutting resistance is generated by the cutting of the workpiece, which generates a spindle load due to the actual cutting, and the motor drive current value corresponding to the spindle load increases. In addition, the loads on the other axes besides the spindle also increase in the same way as the spindle load when machining begins. The section in which the tool is in contact with the workpiece and cutting is being performed is the actual machining section IN3.

[0022] After the workpiece cutting is complete, machine tool 2 moves the tool away from the workpiece. This reduces and stabilizes the spindle load. The period from the completion of workpiece cutting until the spindle load reduces and stabilizes is called the retraction section IN4.

[0023] After this, the rotational speed of the tool decreases and the tool stops rotating. The period from when the rotational speed of the tool decreases until the tool stops rotating is the deceleration period IN5. The machining data acquisition unit 10 acquires machining data that includes the machining data of the actual machining section IN3 and the machining data of at least one of the approach section IN2 and the retraction section IN4.

[0024] In Figure 2, the spindle load in the approach section or tool retraction section is shown as the base load Lb. The base load Lb, which is the load in the approach section or tool retraction section, may fluctuate regardless of machining conditions. For example, if machine tool 2 is not warmed up and machining is started in a cold state, the machining data will increase overall. Specifically, in machining in a cold state, the base load Lb increases, and the spindle load during cutting also increases by the same amount as the increase in base load Lb. In other words, when the machining data increases or decreases due to factors other than machining, these increases or decreases will be reflected in the spindle load. In this case, conventionally, a unique spindle load different from that during normal machining operation was calculated, and this unique spindle load was sometimes judged as abnormal.

[0025] Furthermore, while conventional methods could detect significant machining abnormalities such as tool breakage because the spindle load would change drastically, it was impossible to detect minute tool chipping or machining abnormalities that only caused slight changes.

[0026] The diagnostic system 1 of this embodiment calculates the spindle load during cutting by subtracting the base load Lb from the spindle load during cutting, thereby removing factors other than machining, such as cold working conditions. In Figure 2, the spindle load during cutting, with factors other than machining removed, is shown as the actual cutting load Lc. In this way, the diagnostic system 1 calculates the actual cutting load Lc by subtracting the base load Lb from the spindle load during cutting in order to remove fluctuations in the spindle load caused by factors other than machining. As a result, the diagnostic system 1 can perform highly accurate diagnoses by removing factors other than machining.

[0027] The machining data acquired by the machining data acquisition unit 10 includes physical quantities during machining that are used to calculate the machining state. The physical quantities included in the machining data are motor drive current value, motor drive voltage value, motor rotation speed, motor torque, cutting resistance value, acceleration (vibration), strain amount, etc., obtained from sensors placed on the machine tool 2. The strain amount is, for example, the strain amount of the tool, tool holder, workpiece, and workpiece chuck mechanism. The strain amount is acquired by a strain sensor.

[0028] The machining data acquisition unit 10 acquires machining data such as the waveform of the motor drive current value (drive current waveform), the waveform of the motor drive voltage value (drive voltage waveform), the waveform of the motor acceleration, the waveform of the motor torque, the acceleration (vibration), and the waveform of the amount of strain. The physical quantities included in the machining data may be calculated from information detected by sensors. The machining data may also include machining command values ​​such as the spindle speed command, the inspection results of the machining dimensions, the cutting fluid discharge pressure, and the cutting fluid temperature.

[0029] Machining information includes the machining program number, subprogram number, and tool number. It may also include the machining program with numerical control commands, workpiece type number, tool usage count, tool manufacturing information (such as manufacturing serial number), and machining conditions (feed rate, depth of cut, and motion control method). Numerical control commands are control commands used when the machine tool 2 is numerically controlled, and include, for example, G0 (positioning command), G1 (linear interpolation), and G2 (circular interpolation, clockwise).

[0030] Furthermore, the machining data acquisition unit 10 identifies the machining type based on the machining information. The machining data acquisition unit 10 uniquely identifies the machining type based, for example, on a combination of machining program and tool number in the machining information, or on a machining program line.

[0031] The machining data acquisition unit 10 associates the acquired machining data and machining type for a single machining process and transmits it to the correction section extraction unit 12A and the cutting section extraction unit 12B. The diagnostic system 1 may also have a machining data storage unit (not shown) that stores the machining data and machining type acquired by the machining data acquisition unit 10. In this case, the machining data storage unit stores the machining data and machining type in association.

[0032] The diagnostic system 1 automatically identifies the approach section before cutting, the cutting section, and the retraction section after cutting by having the machine tool 2 perform both air-cutting (an operation that does not cut the workpiece) and the actual cutting in advance using the machining program to be diagnosed, and stores each section in memory.

[0033] The diagnostic system 1 can determine the section in which actual cutting occurred if it can identify the spindle load (motor drive current value, etc.) immediately before and after the actual cutting. For example, if an air-cut operation is performed, machining data will be obtained in which no spindle load is generated due to actual cutting. The spindle load immediately before and after the spindle load generated by actual cutting can be considered a spindle load that does not depend on the actual cutting. Therefore, if an air-cut operation is performed in the same type of machining, spindle load (machining data) that does not include the spindle load from actual cutting will be obtained.

[0034] In this embodiment, the machine tool 2 is pre-configured to perform both air-cut machining and actual machining as identical processes. The correction section extraction unit 12A of the diagnostic system 1 then extracts the machining section, which is the section in which actual cutting was performed, based on the difference in spindle load between air-cut machining and actual machining. That is, the diagnostic system 1 extracts the machining section in which actual cutting was performed based on the difference between the spindle load when air-cut machining is performed and the spindle load when actual machining is performed. The correction section extraction unit 12A also identifies sections in the sections before and after the section in which actual cutting was performed where the spindle load is stable, and designates these as the approach section and the retraction section, respectively. The section between the approach section and the retraction section may also be designated as the machining section.

[0035] The correction interval extraction unit 12A may store the waveform (amount of change, rate of change, etc.) of the machining data at the start and end timings of each interval, or it may store the time from when the tool starts rotating until the start and end timings of each interval.

[0036] The correction section extraction unit 12A stores, for example, the approach waveform, which is the waveform of the machining data in the approach section, the retraction waveform, which is the waveform of the machining data in the retraction section, and the cutting waveform, which is the waveform of the machining data in the cutting section, for each type of machining. Alternatively, the correction section extraction unit 12A may automatically determine the approach waveform, retraction waveform, and cutting waveform in sections such as G0 and G1 of the machining program.

[0037] When diagnosing machining, the correction section extraction unit 12A extracts machining data for the correction section (at least one of the approach section and the retraction section) from the machining data acquired by the machining data acquisition unit 10. Specifically, the correction section extraction unit 12A extracts the waveform of the machining data (base load) for the correction section from the waveform of the machining data (physical quantity) based on the type of machining. That is, based on the approach waveform, the correction section extraction unit 12A extracts the waveform of the machining data for the approach section from the machining data, and based on the retraction waveform, it extracts the waveform of the machining data for the retraction section from the machining data.

[0038] The machining data for the correction section extracted by the correction section extraction unit 12A is data from when the tool is not in contact with the workpiece, and therefore is independent of machining dimensions and machining time. The correction section extraction unit 12A transmits the machining type and the extracted machining data for the approach section and retraction section to the feature calculation unit 13.

[0039] When diagnosing machining, the cutting section extraction unit 12B extracts machining data for the cutting section from the machining data acquired by the machining data acquisition unit 10. Specifically, the cutting section extraction unit 12B extracts the waveform of the machining data (actual cutting load) for the cutting section from the waveform of the machining data based on the type of machining. In other words, the cutting section extraction unit 12B extracts the waveform of the machining data for the cutting section from the machining data based on the cutting waveform.

