JP2023008825A - Diagnosis system and diagnosis method - Google Patents

Abstract

To perform efficient abnormality detection even in small volume multi-kind processing.SOLUTION: A diagnosis system includes: a test piece for abnormality detection which is provided in addition to a workpiece to be processed with a tool for performing predetermined processing; a processing part which processes the test piece with the tool based on the processing of the workpiece at a given time point for each cycle of processing performed on the workpiece with the tool; a sensor which performs sensing on the processing performed on the test piece with the tool; and a determination part which calculates a degree of abnormality based on data sensed with the sensor when the test piece is processed with the tool.SELECTED DRAWING: Figure 8

Description

The present invention relates to diagnostic systems and methods.

2. Description of the Related Art A method of sensing the vibration of a machine tool is already known as a method of grasping the machining status of the machine tool and detecting abnormalities in cutting when the machine tool or the like processes a workpiece.

As a device for determining such an abnormality in the machining situation, there is known a device that distinguishes the same type of processing steps, divides them into groups, and determines a processing abnormality for each group (Patent Document 1).

However, conventional equipment for determining processing abnormalities is a method of diagnosing defects that is based on the premise of learning the same processing multiple times. rice field.

SUMMARY OF THE INVENTION The present invention has been made in view of the above, and an object of the present invention is to perform efficient abnormality detection even in machining of a large variety of products in small quantities.

In order to solve the above-described problems and achieve the object, the present invention provides, in addition to the workpiece to be machined by a tool for performing a predetermined machining, a test piece for abnormality detection, and A processing unit that processes the test piece with the tool based on the processing of the work piece at an arbitrary point in each processing cycle for the work piece, and performs sensing targeting the processing of the test piece with the tool. The apparatus is characterized by comprising a sensor, and a determination unit that calculates a degree of abnormality from data sensed by the sensor when the test piece is machined by the tool.

ADVANTAGE OF THE INVENTION According to this invention, it is effective in the ability to perform an efficient abnormality detection also in the processing of many kinds in a small quantity.

Drawing 1 is a figure showing an example of the whole diagnostic system composition concerning an embodiment. FIG. 2 is a diagram showing an example of the hardware configuration of the machine tool. FIG. 3 is a diagram illustrating an example of a hardware configuration of a state monitoring device; FIG. 4 is a diagram showing an example of the functional block configuration of the condition monitoring device and the machine tool. FIG. 5 is a diagram for explaining processing assumed by a conventional system. FIG. 6 is a diagram for explaining association of processing information and sensor data. FIG. 7 is a diagram for explaining that machining differs for each cycle in single-item machining. FIG. 8 is a diagram showing the configuration of the machine tool. FIG. 9 is a diagram for explaining types of test piece processing. FIG. 10 is a diagram illustrating replacement of the test piece. FIG. 11 is a diagram explaining abnormality diagnosis using a test piece. FIG. 12 is a diagram for explaining abnormality detection based on the machined portion of the test piece. FIG. 13 is a diagram illustrating an example of calculation of the degree of abnormality. FIG. 14 is a diagram showing an example of a GUI screen for notifying the user of the abnormal/normal determination result. FIG. 15 is a flow chart showing an example of processing using an abnormality detection result based on a machined portion of a test piece. 16A and 16B are diagrams for explaining the processing using the abnormality detection result based on the machined portion of the test piece. FIG. 17 is a diagram showing an example of movement of a tool within a machine tool that performs test machining and main machining.

Exemplary embodiments of a diagnostic system and diagnostic method are described in detail below with reference to the accompanying drawings. In addition, the present invention is not limited by the following embodiments, and the constituent elements in the following embodiments can be easily conceived by those skilled in the art, substantially the same, and so-called equivalent ranges. is included. Furthermore, various omissions, replacements, changes and combinations of components can be made without departing from the gist of the following embodiments.

(Overall configuration of diagnostic system)
Drawing 1 is a figure showing an example of the whole diagnostic system composition concerning an embodiment. An overall configuration of a diagnostic system 1 according to this embodiment will be described with reference to FIG.

As shown in FIG. 1, the diagnostic system 1 according to this embodiment includes a condition monitoring device 100 and a machine tool 200. As shown in FIG. Machine tool 200 is communicatively connected to condition monitoring device 100 . Although FIG. 1 shows an example in which one machine tool 200 is connected to the condition monitoring device 100, the present invention is not limited to this. may be connected so as to be communicable with each other.

