JP2020187708A - Machine tool, behavior type determination method and behavior type determination program - Google Patents

Abstract

To provide a technique for determining a behavior type of a worker of a machine tool in more detail.SOLUTION: A machine tool comprises: a work area where a person works on a work-piece; a human detection sensor that detects a motion of a person who is in the work area; and a control device that controls the machine tool. The control device includes: an acquisition unit that acquires a status value indicating a status of the machine tool; and a detection unit that, based on an output value of the human detection sensor and the status value acquired by the acquisition unit, determines a behavior type of the person who is in the work area.SELECTED DRAWING: Figure 3

Description

The present disclosure relates to a technique for determining a behavior type of a worker working on a machine tool.

It is required to collect the operating status of machine tools. The collected operating conditions are used, for example, to review the design concept of machine tools and the production process of workpieces.

In order to analyze the operating status of machine tools in detail, it is necessary to collect various operating conditions such as the working time required for each work process by the worker as well as the machining time required to process the workpiece. is there. In order for the worker to grasp the work time required for each work process, it is necessary to discriminate the action type of the worker in more detail.

Regarding such a technique, Japanese Patent Application Laid-Open No. 2013-73279 (Patent Document 1) discloses a data processing device for classifying the operating status of a manufacturing device. More specifically, when the data processing device detects the holding state of the work with respect to the holding means of the work, and the manufacturing device does not perform processing even though the holding means holds the work. In addition, it is determined that the manufacturing apparatus is in the standby state.

Japanese Unexamined Patent Publication No. 2013-73279

As in the data processing device disclosed in Patent Document 1, the behavior of the operator that can be discriminated is limited only by the gripping state of the work. In order to solve such a problem, it is desired to determine the action type of the machine tool worker in more detail.

In one example of the present disclosure, a machine tool for processing a work includes a work area for a person to work on the work, a motion sensor for detecting the movement of a person in the work area, and the like. It is provided with a control device for controlling the machine tool. The control device is in the work area based on an acquisition unit for acquiring a state value indicating the state of the machine tool, an output value of the motion sensor, and a state value acquired by the acquisition unit. Includes a discriminating unit for discriminating the behavior type of a person.

In one example of the present disclosure, the action type that can be discriminated by the discriminating unit includes during setup work indicating that a person in the work area is working on the work.

In one example of the present disclosure, the machine tool further comprises an operating unit for receiving an operation on the machine tool. The state value includes the operation state of the operation unit. When the movement of the person in the work area is detected by the motion sensor and the operation state indicates that the operation is in progress, the discrimination unit determines that the action type is in the setup work. To do.

In one example of the present disclosure, the action type that can be discriminated by the discriminating unit includes during cleaning work indicating that a person in the work area is cleaning. When the movement of the person in the work area is detected by the motion sensor and the operation state indicates that the operation state is not being operated, the acquisition unit determines that the action type is the cleaning operation. Determine.

In one example of the present disclosure, the machine tool includes an openable / closable door that separates the work installation location and the work area, and an open / close sensor for detecting the open / closed state of the door. The state value includes the open / close state detected by the open / close sensor. When the movement of the person in the work area is detected by the motion sensor and the open / closed state indicates the open state of the door, the discriminating unit determines that the action type is in the setup work. To do.

In one example of the present disclosure, the action type that can be discriminated by the discriminating unit includes during cleaning work indicating that a person in the work area is cleaning. When the movement of a person in the work area is detected by the motion sensor and the open / closed state indicates the closed state of the door, the discriminating unit determines that the action type is in the cleaning operation. To do.

In one example of the present disclosure, the action type that can be discriminated by the discriminating unit includes an incapacitating state indicating that the person is incapacitated in the work area. In the discriminating unit, when the output value by the motion sensor does not change within a predetermined time and the state value acquired by the acquisition unit does not change within a predetermined time, the action type is disabled. Determine that it is in a state.

