JP7412655B1 - Abnormality determination device, abnormality determination system, and abnormality determination method - Google Patents

Abstract

The abnormality determination device includes an operator input unit (11) that receives from an operator a correction value set for a tool operation specified in a machining program used by the machine tool as a current correction value, and an operator input unit (11) that is set in the machine tool. A setting information comparison unit (33) that compares the current correction value and the past correction value that was set for the tool operation when machining was properly executed in the past; An abnormality detection unit (34) detects an abnormality in the current correction value based on the correction value difference that is the difference between the current correction value and the abnormality detection unit (34). It includes a display control section (22) that causes a display device (23) to display information indicating that it is appropriate.

Description

The present disclosure relates to an abnormality determination device, an abnormality determination system, and an abnormality determination method that determine whether a correction value set in a machine tool is abnormal.

A machine tool processes a workpiece while correcting the position of the tool. The machine tool performs machining while correcting the position of the tool based on the correction amount of the tool position input by the operator. Therefore, it is desirable that the correction amount input by the operator be an appropriate correction amount.

The control device for a machine tool described in Patent Document 1 corrects the movement amount of a tool based on a correction amount input by an operator, and stores the input correction amount, correction timing, and operator ID as history data. There is. Then, when the stored operator ID is selected, the control device of the machine tool automatically corrects the movement amount of the tool using the correction amount and correction timing corresponding to this operator ID, and executes machining.

Japanese Patent Application Publication No. 2018-163541

However, in the technology of Patent Document 1, since the correction value is predicted using an approximate formula and automatically corrected, the inappropriate correction value predicted by the approximate formula is adopted, and the automatic correction is performed using the inappropriate correction value. There is a problem in that there is a high possibility that machining will be performed.

The present disclosure has been made in view of the above, and an object of the present disclosure is to obtain an abnormality determination device that can perform processing while reducing the possibility of correction using an inappropriate correction value.

In order to solve the above-mentioned problems and achieve the purpose, an abnormality determination device of the present disclosure allows an operator to use a correction value set for the operation of a tool specified in a machining program used by a machine tool as a current correction value. The operator input section received from and a setting information comparison unit that calculates a correction value difference that is a difference between the correction value and a past correction value . Further, the abnormality determination device of the present disclosure determines that the current correction value is inappropriate when the correction value difference is greater than or equal to the difference threshold, which is a threshold for the correction value difference, and the abnormality determination device of the present disclosure determines that the current correction value is inappropriate. If it is small, the abnormality detection unit detects an abnormality in the current correction value by determining that the current correction value is appropriate, and if the abnormality detection unit detects an abnormality, it determines that the current correction value is inappropriate. and a display control unit that causes the display device to display information indicating that there is a certain fact.

The abnormality determination device according to the present disclosure has the effect of being able to perform processing while reducing the possibility of being corrected with an inappropriate correction value.

A diagram showing the configuration of an abnormality determination system according to an embodiment Flowchart showing the processing procedure of the process executed by the abnormality determination system according to the embodiment A diagram showing an example of a hardware configuration for realizing a machine tool according to an embodiment.

Below, an abnormality determination device, an abnormality determination system, and an abnormality determination method according to embodiments of the present disclosure will be described in detail based on the drawings.

Embodiment.
FIG. 1 is a diagram showing the configuration of an abnormality determination system according to an embodiment. The abnormality determination system 1 includes a machine tool 10 and a server 30. The abnormality determination system 1 determines the correction value set for the tool etc. before the machine tool 10 starts machining, and if there is a setting error, an appropriate correction value candidate (reset candidate value ) and an alarm (fault detection system).

The machine tool 10 includes an operator input section 11, a machining program operation section 12, a machining inference section 13, a setting information storage section 14, a learned model storage section 21, a display control section 22, and a display device 23. have.

The server 30 includes a configuration information acquisition section 31, a configuration information storage section 32, a configuration information comparison section 33, an anomaly detection section 34, a data acquisition section 41, and a model generation section 42. Of the server 30, the data acquisition unit 41 and the model generation unit 42 are learning devices.

Among the components included in the abnormality determination system 1 , at least one of the learned model storage section 21 and the display control section 22 may be arranged outside the machine tool 10 . At least one of the trained model storage unit 21 and the display control unit 22 may be located within the server 30, for example.

Among the components included in the abnormality determination system 1 , at least one of the data acquisition unit 41 and the model generation unit 42 may be located outside the server 30 . At least one of the data acquisition unit 41 and the model generation unit 42 may be placed within the machine tool 10, for example.