The state monitoring device 100 is a device that is communicably connected to the machine tool 200 and monitors the state of the operation of the machine tool 200 .

The machine tool 200 is a machine tool that uses a tool 500 to perform processing such as cutting, grinding, or polishing an object to be processed. It is an example of a machine tool 200 and a target device whose state is to be monitored by the state monitoring device 100 . Note that the target device is not limited to machine tools, and may be any machine that can be subject to condition monitoring. good too. Below, the machine tool 200 will be described as an example of the target device.

A machine tool 200 includes a tool 500 , a sensor 201 installed in the machine tool 200 , and a controller 202 that controls the machine tool 200 .

The tool 500 is a drill, an end mill, a bit tip, a grindstone, or the like. The tool 500 performs various types of processing on a work material, which will be described later.

The sensor 201 detects vibrations, sounds, or the like generated when a tool 500 such as a drill, an end mill, a bit tip, or a grindstone installed in the machine tool 200 comes into contact with the object to be machined during the machining operation, or the tool 500 or the machine tool 200 It is a sensor that detects a physical quantity such as vibration or sound emitted by itself and outputs information of the detected physical quantity to the condition monitoring device 100 as detection information (sensor data). The sensor 201 is composed of, for example, a microphone, a vibration sensor, an acceleration sensor, an AE (Acoustic Emission) sensor, or the like, and is installed, for example, near the tool 500 or near the machine tool motor where vibration or sound can be detected. . The sensor 201 outputs waveform data to the condition monitoring device 100 as measurement data.

The controller 202 provides, as operation information of the machine tool 200, the number of revolutions of the spindle during machining, the feed rate, the coordinate value of the spindle, and the current value of the spindle. information such as the tool maker of the tool 500 and the tool diameter of the tool 500 is output to the condition monitoring device 100 .

Note that the machine tool 200 and the condition monitoring device 100 may be connected in any form of connection. For example, the machine tool 200 and the condition monitoring device 100 may be connected via a dedicated connection line, a wired network such as a wired LAN (Local Area Network), or a wireless network.

Also, the number of sensors 201 may be arbitrary. Moreover, a plurality of sensors 201 that detect the same physical quantity may be provided, or a plurality of sensors 201 that detect mutually different physical quantities may be provided.

Moreover, the sensor 201 and the controller 202 may be provided in the machine tool 200 in advance, or may be attached to the machine tool 200, which is a completed machine, afterward.

(Hardware Configuration of Machine Tool 200)
FIG. 2 is a diagram showing an example of the hardware configuration of the machine tool 200. As shown in FIG. The hardware configuration of the machine tool 200 of this embodiment will be described with reference to FIG.

As shown in FIG. 2, the controller 202 of the machine tool 200 includes a CPU (Central Processing Unit) 51, a ROM (Read Only Memory) 52, a RAM (Random Access Memory) 53, and a communication I/F (interface) 54. , and the drive control circuit 55 are communicably connected via a bus 59 . The sensor 201 is communicably connected to the condition monitoring device 100 .

The CPU 51 is an arithmetic device that controls the entire machine tool 200 . The CPU 51, for example, uses the RAM 53 as a work area (work area) and executes a program stored in the ROM 52 or the like to control the operation of the entire machine tool 200 and implement machining functions.

Communication I/F 54 is an interface for communicating with an external device such as condition monitoring device 100 . The drive control circuit 55 is a circuit that controls driving of the motor 56 . The motor 56 is a motor that drives a tool 500 used for processing, such as a drill, an end mill, a bit tip, a grindstone, etc., and a table on which an object to be processed is placed and moved according to processing. Sensor 201 is as described above.

(Hardware Configuration of Condition Monitoring Device 100)
FIG. 3 is a diagram showing an example of the hardware configuration of the state monitoring device 100. As shown in FIG. The hardware configuration of the condition monitoring device 100 according to this embodiment will be described with reference to FIG.

As shown in FIG. 3, the state monitoring device 100 includes a CPU 61, a ROM 62, a RAM 63, a communication I/F 64, a sensor I/F 65, an auxiliary storage device 66, an input device 67, and a display 68. It is configured to be communicably connected via a bus 69 .

The CPU 61 is an arithmetic device that controls the entire state monitoring device 100 . The CPU 61 executes a program stored in the ROM 62 or the like using the RAM 63 as a work area, for example, thereby controlling the overall operation of the state monitoring device 100 and realizing the state monitoring function.

