Diagnostic apparatus and diagnostic method for machine tools, and diagnostic program

Abstract

To enhance diagnostic precision and minimize implementation of a diagnostic motion.SOLUTION: A diagnosis system 20 includes a first diagnosis unit 21 that uses operation data, which is acquired during normal operation of a machine tool 1, to diagnose whether the machine tool 1 falls under preliminarily classified normalcy or any of plural abnormalities signifying abnormal regions, a second diagnosis unit 22 that, when an abnormal region is not identified even though the first diagnosis unit 21 diagnoses the machine tool as not being normal, causes the machine tool 1 to implement a predetermined diagnostic motion and identifies the abnormal region using acquired diagnostic motion data, and a diagnostic processing update unit 23 that updates the classification of normalcy and / or abnormality signifying an abnormal region, which is made by the first diagnosis unit 21, on the basis of a result of diagnosis conducted by the second diagnosis unit 22.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a diagnostic apparatus, a diagnostic method, and a diagnostic program for diagnosing abnormalities in machine tools.

Background Art

[0002] Unexpected failures in mechanical equipment result in unplanned losses, so it is required to detect signs before the occurrence of failures from the operating state of the mechanical equipment. Also, when detecting signs of a failure, it is necessary to identify the abnormal location that causes the failure in order to eliminate the failure. Patent Document 1 discloses a method of constructing a normal model using state quantities acquired at a time point known to be normal, determining whether the state quantities acquired from a plant at the time of diagnosis are classified into the normal model, displaying that it is normal when classified into the normal model, and displaying that it is in an unknown state when not classified into the normal model. Patent Document 2 discloses a method of diagnosing the presence or absence of an abnormality by performing pattern matching using measurement data of normal or abnormal performance and simulated abnormal data simulating an abnormality in facility equipment generated in consideration of assumed abnormal conditions.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] As a method for acquiring data when performing diagnosis, it can be roughly divided into a method using operations during normal operation performed during a production process such as during the operation of a machining program, and a method using a specific diagnostic operation pattern. In the method using the operations during normal operation, the normal range is set and often diagnosed using data shortly after the manufacture of the product. Therefore, when it deviates from the normal state, there is a problem that it is difficult to determine whether it is a change as an abnormal state due to deterioration of parts or a change that should be regarded as normal, such as a change in the environment or usage conditions. Also, when resetting to the normal state due to no manufacturing defect in the state where the number of years of use has passed, there is a possibility of overlooking a sign of a defect that there is no manufacturing defect but the parts are actually deteriorated. On the other hand, in the method of performing diagnosis using a diagnostic operation pattern, since it can be performed by the operation set by the machine manufacturer, by converting it into an operation pattern that generalizes the characteristics of various models, it becomes easier to collect common usable abnormal state data. Therefore, there is an advantage that the diagnosis accuracy of normal and abnormal is high and the abnormal location can be specified. However, since it is necessary to perform an operation that is not normal operation, there is a problem that if it is performed regularly, there will be a loss of time for diagnosis. This loss of time becomes particularly significant in machine tools that manufacture a variety of products, leading to a decrease in production efficiency.

[0005] Therefore, an object of the present disclosure is to provide a diagnostic apparatus, a diagnostic method, and a diagnostic program for a machine tool that can increase the diagnostic accuracy while minimizing the execution of diagnostic operations and suppressing the occurrence of time loss.

