JP2023113045A - Machining abnormality detection method and machining abnormality detection apparatus for machine tool - Google Patents

Abstract

To realize highly accurate machining abnormality detection without human intervention by automatically selecting a machining abnormality detection algorithm/machining abnormality detection model for accurately determining a machining abnormality.SOLUTION: A machining abnormality detection method for a machine tool acquires image data of a tool and a work material in a machine tool by an imaging device provided in a machine tool (S11), estimates types of the tool and the work material from the acquired image data (S14 and S15), selects a machining abnormality model based on the estimated types of the tool and the work material (S16) and inputs machining data to the selected abnormality detection model to determine presence or absence of the machining abnormality (S17 and S18).SELECTED DRAWING: Figure 4

Description

The present disclosure relates to a method and apparatus for detecting machining anomalies from machining data of machine tools.

There is a technique for determining a machining abnormality using machining data relating to machine control obtained from a numerical controller. Machining data refers to motor rotation command value and position command information, torque data of a motor that controls the machine, etc., which change according to the progress of machining. Predict the processed data by loading an algorithm that has analyzed the processed data in advance or a machine learning/probabilistic/statistical model that has learned normal processed data, and obtain the difference between the predicted value and the actual value as the prediction error. . The prediction error may be data for the number of processed data used, or may be one norm. The prediction error is compared with a preset threshold value, and if the prediction error is larger than the threshold value, it is assumed that the processing is abnormal, and the processing is interrupted or the machine is stopped. If the prediction error is smaller than the threshold, it is assumed that there is no machining abnormality, and machining is continued. When using the above model, in order to increase the detection accuracy of machining abnormality, a plurality of models that have learned machining data under specific machining conditions may be prepared and the model may be selected. Machining conditions are determined by the type of tool, the type of work material, and the like.
On the other hand, there is a technique for determining the shape of a tool and the shape of a work material from image data of the tool and the work material obtained by imaging with a camera (see Patent Document 1, for example). From the image, an area showing the characteristics of the tool or work material is extracted, its shape is determined, and the dimensions of the shape are determined from the distance between the camera and the tool or work material, and the actual size of the shape is determined. This is achieved by using image processing algorithms and machine learning/probabilistic/statistical models learned from image data of tools and work materials.
The model shown here is also one of the algorithms, but in the present disclosure, a deductive algorithm obtained from a theoretical formula is called an algorithm, and an algorithm created inductively based on data is called a model. An algorithm for image processing is called an image processing algorithm, and an algorithm and a model for processing abnormality detection are called a processing abnormality detection algorithm and a processing abnormality detection model, respectively.

Japanese Patent No. 6000478

When a model is used to detect machining anomalies, the detection accuracy is often a trade-off with the generalization performance of the model. When creating a model for detecting processing abnormalities for processing under many conditions, it is necessary to learn a large amount of processing data in advance. A certain degree of effectiveness is obtained for detecting anomalies in machining under each condition, but when high detection accuracy is required, a method of switching to a model that predicts well for specific machining conditions may be selected. In this case, it is necessary to manually select the model or describe the switching of the model in the machining program, so it is impossible to automate the machining process without labor and the possibility of mistakes. However, on the other hand, if a model with high generalization performance but low detection accuracy is used, machining abnormalities may be detected excessively or overlooked, so it is difficult to automatically operate the machine while maintaining machining quality. Can not. This is the same when using the processing abnormality detection algorithm.

Therefore, the present disclosure is a machine tool that can realize highly accurate processing abnormality detection without human intervention by automatically selecting a processing abnormality detection algorithm/processing abnormality detection model for accurately determining processing abnormality. It is an object of the present invention to provide a method and apparatus for detecting a processing abnormality.