Communication I/F 64 is an interface for communicating with an external device such as machine tool 200 . The communication I/F 64 is, for example, a NIC (Network Interface Card) compatible with TCP (Transmission Control Protocol)/IP (Internet Protocol).

Sensor I/F 65 is an interface for receiving detection information from sensor 201 installed in machine tool 200 .

Auxiliary storage device 66 is an HDD (Hard Disk Drive) for storing various data such as setting information for condition monitoring device 100, detection information and context information received from machine tool 200, OS (Operating System), and application programs. It is a non-volatile storage device such as SSD (Solid State Drive) or EEPROM (Electrically Erasable Programmable Read-Only Memory). Although the auxiliary storage device 66 is assumed to be provided in the state monitoring device 100, it is not limited to this. For example, it may be a storage device installed outside the state monitoring device 100, or A storage device provided in a server device capable of data communication with the state monitoring device 100 may be used.

The input device 67 is an input device such as a mouse or keyboard for performing operations such as inputting characters and numbers, selecting various instructions, and moving a cursor.

The display 68 is a display device such as a CRT (Cathode Ray Tube) display, an LCD (Liquid Crystal Display), or an organic EL (Electro-Luminescence) display that displays characters, numbers, various screens, operation icons, and the like.

It should be noted that the hardware configuration shown in FIG. 3 is an example, and it is not necessary to include all of the constituent devices, and other constituent devices may be included. For example, if the condition monitoring device 100 specializes in diagnosing the machine tool 200 and transmits diagnostic results to an external server device or the like, the input device 67 and the display 68 may be omitted.

(Configuration and operation of functional blocks of condition monitoring device 100 and machine tool 200)
FIG. 4 is a diagram showing an example of functional block configurations of the condition monitoring device 100 and the machine tool 200. As shown in FIG. Configurations and operations of functional blocks of the condition monitoring device 100 and the machine tool 200 according to the present embodiment will be described with reference to FIG. 4 .

As shown in FIG. 4 , the machine tool 200 has a processing section 210 . The processing unit 210 is a functional unit that controls the motor 56 to drive and control the tool 500 . Processing unit 210 causes CPU 51 shown in FIG. 2 to execute a program, that is, may be realized by software, may be realized by hardware such as an IC (Integrated Circuit), or may be realized by combining software and hardware. You may implement|achieve using it together.

As shown in FIG. 4, the condition monitoring apparatus 100 includes a collection unit 101, a signal processing unit 102, a feature amount calculation unit 103, a determination unit 104, a machine tool operation determination unit 105, a storage unit 106, an operation and a part 107 . Note that the collection unit 101, the signal processing unit 102, the feature amount calculation unit 103, the determination unit 104, the machine tool operation determination unit 105, the storage unit 106, and the operation unit 107 shown in FIG. 4 cause the CPU 61 shown in FIG. That is, it may be realized by software, by hardware such as an IC (Integrated Circuit), or by using both software and hardware.

The collection unit 101 acquires operation information from the controller 202 and information (such as measured waveforms) from the sensor 201 . The collection unit 101 associates the waveform measured by the sensor 201 with the operation information of the machine tool 200 based on the acquired information. As an example, the time at which the measured waveform and the tool number, sequence number, spindle rotation speed, etc., which is the operation information of the machine tool 200, are recorded in an auxiliary storage device, and are linked by synchronizing the respective times. The collection unit 101 transmits the linked data to the signal processing unit 102 .

The signal processing unit 102 performs predetermined preprocessing. The signal processing unit 102 transmits the preprocessed measurement data and operation information to the feature amount calculation unit 103 .

The feature amount calculation unit 103 calculates the feature amount of processing used in the determination by the determination unit 104 from the preprocessed measurement data and the operation information. The feature amount calculation unit 103 transmits the feature amount of processing to the determination unit 104 . The processing feature amount may be any information as long as it indicates the feature of the information from the sensor 201 . For example, when the information from the sensor 201 is acoustic data collected by a microphone, the feature amount calculation unit 103 calculates energy, frequency spectrum, MFCC (Mel frequency cepstrum coefficient), etc. as processing feature amounts. may

The determining unit 104 calculates the degree of abnormality according to the target of abnormality detection such as the workpiece, the tool 500, the motor of the machine tool 200, and the spindle, based on the feature amount of machining. Specifically, the determination unit 104 calculates the degree of abnormality using learning means such as threshold processing and machine learning (SVM (Support Vector Machine), neural network) based on the feature amount of processing. Note that the method for determining the degree of abnormality is not limited to this, and any method may be used as long as it can be calculated from the feature amount. For example, instead of directly comparing the value of the degree of abnormality with the threshold, a value indicating variation in the degree of abnormality may be compared with the threshold. Determination unit 104 transmits the degree of abnormality to machine tool operation determination unit 105 and storage unit 106 .