Another example of the present disclosure provides a method of determining the behavior type of a person in a machine tool. The machine tool includes a work area for the person to work on the work to be machined, and a motion sensor for detecting the movement of the person in the work area. The discrimination method is based on the step of acquiring the output value of the motion sensor, the step of acquiring the state value indicating the state of the machine tool, the output value of the motion sensor, and the state value. It includes a step of determining the action type of a person in the work area.

In another example of the present disclosure, a program for determining the behavior type of a person in a machine tool is provided. The machine tool includes a work area for the person to work on the work to be machined, and a motion sensor for detecting the movement of the person in the work area. The discrimination program has a step of acquiring the output value of the motion sensor, a step of acquiring a state value indicating the state of the machine tool, an output value of the motion sensor, and the state value of the machine tool. Based on the above, the step of determining the action type of the person in the work area is executed.

The above and other objectives, features, aspects and advantages of the present invention will become apparent from the following detailed description of the present invention as understood in connection with the accompanying drawings.

It is a figure which shows the appearance of a machine tool. It is a figure which shows an example of the device structure of a machine tool. It is a figure which shows an example of the functional structure for realizing the action discrimination function. It is a figure which shows the processing machine which constitutes a machine tool, and the worker. It is the figure which showed the state in the work station from the top. It is the figure which showed the state in the work station from the front. It is the figure which showed the state in the work station diagonally. It is a figure which shows the action type definition used in the action type discrimination method 1. It is a figure which shows the action type definition used in the action type discrimination method 2. It is a figure which shows the action type definition used in the action type discrimination method 3. It is a figure which shows the action type definition used in the action type discrimination method 4. It is a figure which shows an example of the data structure of the work history. It is a figure which shows roughly the cooperative relationship of various equipments constituting a machine tool. It is a schematic diagram which shows an example of the hardware configuration of a control system. It is a block diagram which shows the main hardware composition of PLC (Programmable Logic Controller). It is a block diagram which shows the main hardware composition of a processing machine. It is a figure which shows an example of the hardware composition of an image processing apparatus. It is a flowchart which shows a part of the processing executed by a control device.

Hereinafter, embodiments according to the present invention will be described with reference to the drawings. In the following description, the same parts and components are designated by the same reference numerals. Their names and functions are the same. Therefore, the detailed description of these will not be repeated. In addition, each embodiment and each modification described below may be selectively combined as appropriate.

<A. Appearance of machine tool 10>
A machine tool 10 according to an embodiment will be described with reference to FIG. FIG. 1 is a diagram showing the appearance of the machine tool 10.

Hereinafter, as an example of the machine tool 10, a pallet transport system having a function of automatically transporting a workpiece to be machined according to a predetermined schedule will be described, but the machine tool 10 is not limited to the pallet transport system. The machine tool 10 may be, for example, a processing machine that does not have an automatic work transfer function, or may be a processing machine that includes an arm robot instead of the pallet transfer function.

The machine tool 10 as a pallet transfer system includes one or more control devices 50, one or more storage units 200, one or more transfer devices 300, one or more processing machines 400, and one or more. Includes work station 500 and.

The storage unit 200 is one of the transfer destinations of the pallet PL by the transfer device 300, and is a place for storing the pallet PL. A plurality of pallet PLs can be stored in the storage unit 200. In the storage unit 200, an empty pallet before the work is attached, a pallet to which the work before processing is attached, a pallet to which the work in the middle of processing is attached, or a pallet to which the processed work is attached. Etc. are stored.

The transport device 300 transports the designated pallet PL to the designated location. More specifically, the transport device 300 includes a rail 330 and a carriage 331. The bogie 331 has a fork portion 333 configured to be driveable in a direction orthogonal to the rail 330 (that is, a direction orthogonal to the traveling direction of the bogie 331). The carriage 331 is configured to be movable along the rail 330 by, for example, a servomotor 335 (see FIG. 2) described later. The carriage 331 moves along the rail 330 to the position of the pallet PL to be conveyed, and the pallet PL to be conveyed is placed on the carriage 331 using the fork portion 333. After that, the carriage 331 moves along the rail 330 to the designated destination, and the pallet PL to be transported is carried into the destination using the fork portion 333.