In order to achieve the above object, a first configuration of the present disclosure is a machining abnormality detection method for detecting a machining abnormality from machining information acquired during machining in a machine tool that performs cutting based on numerical control commands. hand,
an image data acquisition step of acquiring image data by imaging a tool and/or a work material in the machine using an imaging device provided in the machine tool;
a tool/work material estimation step of estimating the type of the tool and/or the work material from the acquired image data;
an algorithm/model selection step of selecting a machining abnormality detection algorithm/machining abnormality detection model based on the estimated type of the tool and/or the work material;
and an abnormality determination step of inputting the machining information to the selected machining abnormality detection algorithm/machining abnormality detection model and determining whether or not there is a machining abnormality.
In another aspect of the first configuration, in the above configuration, in the tool/work material estimation step, when estimating the type of the work material, the work material is operated to estimate the weight, and the image The type of the work material is estimated from the size and shape of the work material acquired in the data acquisition step and the estimated weight of the work material.
In another aspect of the first configuration, in the above configuration, in the algorithm/model selection step, a pre-associated machining condition is determined based on the estimated type of the tool and/or the work material. and selecting the abnormal machining detection algorithm/abnormal machining detection model based on the discriminated machining conditions.
In another aspect of the first configuration, in the above configuration, in the abnormality determination step, the processing information is input to the processing abnormality detection algorithm/processing abnormality detection model to determine the degree of abnormality of processing, and the degree of abnormality is determined. is compared with a threshold value, and when the degree of abnormality is larger than the threshold value, it is determined that the processing is abnormal.
Another aspect of the first configuration is characterized in that in the above configuration, when the abnormality determination step determines that there is a machining abnormality, the machine tool is caused to replace the currently used tool with a spare tool of the same type. .
Another aspect of the first configuration is that in the above configuration, when the spare tool is replaced with the spare tool, the imaging device captures an image of the spare tool to acquire image data, and from the acquired image data, the A tool determination step for determining whether or not the spare tool is of the same type as the used tool is further executed, and if the tool determination step determines that the spare tool is not of the same type, machining is interrupted or stopped.

In order to achieve the above object, a second configuration of the present disclosure is a processing abnormality detection device that detects processing abnormality from processing information acquired during processing in a machine tool that performs cutting processing based on numerical control commands. hand,
an image data acquisition means for acquiring image data by imaging a tool and/or a work material in the machine using an imaging device provided in the machine tool;
tool/work material estimation means for estimating the type of the tool and/or the work material from the acquired image data;
algorithm/model selection means for selecting a machining abnormality detection algorithm/machining abnormality detection model based on the estimated type of the tool and/or the work material;
and abnormality determination means for inputting the processing information to the selected processing abnormality detection algorithm/processing abnormality detection model and determining the presence or absence of processing abnormality.
In another aspect of the second configuration, in the above configuration, when estimating the type of the work material, the tool/work material estimation means operates the work material to estimate the weight, and the image The type of the work material is estimated from the size and shape of the work material acquired by the data acquisition means and the estimated weight of the work material.
In another aspect of the second configuration, in the above configuration, the algorithm/model selection means determines machining conditions associated in advance based on the estimated type of the tool and/or the work material. and selecting the abnormal machining detection algorithm/abnormal machining detection model based on the discriminated machining conditions.
In another aspect of the second configuration, in the above configuration, the abnormality determination means inputs the processing information to the processing abnormality detection algorithm/processing abnormality detection model to obtain the degree of abnormality of processing, and determines the degree of abnormality. is compared with a threshold value, and when the degree of abnormality is larger than the threshold value, it is determined that the processing is abnormal.
Another aspect of the second configuration is characterized in that in the above configuration, when the abnormality determination means determines that there is a machining abnormality, the machine tool is caused to replace the currently used tool with a spare tool of the same type.
Another aspect of the second configuration is that in the above configuration, when the spare tool is replaced with the spare tool, the imaging device captures an image of the spare tool to acquire image data, and from the acquired image data, the A tool discriminating means for discriminating whether or not the spare tool is of the same type as the used tool is further provided, and if the tool discriminating means discriminates that the spare tool is not of the same type, machining is interrupted or stopped.

In the present disclosure, the types of tools refer to those classified according to materials and shapes, processing applications such as drills and end mills, and types of cutting edges such as solids and inserts.
Further, in the present disclosure, it is assumed that it is known in advance under what machining conditions the machining abnormality detection model is effective. It is also assumed that the correspondence between the combination of the type of tool and the type of work material and the machining conditions is known in advance.
The type of tool is specified from the image data of the tool captured by an imaging device such as a camera. A model is created by inputting image data of various tools in advance, detecting the image area of the tool, and outputting estimated values of the diameter, length, and material of the tool. On the other hand, for the diameter and length dimensions of the tool on the image obtained from the detected image area of the tool, a scale for conversion to actual dimensions is obtained according to the positional relationship between the camera and the tool. A captured image of the tool is input to the model, and estimated values of the tool material, diameter, length, tip angle and torsion angle of the tool are obtained. Then, the diameter and length are multiplied by the scale to convert to the material and dimensions of the actual tool. Since it is possible to identify the material of the tool based on the degree of light reflection and brightness, it is possible to estimate the material from the image data.