The storage unit 106 stores the degree of abnormality calculated by the determination unit 104 in a form associated with the operation information of the machine tool 200 .

It should be noted that the operation unit 107 may receive the degree of abnormality without obtaining it from the determination unit 104 . The operating unit 107 receives the degree of abnormality input from the input device 67 realized by, for example, a keyboard and a touch panel, and stores it in a form linked with the operation information of the machine tool 200 .

A machine tool operation determination unit 105, which is an operation determination unit, determines the machine tool 200 (tool 500) according to the degree of abnormality calculated by the determination unit 104 or the degree of abnormality stored in the storage unit 106. determine the behavior of For example, when the degree of abnormality shows a characteristic that is significantly deviated from similar machining so far, the machine tool operation determination unit 105 determines an operation to immediately stop machining, and instructs the controller 202 of the machine tool 200 can send

Next, a machining program for general cutting will be described.

Here, FIG. 5 is a diagram for explaining processing assumed by the conventional system. As shown in FIG. 5, when an unmachined workpiece is machined by a machining program, focusing on the type of tool 500 as information acquired from the controller of the machine tool, after a plurality of machining operations by tool A, other tools can be switched to In this case, since the machining 1-1 and 1-2 use the same tool A, they can be regarded as machining with the same machining information. Further, even when the machining program is executed a plurality of times, machining 1-1, 2-1, and N-1 performing similar machining can be regarded as machining of the same machining information. In this way, the conventional system performs machining that can be linked as the same machining information within the same machining program or across a plurality of machining cycles. Machining information associated with sensor data that can be obtained from the controller of the machine tool includes the type of tool 500, as well as the number of machining times, machining program, spindle rotation speed, sequence number, and other machining-related information. This case applies to sites where multiple identical products are produced, such as factory lines.

FIG. 6 is a diagram for explaining association of processing information and sensor data. In order to observe the change in the feature value of a specific machining, it is necessary to consider the case where there are multiple machining that can be regarded as the same machining information in the machining program, or when the machining program is executed multiple times and the machining of the same machining information is performed. It should be grouped and processed. As an example of a case in which there are a plurality of machining operations that can be regarded as the same machining information in the machining program, there is an example in which 1-4, 1-5, and 1-6, which are the same tool C, are regarded as the same machining information and grouped. mentioned. As an example of processing the same processing information by executing the processing program a plurality of times, there is an example in which 1-3, 2-3, . Therefore, as shown in FIG. 6, the state monitoring device can perform abnormality diagnosis using time-series data of the same grouped processing information.

Next, a case in which machining differs for each cycle in one-piece machining will be described.

FIG. 7 is a diagram for explaining that machining differs for each cycle in single-item machining. As shown in Fig. 7, in single-item machining sites such as mold machining, unlike multiple machining of the same product in a factory line, each cycle (cycle of machining one workpiece) The size, the shape of the workpiece, and the structure of the NC program to be processed are different. Therefore, even if the same tool is used, the machining location and machining time change each time machining is performed. Also, as shown in FIG. 7, the tools used vary from cycle to cycle. Machining 1-1, 2-6, and 3-1 are machining of the same tool A, but there is a possibility that the sensed feature amounts cannot be compared because the work material and machining location are different. Therefore, when machining differs for each cycle in one-piece machining, there is no machining in the same context as described with reference to FIG. 6, or the conditions cannot be easily compared.

Therefore, in the machine tool 200 of the present embodiment, a work material (test piece) for abnormality diagnosis measurement is installed in addition to the work material to be machined in the machine tool 200 .

Here, FIG. 8 is a diagram showing the configuration of the machine tool 200. As shown in FIG. As shown in FIG. 8, the machine tool 200 has a workpiece (test piece) 400 for abnormality diagnosis measurement in addition to a workpiece 300 to be machined in the machine tool 200 . A test piece 400 is a material that can be processed with a general tool 500 such as a drill, end mill, face mill, or the like. That is, the test piece 400 need not be prepared for each tool 500. FIG. The size and material of the test piece 400 are designed according to the tool 500 to be used and the physical information to be obtained. A plurality of test pieces 400 may be installed according to the tool 500 to be used.