The operator input unit 11 receives data input by an operator. The operator input unit 11 receives, for example, processing setting information, difference threshold values, etc. input by an operator. The machining process setting information input by the operator includes machining program information, correction information, and tool numbers (tool identification information).

The information on the machining program is, for example, a program number (program identification information). The program number is information that identifies the machining program. FIG. 1 shows a case where the operator input unit 11 receives a program number as information on a machining program. Note that the program number may be any information as long as it identifies a machining program for machining the workpiece.

The correction information is information in which a correction number (correction identification information) and a correction value are associated with each other. The correction value is, for example, a value set for the tool operation defined in the machining program, for correcting the tool operation. The correction number is information that identifies the correction item corresponding to the correction value. Note that the correction number may be any information as long as it identifies the correction item corresponding to the correction value. For example, when the correction item is the amount of tool movement, "001" or the like is set as the correction number. In this case, in the correction information, "001" is associated with a correction value for the tool movement amount specified in the machining program. The tool number is information that identifies the tool. Note that the tool number may be any information as long as it identifies the tool.

The difference threshold is a threshold for the difference between an appropriate correction value used in the past (hereinafter sometimes referred to as past correction value) and the currently set correction value (hereinafter sometimes referred to as current correction value). be.

Note that the setting information may include information other than the program number as information on the machining program. The information on the machining program may include, for example, a time stamp, shape information, machining command information (for example, M code, G code), and the like. The time stamp is information indicating the date and time when the processing program was created, and the shape information is information indicating the shape of the product produced by the processing program. Note that the information included in the machining program information is not limited to the above information. The information on the machining program only needs to include at least one of a program number, a time stamp, and shape information.

In this way, the setting information includes correction values and machining program information. Further, the setting information may include at least one of a correction number and a tool number. The machine tool 10 processes various workpieces using various machining programs and various setting information. In this embodiment, a case will be described in which the setting information input by the operator is a program number, correction information, and tool number.

Operator input section 11 sends the program number, correction information, and tool number to machining program operating section 12 . That is, the operator input unit 11 sends setting information for machining processing to the machining program operation unit 12.

Further, the operator input unit 11 stores the difference threshold value in the setting information storage unit 14. Further, the operator input unit 11 sends the difference threshold value to the abnormality detection unit 34 of the server 30. Note that in FIG. 1, illustration of a connection line connecting the operator input section 11 and the abnormality detection section 34 is omitted.

The machining program operating unit 12 receives setting information including a program number, correction information, and tool number from the operator input unit 11. The machining program operation unit 12 sends setting information in which the program number, correction information, and tool number are associated with each other to the machining inference unit 13. Further, the machining program operation section 12 sends setting information in which the program number, correction information, and tool number are associated with each other to the setting information comparison section 33 of the server 30. The setting information that the machining program operation section 12 sends to the machining inference section 13 and the setting information comparison section 33 is the setting information currently set in the machine tool 10 (hereinafter sometimes referred to as current setting information).

The trained model storage unit 21 stores the trained model generated by the model generation unit 42 of the server 30. The learned model means that the machining process performed using the current correction value (hereinafter referred to as the current machining process) is different from the normal machining process performed using the past correction value (hereinafter referred to as past machining process). This is a function for inferring whether or not the processing is the same as the processing (sometimes referred to as processing). The learned model is used to determine whether the current processing and the past processing are the same processing.

The same machining process is executed using the same machining program and the same tool in the current and past, and the past correction value used in the normal machining process executed in the past and the current correction value. This is processing in which the difference between the

The machining inference unit 13 receives current setting information from the machining program operating unit 12 and reads the learned model from the learned model storage unit 21. The machining inference unit 13 inputs the current setting information into the learned model to infer whether the current machining process to be executed from now on and the past machining process are the same machining process.

If the processing inference section 13 determines that the current processing and the past processing are not the same processing, the processing inference section 13 sends this determination result to the display control section 22 . Further, when the processing inference unit 13 determines that the current processing and the past processing are the same processing, the processing inference unit 13 stores the current setting information in the setting information storage unit 14. That is, the machining inference section 13 causes the setting information storage section 14 to store the program number, correction information, and tool number.

The setting information storage section 14 stores processing success/failure information, current setting information sent from the processing inference section 13, and difference thresholds sent from the operator input section 11. The machining success/failure information is information indicating whether the currently executed machining process is normal machining or abnormal machining. Processing success/failure information is determined based on the shape of the finished product produced by the current processing.

When the display control unit 22 receives information from the processing inference unit 13 indicating that the current processing and the past processing are not the same processing, the display control unit 22 distinguishes between the current processing and the past processing. Information indicating that comparison is not possible is displayed on the display device 23.