It is difficult to identify the material of the work material only from its appearance. Therefore, the material is specified based on the image data of the work material captured by an imaging device such as a camera and the weight of the work material. A model is created by inputting image data of work materials of various sizes and materials in advance, detecting image regions of the work materials, and outputting estimated values of the size and material of the work materials. On the other hand, for the size of the work piece on the image obtained from the detected image area of the work piece, a scale for converting it into an actual size is found according to the positional relationship between the camera and the work piece. On the other hand, the shaft of the machine on which the work material is mounted is operated, and the weight of the work material is obtained from the inertial force. A photographed image of the work material is input to the model, and estimated values of the size and material of the work material are obtained. The estimated size is multiplied by the scale to convert to the actual size of the work material. The specific gravity of the work material is obtained from the estimated size and weight, and the material of the work material is specified from the estimated value of the material and the specific gravity.

According to the present disclosure, it is possible to estimate the type of tool and / or work material from the image data of the imaging device, and automatically create a processing abnormality detection algorithm / processing abnormality detection model that accurately determines processing abnormality from the estimation result. can be selectively selected. Therefore, highly accurate processing abnormality detection can be realized without human intervention.
The selected algorithm/model can automatically continue the machining intended by the user by determining whether or not there is a machining abnormality based on the input of machining information, and determining whether to continue machining if there is no machining abnormality. In addition, the machining program can be reused because there is no need to write a command for exchanging the machining error detection algorithm/machining error detection model in the machining program.
As described above, it is possible to automatically select a processing abnormality detection algorithm/processing abnormality detection model, and to automatically continue processing according to the user's intention. Therefore, it is possible to promote unmanned factories and increase the operating rate of machines.
In addition, it prevents the erroneous selection of algorithms/models used for manual detection of machining anomalies, and prevents the wear and tear of tools and work materials and the damage of machine parts caused by erroneous selection of anomaly detection algorithms/models for machining anomalies. can be prevented.

and FIG. 11 is a block diagram illustrating a conventional machining abnormality detection device for machine tools. 2 is a flow chart of a conventional method for detecting a processing abnormality in a machine tool; 1 is a block diagram showing an example of a processing abnormality detection device for a machine tool of the present disclosure; FIG. 4 is a flow chart showing an example of a method for detecting an abnormality in machining of a machine tool according to the present disclosure;

Embodiments of the present disclosure will be described below with reference to the drawings.
First, a conventional method and apparatus for detecting an abnormality in machining of a machine tool will be described with reference to FIGS.
FIG. 1 shows the configuration of a conventional machining abnormality detection device 10 for a machine tool. Here, the machine tool is provided with an NC unit 11 and a machining data storage unit 12 for storing machine operation data of the machine tool during machining.
The processing abnormality detection device 10 also includes a model selection screen 13 for selecting a processing abnormality detection model for detecting a processing abnormality, a model selection unit 14 for selecting and reading model data with a name selected on the screen, and a a selected model storage unit 15 for storing a model; and an abnormality degree calculation unit 16 for inputting the processed data stored in the processed data storage unit 12 to the model stored in the selected model storage unit 15 to obtain a predicted value of processing abnormality. It has
Furthermore, the processing abnormality detection device 10 includes a threshold setting unit 17 that sets a threshold value for determining processing abnormality, a threshold storage unit 18 that stores the threshold value set by the threshold setting unit 17, and an abnormality degree calculation unit 16. and a processing abnormality determination unit 19 that compares the abnormality degree stored in the threshold storage unit 18 with the threshold value stored in the threshold value storage unit 18 and determines that a processing abnormality has occurred when the abnormality degree exceeds the threshold value.

FIG. 2 shows the flow of a conventional processing abnormality detection method. A model used for detecting a machining abnormality is selected from the model selection screen 13 and stored in the model selection unit 14 (S1), and the NC unit 11 stores data relating to machine operation in the machining data storage unit 12 according to the progress of machining. (processing data) is acquired (S2).
Then, the processing data is input to the model, the degree of processing abnormality is obtained as the degree of abnormality (S3), the threshold stored in the threshold storage unit 18 is compared with the degree of abnormality (S4), and if the degree of abnormality is equal to or less than the threshold continues machining, and if the degree of abnormality is greater than the threshold, commands the NC unit 11 to interrupt or stop machining.