[0040] The machining data for the machining section extracted by the machining section extraction unit 12B is data obtained when the tool is in contact with the workpiece, and therefore depends on the machining dimensions and machining time. The machining section extraction unit 12B transmits the machining type and the machining data for the extracted machining section to the feature calculation unit 13.

[0041] The diagnostic system 1 may extract machining data for the correction section and the cutting section by any method. For example, the diagnostic system 1 may extract machining data for the correction section and the cutting section from the machining data based on a machining program that includes NC control commands. In this case, the correction section extraction unit 12A determines the approach section and the retraction section based on the machining program and extracts machining data for the approach section and the retraction section from the machining data. The cutting section extraction unit 12B determines the cutting section based on the machining program and extracts machining data for the cutting section from the machining data.

[0042] For example, if the numerical control command is G0, it can be determined that it is a movement section in which no machining is performed, and if it is G1 or G2, it can be determined that it is a section that includes machining performed at a constant speed. Therefore, the correction section extraction unit 12A may use the G0 section as the correction section, and the cutting section extraction unit 12B may use the G1 or G2 section as the cutting section.

[0043] The feature calculation unit 13 calculates the feature quantities of the correction section from the machining data of the correction section and the feature quantities of the cutting section from the machining data of the cutting section. The feature calculation unit 13 calculates the feature quantities of the correction section from the machining data of at least one of the approach section and the retraction section. For example, the feature calculation unit 13 calculates the average value of the feature quantities calculated from the machining data of the approach section and the feature quantities calculated from the machining data of the retraction section as the feature quantities of the correction section. The feature quantities of the correction section are feature quantities used to correct the feature quantities of the cutting section.

[0044] Features are, for example, statistical values ​​for a single machining operation. Examples of features include the mean, maximum, minimum, integral, median, range (difference between the maximum and minimum values), and at least one of these standard deviations of the machining data. The integral is the value obtained by integrating the feature over time. Therefore, the feature of a cutting section is the value obtained by integrating the machining data over the time of the cutting section. Similarly, the feature of an approach section is the value obtained by integrating the machining data over the time of the approach section, and the feature of a retreat section is the value obtained by integrating the machining data over the time of the retreat section.

[0045] In the following, we may describe cases where the correction interval is either an approach interval or a retreat interval, but the correction interval is at least one of the approach interval and the retreat interval. The feature calculation unit 13 transmits the calculated features to the corrected feature calculation unit 14 and the change trend calculation unit 15.

[0046] The corrected feature calculation unit 14 calculates the actual feature (actual feature) corresponding to the cutting process for the tool currently in use, based on the feature of the cutting section and the feature of the correction section. The feature of the cutting section is the first feature, the feature of the correction section is the second feature, and the actual feature is the third feature.

[0047] The corrected feature calculation unit 14 calculates actual feature quantities corresponding to the actual cutting process by performing various calculations on the feature quantities of the correction section and the feature quantities of the cutting section. For example, the corrected feature calculation unit 14 calculates actual feature quantities by subtracting the feature quantities of the correction section from the feature quantities of the cutting section. That is, the corrected feature calculation unit 14 corrects the actual feature quantities of the cutting section by subtracting feature quantities that do not depend on the cutting dimensions (cutting time) (features of the approach section or retraction section) from the feature quantities of the cutting section. Therefore, the actual feature quantities calculated by the corrected feature calculation unit 14 are feature quantities obtained by correcting the feature quantities of the cutting section using the feature quantities of the correction section.

[0048] The corrected feature calculation unit 14 may calculate the actual feature quantity by a process other than subtraction. Furthermore, if the feature quantity is an integral value, the corrected feature calculation unit 14 calculates the actual feature quantity by subtraction according to the ratio of the correction interval time to the cutting interval time. The process for calculating the actual feature quantity when the feature quantity is an integral value will be described later.

[0049] When a diagnostic model is generated for diagnosing the machining state, tool wear state, etc., the corrected feature calculation unit 14 transmits the machining type and actual features to the learning unit 16. Furthermore, after the diagnostic model is generated, when the machining state, tool wear state, etc. are actually diagnosed, the corrected feature calculation unit 14 associates the machining type and actual features and transmits them to the trend data storage unit 22 and the machining diagnosis unit 17.

[0050] The change trend calculation unit 15 calculates the change trend (amount of change, rate of change, etc.) of feature quantities from the past to the present for each type of machining. Details of the change trend of feature quantities will be described later. The change trend calculation unit 15 calculates the change trend of feature quantities based on multiple machining data acquired over multiple machining intervals (for example, 10 machining intervals) in which machining was performed under the same machining conditions from past machining to present machining. Here, one machining interval corresponds to the machining of one workpiece (one machining operation). In other words, one machining interval includes one cutting machining interval.

[0051] The machining section here may be the combined section of the correction section and the cutting section, or it may be the cutting section only. In other words, the machining section may be the section where the cutting section and the correction section can be distinguished, or it may be the section where they cannot be distinguished.

[0052] The following describes the case where the processing interval used by the change trend calculation unit 15 to calculate the change trend of the feature quantity is a cutting processing interval, but the processing interval may include a correction interval and a cutting processing interval. The change trend calculation unit 15 associates the processing type with the change trend of the feature quantity and stores it in the trend data storage unit 22.

[0053] The trend data storage unit 22 receives and stores the actual feature quantities for each processing type from the corrected feature quantity calculation unit 14. The trend data storage unit 22 stores the changes in the actual feature quantities for each processing type by receiving and storing the actual feature quantities for each processing step from the corrected feature quantity calculation unit 14. The trend data storage unit 22 stores the changes in the new actual feature quantities each time the tool is changed.

[0054] Furthermore, the trend data storage unit 22 receives and stores the change trends of feature quantities for each type of machining from the change trend calculation unit 15. The information stored in the trend data storage unit 22 is used by the machining diagnosis unit 17 when diagnosing the machining state and the wear state of the tool.

[0055] The learning unit 16 generates a diagnostic model for each type of machining based on past real-world features. The diagnostic model is a model that diagnoses the machining state and tool wear state based on the real-world features. For example, the diagnostic model is a model that determines whether or not the real-world features exceed a threshold (threshold determination model). In this case, the diagnostic model is provided with upper and lower thresholds for the real-world features through learning. The upper threshold is the first threshold, and the lower threshold is the second threshold.

[0056] The upper threshold is a threshold value for real-world features, such as the motor drive current value, used to determine whether or not to replace the tool. The tool is replaced when it is worn down and the real-world features exceed the upper threshold. The lower threshold is a threshold value for real-world features used to determine whether or not the tool is in an abnormal state (e.g., broken). The tool is replaced when it is in an abnormal state and the real-world features fall below the lower threshold.

[0057] Note that the upper and lower thresholds of the diagnostic model are not necessarily generated through learning. The upper and lower thresholds of the diagnostic model can also be set by the user.

[0058] Furthermore, the diagnostic model may predict tool life based on the changes in actual features of the tool currently in use. That is, the diagnostic model may predict tool life as the wear state of the tool. In this case, the diagnostic model calculates a regression line based on the changes in actual features of multiple machining operations using the tool currently in use, and predicts tool life based on the calculated regression line and an upper threshold. Alternatively, the diagnostic model may predict tool life based on the changes in actual features (current value and rate of increase, etc.) and the upper threshold of the diagnostic model.