Further, when information indicating that the setting information (correction value) is inappropriate is sent from the server 30, the display control unit 22 displays an alarm indicating that the correction value is inappropriate on the display device 23. let Further, when a correction value candidate (resetting candidate value) included in the setting information is sent from the server 30, the display control unit 22 causes the display device 23 to display the resetting candidate value. Further, when information indicating that the correction value is appropriate is sent from the server 30, the display control unit 22 causes the display device 23 to display information indicating that the correction value is appropriate.

The setting information acquisition unit 31 reads the current setting information and the difference threshold from the setting information storage unit 14 and stores them in the setting information storage unit 32 when the current processing process is executed. Furthermore, when the setting information storage section 14 stores the processing success/failure information, the setting information acquisition section 31 reads the processing success/failure information from the setting information storage section 14 . That is, the setting information acquisition unit 31 reads the processing success/failure information from the setting information storage unit 14 after the current processing process is completed. The setting information acquisition section 31 stores the read processing success/failure information in the setting information storage section 32 in association with the current setting information and the difference threshold stored in the setting information storage section 14 . Note that the setting information storage unit 14 may transmit the processing success/failure information, the current setting information, and the difference threshold to the setting information acquisition unit 31.

The setting information storage unit 32 has a collection database that stores collected data, and stores processing success/failure information, setting information, and difference threshold values in association with each other in this collection database. The setting information stored in the setting information storage section 32 is past setting information. In this way, the setting information is current setting information before the processing is completed, and becomes past setting information when associated with the processing success/failure information after the processing is completed. Note that the past setting information does not need to include the difference threshold.

The setting information comparison unit 33 receives current setting information in which a program number, correction information, and tool number are associated with each other from the machining program operating unit 12. Note that the setting information comparison unit 33 may read the current setting information from the setting information storage unit 14 or may receive the current setting information from the setting information storage unit 14.

Further, the setting information comparing section 33 reads out from the setting information storage section 32 past setting information having the same program number and tool number as the program number and tool number included in the current setting information. Note that the setting information comparison section 33 may read a plurality of pieces of past setting information from the setting information storage section 32.

The setting information comparison unit 33 compares current setting information and past setting information. Specifically, the setting information comparison unit 33 compares the correction value of the correction information included in the current setting information and the correction value of the correction information included in the past setting information. Note that, when a plurality of past correction values are read out, the setting information comparison unit 33 compares the average value of the plurality of past correction values and the current correction value. Further, the setting information comparison unit 33 may compare the mode or median value of a plurality of past correction values with the current correction value.

The setting information comparison unit 33 calculates the difference (hereinafter sometimes referred to as correction value difference) between the correction value of the correction information included in the current setting information and the correction value of the correction information included in the past setting information. , and sends the correction value difference to the abnormality detection section 34.

The abnormality detection unit 34 determines whether the current setting information (correction value) is an appropriate value based on the correction value difference sent from the setting information comparison unit 33 and the difference threshold sent from the operator input unit 11. Determine whether it exists or not. The abnormality detection unit 34 determines that the current correction value is inappropriate when the correction value difference is greater than or equal to the difference threshold, and determines that the current correction value is inappropriate when the correction value difference is smaller than the difference threshold. It is determined that there is.

When the abnormality detection unit 34 determines that the current correction value is appropriate, it sends information indicating that the current correction value is appropriate to the display control unit 22. If the abnormality detection unit 34 determines that the current correction value is inappropriate, it sends information (alarm) indicating that the current correction value is inappropriate to the display control unit 22.

Further, when the abnormality detection unit 34 determines that the current correction value is inappropriate, the abnormality detection unit 34 acquires from the setting information comparison unit 33 the past correction value that the setting information comparison unit 33 used for comparison. That is, the abnormality detection unit 34 acquires, from the setting information comparison unit 33, a past correction value that is compared with the current correction value that has been determined to be inappropriate, among the past correction values. The abnormality detection unit 34 determines a resetting candidate value that is an appropriate correction value candidate based on the acquired past correction value. For example, the abnormality detection unit 34 determines the average value of the acquired past correction values as the resetting candidate value. That is, the abnormality detection unit 34 determines the average value of the past correction values compared with the current correction value determined to be inappropriate among the past correction values as the resetting candidate value. The abnormality detection unit 34 sends the determined resetting candidate value to the display control unit 22.

The data acquisition unit 41 acquires setting information including information on a machining program, a tool, and a correction value when machining is performed normally, as learning data. The learning data is data in which a program number, a tool number, and correction information are associated with each other when machining is performed normally. The data acquisition unit 41 acquires learning data from the setting information storage unit 32, for example.