The processing machine 400 is one of the transfer destinations of the pallet PL by the transfer device 300. The processing machine 400 processes the work attached to the carried-in pallet PL according to a processing program designed in advance. When the processing of the work is completed, the pallet PL in the processing machine 400 is conveyed to the storage unit 200 or the work station 500 by the transfer device 300. Further, the processing machine 400 is provided with an operation panel 430 that receives various operations on the processing machine 400.

The work station 500 is one of the transfer destinations of the pallet PL by the transfer device 300. The work station 500 is a work area for an operator to perform various operations on the pallet PL that has been brought in. At the work station 500, the worker attaches the work to be processed to the carried-in pallet PL, removes the processed work from the pallet PL, cleans the work area, and the like. When the work on the pallet PL is completed, the operator performs an operation for instructing the completion of the work. Based on this, the pallet PL in the work station 500 is conveyed to the storage unit 200 or the processing machine 400 by the transfer device 300.

<B. Equipment configuration of machine tool 10>
FIG. 2 is a diagram showing an example of the device configuration of the machine tool 10. An example of the device configuration of the machine tool 10 will be described with reference to FIG.

As shown in FIG. 2, the machine tool 10 includes a control device 50, remote I / O (Input / Output) units 61 to 64, a transfer device 300, a processing machine 400, and a work station 500.

The “control device 50” as used herein means a device that controls a machine tool 10. The device configuration of the control device 50 is arbitrary. The control device 50 may be composed of a single control unit or a plurality of control units. In the example of FIG. 2, the control device 50 includes a control system 100 and a control panel 150.

The control panel 150 controls various industrial devices for automating the processing process. The control panel 150 includes the PLC 151.

The control system 100 and the PLC 151 are connected to the network NW1. The control system 100 and the PLC 151 may be connected by wire or wirelessly. EtherNET (registered trademark) or the like is adopted for the network NW1. The control system 100 sends a control command to the PLC 151 via the network NW1. The control system 100 specifies the pallet PL to be transported, the destination of the pallet PL to be transported, the start / stop of transport of the pallet PL to be transported, and the processing by the processing machine 400 according to the control command. Specify the start / stop of machining.

The remote I / O units 61-64 and PLC151 are connected to the network NW2. It is preferable to adopt a field network that performs constant periodic communication for the network NW2. A field network is a common name for a network in which the arrival time of data is guaranteed. As the field network, EtherCAT (registered trademark), EtherNet / IP (registered trademark), CC-Link (registered trademark), CompoNet (registered trademark) and the like are adopted.

The transport device 300 includes one or more servo drivers 334 and one or more servo motors 335. A remote I / O unit 61 is installed in or around the transport device 300. The remote I / O unit 61 mediates the exchange of data between various drive units (for example, the servo driver 334) in the transfer device 300 and the PLC 151. The servo driver 334 receives a control command from the PLC 151 via the remote I / O unit 61 at regular intervals, and drives and controls the servo motor 335 according to the control command. As an example, one servomotor 335 drives and controls the above-mentioned carriage 331 (see FIG. 1), and another servomotor 335 drives and controls the above-mentioned fork portion 333 (see FIG. 1).

The processing machine 400 includes a CNC (Computer Numerical Control) 401, a servo driver 411, a servo motor 412, and an operation panel 430. A remote I / O unit 62 is installed in or around the processing machine 400. The remote I / O unit 62 mediates the exchange of data between various drive units (for example, CNC 401 and operation panel 430) in the processing machine 400 and the PLC 151. The servo driver 411 receives a control command from the PLC 151 via the remote I / O unit 62 at regular intervals, and drives and controls the servo motor 412 according to the control command. The operation panel 430 transmits the operation input received from the operator to the PLC 151 via the remote I / O unit 62.