[0059] The learning unit 16 learns the upper and lower thresholds of the diagnostic model by learning the changes in past real features, and generates a diagnostic model. The learning unit 16 learns the upper and lower thresholds using methods such as multiple regression analysis, decision trees, and random forests.

[0060] The learning unit 16 excludes from learning real feature trends where the upward trend of the real feature differs from that of other real features in the past. That is, the learning unit 16 learns upper and lower thresholds based on the trends of real features where the upward trend of the real feature is normal (for example, real features where the average value of the rate of increase is within the standard range) in the past. In addition, the learning unit 16 excludes from learning real feature trends where the real feature when a tool is replaced due to tool wear is below the standard value.

[0061] The learning unit 16 learns upper and lower thresholds based, for example, on the actual features when a tool is replaced with a new one and the actual features when a tool is replaced due to tool wear. The learning unit 16 sets the minimum value of the actual features when a tool is replaced with a new one as the lower threshold. The learning unit 16 also sets the maximum value of the actual features when a tool is replaced with a new one due to tool wear as the upper threshold. Note that the learning process by the learning unit 16 described here is just one example, and the learning unit 16 may learn the upper and lower thresholds by any method.

[0062] Furthermore, the learning unit 16 may learn the rate of increase or amount of increase per processing of the actual features. For example, the learning unit 16 sets the maximum rate of increase as the upper limit threshold for the rate of increase in a normal progression of the actual features where the upward trend of the actual features is normal, and sets the minimum rate of increase as the lower limit threshold for the rate of increase in a normal progression of the actual features.

[0063] Furthermore, the learning unit 16 sets the maximum increase in the actual feature quantity as the upper limit threshold when the upward trend of the actual feature quantity is normal, and sets the minimum increase in the actual feature quantity as the lower limit threshold when the upward trend of the actual feature quantity is normal.

[0064] The learning unit 16 sets upper and lower threshold values ​​for each type of machining in the diagnostic model, and stores the set diagnostic models in the diagnostic model storage unit 23. The learning unit 16 and the diagnostic model storage unit 23 may be implemented on an external device or CNC machine separate from the diagnostic system 1.

[0065] The learning unit 16 may learn the approach section before cutting, the cutting section, and the retraction section after cutting based on the waveforms of the actual features. In this case, the learning unit 16 sets the average value of the waveforms of multiple actual features as the reference waveform of the actual features, and sets the approach section before cutting, the cutting section, and the retraction section after cutting based on the reference waveform.

[0066] The processing diagnostic unit 17 reads a diagnostic model corresponding to the processing type from the diagnostic model storage unit 23. The processing diagnostic unit 17 also receives the processing type and actual features from the corrected feature calculation unit 14. The processing diagnostic unit 17 also reads the trend of the actual features corresponding to the processing type and the trend of changes in the features corresponding to the processing type from the trend data storage unit 22.

[0067] The machining diagnostic unit 17 diagnoses the machining state and tool wear state based on the diagnostic model and actual features, and diagnoses the machining state based on the trend of changes in the features.

[0068] The machining diagnosis unit 17 diagnoses tool life, machining conditions (e.g., machining abnormalities), etc., based on statistical quantities using the features stored in the trend data storage unit 22 as the population, and the actual features calculated by the corrected feature calculation unit 14.

[0069] The machining diagnostic unit 17 determines the tool wear status by, for example, applying the actual feature quantities received from the corrected feature quantity calculation unit 14 to the diagnostic model. The machining diagnostic unit 17 determines that the tool is worn and needs to be replaced if the current actual feature quantities exceed the upper threshold of the diagnostic model.

[0070] Furthermore, the machining diagnostic unit 17 determines that the tool is in an abnormal state (e.g., tool breakage) and therefore needs to be replaced if the current actual feature quantity falls below the lower threshold of the diagnostic model. Thus, the upper threshold of the diagnostic model is used for diagnosing tool wear, and the lower threshold of the diagnostic model is used for diagnosing abnormal tool conditions. The upper threshold of the diagnostic model may also be used to detect a decrease in cutting amount due to errors in workpiece coordinate or tool correction.

[0071] Furthermore, the machining diagnostic unit 17 may predict the lifespan of the tool currently in use by applying the trends of the actual features stored in the trend data storage unit 22 to the diagnostic model. In this case, the diagnostic model calculates a regression line or a curve-fit curve and predicts the lifespan of the tool currently in use based on the trend shown by the calculated regression line or curve-fit curve. As an indicator of the lifespan of the tool currently in use, the machining diagnostic unit 17 predicts, for example, how many more machining operations it will take for the actual features to exceed an upper threshold.

[0072] Alternatively, the machining diagnostic unit 17 may determine the machining state by applying the changes in the actual features stored in the trend data storage unit 22 to a diagnostic model. In this case, the diagnostic model determines that the machining state is abnormal when the amount of change, rate of change, etc., of the actual features change rapidly (exceeds a baseline value). For example, the diagnostic model determines that the machining state is abnormal when the amount of change in the actual features of the tool currently in use exceeds a threshold set for the amount of change of those actual features.

[0073] Furthermore, the processing diagnosis unit 17 diagnoses the processing state based on the trend of changes in the feature quantities stored in the trend data storage unit 22. For example, the processing diagnosis unit 17 determines that the processing state is abnormal if the trend of changes in the feature quantities rises sharply or the variability increases. For example, the processing diagnosis unit 17 determines whether the processing state is abnormal based on a regression line obtained from the trend of changes in the feature quantities received from the trend data storage unit 22.

[0074] The processing diagnostic unit 17 may estimate the cause of an abnormal processing state based on the trend of change (waveform) of the feature quantities received from the trend data storage unit 22. In this case, the processing diagnostic unit 17 stores the correspondence between the trend of change (waveform) of the feature quantities and the cause of the abnormality when this trend occurs. The processing diagnostic unit 17 identifies the cause of the abnormality based on this correspondence and the trend of change of the feature quantities.

[0075] The processing diagnostic unit 17 determines, for example, that the cause of the abnormality corresponding to the processing state with the largest correlation coefficient between the change trend of the stored feature quantity and the change trend of the received feature quantity is the cause of the current abnormality.

[0076] The machining diagnostic unit 17 transmits the diagnostic result to the diagnostic result output unit 18. If the diagnostic result indicates an abnormal machining condition or tool wear condition (replacement timing), the diagnostic result output unit 18 transmits the diagnostic result to an external device or machine tool 2. As a result, the machine tool 2 performs an action based on the diagnostic result. For example, if the diagnostic result output unit 18 transmits information identifying the tool and a diagnostic result indicating that this tool needs to be replaced to the machine tool 2, the machine tool 2 replaces the tool based on the information identifying the tool.

[0077] Furthermore, if the diagnostic results show a rapid change in the actual feature quantities or the trend of change in the feature quantities (for example, a rapid increase), the diagnostic result output unit 18 provides feedback control to the machine tool 2 by outputting an operation control command to mitigate the machining operation.

[0078] For example, if the actual feature quantity shows a higher value than usual, the diagnostic result output unit 18 provides feedback control to the machine tool 2 by outputting an operation control command to slow down the machining operation.

[0079] The diagnostic result output unit 18 may also transmit the diagnostic results to a display device (not shown) and have the diagnostic results displayed on the display device.

[0080] Next, the operation of each component in the diagnostic system 1 will be described. Figure 4 is a flowchart showing the processing procedure of the diagnostic system according to the embodiment. After air cutting and actual machining have been performed for each machining type in advance, the learning unit 16 of the diagnostic system 1 generates a diagnostic model for each machining type based on the actual features. Alternatively, the learning unit 16 of the diagnostic system 1 may generate a diagnostic model for each machining type based on the actual features after G0, G1, or G2, etc., of the control command for the machining to be diagnosed has been executed.