The data acquisition unit 41 acquires learning data when the process is successfully processed, based on the processing success/failure information registered in the setting information storage unit 32. Note that the data acquisition unit 41 may acquire the learning data from the machine tool 10. The data acquisition unit 41 sends learning data including setting information to the model generation unit 42 .

The model generation unit 42 uses the learning data to generate a learned model for inferring whether the current processing is the same processing as a processing that was successfully processed in the past. The learned model is used to determine whether the current processing and the past processing are the same processing. The model generation unit 42 stores the generated trained model in the trained model storage unit 21.

Note that the abnormality determination system 1 may be configured with one device, or may be configured with three or more devices. For example, the abnormality determination system 1 may be an abnormality determination device including components of the machine tool 10 and components of the server 30. When the abnormality determination system 1 is an abnormality determination device including components of the machine tool 10 and components of the server 30, the abnormality determination device includes, for example, an operator input section 11, a machining inference section 13, and a setting It includes an information storage section 32, a setting information comparison section 33, an abnormality detection section 34, and a display control section 22. Further, the abnormality determination device may include a machining program operating section 12.

FIG. 2 is a flowchart showing the processing procedure of the process executed by the abnormality determination system according to the embodiment. Note that the input/output device shown in FIG. 2 is a device that receives information input by an operator or a device that provides information to the operator. The input/output devices here are the operator input section 11 and the display device 23 of the machine tool 10.

The setting information acquisition unit 31 of the server 30 acquires the setting information, the difference threshold, and the processing success/failure information from the setting information storage unit 14. The setting information storage unit 32 stores machining success/failure information, difference threshold values, and setting information in association with each other.

The data acquisition unit 41 acquires the setting information when it is processed normally as learning data (step S101). That is, the data acquisition unit 41 acquires, as learning data, the setting information in which the processing success/failure information indicates that the processing was normal. The data acquisition unit 41 acquires learning data from, for example, the setting information storage unit 32 and sends it to the model generation unit 42 .

The setting information of the learning data includes, for example, a program number, a tool number, and correction information (correction number and correction value). Note that the information included in the setting information of the learning data is not limited to the information described above.

The model generation unit 42 generates a learned model using the learning data (step S102), and sends it to the machine tool 10. Specifically, the model generation unit 42 calculates whether the current machining process is past or not based on learning data that is created based on a combination of the program number, tool number, and correction information when machining is performed normally. Learn whether the processing is the same as the processing of . That is, the model generation unit 42 generates a learned model that infers whether the current machining process is the same as the past machining process from the setting information when the machine tool 10 normally processes the machine tool 10. .

Note that the model generation unit 42 may learn whether the current machining process is the same machining process as the past machining process, according to learning data created for the plurality of machine tools 10. . Further, the model generation unit 42 may acquire learning data from a plurality of machine tools 10 used in the same area, or may acquire learning data collected from a plurality of machine tools 10 operating independently in different areas. You may also obtain data for Even when learning data is acquired from a plurality of machine tools 10, the model generation unit 42 uses the same process as when acquiring learning data from one machine tool 10 to match the current machining process to the past machining process. Learn whether the processing is the same or not.

Further, the machine tool 10 on which learning data is collected may be added to the collection target midway through, or may be excluded from the collection target. Furthermore, the learning device (data acquisition unit 41 and model generation unit 42) that has learned whether or not the current machining process is the same as the past machining process for a certain machine tool 10 is transferred to a different machine tool. 10, the learned model may be updated by relearning whether the current machining process is the same as the past machining process for the other machine tool 10. The machine tool 10 stores the learned model in the learned model storage unit 21 (step S103).

When machining is started in the machine tool 10, the operator input unit 11 receives current setting information and a difference threshold input by the operator (step S104). The timing at which the operator inputs the current setting information and the difference threshold value into the operator input section 11 may be, for example, the timing at which the machining program is set (before the cycle starts), but is not limited to this timing. The difference threshold may be, for example, an allowable value for the difference when comparing a past correction value and a current correction value, but is not limited to this allowable value.

The operator input unit 11 sends the received current setting information and difference threshold to the server 30 (step S105). Specifically, the operator input section 11 sends the current setting information to the setting information comparison section 33 via the machining program operation section 12, and sends the difference threshold value corresponding to the current setting information to the abnormality detection section 34. Thereby, the server 30 acquires the current setting information and the difference threshold (step S106).