The work station 500 includes a motion sensor 530 and various other sensors 550. Remote I / O units 63 and 64 are installed in or around the work station 500.

The remote I / O unit 63 mediates the exchange of data between the motion sensor 530 and the PLC 151. The motion sensor 530 detects the operating state of the worker at the work station 500. In the example of FIG. 2, the motion sensor 530 is composed of an image processing device 532 and a camera 534. The details of the method of detecting the operating state of the operator by the motion sensor 530 will be described later. The image processing device 532 sends the detected operating state to the PLC 151 via the remote I / O unit 63 at regular intervals.

Note that FIG. 2 shows an example in which the motion sensor 530 is composed of the image processing device 532 and the camera 534, but the motion sensor 530 is not limited to the example of FIG. Any motion sensor capable of detecting the operating state can be substituted. As an example, the motion sensor 530 may be a load cell arranged at each location under the floor of the work station 500. The load cell detects the force applied to the floor of the work station 500. When the detected value of the load cell exceeds a predetermined value, it means that there is an operator on the load cell. By comprehensively analyzing the detection results of the load cells at each location, the operating state of the operator can be detected.

The remote I / O unit 64 mediates the exchange of data between the various sensors 550 and the PLC 151. The various sensors 550 are arbitrary sensors for detecting the state of the machine tool 10. The various sensors 550 include, for example, an open / close sensor 541 (see FIGS. 5 and 6) described later, a clamp sensor 543 (see FIGS. 5 and 6) described later, an area sensor 545 (see FIG. 5) described later, and the like. .. The detected values of the various sensors 550 are sent to the PLC 151 via the remote I / O unit 64 at regular intervals.

<C. Behavior discrimination function>
In order to accurately analyze the operating status of machine tools, it is necessary for workers to collect the work time required for each work process. For that purpose, it is necessary to discriminate the action type performed by the worker at the work station 500 in more detail. The machine tool 10 according to the present embodiment acquires a state value indicating the state of the machine tool 10 (hereinafter, also referred to as “machine tool state value”), and the machine tool state value and the above-mentioned motion sensor 530. Based on the output value, the action type of the worker existing in the work station 500 is determined.

The "machine tool state value" referred to here is an arbitrary index for specifying the state of the machine tool 10 in operation. Typically, the machine tool state value is a physical quantity that changes according to the work status or operation instruction of the worker with respect to the machine tool 10, or various variable values specified in the program (for example, during machining / non-machining). (Variable value indicating). The details of the machine tool state value will be described later.

When the machine tool 10 uses two pieces of information, the detection result of the worker by the motion sensor 530 and the machine tool state value, the action type of the worker is more different than when one piece of information is used. It can be classified in detail. The classification result of such an action type is used, for example, to analyze the work time required for each work process by the worker. Designers and managers can accurately analyze the operating status of machine tools by grasping the work time for each work process that is classified in more detail, and review the design concept of the machine tool and the production process of the work. Can be done.

FIG. 3 is a diagram showing an example of a functional configuration for realizing the behavior discrimination function. The control device 50 includes an acquisition unit 152 and an action determination unit 154 as a functional configuration. These functional configurations are implemented in, for example, the control system 100 or the PLC 151 constituting the control device 50. In a certain aspect, one function of the acquisition unit 152 and the action determination unit 154 is implemented in the control system 100, and the other function is implemented in the PLC 151. In another aspect, both the acquisition unit 152 and the action determination unit 154 are implemented in the control system 100. In another aspect, both the acquisition unit 152 and the action determination unit 154 are implemented in the PLC 151.

The image processing device 532 includes a person detection unit 552 and a motion analysis unit 554 as functional configurations. The person detection unit 552 and the motion analysis unit 554 may be mounted on the control device 50 instead of the image processing device 532.