Means for Solving the Problems

[0006] To achieve the above object, a first configuration of the present disclosure is a diagnostic apparatus for diagnosing an abnormality of a machine tool, using the operation data acquired during normal operation of the machine tool, the machine tool diagnoses whether it is any of a plurality of abnormal types pre-classified as normal and , including the abnormal part a first diagnostic unit, even if it is diagnosed as abnormal by the first diagnostic unit, if the Abnormal part cannot be specified, the machine tool is made to perform a predetermined diagnostic operation, and using the acquired diagnostic operation data, the Abnormal parta second diagnostic unit that identifies a diagnostic process update unit that updates the classification of the normal and / or the type of abnormality in the first diagnostic unit based on the diagnostic result by the second diagnostic unit, characterized by comprising: Another aspect of the first configuration is that, in the above configuration, the first diagnostic unit is the normal diagnosis and the Abnormal part When neither the identification of Abnormal part can be executed, calculate the ranking of the relevance between the diagnostic result and each of the The second diagnostic unit identifies the Abnormal part based on the calculated ranking, characterized by doing so. Another aspect of the first configuration is that, in the above configuration, the diagnostic process update unit is the Abnormal part When identified by the second diagnostic unit, update the setting range of the type of the identified abnormality in the first diagnostic unit , including the abnormal part , characterized by doing so. Another aspect of the first configuration is that, in the above configuration, the diagnostic process update unit is the Abnormal part When not identified by the second diagnostic unit, update the normal setting range in the first diagnostic unit, characterized by doing so. To achieve the above object, a second configuration of the present disclosure is a diagnostic method for diagnosing an abnormality of a machine tool, The computer of the machine tool Using the operation data acquired during the normal operation of the machine tool, a first diagnostic step of diagnosing whether the machine tool is any of a pre-classified normal and , including the abnormal part a plurality of types of abnormalities; Even if it is diagnosed as abnormal in the first diagnostic step and the Abnormal part cannot be identified, causing the machine tool to perform a predetermined diagnostic operation, and using the acquired diagnostic operation data to identify the Abnormal part a second diagnostic step; A diagnostic process update step of updating the classification of the normal and / or the type of abnormality in the first diagnostic step based on the diagnostic result by the second diagnostic step, characterized by executing. Another aspect of the second configuration is that, in the above configuration, in the first diagnosis step, when neither the normal diagnosis nor the Abnormal part identification can be performed, the rank of the relevance between the diagnosis result and each of the Abnormal part is calculated, and in the second diagnosis step, based on the calculated rank, the Abnormal part is identified. Another aspect of the second configuration is that, in the above configuration, in the diagnosis process update step, when the Abnormal part is identified by the second diagnosis step, the setting range of the type of the abnormality in the first diagnosis step is updated. , including the abnormal part This is characterized by. Another aspect of the second configuration is that, in the above configuration, in the diagnosis process update step, when the Abnormal part is not identified by the second diagnosis step, the normal setting range in the first diagnosis step is updated. To achieve the above object, a third configuration of the present disclosure is a diagnostic program for a machine tool, characterized in that the control device of the machine tool is caused to execute the diagnostic method of the machine tool according to any one of the second configurations.

Advantages of the Invention

[0007] According to the present disclosure, diagnosis using operation data and diagnosis using diagnostic operation data are used in combination, and the diagnosis using diagnostic operation data is executed only when the Abnormal part cannot be identified by the diagnosis result based on the operation data. Therefore, it is possible to increase the diagnostic accuracy while suppressing the occurrence of time loss by minimizing the implementation of diagnostic operations. Therefore, it is particularly beneficial in machine equipment that manufactures a variety of products.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. FIG. 1 is a block configuration diagram showing an example of a diagnostic device for a machine tool according to a first configuration. The machine tool 1 is controlled by an NC device 10. The NC device 10 includes a program interpretation unit 11 and a machine operation command unit 12. The program interpretation unit 11 interprets a program input by an operator using an input means (not shown) into a spindle rotation command, a feed axis operation command, and an operation command for peripheral devices. The machine operation command unit 12 controls the spindle motor, each feed axis, and peripheral devices based on the commands sent from the program interpretation unit 11. In the diagnostic device 20, based on a diagnostic program according to a third configuration input to the NC device 10, information used for controlling the spindle motor and each feed axis from the machine operation command unit 12 and information from sensors provided separately for diagnosis are acquired, and a diagnosis of the presence or absence of an abnormality is performed. The diagnostic device 20 includes a first diagnostic unit 21, a second diagnostic unit 22, and a diagnostic process update unit 23.