Next, the method and apparatus for detecting an abnormality in machine tool processing according to the present disclosure will be described with reference to FIGS.
FIG. 3 shows an example of a processing abnormality detection device. Unlike the conventional machining error detection device 10 shown in FIG. 1, this machining error detection device 20 does not have the model selection screen 13 and the machining error determination unit 19. FIG. Here, an in-machine photographing section 21 , a photographed data storage section 22 , a tool estimating section 23 , a weight estimating section 24 , and a cut material estimating section 25 are provided.
The in-machine photographing unit 21 is provided with an imaging device (here, a camera) and images tools and work materials in the machine.
The photographed data storage unit 22 stores image data of tools and work materials photographed by the in-machine photographing unit 21 . The in-flight photographing unit 21 and the photographed data storage unit 22 are examples of the image data acquiring unit of the present disclosure.
The tool estimation unit 23 estimates the type of tool from the image data of the tool stored in the photographed data storage unit 22 . The tool estimation unit 23 is an example of the tool/work material estimation means of the present disclosure.
The weight estimating unit 24 moves the work material according to a command from the NC unit 11 and estimates the weight of the work material from the inertial force.
The work material estimation unit 25 estimates the type of the work material from the weight estimated by the weight estimation unit 24 and the image data of the work material stored in the image data storage unit 22 . The weight estimation unit 24 and the work material estimation unit 25 are examples of tool/work material estimation means of the present disclosure.

Further, the machining abnormality detection device 20 includes a tool estimation result storage unit 26, a work material estimation result storage unit 27, a machining condition determination unit 28, a spare tool replacement determination unit 29, and a tool confirmation unit 30. there is
The tool estimation result storage unit 26 stores information on the types of tools estimated by the tool estimation unit 23 .
The work material estimation result storage unit 27 stores information on the type of work material estimated by the work material estimation unit 25 .
The machining condition determination unit 28 determines machining conditions necessary for model selection based on the information on the tool type stored in the tool estimation result storage unit 26 and the information on the type of work material stored in the work material estimation result storage unit 27. determine.

The model selection unit 14 selects a model to be used for detecting machining abnormality based on the machining conditions determined by the machining condition determination unit 28 . The machining condition determination unit 28 and the model selection unit 14 are examples of algorithm/model selection means of the present disclosure.
The spare tool replacement determination unit 29 compares the degree of abnormality obtained by the degree of abnormality calculation unit 16 with the threshold stored in the threshold storage unit 18, and determines that the machining quality cannot be maintained when the degree of abnormality exceeds the threshold. Then, it is determined that the current tool needs to be replaced with the spare tool. The degree-of-abnormality calculation unit 16 and the spare tool replacement determination unit 29 are an example of the abnormality determination means of the present disclosure.
The tool confirmation unit 30 estimates the type of the spare tool replaced with the current tool, and confirms whether or not the type of the current tool and the tool are the same. The tool confirmation unit 30 is an example of tool determination means of the present disclosure.

FIG. 4 shows the flow of the processing abnormality detection method of the present disclosure. First, the camera of the in-machine photographing unit 21 images a tool and a work material mounted inside the machine, and the image data is stored in the photographed data storage unit 22 (S11: image data acquisition step). Further, the weight estimator 24 moves the work material according to the command from the NC unit 11 and estimates the weight of the work material from the inertial force (S12). Furthermore, the NC unit 11 acquires the machining data stored in the machining data storage unit 12 according to the progress of machining (S13).
Next, the tool estimation unit 23 estimates the type of tool from the image data of the tool stored in the photographed data storage unit 22, and stores the type of tool in the tool estimation result storage unit 26 (S14: tool/work material estimation step). On the other hand, the work material estimating unit 25 estimates the type of the work material from the weight of the work material estimated by the weight estimating unit 24 and the image data of the work material stored in the photographed data storage unit 22. The type of work material is stored in the cutting material estimation result storage unit 27 (S15: tool/work material estimation step).