Hereinafter, the function of the acquisition unit 152, the function of the person detection unit 552, the function of the motion analysis unit 554, and the function of the action determination unit 154 will be described in order.

(C1. Acquisition unit 152)
First, the function of the acquisition unit 152 will be described. The acquisition unit 152 acquires a state value (that is, a machine tool state value) indicating the state of the machine tool 10 from the above-mentioned various sensors 550 (see FIG. 2). The acquisition unit 152 may be configured to acquire one type of machine tool state value, or may be configured to acquire a plurality of types of machine tool state values. The acquired machine tool state value is output to the action determination unit 154.

Hereinafter, specific examples 1 to 4 of the machine tool state values acquired by the acquisition unit 152 will be described in order.

(A) Specific example of machine tool state value 1
First, a specific example 1 of the machine tool state value will be described with reference to FIG. FIG. 4 is a diagram showing a processing machine 400 constituting the machine tool 10 and an operator U1.

As shown in FIG. 4, the processing machine 400 is provided with an operation panel 430 (operation unit). The operation panel 430 accepts various operations on the processing machine 400. In the example of FIG. 4, the operation panel 430 is operated by the operator U1.

The acquisition unit 152 acquires the operation state of the operation panel 430 by the operator U1 as the machine tool state value. Typically, the acquisition unit 152 acquires the operation content input to the operation panel 430 from the operation panel 430, and determines whether the operation panel 430 is in operation or non-operation. As an example, the acquisition unit 152 determines that the operation is not being performed when there is no operation input to the operation panel 430 for a certain period of time or more, and determines that the operation is being performed otherwise. As a result, the acquisition unit 152 acquires the operation state indicating that it is operating or not operating as the machine tool state value.

(B) Specific example of machine tool state value 2
Next, a specific example 2 of the machine tool state value will be described with reference to FIGS. 5 and 6. FIG. 5 is a view showing the inside of the work station 500 from above. FIG. 6 is a front view of the inside of the work station 500.

As shown in FIGS. 5 and 6, a door DR is provided so as to separate the installation location of the work transported to the work station 500 by the transport device 300 from the work area where the worker U2 performs the setup work. Be done. The setup work means a work of attaching a work to be machined to a pallet, a work of removing a machined work from a pallet, and the like.

The acquisition unit 152 acquires the open / closed state of the door DR as a machine tool state value. More specifically, the worker U2 opens the door DR based on the empty pallet PL being carried into the work station 500, and starts the work W attachment work. When the installation work of the work W is completed, the worker U2 closes the door DR and presses the work completion button BT. The pallet PL is carried out from the work station 500 based on the fact that the work completion button BT is pressed. In this way, the worker U2 opens the door DR during the work W mounting work, and closes the door DR based on the completion of the work W mounting work.

Further, the worker U2 opens the door DR based on the fact that the pallet PL on which the processed work is carried is carried into the work station 500, and starts the work of removing the work W. When the work W removal work is completed, the worker U2 closes the door DR and presses the work completion button BT. Based on the work completion button BT being pressed, the empty pallet PL is carried out from the work station 500. In this way, the worker U2 opens the door DR during the work W removal work, and closes the door DR based on the completion of the work W removal work.

As described above, the open / closed state of the door DR can be an index (that is, a machine tool state value) for specifying the state of the machine tool 10.

An open / close sensor 541 is provided on the door DR in order to detect the open / closed state of the door DR. The open / close sensor 541 is an example of the above-mentioned various sensors 550 (see FIG. 2). The open / close sensor 541 has a wireless communication function. When the door DR is open, the open / close sensor 541 outputs a signal indicating the open state to the remote I / O unit 64 (see FIG. 2) described above. On the other hand, when the door DR is closed, the open / close sensor 541 outputs a signal indicating the open state to the remote I / O unit 64 described above. The remote I / O unit 64 transmits the open / closed state received from the open / close sensor 541 to the control device 50 via the above-mentioned network NW2 (see FIG. 2) at regular intervals. As a result, the acquisition unit 152 of the control device 50 acquires the open / closed state of the door DR.