[0010] The first diagnostic unit 21 performs diagnosis using operation data during normal operation. The diagnostic process is carried out by a diagnostic model created by extracting characteristic quantities of the state using normal operation data at the initial stage of manufacturing of the machine tool and abnormal operation data in accumulated defect cases. Also, the operation data during normal operation is divided into during machining operation and during non-machining operation, and each has a diagnostic model. Since the operation data due to the operation during machining varies greatly depending on the tool used for machining, the material of the workpiece, the machining conditions, etc., and the machining content, it is difficult to operate a diagnostic model across machine tools. However, the operations during non-machining have many similar operations regardless of the machine tool, such as rapid feed of the feed axis and acceleration / deceleration of the spindle, and have the characteristic that it is easy to operate a diagnostic model across machine tools and models.

[0011] The second diagnosis unit 22 performs diagnosis by carrying out specific diagnostic operations effective for identifying abnormal locations. For example, in order to diagnose bearing damage of the feed shaft, a full-stroke operation is carried out at a specific feed speed; in order to diagnose bearing damage of the main shaft, an idling operation is carried out at a specific feed speed, and so on. Upon receiving the diagnosis result of the second diagnosis unit 22, the diagnosis process update unit 23 performs update and re-learning of the diagnosis model used for diagnosis in the first diagnosis unit 21. Fig. 2 shows an example of diagnosis settings by the diagnosis process update unit 23. In the first diagnosis unit 21, as shown in Fig. 2(A), normal and types of abnormal parts (here, two categories of abnormal A and abnormal B) are classified, and it is assumed that a new diagnosis point not classified into any frame is detected. In that case, diagnosis in the second diagnosis unit 22 is carried out. When it is diagnosed as abnormal A in the second diagnosis unit 22, as shown in Fig. 2(B), in the first diagnosis unit 21, the diagnosis setting range is updated so that the new diagnosis point is classified as abnormal A. Also, when it is not diagnosed as any abnormality in the second diagnosis unit 22, as shown in Fig. 2(C), in the first diagnosis unit 21, the diagnosis setting range is updated so that the new diagnosis point is classified as normal. Also, when multiple machines are connected by a network, the diagnosis model can be shared.

[0012] Fig. 3 shows a flowchart of the diagnosis method according to the second configuration executed by the diagnosis device 20. First, in the first diagnosis unit 21, it is determined whether it is in normal operation (S0). Here, it is determined that it is in normal operation during program operation such as during the operation of the processing program, and diagnosis is not carried out in the state of manual operation by the operator such as during override change. If it is in normal operation, next, it is determined whether it is in the processing operation (S1). Here, the operation in which the main shaft is not rotating is determined as the non-processing operation, and the operation in which the main shaft is rotating is determined as the processing operation. If it is determined that the processing operation is in progress in S1, then in S2, the diagnostic determination process for processing is performed, and in S3, it is determined whether it is normal. If it is determined to be normal here, then in S4, it is displayed on the monitor or the like of the NC device 10 that it is normal. However, as a normal state, it may not be necessary to display anything in particular. On the other hand, if it is determined to be abnormal in S3, then in S5, it is determined whether the abnormal part has been specified. If the abnormal part is specified as any of the pre-classified types as shown in FIG. 2 here, then in S6, it is displayed on the monitor or the like of the NC device 10 that an abnormality has occurred in the specified abnormal part.

[0013] Even if it is determined to be abnormal in the determination of S3, if the abnormal part is not specified in the determination of S5, then in S7, the calculation of the relevance to the abnormal part is performed. For example, as shown in FIG. 2(A), assuming that a new diagnosis point that does not correspond to any of the abnormalities A and B is detected, the first diagnostic unit 21 calculates the order of relevance to the abnormal part based on the distance from the center of gravity position of each cluster of normal and the types of abnormal parts. Also, in the diagnostic result of the first diagnostic unit 21, if the nearby abnormal part is related to the feed axis, the diagnosis of the abnormal part in the second diagnostic unit 22 related to the spindle parts may be set not to be performed, etc., and the relevance may be determined by the abnormal part in unit units. The processes from S1 to S7 except for S4 and S6 are the first diagnostic steps of the present disclosure.