Further, the operator input unit 11 sends setting information to the machining inference unit 13 via the machining program operation unit 12. The machining inference unit 13 receives current setting information from the machining program operating unit 12 and reads the learned model from the learned model storage unit 21. The machining inference unit 13 inputs the current setting information into the learned model to determine the current machining process (the contents currently set in the machine tool 10) and the past machining process (the contents set in the machine tool 10 in the past). It is determined whether or not the contents (contents that were previously processed) are the same processing (step S107).

The processing inference unit 13 uses the trained model stored in the trained model storage unit 21 to infer the identity of the processing by unsupervised learning. That is, the processing inference unit 13 infers to which cluster the setting information belongs by inputting the setting information input by the operator to the learned model. In other words, the machining inference unit 13 infers which past machining process the current machining process corresponding to the setting information input by the operator corresponds to.

In the present embodiment, a case has been described in which the processing inference unit 13 infers whether the processing is the same as the past processing using the learned model learned by the model generation unit 42 of the server 30. The machining inference unit 13 may acquire a learned model from outside, such as another machine tool 10, and infer whether or not the machining process is the same as the past machining process based on this learned model.

Furthermore, in this embodiment, a case has been described in which the machining inference unit 13, which is an inference device, is arranged in the machine tool 10, but the inference device is connected to the machine tool 10 via a network, for example. It may be a separate device from the machine tool 10.

Further, in this embodiment, a case has been described in which the data acquisition unit 41 and model generation unit 42, which are learning devices, are arranged in the server 30, but the learning device may be built in the machine tool 10. Further, the learning device may be, for example, a device separate from the server 30 and connected to the server 30 via a network. Furthermore, both the learning device and the reasoning device may reside on the server 30.

If the processing inference unit 13 determines that the current processing and the past processing are not the same processing (step S<b>107 , No), the processing inference unit 13 sends this determination result to the display control unit 22 . The display control unit 22 causes the display device 23 to display information indicating that the current setting information and past setting information cannot be compared (information indicating that comparison is not possible) (step S108). This allows the machine tool 10 to notify the operator that the current correction value and past correction values cannot be compared.

On the other hand, when the processing inference unit 13 determines that the current processing and the past processing are the same processing (step S107, Yes), the processing inference unit 13 stores the current setting information in the setting information storage unit 14. . Further, the setting information acquisition unit 31 reads the current setting information from the setting information storage unit 14 and stores it in the setting information storage unit 32.

The setting information comparison unit 33 receives current setting information in which a program number, correction information, and tool number are associated with each other from the machining program operating unit 12. Further, the setting information comparison unit 33 reads out past correction information having the same program number and tool number as the program number and tool number included in the current setting information from the setting information storage unit 32.

The setting information comparison unit 33 compares the current setting information and the setting information accumulated in the past (step S109). Specifically, the setting information comparison unit 33 compares the correction value of the correction information included in the current setting information and the correction value of the correction information included in the past setting information.

Note that the setting information comparison unit 33 may compare setting information not only between the same machine tools 10 but also between different machine tools 10. That is, the setting information comparison unit 33 may compare the current setting information with setting information set in the past on another machine tool 10 different from the machine tool 10 to which the current setting information is set. .

The setting information comparison unit 33 calculates a correction value difference, which is the difference between the correction value of the correction information included in the current setting information and the correction value of the correction information included in the past setting information, and determines whether the correction value difference is abnormal. It is sent to the detection unit 34.

The abnormality detection section 34 determines whether the current setting information (correction value) is an abnormal value based on the correction value difference sent from the setting information comparison section 33 and the difference threshold sent from the operator input section 11. It is determined whether there is one (step S110).

For example, if the correction value difference is greater than or equal to the difference threshold, the abnormality detection unit 34 determines that the current correction value is a setting abnormality, and if the correction value difference is smaller than the difference threshold, the current correction value is It is determined that the setting value is normal. Further, the abnormality detection unit 34 determines that the correction value difference is normal if it is less than a specific ratio (for example, half) of the difference threshold, and that it is possible that the difference is abnormal if it is more than half of the difference threshold and smaller than the difference threshold. If the difference is equal to or greater than the difference threshold value, it can be determined that there is an abnormality.

If the abnormality detection unit 34 determines that the current correction value is appropriate (step S110, no problem), it sends information indicating that the current correction value is appropriate to the display control unit 22. Thereby, the display control unit 22 causes the display device 23 to display information indicating that the correction value is appropriate. Then, the machine tool 10 enters a state in which it can accept a machining start instruction, that is, a cycle start instruction.

On the other hand, if the abnormality detection unit 34 determines that the current correction value is inappropriate (step S110, problem exists), it sends an alarm to the display control unit 22 indicating that the current correction value is inappropriate.