[0081] After this, when the machine tool 2 starts actual machining, the machining data acquisition unit 10 acquires machining data and machining information from the machine tool 2 (step S10). Based on the machining information, the machining data acquisition unit 10 identifies the type of machining (step S20).

[0082] The interval extraction unit 11 extracts intervals from the machining data (step S30). Specifically, the correction interval extraction unit 12A extracts correction intervals from the machining data for each machining type (for each diagnostic model). In addition, the cutting machining interval extraction unit 12B extracts cutting machining intervals from the machining data for each machining type.

[0083] The feature calculation unit 13 calculates the feature quantities of the correction section (step S40). For example, the feature calculation unit 13 calculates the feature quantities of the approach section or the tool retraction section as the feature quantities of the correction section.

[0084] Furthermore, the feature calculation unit 13 calculates the feature quantities of the cutting section (step S50). Note that the diagnostic system 1 may execute the processes of step S40 and step S50 in any order.

[0085] The corrected feature calculation unit 14 calculates actual feature quantities based on the feature quantities of the cutting section and the feature quantities of the correction section (step S60). If the feature quantities are the mean, maximum, minimum, median, or integral of the machining data, the corrected feature calculation unit 14 calculates actual feature quantities by subtracting the feature quantities of the correction section from the feature quantities of the cutting section. In other words, the corrected feature calculation unit 14 calculates actual feature quantities with factors other than machining removed by subtracting the feature quantities of the approach section or retraction section (features that do not depend on machining dimensions, etc.) from the feature quantities of the cutting section.

[0086] Furthermore, if the feature is the integral value of the processed data, the corrected feature calculation unit 14 calculates the actual feature using the following equation (1).

[0087]

number

[0088] In other words, if the feature is the integral value of the machining data, the corrected feature calculation unit 14 calculates the integral value of the approach section by integrating the spindle load, such as the motor drive current value of the approach section, over the time of the approach section. The corrected feature calculation unit 14 also calculates the integral value of the cutting section by integrating the spindle load, such as the motor drive current value of the cutting section, over the time of the cutting section. The corrected feature calculation unit 14 multiplies or divides the integral value of the approach section by a value corresponding to the ratio of the length of the approach section to the length of the cutting section. The corrected feature calculation unit 14 calculates the actual feature by subtracting the result of the multiplication or division operation from the integral value of the cutting section, thereby removing factors other than cutting.

[0089] Thus, when the feature is the integral value of the machining data, the corrected feature calculation unit 14 performs a subtraction operation according to the ratio of the length of the approach section and the length of the cutting section. In equation (1) above, the integral value of the approach section is multiplied by the value obtained by dividing the length of the cutting section by the length of the approach section, but the integral value of the retraction section may be multiplied by the value obtained by dividing the length of the cutting section by the length of the retraction section. That is, the corrected feature calculation unit 14 may calculate the integral value of the retraction section by integrating the spindle load of the retraction section over the time of the retraction section.

[0090] Furthermore, if the feature quantities are the range values ​​or standard deviations of the machining data, they are not affected by fluctuations in the spindle load during the approach and tool retraction sections, so the corrected feature quantity calculation unit 14 uses the feature quantities in the cutting section as they are.

[0091] The machining diagnostic unit 17 determines the tool wear status based on the actual feature quantities for each machining type calculated by the corrected feature quantity calculation unit 14 (step S70). In other words, the machining diagnostic unit 17 performs tool wear diagnosis based on the actual feature quantities.

[0092] Furthermore, after the feature quantities for the cutting section or correction section have been calculated, the change trend calculation unit 15 calculates the change trend (change amount, etc.) of the feature quantities for each type of machining (step S65). The machining diagnosis unit 17 determines the machining state based on the change trend of the feature quantities for each type of machining calculated by the change trend calculation unit 15 (step S75).

[0093] In this way, the machining diagnostic unit 17 performs tool wear diagnosis based on actual feature quantities and performs machining anomaly diagnosis based on the trend of change in feature quantities. The diagnostic system 1 may perform the series of processes in steps S65 and S75 before or after the series of processes in steps S60 and S70. The diagnostic system 1 may also perform the series of processes in steps S65 and S75 and the series of processes in steps S60 and S70 in parallel.

[0094] The machining diagnostic unit 17 transmits the diagnostic result to the diagnostic result output unit 18. The diagnostic result output unit 18 then outputs the diagnostic result to the machine tool 2 or an external device such as a display device (step S80). The diagnostic result output unit 18 outputs, for example, an alarm indicating that a tool needs to be changed. The diagnostic result output unit 18 also outputs, for example, an alarm indicating that the machining condition is abnormal.

[0095] The diagnostic result output unit 18 provides feedback control to the machine tool 2 by outputting an operation control command to slow down the machining operation if, for example, the actual feature quantity shows a higher value than usual. For example, when the workpiece material is expensive or when high-precision machining is required, it may be desirable to perform accurate machining even if it means increasing the machining time. In this case, when the feature quantity increases, the diagnostic system 1 reduces the load on the tool by lowering the tool feed rate and reducing the amount of material removed per unit time. As a result, the diagnostic system 1 can prevent the occurrence of machining defects and reduce losses due to defective products and the effort required for rework after defective products are produced.

[0096] Figure 5 is a diagram illustrating the process by which the diagnostic system according to the embodiment calculates real features using the integrated values ​​of machining data. In the graph shown in Figure 5, the horizontal axis represents time, and the vertical axis represents the spindle load (motor drive current value, etc.). Figure 5 shows the spindle load waveform Wm shown in Figure 3, the length L2 of the approach section IN2, the length L3 of the actual machining section IN3, and the length L4 of the retraction section IN4.

[0097] A single machining process Px includes an approach section IN2, an actual machining section IN3, and a retraction section IN4. When the feature is the integral value of the machining data, the feature differs depending on the length of the section. Therefore, the corrected feature calculation unit 14 performs a subtraction operation using equation (1) or the like, according to the ratio of the length L2 of the approach section IN2 and the length L3 of the actual machining section IN3. The corrected feature calculation unit 14 may also use the length L4 of the retraction section IN4 instead of the length L2 of the approach section IN2.

[0098] Figure 6 is a diagram illustrating the process by which the diagnostic system according to the embodiment determines the machining state and tool wear state based on feature quantities. In the graph shown in Figure 6, the horizontal axis represents the number of machining operations, and the vertical axis represents the actual feature quantities.

[0099] In other words, in the graphs from Figure 6 onward, numerical values ​​such as actual features are plotted for each machining operation, including the cutting section, to generate the graph.

[0100] Diagnostic system 1 calculates actual feature quantities for each machining operation. As machining is repeated, the tool wears down, and the actual feature quantities increase. Figure 6 shows a graph plotting machining data for each operation, for example, the average machining load for each operation.

[0101] The machining diagnostic unit 17 determines that the tool is worn and needs to be replaced if the actual feature quantity exceeds the upper threshold Uth. Figure 6 shows the case where, at time T1, the actual feature quantity X1 exceeds the upper threshold Uth, and at time T2, the actual feature quantity X2 exceeds the upper threshold Uth. If the machining diagnostic unit 17 determines that the tool needs to be replaced, the user replaces the tool with a new one. That is, after the actual feature quantities X1 and X2 exceed the upper threshold Uth, the tool is replaced with a new one. As a result, the average value of the cutting resistance becomes the value when the tool is new.