Also, the test piece 400 can have the sensor 201 attached to or built into the test piece 400 itself. Sensor 201 of test piece 400 transmits the sensed physical quantity to condition monitoring device 100 . Although the details will be described later, by using the test piece 400 in this manner, the same machining can be reliably performed for each machining cycle even in the machining of a single item, and the abnormality diagnosis of the tool 500 can be performed.

Machining of the test piece 400 is designed to be physically the same as machining of the work material 300 machined in the machine tool 200 . As a result, it is possible to apply an abnormality detection method used when the same processing is repeatedly performed in a factory line to abnormality detection used in small-lot, high-mix processing such as mold processing. Machining of the test piece 400 and machining of the work material 300 are preferably compared under the same machining conditions. The piece 400 may be processed. However, when the test piece 400 is repeatedly processed by the same tool 500, the tool 500 repeatedly processes the test piece 400 under the same processing conditions.

Here, the types of processing of the test piece 400 will be described.

FIG. 9 is a diagram for explaining the types of processing of the test piece 400. FIG. As shown in FIG. 9, for machining the test piece 400, the machining method and replacement method can be determined according to the tool 500 to be used. As shown in FIG. 9A, when the tool 500 is a drilling tool such as a drill, the surface of the test piece 400 is drilled at regular intervals. In this case, the test piece 400 can be used until the entire surface of the test piece 400 is processed. As shown in FIGS. 9B and 9C, when the tool 500 is a face mill, an end mill tool, or the like, the surface or side of the test piece 400 can be machined.

Depending on the type of tool 500 used and the tool diameter of the tool 500, the physical quantity that can be sensed may change significantly due to the difference in machining positions such as the side and center of the test piece 400, and there may be cases where normal abnormality determination cannot be performed. be. As shown in FIG. 9(d), only the central portion of the test piece 400 may be used for abnormality determination without using the end portions.

Next, replacement of the test piece 400 will be described.

FIG. 10 is a diagram illustrating replacement of the test piece 400. FIG. The test piece 400 is replaced at the timing when the machining area becomes smaller by continuing the machining of the test piece 400 . For example, in the case of drilling, the test piece 400 must be replaced because it cannot be machined when the entire surface of the test piece 400 has been machined. Further, in the case of surface milling of the test piece 400, the test piece length of the test piece 400 is shortened by continuing the processing. Machining of the shortened test piece 400 affects the physical quantity to be sensed due to the generation of chatter and the difference in physical characteristics. determine the timing. For example, as shown in FIG. 10, when chattering is likely to occur due to the test piece length of the test piece 400 with the tool 500, if the test piece 400 is machined by twice or more the amount of protrusion of the tool 500, replacement is required. Become. As an example, when the test piece length is XX mm (mm) and the tool length is YY mm (mm), chattering is likely to occur. , will be replaced. The values of XX and YY are values arbitrarily determined according to the situation on site.

As described above, the test piece 400 does not need to be replaced each time test machining is performed on the test piece 400. When the test piece 400 needs to be replaced, the machine tool operation determination unit 105 of the state monitoring device 100 issues a replacement command. good.

Next, abnormality diagnosis using the test piece 400 in the condition monitoring device 100 will be described.

FIG. 11 is a diagram illustrating abnormality diagnosis using the test piece 400. FIG. As shown in FIG. 11, machine tool 200 processes test piece 400 at an arbitrary point in each machining cycle. In this way, time-series data of the same processed information are grouped, and abnormality diagnosis can be performed on the time-series data.

As shown in FIG. 11, machining 1-A, 2-A, and 3-A of the test piece 400 by the tool A differs from machining 1-1, 2-6, and 3-1 in that the same work material and machining are used. The type is guaranteed, and the feature values extracted from the sensed physical values can be compared. In addition, after the tool B, it can process similarly.

As long as the test piece 400 is processed by the same tool 500, the test piece 400 may be processed at any timing, not only at the beginning but also during or after processing.

The sensor 201 of the test piece 400 transmits sensed time-series data to the condition monitoring device 100 .

12A and 12B are diagrams for explaining abnormality detection based on a machined portion of the test piece 400. FIG. As shown in FIG. 12 , the condition monitoring device 100 calculates the degree of abnormality based on the feature amount calculated from the physical amount of the same machining information obtained by machining the test piece 400 . When the test piece 400 is used, time-series changes in the state of the tool 500 appear as the degree of abnormality, so the degree of wear of the tool 500, breakage of the tool 500, occurrence of chipping, and the like serve as indicators of abnormality.