Next, the machining condition discriminating unit 28 discriminates the machining conditions necessary for model selection from the estimated tool type and work material type, and the model selecting unit 14 determines the machining conditions based on the discriminated machining conditions. A model to be used for detecting machining abnormality is selected (S16: algorithm/model selection step).
Next, the abnormality degree calculation unit 16 inputs the machining data stored in the machining data storage unit 12 to the selected model to obtain the machining abnormality degree (S17: abnormality determination step), and the spare tool replacement determination unit 29 compares the threshold stored in the threshold storage unit 18 with the degree of abnormality (S18: abnormality determination step). If the degree of abnormality is equal to or less than the threshold, the process returns to S13 to continue machining, and if the degree of abnormality is greater than the threshold, the current tool is replaced with a spare tool (S19).
Next, the spare tool is imaged by the camera of the in-machine photographing unit 21 and the image data is stored in the photographed data storage unit 22 (S20), and the type of tool is estimated by the tool estimation unit 23 from the image data of the spare tool ( S21).
Then, the tool confirmation unit 30 determines whether or not the types of the current tool and the spare tool are the same (S22: tool determination step). If the types are different, the NC unit 11 is instructed to interrupt or stop machining.

As described above, the machine tool processing abnormality detection method and processing abnormality detection device 20 of the above-described embodiments obtain image data by capturing images of the tool and the work material in the machine tool using an imaging device provided in the machine tool. Estimate the type of tool and work material from the obtained image data, select the abnormal machining detection model based on the estimated type of tool and work material, and input the machining data to the selected abnormal machining detection model. Then, the presence or absence of machining abnormality is determined.
According to this configuration, it is possible to estimate the types of the tool and the work material from the image data of the camera and the operation of the machine. can be selected. Therefore, highly accurate processing abnormality detection can be realized without human intervention.
The selected model can automatically continue the machining intended by the user according to the threshold by judging whether to continue machining by comparing with the threshold.
In addition, the machining program can be reused because there is no need to write a command to replace the machining error detection model in the machining program. When the degree of abnormality exceeds the threshold, the tool is replaced with a spare tool.
As described above, it is possible to automatically estimate the machining conditions and automatically continue the machining in accordance with the user's intention. Therefore, it is possible to promote unmanned factories and increase the operating rate of machines.
In addition, it is possible to prevent erroneous selection of a model to be used for detection of machining abnormality by hand, and prevent wear of tools and workpieces and damage to machine parts caused by erroneous selection of a machining abnormality detection model.

In the present disclosure, as an example of an image processing algorithm for obtaining the dimensions, size, and shape of a tool or a work piece from a captured image, there is a deep learning method, which is an inductive algorithm. There is Region CNN as a method for identifying the imaging area of a tool or work material from captured images inside the machine and detecting it as a tool or work material, and there is a generation query network that generates a three-dimensional shape from the captured image.
In addition, when selecting machining conditions for selecting a machining error detection model, if there is a model with generalization performance for an arbitrary work material type for a certain tool type, or if a certain work material type has an arbitrary tool If there is a model with generalization performance for the type, machining conditions for selecting a model may be determined based on at least one of specifying the type of tool and specifying the type of work material. Machining conditions recommended by the tool manufacturer or machining conditions set by the user may be used as the machining conditions corresponding to the types of tools and work materials.
Examples of processing error detection algorithms and processing error detection models used for detecting processing errors are as follows. As for the algorithm, the n-th order harmonic component of rotation is subtracted from the motor torque of the tool spindle, and this is used as the machining component torque for abnormality detection. The machining component torque during abnormal machining has a different tendency and magnitude from that during normal machining, so detection using a threshold is possible. In the above embodiment, the abnormal machining detection model is used to determine whether or not there is a machining abnormality. good.
Models include neural networks that infer and output future input values for inputs used for anomaly detection.

In the above embodiment, when the degree of abnormality in the degree-of-abnormality calculator exceeds the threshold value, the current tool is replaced with a spare tool. may be interrupted/stopped.

10, 20... Machining abnormality detector, 11... NC unit, 12... Machining data storage unit, 13... Model selection screen, 14... Model selection unit, 15... Selected model storage unit, 16... Abnormality degree calculation unit 17 Threshold setting unit 18 Threshold storage unit 19 Machining abnormality determination unit 21 In-machine photographing unit 22 Photographed data storage unit 23 Tool estimation unit 24 Weight estimation unit 25 Work material estimation unit 26 Tool estimation result storage unit 27 Work material estimation result storage unit 28 Machining condition determination unit 29 Spare tool replacement determination Part 30... Tool confirmation part.