[0102] Furthermore, the machining diagnostic unit 17 may determine that a tool change is imminent if the difference between the actual feature quantity and the upper threshold Uth falls below a reference value. In this case, the difference between the actual feature quantity and the upper threshold Uth is displayed on a display device or the like. Based on this, the user may either change the tool to a new one or continue machining. Note that Figure 6 shows a case where a tool change is performed even when it is determined that a tool change is imminent. Figure 6 shows a case where the tool has been changed twice before time T1.

[0103] Furthermore, the machining diagnostic unit 17 determines the machining state using the actual feature quantity and the lower threshold Lth. Specifically, the machining diagnostic unit 17 determines that the tool is in an abnormal state, such as broken, and therefore the tool needs to be replaced, when the actual feature quantity falls below the lower threshold Lth of the diagnostic model. Figure 6 shows the case where the actual feature quantity X3 falls below the lower threshold Lth at time T3.

[0104] Furthermore, the machining diagnostic unit 17 predicts the lifespan of the tool currently in use based on the changes in the actual feature quantity. For example, the machining diagnostic unit 17 predicts the lifespan of the tool (information indicating how many more machining operations it will take for the actual feature quantity to exceed the upper threshold Uth) based on the difference between the actual feature quantity and the upper threshold Uth, and the amount or rate of increase in the actual feature quantity per operation.

[0105] Furthermore, the processing diagnosis unit 17 diagnoses the processing status based on the trend of changes in the feature quantities stored in the trend data storage unit 22. An example of a method for determining the processing status is described below.

[0106] Figure 7 illustrates a first processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of change in the actual feature quantities. Figure 8 illustrates a second processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of change in the actual feature quantities. Figure 9 illustrates a third processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of change in the actual feature quantities. Figure 10 illustrates a fourth processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of change in the actual feature quantities. Figure 11 illustrates a fifth processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of change in the actual feature quantities. Figure 12 illustrates a sixth processing example in which the diagnostic system according to the embodiment determines the processing state based on the trend of change in the actual feature quantities.

[0107] In the graphs shown in Figures 7 to 12, the horizontal axis represents the number of processing steps, and the vertical axis represents the actual feature quantities. The processing diagnostic unit 17 of the diagnostic system 1 calculates the trend of change in the actual feature quantities over multiple processing steps (for example, 10 processing intervals) from past processing steps to the current processing step, and determines the processing status based on the calculated trend of change in the actual feature quantities.

[0108] If there is no change in the processing state, the values ​​of the actual features will not change significantly in the preceding and succeeding processing cycles or multiple intervals, or the actual features will show a stable upward or downward trend. On the other hand, if there is a change in the processing state as shown below, the processing load changes, and a change appears in the trend of change of the actual features. This results in a unique point of change in the trend of change of the actual features.

[0109] For example, machine tool 2 may experience changes in actual features related to the tool state, changes in actual features related to the workpiece state, changes in actual features related to the machining environment, and changes in actual features caused by the operation.

[0110] The graphs in Figures 7 to 10 show the changes in actual features related to the tool condition, and the graph in Figure 11 shows the changes in actual features related to the workpiece condition. Figure 7 shows the changes in actual features when the cutting volume decreases due to minute chipping of the tool tip at time T4.

[0111] Figure 8 shows the changes in real features when the tool is damaged and the cutting volume changes due to the formation or detachment of a built-up edge at time T5. A built-up edge is a portion of the cutting edge where molten material from the workpiece adheres to and solidifies. A built-up edge is formed on the tool when molten material from the workpiece adheres to the cutting edge, and the built-up edge detaches from the tool when this material separates from the tool.

[0112] When a built-up edge is formed and detaches, the cutting volume decreases after the detachment, and then the cutting volume rapidly increases due to tool damage, causing the actual feature quantity to change.

[0113] Figure 9 shows the changes in real-world features when the cutting resistance fluctuates significantly with each machining operation due to tool degradation.

[0114] Figure 10 shows the change in real features when the change in cutting resistance increases significantly due to the peeling of the tool's coating. This illustrates that the cutting resistance increases sharply when the tool's coating peels off.

[0115] Figure 11 shows the changes in actual feature quantities when the cutting resistance changes due to a change in the material hardness or material shape of the workpiece in the preceding process or pre-processing at time T8.

[0116] Here, the pre-processing refers to the processes involved in forming the workpiece, such as casting or forging, while pre-machining refers to the processing performed before the workpiece is cut, such as rough machining. For example, if the material lot of the workpiece is changed, the material hardness or shape of the workpiece changes, and the cutting resistance changes suddenly, causing the actual characteristic quantities to change.

[0117] Figure 12 shows a graph of the case where the cutting resistance suddenly increases at time T9 due to a change in the machining environment. For example, if the discharge pressure or discharge volume of the coolant decreases, if the discharge of the coolant stops, or if the direction of the coolant discharge changes, the cutting resistance will suddenly increase, causing the actual characteristic quantity to change.

[0118] Furthermore, changes caused by the work process can also alter the cutting volume or cutting resistance. For example, if tool compensation (coordinate correction based on the tool's length or diameter) is performed improperly, the cutting volume will increase sharply due to changes caused by the work process. In this case, the graph will be similar to that shown in Figure 12.

[0119] As shown in Figures 7 to 12, even when the machining condition is abnormal, the change in the machining condition is often not such that it significantly exceeds the upper threshold Uth. For example, as shown in Figure 7, when a minute tool defect occurs, the spindle load due to cutting decreases relatively because the actual feature quantity (cutting volume) decreases, but the change in the actual feature quantity is small. Therefore, in order to detect small changes in the actual feature quantity, the machining diagnostic unit 17 may calculate the standard deviation of the actual feature quantity in multiple machining sections in which machining was performed under the same machining conditions, and determine the machining condition based on the standard deviation of the change from the past.

[0120] Figure 13 is a diagram illustrating a first processing example in which the diagnostic system according to the embodiment determines the processing state based on actual feature quantities. In the first processing example, the diagnostic system 1 determines the processing state based on the amount of change (standard deviation) of the actual feature quantities.

[0121] The graph on the left in Figure 13, GR1, is the same graph as in Figure 7, showing the changes in actual features. The graph in the center of Figure 13, GR2, is a graph that shows multiple processing intervals (for example, 10 processing intervals) that are subject to abnormal processing status judgment from graph GR1 as processing interval D1. The graph on the right in Figure 13, GR3, is a graph that shows the change in actual features (standard deviation) from graph GR2. In graph GR3 in Figure 13, the horizontal axis is the number of processing steps, and the vertical axis is the standard deviation. Graph GR3 shows the standard deviation for a certain number of processing steps, including past processing steps, for the entire processing interval.

[0122] The processing diagnostic unit 17 calculates the change in actual features for each of the multiple processing intervals, and in order to do so, it calculates the standard deviation of the actual features. This allows the trend of change in the standard deviation, as shown in graph GR3, to be calculated in relation to the change in features in graph GR2. The processing diagnostic unit 17 highlights small changes in actual features by calculating the standard deviation of a specific number of processing steps (for example, 10 processing steps) from past processing steps to the current processing step for each processing step. The processing diagnostic unit 17 determines the processing state based on the standard deviation of the actual features in the multiple processing intervals D1, thereby excluding sudden changes in actual features (such as false detections).

[0123] When the processing is normal, the change in the actual feature is stable. In other words, when the processing is normal, the difference (change) between the actual feature from the previous processing step and the actual feature from the current processing step does not fluctuate significantly and remains stable.