Here, an example of calculation of the degree of abnormality in the determination unit 104 of the condition monitoring device 10 will be described in detail. FIG. 13 is a diagram illustrating an example of calculation of the degree of abnormality. FIG. 13 explains an example of calculation of the degree of abnormality for the data of the N-th processing in the example shown in FIG. 12, for example.

A first example of calculation of the degree of abnormality shown in FIG. 13 is an example in which the power of vibration is used as the degree of abnormality. The determination unit 104 of the condition monitoring device 10 first converts the N-th processed sampling data (processed NA) into a spectrogram by short-time Fourier transform. Next, the determination unit 104 of the condition monitoring device 10 calculates the total power of the spectrogram data. The determination unit 104 of the condition monitoring device 10 sets the calculated sum of the powers of the spectrogram data as the value of the degree of abnormality for the N-th processed sampling data (processed NA).

A second example of calculating the degree of abnormality shown in FIG. 13 is an example in which the Mahalanobis distance is used as the degree of abnormality. The Mahalanobis distance is a distance that incorporates correlations between multiple variables to reveal relationships with known samples. The determination unit 104 of the condition monitoring device 10 first converts the N-th processed sampling data (processed NA) into a spectrogram by short-time Fourier transform. Next, the determination unit 104 of the condition monitoring device 10 learns the spectrogram data up to M processing eyes (M<N) and calculates the variance-covariance matrix Σ and the mean value vector μ, which are Mahalanobis distance parameters. Next, the determination unit 104 of the condition monitoring device 10 calculates the Mahalanobis distance for inferring whether there is a difference between the parameters (learning data) of the data up to the Mth processing and the spectrogram data of the Nth processing. The determination unit 104 of the condition monitoring device 10 uses the calculated Mahalanobis distance as the value of the degree of abnormality for the sampling data of the N-th processing (processing NA).

Here, FIG. 14 is a diagram showing an example of a GUI screen for notifying the user of the abnormal/normal determination result. The determination unit 104 of the condition monitoring device 10 displays on the display 68 a GUI (Graphical User Interface) screen for notifying the user of the abnormal/normal determination result. As shown in FIG. 14, the determination unit 104 displays, as a GUI screen, a graph of the degree of abnormality corresponding to the machining section. As shown in FIG. 14, the determination unit 104 of the condition monitoring device 10 displays, for example, the abnormal processing score c indicating the degree of abnormality together with the waveform score a and the processed section b on the GUI screen.

A waveform score a is waveform data detected by the sensor 201 .

The machining interval b is data indicating an operation interval of a predetermined operation of the machine tool 200 (for example, actual cutting time for the machining object). The horizontal line x shown in the machining section b indicates the cutting feed time when cutting the object to be machined.

The abnormal processing score c is data indicating the degree of abnormality calculated by the determination unit 104 . The abnormal processing score c in FIG. 14 is an example in which the Mahalanobis distance is used as the degree of abnormality. When the degree of abnormality calculated by the determination unit 104 exceeds the set threshold value t as shown in the abnormal processing score c in FIG. 14, the determination unit 104 displays an error alert E for notification of abnormality on the GUI screen. Note that the determination unit 104 may be able to freely set the threshold value.

In the present embodiment, when the degree of abnormality calculated by the determination unit 104 exceeds the set threshold value t, an error alert E for notification of abnormality is displayed on the GUI screen. A sentence, an icon, or the like indicating abnormality/normality may be displayed on the GUI screen.

In this embodiment, an example of displaying an error alert E for notifying an abnormality on the GUI screen when the degree of abnormality in the abnormality/normality determination exceeds the threshold has been described, but the present invention is not limited to this. For example, the determination unit 104 of the condition monitoring device 10 may select settings for notification to the controller 202 of the machine tool 200 . By doing so, the determination unit 104 of the condition monitoring device 10 can transmit an abnormality notification to the controller 202 of the machine tool 200 when the degree of abnormality calculated by the determination unit 104 exceeds the set threshold value t. can. On the side of the controller 202 of the machine tool 200 , the program of the controller 202 can read an abnormality notification to stop machining, or turn on a patrol lamp provided in the machine tool 200 .

Next, an example of processing using an abnormality detection result based on a machined portion of the test piece 400 will be described.