Further, when the abnormality detection unit 34 determines that the current correction value is inappropriate, the abnormality detection unit 34 compares the past correction values (correction values accumulated in the past) used for comparison by the setting information comparison unit 33 with the setting information comparison unit 34. 33. The abnormality detection unit 34 calculates a resetting candidate value based on the acquired correction values accumulated in the past (step S111).

Note that the correction values accumulated in the past used by the abnormality detection unit 34 are not limited to correction values used in the same machine tool 10, but also correction values used in another machine tool 10 different from the one to which the current correction value is set. The correction value used in the machine tool 10 may be used.

The abnormality detection unit 34 sends the determined resetting candidate value to the display control unit 22. The abnormality detection unit 34 sends, for example, the average value of correction values accumulated in the past to the display control unit 22 as a reset candidate value. Further, the abnormality detection section 34 may send the range of normal correction values accumulated in the past to the display control section 22 as resetting candidate values. Further, the abnormality detection unit 34 may send a reset candidate value expressed in a histogram to the display control unit 22, taking into consideration the frequency with which it is used as a normal correction value. That is, the abnormality detection unit 34 may send a histogram including information on the frequency of use of past correction values used as normal correction values to the display control unit 22 as a resetting candidate value.

The display control unit 22 of the machine tool 10 outputs an alarm indicating that the correction value is inappropriate and a reset candidate value to the display device 23 (step S112). Thereby, the display device 23 displays the alarm and the reset candidate value on the display device 23. The display device 23 may display the reset candidate values in a list, may display them as a histogram, or may display the reset candidate value (modest value) that has been used the most. After the reset candidate values are displayed, the machine tool 10 is in a state where it can accept correction values from the operator.

The operator input unit 11 receives the correction value input by the operator (step S113). That is, the operator input unit 11 receives a problem solution (revised correction value) input by the operator based on the alarm and reset candidate value displayed on the machine tool 10.

Note that even if the abnormality detection unit 34 determines that the current correction value is inappropriate, the machine tool 10 may use the current correction value. That is, the machine tool 10 may use the corrected correction value input by the operator, or may use the original correction value as is. When the machine tool 10 receives the correction value, it enters a state in which it can accept a machining start instruction, that is, a cycle start instruction.

When a cycle start instruction is input by the operator, the operator input unit 11 receives the cycle start instruction (step S114). The operator input unit 11 receives a cycle start instruction, for example, when a cycle start button for instructing the start of machining is pressed. Thereby, the machine tool 10 starts machining (cycle start) using the input correction value (step S115).

When the machine tool 10 completes machining, the shape of the finished product is measured, and the success or failure of completion is determined. The machine tool 10 receives machining success/failure information, which is a success/failure determination result, and stores it in the setting information storage section 14 . The machine tool 10 stores setting information and machining success/failure information in association with each other in the setting information storage unit 14 . As a result, the setting information stored in the setting information storage section 14 becomes past setting information.

The setting information acquisition unit 31 reads past setting information, difference thresholds, and processing success/failure information from the setting information storage unit 14 . The setting information acquisition unit 31 stores past setting information, difference thresholds, and processing success/failure information in the setting information storage unit 32. As a result, past setting information, difference threshold values, and processing success/failure information are accumulated in the setting information storage section 32.

Note that the setting information acquisition unit 31 stores the current setting information in the setting information storage unit 32 when the current processing process is executed, and sets the processing success/failure information after the current processing process is completed. It may also be stored in the information storage section 32. In this case as well, the setting information acquisition unit 31 stores the setting information, the difference threshold value, and the processing success/failure information in the setting information storage unit 14 in association with each other. The storage of the setting information, the difference threshold value, and the machining success/failure information in the setting information storage unit 14 may be performed periodically at a specific cycle.

Here, the hardware configurations of the machine tool 10 and the server 30 will be explained. Note that since the machine tool 10 and the server 30 have similar hardware configurations, the hardware configuration of the machine tool 10 will be described here.

FIG. 3 is a diagram showing an example of the hardware configuration for realizing the machine tool according to the embodiment. The machine tool 10 can be realized by an input device 300, a processor 100, a memory 200, an output device 400, and a display device 23. An example of the processor 100 is a CPU (Central Processing Unit, also referred to as a central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, or DSP (Digital Signal Processor)) or a system LSI (Large Scale Integration). Examples of the memory 200 are RAM (Random Access Memory) and ROM (Read Only Memory).

The machine tool 10 is realized by the processor 100 reading and executing a computer-executable processing program stored in the memory 200 for executing the operations of the machine tool 10. It can be said that the processing program for executing the operation of the machine tool 10 causes the computer to execute the procedure or method of the machine tool 10.