[0124] When the processing diagnostic unit 17 calculates the standard deviation for processing interval D1, for example, the standard deviation St for processing interval D1 stands out more than the standard deviations of other intervals, as shown in graph GR3. In other words, the change in the standard deviation is greater than the change in the actual features when the processing state is abnormal. For example, when processing interval D1 is defined as the Xth (X is a natural number)th processing, the processing diagnostic unit 17 calculates the standard deviation of the actual features from the most recent Xth processing to the (X-9th)th processing. When the (X+1)th processing is completed, the processing diagnostic unit 17 calculates the standard deviation of the actual features from the (X+1)th processing to the (X-8th)th processing.

[0125] The machining diagnostic unit 17 determines that the machining state of the machining section D1 from which the standard deviation was calculated is abnormal if the calculated standard deviation of the machining section D1 is greater than or equal to the standard deviation threshold Th. The machining diagnostic unit 17 sets a threshold Th based on, for example, the trend of change in the standard deviation, and detects the abnormal state based on the threshold Th. Note that the threshold Th may be set by the user.

[0126] Thus, the machining diagnostic unit 17 determines the machining state based on the standard deviation of actual feature quantities in multiple machining sections where machining is performed under the same machining conditions. This allows it to determine the machining state based on more pronounced changes than when determining the machining state based on actual feature quantities, as explained in Figure 7. Therefore, the machining diagnostic unit 17 can determine the machining state more easily and accurately by determining the machining state based on the standard deviation of actual feature quantities in multiple machining sections where machining is performed under the same machining conditions.

[0127] Next, a second processing example in which the diagnostic system 1 determines the processing state based on actual features will be described. In the second processing example, the diagnostic system 1 determines the processing state based on the variability of the actual features from the regression line.

[0128] The processing diagnostic unit 17 calculates a regression line (regression equation) of the actual features of multiple processing intervals (for example, 10 processing intervals) from past processing to the current processing, and calculates the variability (standard deviation) from the calculated regression line using the following equation (2).

[0129]

number

[0130] In equation (2), St is the variability (standard deviation) from the regression line, and n is the number of processing intervals used to calculate the regression line. Also, x i The features are the nth (n is a natural number) real features from the most recent to the nth (n is a natural number) in the machining section which is the diagnostic interval, X is the value of the corresponding point calculated from the regression equation (x = aN + b), and N is the number of times each tool was used from the most recent to the nth in the machining section. Note that a (regression coefficient) and b (intercept) in the regression equation are values ​​calculated in the diagnostic interval.

[0131] Figure 14 is a diagram illustrating a second processing example in which the diagnostic system according to the embodiment determines the processing state based on actual features. In the graph shown in Figure 14, the horizontal axis represents the number of processing cycles, and the vertical axis represents the actual features.

[0132] Figure 14 shows the trend of the actual features and the regression line Y1 of the actual features in processing interval D2, which is used to determine the processing state. When the actual features show a stable upward trend, the deviation from the regression line Y1 is small, but when the deviation from the regression line Y1 is large, the standard deviation from the regression line Y1 is large.

[0133] The machining diagnostic unit 17 calculates a regression line Y1 from the actual features of machining intervals D2, going back n (where n is a natural number) from the most recent cutting section, and calculates the residuals of the actual features from the regression line Y1 for machining interval D2. Figure 14 shows the case where the residuals for each machining operation in machining interval D2 are calculated. The machining diagnostic unit 17 determines whether the machining state is abnormal or normal based on whether the square root of the residuals from the regression line Y1 of the actual features is above a threshold. In this way, the machining diagnostic unit 17 can capture the trend of change in the actual features to a large extent by calculating the standard deviation from the regression line Y1.

[0134] Figure 15 is a diagram illustrating a third processing example in which the diagnostic system according to the embodiment determines the processing state based on actual features. In the third processing example, the diagnostic system 1 determines the processing state based on the regression line Y1 of the actual features. In the graph shown in Figure 15, the horizontal axis represents the number of processing cycles, and the vertical axis represents the actual features.

[0135] The processing diagnostic unit 17 calculates the regression line Y1 in the third processing example using the same method as in the second processing example. The processing diagnostic unit 17 determines the processing state based on at least one of the trend of change in the slope and the trend of change in the intercept of the calculated regression line Y1.

[0136] The machining diagnostic unit 17 determines, for example, that the machining condition is abnormal if the slope of the regression line Y1 exceeds the reference range. The machining diagnostic unit 17 also determines that the machining condition is abnormal if, for example, the intercept of the regression line Y1 exceeds the reference range.

[0137] The reference range for the slope may be set by the machining diagnostic unit 17 based on past slopes, or it may be set by the user. The machining diagnostic unit 17 sets the reference range for the slope based, for example, on the average value and standard deviation of past slopes.

[0138] Furthermore, the reference range for the intercept may be calculated by the processing diagnostic unit 17 based on past intercepts, or it may be set by the user. The processing diagnostic unit 17 sets the reference range for the intercept based, for example, on the mean value and standard deviation of past intercepts.

[0139] When a tool deteriorates rapidly, the condition of the tool's cutting edge changes significantly with each machining operation, causing large fluctuations in cutting resistance. Figure 16 is a diagram illustrating an example of the changes in actual feature quantities calculated by the diagnostic system according to the embodiment when a tool deteriorates. In the graph shown in Figure 16, the horizontal axis represents the number of machining operations, and the vertical axis represents the actual feature quantities.

[0140] Diagnostic System 1 shows that the cutting resistance fluctuates slightly with each machining operation, depending on the type of machining. In this case, if the tool deteriorates rapidly, the amount of fluctuation in cutting resistance will be larger than before the deterioration. Also, if the tool deteriorates rapidly, the cutting resistance may change from an upward trend to a downward trend. Figure 16 shows a case where, at time T10, the tool deteriorated rapidly, causing the actual feature quantity to change from an upward trend to a downward trend, and the actual feature quantity fluctuated greatly up and down with each machining operation.

[0141] Figure 17 is a diagram illustrating the process by which the diagnostic system according to the embodiment determines the processing status in the second processing example with respect to the graph shown in Figure 16. In the second processing example, the diagnostic system 1 determines the processing status based on the trend of change in the variability (standard deviation) from the regression line of the actual features. In the graph shown in Figure 17, the horizontal axis is the number of processing cycles, and the vertical axis is the standard deviation from the regression line of the actual features. Figure 17 shows the trend of change in the standard deviation from the regression line of the actual features.

[0142] The machining diagnostic unit 17 calculates a regression line for the actual features shown in Figure 16 and calculates the deviation (standard deviation) of the actual features from the regression line. Then, the machining diagnostic unit 17 determines whether the machining state is abnormal or normal based on whether the standard deviation of the actual features from the regression line is greater than or equal to the threshold Th. Figure 17 shows a case where the standard deviation of the actual features from the regression line has increased due to tool deterioration at time T10.

[0143] Figure 18 is a diagram illustrating the first example of the process by which the diagnostic system according to the embodiment determines the processing state in the third processing example with respect to the graph shown in Figure 16. In the first example of the third processing example, the diagnostic system 1 determines the processing state based on the trend of change in the slope of the regression line of the real features. In the graph shown in Figure 18, the horizontal axis is the number of processing cycles, and the vertical axis is the slope of the regression line. Figure 18 shows the trend of change in the slope of the regression line.