[0014] When the relevance to the abnormal part is calculated in S7, then in S8, the diagnostic operation is performed in the second diagnostic unit 22. Since this diagnosis is performed by a diagnostic operation suitable for the abnormal part to be specified, it is efficient to perform it in descending order based on the order of relevance to the abnormal part calculated by the first diagnostic unit 21. The second diagnostic unit 22 performs the diagnostic operation by interrupting the diagnostic operation at the end of the machining program, or by instructing the operator to perform the diagnostic operation in combination with the notification of the abnormality in the result of the first diagnostic unit 21. After performing the diagnostic operation in S8, in S9, it is determined whether or not an abnormal part has been specified. If an abnormal part has been specified here, in S10, it is displayed on the monitor etc. of the NC device 10 that an abnormality has occurred in the specified abnormal part, and in S11, the diagnostic determination process during machining in the first diagnostic unit 21 is updated. That is, as shown in FIG. 2(B), the diagnostic setting range is updated so that the new diagnostic point is included in the abnormal category to which the abnormal part belongs.

[0015] On the other hand, if an abnormal part could not be specified in S9, in S12, it is displayed on the monitor etc. of the NC device 10 that since the abnormal part could not be specified, the result of the first diagnostic unit 21 is a change in the usage situation, and in S11, the diagnostic determination process during machining in the first diagnostic unit 21 is updated. That is, as shown in FIG. 2(C), the diagnostic setting range is updated so that the new diagnostic point is included in the normal category. The processes from S8 to S12 except for S11 are the second diagnostic step of the present disclosure, and S11 is the diagnostic process update step of the present disclosure. In addition, even when it is determined as non-machining in the determination of S1, if the processes of S22 to S32 are executed in the same flow as the machining diagnosis, it is possible to specify normal and abnormal parts. Also in this case, the processes from S22 to S27 except for S24 and S26 are the first diagnostic step of the present disclosure, and the processes from S28 to S32 except for S31 are the second diagnostic step of the present disclosure. And S31 is the diagnostic process update step of the present disclosure.

[0016] As described above, the diagnostic apparatus 20 of the above-described embodiment includes a first diagnostic unit 21 that diagnoses, using the operation data acquired during the normal operation of the machine tool 1, whether the machine tool 1 is normal or one of a plurality of types of abnormalities including abnormal parts, which are classified in advance. Further, when the diagnostic apparatus 20 cannot identify the abnormal part even though it is diagnosed as abnormal by the first diagnostic unit 21, the diagnostic apparatus 20 causes the machine tool 1 to perform a predetermined diagnostic operation and includes a second diagnostic unit 22 that identifies the abnormal part using the acquired diagnostic operation data. Then, the diagnostic apparatus 20 includes a diagnostic process update unit 23 that updates the classification of normal and / or abnormal parts in the first diagnostic unit 21 based on the diagnostic result by the second diagnostic unit 22. The diagnostic apparatus 20 executes the diagnostic method described in FIG. 3 based on a diagnostic program. According to this configuration, diagnosis using operation data and diagnosis using diagnostic operation data are used in combination, and the diagnosis using diagnostic operation data is executed only when the abnormal part cannot be identified from the diagnostic result using operation data. Therefore, it is possible to increase the diagnostic accuracy while suppressing the occurrence of time loss by minimizing the execution of diagnostic operations. Therefore, it is particularly beneficial for machine equipment that manufactures a variety of products.