The processing program executed by the machine tool 10 has a module configuration including a machining program operation section 12, a machining inference section 13, and a display control section 22, and these are loaded onto the main memory. generated on the device.

The processing program executed by the machine tool 10 includes a program that associates program numbers, correction information, and tool numbers, and a program that infers whether the current machining process and the past machining process are the same machining process. It includes a program, a program for displaying various information on the display device 23, and the like.

The input device 300 receives setting information and the like from an operator and sends it to the processor 100. The processing executed by the input device 300 corresponds to the processing executed by the operator input unit 11.

The memory 200 stores setting information, difference thresholds, processing success/failure information, processing programs, and the like. The setting information, the difference threshold, the machining success/failure information, and the processing program are read from the memory 200 by the processor 100. Furthermore, the memory 200 is used as a temporary memory when the processor 100 executes various processes.

The process executed by the output device 400 corresponds to the process in which the machine tool 10 transmits information to the server 30. The output device 400 sends various information such as setting information to the server 30.

The processing program may be provided as a computer program product by being stored in a computer readable storage medium in an installable or executable format file. Further, the processing program may be provided to the machine tool 10 via a network such as the Internet. Note that some of the functions of the machine tool 10 may be realized by dedicated hardware such as a dedicated circuit, and some may be realized by software or firmware.

In this way, the machine tool 10 of the present embodiment determines whether the current machining is the same as the past machining, and if they are the same, the server 30 determines whether the current correction value is abnormal. It makes a judgment, and if there is an abnormality, a reset candidate value and an alarm are displayed. Thereby, the abnormality determination system 1 can notify the operator of a defect in the correction value before starting machining, and can prevent the occurrence of a machining defect from being overlooked.

In addition, since the abnormality determination system 1 uses the learned model to determine whether the current machining is the same as the past machining, the abnormality determination system 1 uses not only the correction value of one machine tool 10 but also the correction value of other machine tools 10. Using the values, it is possible to perform identity determination with even higher accuracy. Moreover, since the abnormality determination system 1 calculates the reset candidate value using the correction values of other machine tools 10, it is possible to provide the operator with a more accurate reset candidate value.

Further, the abnormality determination system 1 determines that there is a possibility of abnormality when the correction value difference is more than half of the difference threshold and smaller than the difference threshold, and notifies the operator. As a result, the abnormality determination system 1 can alert the operator even if it is difficult to automatically determine whether or not it will lead to machining defects, which can lead to suppression of machining defects. .

Further, the abnormality determination system 1 displays a list of resetting candidate values, for example. As a result, the operator can easily grasp the plurality of resetting candidate values, and can easily select an appropriate resetting candidate value from among the plurality of resetting candidate values.

Further, the abnormality determination system 1 displays the resetting candidate values in the form of a histogram, for example. Thereby, the operator can easily grasp the tendency of the reset candidate values and easily select an appropriate reset candidate value.

Further, the abnormality determination system 1 displays, for example, the most frequent value of the reset candidate values. Thereby, it is possible to easily grasp the tendency of the reset candidate values, and it becomes possible to easily select an appropriate reset candidate value.

By selecting an appropriate resetting candidate value, the abnormality determination system 1 can cause the machine tool 10 to perform machining using an appropriate correction value corresponding to the selected appropriate resetting candidate value.

In the abnormality determination system 1 of the present embodiment, the machining inference unit 13 infers whether the current machining process is the same as the past machining process using the learned model. 13 may be inferred based on the comparison result of the program name, program number, tool number, etc. In this case, it becomes possible to easily implement a device for inference.

In this way, the abnormality determination system 1 of the embodiment calculates the difference between the current correction value set in the machine tool 10 and the past correction value set when machining was properly executed in the past. Based on this, abnormalities in the current correction value are detected. When an abnormality is detected, the abnormality determination system 1 causes the display device 23 to display information indicating that the current correction value is inappropriate. Thereby, the abnormality determination system 1 can perform processing while reducing the possibility of being corrected with an inappropriate correction value. In this manner, the abnormality determination system 1 can detect errors in tool settings before starting machining, thereby preventing machining defects.

The configuration shown in the above embodiments is an example, and it is possible to combine it with another known technology, and a part of the configuration can be omitted or changed without departing from the gist. It is possible.

1 abnormality determination system, 10 machine tool, 11 operator input section, 12 machining program operation section, 13 machining inference section, 14 setting information storage section, 21 learned model storage section, 22 display control section, 23 display device, 30 server, 31 setting information acquisition unit, 32 setting information storage unit, 33 setting information comparison unit, 34 abnormality detection unit, 41 data acquisition unit, 42 model generation unit, 100 processor, 200 memory, 300 input device, 400 output device.