[0144] The machining diagnostic unit 17 calculates a regression line for the actual features shown in Figure 16 and calculates the slope of the calculated regression line. For example, if the slope of the regression line exceeds a reference range, the machining diagnostic unit 17 determines that the machining condition is abnormal. Figure 18 shows a case where the slope of the regression line decreases due to tool deterioration, and at time T10, the slope of the regression line falls below the lower limit threshold Th1.

[0145] Figure 19 is a diagram illustrating a second example of the process by which the diagnostic system according to the embodiment determines the processing state in the third processing example with respect to the graph shown in Figure 16. In the second example of the third processing example, the diagnostic system 1 determines the processing state based on the trend of change in the intercept of the regression line of the real features. In the graph shown in Figure 19, the horizontal axis is the number of processing cycles, and the vertical axis is the intercept of the regression line. Figure 19 shows the trend of change in the intercept of the regression line.

[0146] The machining diagnostic unit 17 calculates a regression line for the actual features shown in Figure 16 and calculates the intercept of the calculated regression line. For example, if the intercept of the regression line exceeds the reference range, the machining diagnostic unit 17 determines that the machining condition is abnormal. Figure 19 shows a case where the intercept of the regression line rises due to tool deterioration, and at time T10 it exceeds the upper threshold Th2 of the intercept of the regression line. Figure 19 shows a case where the intercept of the regression line rises due to tool deterioration at time T10.

[0147] While it is difficult to detect anomalies in the trend of changes in the actual features shown in the graph in Figure 16, the diagnostic system 1 can easily determine the processing state and easily detect anomalies by using one of the methods described in Figures 17 to 19.

[0148] Figure 20 is a diagram illustrating the spindle load data used by the comparative example's diagnostic system. In the graph shown in Figure 20, the horizontal axis represents time, and the vertical axis represents the spindle load. The comparative example's diagnostic system calculates feature quantities based on the spindle load (such as the motor drive current value), which includes influences other than those caused by actual machining, and diagnoses the tool wear state based on these feature quantities. In the case of the comparative example's diagnostic system, physical quantities such as the motor drive current value may change due to temperature changes, deterioration, etc., of the machine tool 2. The following three factors can be cited as causes of changes in physical quantities. (Factor F1) Increase or decrease in operating resistance (such as bearing friction resistance) or sliding resistance due to temperature changes in the machine tool 2 or motor. (Factor F2) Increase or decrease in operating resistance or sliding resistance due to maintenance or replacement of parts of machine tool 2. (Factor F3) Increase or decrease in rotational resistance or rotational force due to the length of the bar material in an automatic lathe.

[0149] Sliding resistance is the dynamic friction that occurs when, for example, a ball screw or an LM (Linear Motion) guide rotates or moves back and forth. Bar material is a long, round bar-shaped workpiece, and after one cutting process, the machined portion is cut off and the next cutting process is performed. In the case of bar material, since the machined portion is cut off, the length decreases as the number of cutting processes increases, and the rotational resistance or rotational force during machining changes.

[0150] Figure 20 shows the waveform W1 of the spindle load under normal conditions and the waveform W2 when the spindle load increases due to factors other than machining. For example, if machine tool 2 is not warmed up and machining is started in a cold state, machining data such as the spindle load may increase overall, resulting in waveform W2, as shown in Figure 20. In this case, the diagnostic system of the comparative example will calculate feature quantities based on the increased machining data. Therefore, the diagnostic system of the comparative example will calculate unique feature quantities that differ from those during normal continuous operation, and will determine the tool wear state, etc., based on these unique feature quantities.

[0151] Thus, in the comparative example, when the machining data is affected by factors other than machining, the diagnostic system determines the tool wear condition based on the feature quantities in which the increase or decrease is reflected. Therefore, it may not be able to accurately determine the tool wear condition.

[0152] Figure 21 is a diagram illustrating the features used by the diagnostic system of the comparative example. In the graph shown in Figure 21, the horizontal axis represents the number of machining operations, and the vertical axis represents the actual features. When tool breakage or significant machining abnormalities occur, the features change significantly, and the features exceed the upper threshold Uth or lower threshold Lth, allowing the diagnostic system of the comparative example to detect abnormalities in the machining state. However, for minor tool defects or machining abnormalities where the machining state changes only slightly, as shown in data d1 to d3 in Figure 21, the features do not exceed the upper threshold Uth or lower threshold Lth, and the diagnostic system of the comparative example could not detect abnormalities in the machining state.

[0153] On the other hand, since the diagnostic system 1 determines the machining state based on the trend of changes in feature quantities, it can also detect machining anomalies such as tool defects or slight changes in the machining state.

[0154] Figure 22 is a diagram illustrating the timing of tool replacement when the diagnostic system according to the embodiment determines the wear state of the tool. In Figure 22, the timing of tool replacement when the diagnostic system 1 determines the wear state of the tool is shown, and the timing of tool replacement when the diagnostic system of the comparative example determines the wear state of the tool. In Figure 22, the horizontal axis represents the number of machining operations, and the vertical axis represents the actual feature quantity.

[0155] The diagnostic system in the comparative example calculates feature quantities based on motor drive current values ​​and other factors that include variations unrelated to actual machining. As mentioned above, feature quantities may fluctuate due to factors unrelated to actual machining, such as sliding resistance. In this case, even under normal machining conditions, the diagnostic system in the comparative example may mistakenly diagnose a sudden increase or decrease in feature quantities as an abnormality.

[0156] The diagnostic system 1 of this embodiment automatically identifies the actual machining section IN3, extracts only the change in feature quantities due to the actual machining, and calculates the actual feature quantities by removing the change that is not related to machining. Therefore, the change in actual feature quantities calculated by the diagnostic system 1 of this embodiment can be said to be an accurate change due to the actual machining. As a result, even when the change in the actual feature quantities calculated in cutting is small, the diagnostic system 1 of this embodiment can capture minute changes due to the actual machining, and can easily detect abnormalities in the tool wear state and machining state.

[0157] The diagnostic system in the comparative example determines the timing of tool replacement based on, for example, the number of machining operations (50 in Figure 22). Therefore, in reality, tools may be replaced even if they are not at the end of their lifespan, or tools may not be replaced even if they have exceeded their lifespan.

[0158] On the other hand, the diagnostic system 1 of the embodiment can accurately determine the tool wear state based on actual features. This allows the user to replace the tool at an appropriate time according to the tool wear state. For example, if the upward trend of the actual features due to tool wear is gradual, the diagnostic system 1 of the embodiment can perform more machining operations than the number of machining operations (50) specified by the diagnostic system of the comparative example, thus reducing the cost associated with tool replacement. Figure 22 shows the case where the diagnostic system 1 of the embodiment replaces the tool after 70 machining operations when the progression of tool wear is gradual (C1).

[0159] Furthermore, in the comparative example's diagnostic system, if the tool deteriorated or wore rapidly, the tool was not replaced, resulting in machining defects. On the other hand, the diagnostic system 1 of the embodiment can replace the tool regardless of the number of machining operations if the tool deteriorates or wears rapidly, thus preventing machining defects caused by deterioration or wear. In addition, the diagnostic system 1 of the embodiment can detect the occurrence of sudden machining defects, thus preventing defective products from being shipped. Figure 22 shows the case where the diagnostic system 1 of the embodiment replaced the tool after 35 machining operations when the tool deteriorated or wore rapidly (C2).

[0160] In this way, the diagnostic system 1 can reduce the likelihood of misdiagnosing and detecting machining while it is being overshadowed by other factors (such as sliding friction resistance) by removing elements unrelated to the actual cutting load from the machining data, and can also reduce misdiagnosis and misdetection caused by other factors.