Claims (12)

A machining abnormality detection method for detecting a machining abnormality from machining information acquired during machining in a machine tool that performs cutting based on a numerical control command,
an image data acquisition step of acquiring image data by imaging a tool and/or a work material in the machine using an imaging device provided in the machine tool;
a tool/work material estimation step of estimating the type of the tool and/or the work material from the acquired image data;
an algorithm/model selection step of selecting a machining abnormality detection algorithm/machining abnormality detection model based on the estimated type of the tool and/or the work material;
an anomaly determination step of inputting the machining information to the selected machining anomaly detection algorithm/machining anomaly detection model to determine the presence or absence of an anomaly in machining;
A machining abnormality detection method for a machine tool, comprising: In the tool/work material estimation step, when estimating the type of the work material, the work material is moved to estimate the weight, and the size of the work material acquired in the image data acquisition step is calculated. 2. The method of detecting an abnormality in machining of a machine tool according to claim 1, wherein the type of the work material is estimated from the shape and the estimated weight of the work material. In the algorithm/model selection step, based on the estimated type of the tool and/or the work material, a pre-associated machining condition is discriminated, and based on the discriminated machining condition, the machining abnormality is determined. 3. A method for detecting an abnormality in machining of a machine tool according to claim 1, wherein a detection algorithm/an abnormality in machining detection model is selected. In the abnormality determination step, the processing information is input to the processing abnormality detection algorithm/processing abnormality detection model to obtain the degree of processing abnormality, and the degree of abnormality is compared with a predetermined threshold. 4. A method for detecting an abnormality in machining of a machine tool according to claim 1, wherein an abnormality in machining is determined when the difference is large. 5. The machine tool according to any one of claims 1 to 4, wherein when it is determined that there is a machining abnormality in the abnormality determination step, the machine tool is caused to replace the currently used tool with a spare tool of the same type. Machining anomaly detection method. When the spare tool is replaced with the spare tool, the imaging device captures an image of the spare tool to acquire image data, and from the acquired image data, it is determined whether the spare tool is of the same type as the tool to be used. 6. The method of detecting an abnormality in machining of a machine tool according to claim 5, further comprising the step of further executing a tool discrimination step, and interrupting or stopping the machining if the tool discrimination step discriminates that the tools are not of the same type. A machining abnormality detection device for detecting a machining abnormality from machining information acquired during machining in a machine tool that performs cutting based on a numerical control command,
an image data acquisition means for acquiring image data by imaging a tool and/or a work material in the machine using an imaging device provided in the machine tool;
tool/work material estimation means for estimating the type of the tool and/or the work material from the acquired image data;
algorithm/model selection means for selecting a machining abnormality detection algorithm/machining abnormality detection model based on the estimated type of the tool and/or the work material;
abnormality determination means for inputting the machining information to the selected machining abnormality detection algorithm/machining abnormality detection model and determining the presence or absence of a machining abnormality;
A machining abnormality detection device for a machine tool, comprising: When estimating the type of the work material, the tool/work material estimation means estimates the weight of the work material by moving the work material, and calculates the size of the work material acquired by the image data acquisition means. 8. A processing abnormality detection device for a machine tool according to claim 7, wherein the type of the work material is estimated from the shape and the estimated weight of the work material. The algorithm/model selection means discriminates a pre-associated machining condition based on the estimated type of the tool and/or the work material, and determines the machining abnormality based on the discriminated machining condition. 9. The abnormal machining detection device for a machine tool according to claim 7, wherein a detection algorithm/abnormal machining detection model is selected. The abnormality determination means inputs the processing information to the processing abnormality detection algorithm/processing abnormality detection model, obtains the degree of abnormality of processing, compares the degree of abnormality with a predetermined threshold value, and determines that the degree of abnormality is higher than the threshold value. 10. The abnormal machining detection device for a machine tool according to any one of claims 7 to 9, characterized in that when the difference is large, it is determined that the machining is abnormal. 11. The machining of the machine tool according to any one of claims 7 to 10, wherein when the abnormality determination means determines that there is a machining abnormality, the machine tool is caused to replace the currently used tool with a spare tool of the same type. Anomaly detection device. When the spare tool is replaced with the spare tool, the imaging device captures an image of the spare tool to acquire image data, and from the acquired image data, it is determined whether the spare tool is of the same type as the tool to be used. 12. The abnormal machining detection apparatus for a machine tool according to claim 11, further comprising tool discriminating means for determining that the tools are not of the same type, and interrupting or stopping machining when said tool discriminating means determines that the tools are not of the same type.

Images