Claims (14)

an operator input unit that receives from an operator a correction value set for a tool operation specified in a machining program used by the machine tool as a current correction value;
The current correction value set in the machine tool is compared with the past correction value set in the operation of the tool when machining was properly executed in the past. a setting information comparison unit that calculates a correction value difference that is a difference from the past correction value ;
If the correction value difference is greater than or equal to a difference threshold, which is a threshold for the correction value difference, it is determined that the current correction value is inappropriate; if the correction value difference is smaller than the difference threshold, the current correction value is determined to be inappropriate; an abnormality detection unit that detects an abnormality in the current correction value by determining that the current correction value is appropriate ;
a display control unit that causes a display device to display information indicating that the current correction value is inappropriate when the abnormality detection unit detects an abnormality;
An abnormality determination device comprising: further comprising a machining inference unit that infers whether the current machining process executed by the machine tool using the current correction value is the same machining process as a past machining process that was properly executed in the past;
The setting information comparison unit compares the current correction value and the past correction value when the current processing and the past processing are the same processing,
The display control unit displays information indicating that the current correction value and the past correction value cannot be compared when the current processing and the past processing are not the same processing. let,
The abnormality determination device according to claim 1, characterized in that: When the abnormality detection unit detects the abnormality, the abnormality detection unit determines a resetting candidate value that is an appropriate correction value candidate based on the past correction value compared with the current correction value,
the display control unit displays the resetting candidate value on a display device;
The abnormality determination device according to claim 1, characterized in that: further comprising a setting information storage unit that stores past setting information that is setting information for the machine tool including the past correction value and information on the machining program to which the past correction value was applied,
The setting information comparison unit includes information about the current correction value, information about the machining program to which the current correction value is applied, and information about the tool to which the current correction value is applied. Comparing the current correction value and the past correction value using current setting information that is setting information and the past setting information;
The abnormality determination device according to claim 1, characterized in that: The operator input unit receives a difference threshold that is a threshold for the correction value difference from an operator,
The abnormality detection unit detects the abnormality based on the correction value difference and the difference threshold.
The abnormality determination device according to claim 1, characterized in that: The processing inference unit is configured to infer whether a processing process executed using the current correction value is the same processing process as a normal processing process executed using the past correction value. using the learned model to infer whether the current processing is the same processing as the past processing;
The abnormality determination device according to claim 2, characterized in that: a data acquisition unit that acquires learning data including the past correction values;
a model generation unit that uses the learning data to generate the learned model for inferring whether the current processing is the same as the past processing;
further comprising;
The abnormality determination device according to claim 6, characterized in that: The operator input section, the processing inference section, and the display control section are arranged in the machine tool,
The abnormality determination device according to claim 2, characterized in that: The setting information comparison section and the abnormality detection section are arranged in a server connected to the machine tool,
The abnormality determination device according to claim 1, characterized in that: The information on the machining program to which the past correction value has been applied includes program identification information for identifying the machining program, a time stamp that is information on the date and time when the machining program was created, and information on the machining program created by the machining program. shape information, which is information indicating the shape of the product,
The abnormality determination device according to claim 1, characterized in that: The setting information includes at least one of tool identification information that identifies the tool and correction identification information that identifies a correction item corresponding to the past correction value.
The abnormality determination device according to claim 4, characterized in that: The resetting candidate value includes at least one of an average value of the past correction values, a range of the past correction values, and a histogram including information on frequency of use of the past correction values. ing,
The abnormality determination device according to claim 3, characterized in that: An abnormality determination system comprising the abnormality determination device according to any one of claims 1 to 12. an operator input step in which the abnormality determination device receives from an operator a correction value set for a tool operation specified in a machining program used by the machine tool as a current correction value;
The abnormality determination device compares the current correction value set in the machine tool with a past correction value set in the operation of the tool when machining was properly executed in the past. a setting information comparison step of calculating a correction value difference that is a difference between the current correction value and the past correction value ;
If the correction value difference is greater than or equal to a difference threshold, which is a threshold for the correction value difference, the abnormality determination device determines that the current correction value is inappropriate, and if the correction value difference is greater than the difference threshold. is also small, an abnormality detection step of detecting an abnormality in the current correction value by determining that the current correction value is appropriate ;
a display control step of causing a display device to display information indicating that the current correction value is inappropriate when the abnormality determination device detects an abnormality;
An abnormality determination method characterized by comprising:

Images