[0017] Note that the types of abnormalities are not limited to the two categories as in the above-described embodiment. Three or more categories may be set. In the above-described embodiment, the abnormal part is specified as the type of abnormality, but in addition to this, the degree of abnormality, the cause of the abnormality, etc. can also be specified. The present disclosure is not limited to the type of machine tool. Further, the present disclosure is not directed to only one machine tool. When a plurality of machines are connected by a network as described above, diagnosis can be performed on a plurality of machine tools by sharing a diagnostic model. Therefore, the diagnostic apparatus may be installed at a location different from one or more machine tools.

Explanation of Reference Numerals

[0018] 1 ··· Machine tool, 10 ··· NC device, 11 ··· Program interpretation unit, 12 ··· Machine operation command unit, 20 ··· Diagnostic apparatus, 21 ··· First diagnostic unit, 22 ··· Second diagnostic unit, 23 ··· Diagnostic process update unit.

Claims

1. A diagnostic device for diagnosing an abnormality of a machine tool, a first diagnostic unit that diagnoses whether the machine tool is any of a pre-classified normal condition and a plurality of types of abnormalities including an abnormal part, using operation data acquired during normal operation of the machine tool; a second diagnostic unit that, when the abnormal part cannot be specified even though it is diagnosed as abnormal by the first diagnostic unit, causes the machine tool to perform a predetermined diagnostic operation and specifies the abnormal part using the acquired diagnostic operation data; a diagnostic process update unit that updates the classification of the normal condition and / or the types of abnormalities in the first diagnostic unit based on the diagnostic result by the second diagnostic unit; A diagnostic device for a machine tool, comprising the above.

2. When the first diagnostic unit cannot execute either the normal diagnosis or the specification of the abnormal part, the first diagnostic unit calculates the ranking of the relevance between the diagnostic result and each abnormal part, The diagnostic device for a machine tool according to claim 1, wherein the second diagnostic unit specifies the abnormal part based on the calculated ranking.

3. The diagnostic process update unit updates the setting range of the type of abnormality including the specified abnormal part in the first diagnostic unit when the abnormal part is specified by the second diagnostic unit, according to claim 1 or 2. A diagnostic device for a machine tool as described.

4. The diagnostic process update unit updates the normal setting range in the first diagnostic unit when the abnormal part is not specified by the second diagnostic unit, according to any one of claims 1 to 3. A diagnostic device for a machine tool as described.

5. A diagnostic method for diagnosing an abnormality of a machine tool, wherein a computer of the machine tool performs a first diagnostic step of diagnosing whether the machine tool is any of a pre-classified normal condition and a plurality of types of abnormalities including an abnormal part, using operation data acquired during normal operation of the machine tool; a second diagnostic step of, when the abnormal part cannot be specified even though it is diagnosed as abnormal in the first diagnostic step, causing the machine tool to perform a predetermined diagnostic operation and specifying the abnormal part using the acquired diagnostic operation data; a diagnostic process update step of updating the classification of the normal condition and / or the types of abnormalities in the first diagnostic step based on the diagnostic result by the second diagnostic step; A diagnostic method for a machine tool, characterized by executing the above.

6. In the first diagnostic step, when neither the normal diagnosis nor the identification of the abnormal part can be performed, the ranking of the relevance between the diagnostic result and each abnormal part is calculated, In the second diagnostic step, based on the calculated ranking, the abnormal part is identified. The diagnostic method for a machine tool according to claim 5, characterized in that.

7. In the diagnostic process update step, when the abnormal part is identified by the second diagnostic step, the setting range of the type of abnormality including the identified abnormal part in the first diagnostic step is updated. The diagnostic method for a machine tool according to claim 5 or 6, characterized in that.

8. In the diagnostic process update step, when the abnormal part is not identified by the second diagnostic step, the normal setting range in the first diagnostic step is updated. The diagnostic method for a machine tool according to any one of claims 5 to 7, characterized in that.

9. A diagnostic program for a machine tool for causing a control device of a machine tool to execute the diagnostic method for a machine tool according to any one of claims 5 to 8.

Images