Here, FIG. 15 is a flow chart showing an example of processing using the abnormality detection result based on the machined portion of the test piece 400, and FIG. be.

As described above, the machine tool operation determination unit 105 of the condition monitoring device 100 can send a command to the machine tool 200 based on the degree of abnormality of the machined portion of the test piece 400 . The examples shown in FIGS. 15 and 16 show examples in which the tool 500 is replaced before the next machining when it is determined that the tool 500 is abnormal as a result of the degree of abnormality.

As shown in FIG. 15, the condition monitoring device 100 receives information from the machine tool 200 indicating that, for example, the test piece 400 of the tool A has been machined (step S1). Next, the machine tool operation determination unit 105 of the state monitoring device 100 determines whether the tool A is normal based on the degree of abnormality of the machined portion of the test piece 400 (step S2).

In determining the degree of abnormality of the machined portion of the test piece 400, the determination unit 104 of the state monitoring device 100 determines, for example, wear, breakage, or chipping of the tool 500, or when there is a significant change in the degree of abnormality from the past. and so on.

As shown in FIG. 16, when the machine tool operation determination unit 105 of the state monitoring device 100 determines that the tool A is abnormal from the abnormality detection result of the 2-A machining of the 2 machining items (No in step S2), the 3 machining items A command is sent to the machine tool 200 side to replace the tool A-2 with a new tool A-2 at an arbitrary position before entering (step S3). The command transmitted by the machine tool operation determination unit 105 of the state monitoring device 100 may be not only the replacement of the tool 500, but also the temporary stop/emergency stop of the machine or generation of an alert. After that, the machine tool operation determination unit 105 of the state monitoring device 100 waits for the next machining.

Next, the movement of the tool 500 in the machine tool 200 that performs test machining on the test piece 400 and main machining on the work material 300 will be described.

FIG. 17 is a diagram showing an example of movement of the tool 500 inside the machine tool 200 that performs test machining and main machining. In general, the movement of the tool 500 in the machine tool 200 is often due to the z-direction movement of the main axis of the machine tool 200 to which the tool 500 is attached and the x- and y-axis movement of the table on which the work material 300 is placed. Here, for example, an example of movement for machining of one machining item, tool A, in FIG. 11 will be described.

As shown in FIG. 17, after the tool A is replaced (1), the processing section 210 of the machine tool 200 moves the tool A toward the test piece 400 (2). After moving the tool A to the test piece 400, the processing unit 210 of the machine tool 200 processes the test piece 400 (3). If there is no problem in the abnormality diagnosis result determined from the physical quantity sensed by the sensor 201 of the test piece 400, the processing unit 210 of the machine tool 200 moves the tool A toward the workpiece 300, which is the workpiece ( 4). Then, the tool A performs machining 1-1 and 1-2 (see FIG. 11) of the work material 300 (5). The tool A is replaced with the tool B after the machining 1-1, 1-2 of the work material 300 is completed. After that, the machine tool 200 repeats the machining of the test piece 400 and the abnormality determination in the same procedure.

As described above, according to the present embodiment, in addition to the work material (workpiece) to be actually processed, the work material (test piece ) is prepared, and by processing the test piece at any timing for which you want to detect an abnormality, you can acquire vibrations (other sensing signals) for abnormality detection that do not depend on the actual processing target, and perform abnormality determination. As a result, efficient abnormality detection can be performed even in the processing of a large variety of products in small quantities.

The program executed by the condition monitoring device 100 and the machine tool 200 of the above-described embodiment may be configured so as to be preinstalled in a ROM or the like and provided.

Further, the programs executed by the condition monitoring device 100 and the machine tool 200 of the above-described embodiments are stored in installable format or executable format files on a CD-ROM (Compact Disc Read Only Memory), flexible disk (FD). , CD-R (Compact Disc-Recordable), DVD (Digital Versatile Disc), or other computer-readable recording medium, and provided as a computer program product.

Further, the programs executed by the condition monitoring device 100 and the machine tool 200 of the above embodiments are stored on a computer connected to a network such as the Internet, and are provided by being downloaded via the network. good too. Further, the programs executed by the condition monitoring device 100 and the machine tool 200 of the above embodiments may be provided or distributed via a network such as the Internet.

Further, the programs executed by the condition monitoring device 100 and the machine tool 200 of the above-described embodiment have a module configuration including each of the above-described functional units. is read out and executed to load each of the functional units described above onto the main memory, and each functional unit is generated on the main memory.