[0161] As a result, the diagnostic system 1 can stabilize process quality through 100% workpiece diagnosis, preventing the occurrence of defective products and preventing defective products from being shipped. Therefore, the diagnostic system 1 can eliminate processes such as visual inspection, sampling inspection, and image inspection, thereby reducing man-hours.

[0162] The diagnostic system 1 may be implemented on a single computer, or on multiple networked computers or CNC machines. Here, we will describe the hardware configuration of the diagnostic system 1 when it is implemented on a single computer.

[0163] The diagnostic system 1 is implemented by a processing circuit. The processing circuit may be a processor and memory that execute a program stored in memory, or it may be dedicated hardware.

[0164] Figure 23 is a diagram showing an example of the configuration of a processing circuit when the processing circuit of the diagnostic system according to the embodiment is realized with a processor and memory. The processing circuit 90 shown in Figure 23 comprises a processor 91 and memory 92. When the processing circuit 90 is composed of a processor 91 and memory 92, each function of the processing circuit 90 is realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a diagnostic program and stored in memory 92. In the processing circuit 90, each function is realized by the processor 91 reading and executing the diagnostic program stored in memory 92. In other words, the processing circuit 90 includes memory 92 for storing a diagnostic program that will ultimately be executed as a result of the processing of the diagnostic system 1. This diagnostic program can also be said to be a program that causes the diagnostic system 1 to execute each function realized by the processing circuit 90. This diagnostic program may be provided on a computer-readable recording medium on which the diagnostic program is recorded, or it may be provided by other means such as a communication medium.

[0165] The diagnostic program described above can also be described as a program that causes the diagnostic system 1 to execute the processes in steps S10 to S80 of Figure 4. Here, the processor 91 is, for example, a CPU (Central Processing Unit), processing unit, arithmetic unit, microprocessor, microcomputer, or DSP (Digital Signal Processor). The memory 92 is, for example, a non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable ROM), EEPROM (Registered Trademark) (Electrically EPROM), magnetic disk, flexible disk, optical disk, compact disk, minidisc, or DVD (Digital Versatile Disc).

[0166] Figure 24 shows an example of the configuration of a processing circuit when the processing circuit of the diagnostic system according to the embodiment is configured with dedicated hardware. The processing circuit 93 shown in Figure 24 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. The processing circuit 93 may be partially implemented with dedicated hardware and partially implemented with software or firmware. In this way, the processing circuit 93 can realize each of the above functions with dedicated hardware, software, firmware, or a combination thereof.

[0167] As described above, the diagnostic system 1 of this embodiment calculates actual feature quantities corresponding to the actual cutting load, which is the load of the cutting process, by subtracting the feature quantities in the correction section from the feature quantities in the cutting section, and performs a machining diagnosis based on these actual feature quantities. As a result, the diagnostic system 1 can perform a machining diagnosis based on actual feature quantities corresponding to the actual cutting load during cutting, with factors other than machining, such as cold working conditions, removed. Therefore, the diagnostic system 1 can achieve a highly accurate machining diagnosis even when the change in the feature quantities of the machining data calculated from the machining data during cutting is small.

[0168] Furthermore, the diagnostic system 1 extracts the cutting section and correction section based on the processing data obtained when air cutting and actual processing have been performed in advance, so it can accurately extract the cutting section and correction section.

[0169] Furthermore, the diagnostic system 1 calculates the trend of changes in the feature quantities of machining data from the past to the present, and performs machining diagnosis based on the calculated trend of changes. As a result, the diagnostic system 1 can achieve highly accurate machining diagnosis even when the changes in the feature quantities of machining data calculated from the machining data are small in cutting processes.

[0170] Furthermore, since the diagnostic system 1 determines the machining status by the machine tool 2 based on the standard deviation of the trend of change, it can achieve highly accurate machining diagnosis even when the changes in the feature quantities of the machining data are even smaller.

[0171] Furthermore, since the diagnostic system 1 determines the machining state by the machine tool 2 based on the regression line of the change trend, it can achieve highly accurate machining diagnosis even when the changes in the feature quantities of the machining data are even smaller.

[0172] The configurations shown in the above embodiments are merely examples, and can be combined with other known technologies. It is also possible to omit or modify parts of the configuration without departing from the gist of the invention. [Explanation of Symbols]

[0173] 1 Diagnostic system, 2 Machine tool, 10 Machining data acquisition unit, 11 Interval extraction unit, 12A Correction interval extraction unit, 12B Cutting interval extraction unit, 13 Feature calculation unit, 14 Corrected feature calculation unit, 15 Change trend calculation unit, 16 Learning unit, 17 Machining diagnostic unit, 18 Diagnostic result output unit, 22 Trend data storage unit, 23 Diagnostic model storage unit, 90, 93 Processing circuit, 91 Processor, 92 Memory, d1~d3 Data, D1, D2 Machining interval, F1~F3 Factor, GR1~GR3 Graph, IN1 Acceleration interval, IN2 Approach interval, IN3 Actual machining interval, IN4 Retreat interval, IN5 Deceleration period, L2~L4 Length, Lb Base load, Lc Actual cutting load, Lth Lower threshold, Rm, W1, W2, Wm Waveform, St Standard deviation, T1, T2, T3, T4, T5, T8, T9, T10 time, Th threshold, Uth upper threshold, X1~X3 actual features, Y1 regression line.

Claims

1. A machining data acquisition unit that acquires multiple machining data from a machine tool for multiple machining operations performed under the same machining conditions from past machining operations to the present machining operation, A feature calculation unit that calculates feature quantities of the processing data from the processing data, A change trend calculation unit that calculates the change trend of the aforementioned feature quantities, A machining diagnostic unit that performs machining diagnostics based on the aforementioned trend of change, Equipped with, A diagnostic system characterized by the following features.

2. The machining diagnostic unit determines the machining state by the machine tool based on the change trend and the threshold of the change trend. The diagnostic system according to feature 1.

3. The machining diagnostic unit determines the machining state by the machine tool based on the standard deviation of the change trend. The diagnostic system according to feature 1.

4. The machining diagnostic unit determines the machining state by the machine tool based on the regression line of the change trend. The diagnostic system according to feature 1.

5. The system further includes a diagnostic result output unit that outputs the diagnostic results of the machining diagnosis to an external device or the machine tool. A diagnostic system according to any one of claims 1 to 4.

6. The diagnostic result output unit provides feedback control of the machine tool by outputting an operation control command corresponding to the diagnostic result to the machine tool. The diagnostic system according to claim 5, characterized in that it is the same as described in claim 5.

7. A diagnostic system for diagnosing machining by a machine tool includes a machining data acquisition step which involves acquiring multiple machining data from the machine tool for multiple machining operations performed under the same machining conditions from past machining operations to the present machining operation, The diagnostic system includes a feature calculation step of calculating feature quantities from the processing data, The diagnostic system includes a change trend calculation step for calculating the change trend of the feature quantity, The diagnostic system includes a machining diagnostic step in which it performs a machining diagnostic based on the trend of change, including, A diagnostic method characterized by the following features.

8. A machining data acquisition step involves acquiring multiple machining data from a machine tool for multiple machining operations performed under the same machining conditions from past machining operations to the present machining operation. A feature calculation step of calculating the feature quantities of the processed data from the processed data, A change trend calculation step for calculating the change trend of the aforementioned feature quantities, A machining diagnosis step in which a machining diagnosis is performed based on the aforementioned trend of change, Make the computer execute it. A diagnostic program characterized by the following features.

Images