Aspects of the present invention are, for example, as follows.
<1>
A test piece for abnormality detection provided in addition to a workpiece to be processed by a tool for performing predetermined processing,
a machining unit for machining the test piece with the tool based on the machining of the workpiece at an arbitrary point in each cycle of machining the workpiece with the tool;
a sensor that performs sensing for processing of the test piece by the tool;
a determination unit that calculates the degree of abnormality from data sensed by the sensor when the test piece is processed by the tool;
A diagnostic system comprising:
<2>
An operation determination unit that determines an operation of the tool according to the degree of abnormality calculated by the determination unit,
The operation determination unit transmits an arbitrary operation command to the tool based on the operation of machining the test piece.
The diagnostic system according to <1> characterized by:
<3>
The processing unit continuously processes the test piece and the workpiece with the tool,
The diagnostic system according to <1> or <2> characterized by:
<4>
The determination unit calculates the degree of abnormality using learning means based on the feature amount of processing for the test piece,
The diagnostic system according to any one of claims <1> to <3> characterized by:
<5>
The test piece is a material that can be processed by the tool to be used,
The diagnostic system according to any one of <1> to <4> characterized by:
<6>
A plurality of the test pieces are installed according to the tool to be used,
The diagnostic system according to any one of <1> to <4> characterized by:
<7>
The test piece comprises the sensor,
The diagnostic system according to any one of <1> to <6> characterized by:
<8>
a collection unit that collects and links the operation information of the tool and the data sensed by the sensor;
a signal processing unit that pre-processes the sensed data and associates it with the operation information of the tool;
A feature quantity calculation unit that calculates a feature quantity for preprocessed data;
with
The determination unit calculates the degree of abnormality from the feature amount calculated by the feature amount calculation unit,
The diagnostic system according to any one of <1> to <7> characterized by:
<9>
A diagnostic method performed in a diagnostic system, comprising:
Using a test piece for abnormality detection provided in addition to the workpiece to be processed by a tool that performs predetermined processing,
machining the test piece with the tool based on the machining of the workpiece at any point in each cycle of machining the workpiece with the tool;
a step of calculating the degree of abnormality from data sensed by a sensor when the test piece is processed by the tool;
A diagnostic method comprising:

1 diagnostic system 101 collection unit 102 signal processing unit 103 feature amount calculation unit 104 determination unit 105 operation determination unit 201 sensor 210 processing unit 300 workpiece 400 test piece 500 tool

JP 2019-159728 A

Claims (9)

A test piece for abnormality detection provided in addition to a workpiece to be processed by a tool for performing predetermined processing,
a machining unit for machining the test piece with the tool based on the machining of the workpiece at an arbitrary point in each cycle of machining the workpiece with the tool;
a sensor that performs sensing for processing of the test piece by the tool;
a determination unit that calculates the degree of abnormality from data sensed by the sensor when the test piece is processed by the tool;
A diagnostic system comprising: An operation determination unit that determines an operation of the tool according to the degree of abnormality calculated by the determination unit,
The operation determination unit transmits an arbitrary operation command to the tool based on the operation of machining the test piece.
2. The diagnostic system of claim 1, wherein: The processing unit continuously processes the test piece and the workpiece with the tool,
3. The diagnostic system according to claim 1 or 2, characterized in that: The determination unit calculates the degree of abnormality using learning means based on the feature amount of processing for the test piece,
2. The diagnostic system of claim 1, wherein: The test piece is a material that can be processed by the tool to be used,
2. The diagnostic system of claim 1, wherein: A plurality of the test pieces are installed according to the tool to be used,
2. The diagnostic system of claim 1, wherein: The test piece comprises the sensor,
2. The diagnostic system of claim 1, wherein: a collection unit that collects and links the operation information of the tool and the data sensed by the sensor;
a signal processing unit that pre-processes the sensed data and associates it with the operation information of the tool;
A feature quantity calculation unit that calculates a feature quantity for preprocessed data;
with
The determination unit calculates the degree of abnormality from the feature amount calculated by the feature amount calculation unit,
2. The diagnostic system of claim 1, wherein: A diagnostic method performed in a diagnostic system, comprising:
Using a test piece for abnormality detection provided in addition to the workpiece to be processed by a tool that performs predetermined processing,
machining the test piece with the tool based on the machining of the workpiece at any point in each cycle of machining the workpiece with the tool;
a step of calculating the degree of abnormality from data sensed by a sensor when the test piece is processed by the tool;
A diagnostic method comprising:

Images