(C) Specific example of machine tool state value 3
Subsequently, a specific example 3 of the machine tool state value will be described with reference to FIGS. 5 and 6. The acquisition unit 152 acquires a physical quantity indicating the strength at which the work W is fixed to the jig AP attached to the pallet PT as a machine tool state value. The physical quantity is detected by, for example, the clamp sensor 543. The clamp sensor 543 is an example of the above-mentioned various sensors 550 (see FIG. 2).

The worker U2 fixes the work W to the jig AP using the fixtures FA to FD. The clamp sensor 543 detects, for example, the clamp strength of the fixture FA. At this time, before the work W is attached to the jig AP, the clamp strength detected by the clamp sensor 543 becomes substantially zero. Then, as the work of attaching the work W to the jig AP progresses, the clamp strength detected by the clamp sensor 543 increases. On the other hand, in the work W removal work, the clamp strength detected by the clamp sensor 543 decreases as the removal work progresses.

As described above, since the clamp strength changes according to the progress of the setup work, it can be an index (that is, a machine tool state value) for specifying the state of the machine tool 10.

The clamp sensor 543 has a wireless communication function, and transmits the detected clamp strength to the remote I / O unit 64 (see FIG. 2) at regular intervals. The remote I / O unit 64 transmits the clamp strength received from the clamp sensor 543 to the control device 50 via the above-mentioned network NW2 (see FIG. 2) at regular intervals. As a result, the acquisition unit 152 of the control device 50 acquires the clamp strength from the clamp sensor 543.

Although one clamp sensor 543 is shown in the examples of FIGS. 5 and 6, a plurality of clamp sensors 543 may be provided. In this case, each of the plurality of clamp sensors 543 is provided for each of the fixtures FA to FD.

(D) Specific example of machine tool state value 4
Subsequently, a specific example 4 of the machine tool state value will be described with reference to FIGS. 5 and 6. The acquisition unit 152 acquires the output value of the area sensor 545 as the machine tool state value. The area sensor 545 is an example of the above-mentioned various sensors 550 (see FIG. 2).

The area sensor 545 includes a light emitting unit 545A and a light receiving unit 545B. The light emitting unit 545A emits light toward the light receiving unit 545B. The light receiving unit 545B receives the light emitted from the light projecting unit 545A and outputs the intensity of the light. The light projecting unit 545A and the light receiving unit 545B are arranged so that the light emitted from the light projecting unit 545A is blocked by the worker U2 who is working. In other words, the floodlight unit 545A and the light receiving unit 545B are arranged so that the light emitted from the floodlight unit 545A passes between the work transfer location in the work station 500 and the work area of the worker U2. Will be done.

Since the worker U2 is near the pallet PL during the setup work, the light emitted from the floodlight unit 545A is blocked by the worker U2. When the setup work is completed, the worker U2 leaves the work area. Therefore, after the setup work is completed, the light emitted from the floodlight unit 545A is not blocked by the worker U2. Since the intensity of light received by the light receiving unit 545B from the light projecting unit 545A changes according to the progress of the work W mounting work, it is an index for identifying the state of the machine tool 10 (that is, that is). It can be a machine tool state value).

The light receiving unit 545B outputs to the remote I / O unit 64 (see FIG. 2) whether or not the light from the light projecting unit 545A is blocked. The remote I / O unit 64 transmits whether or not the light from the light projecting unit 545A is blocked to the control device 50 via the above-mentioned network NW2 (see FIG. 2) at regular intervals.

(C2. Person detection unit 552)
Next, with reference to FIG. 7, the function of the person detection unit 552 shown in FIG. 3 will be described. FIG. 7 is an oblique view of the inside of the work station 500.

In the example of FIG. 7, the jig AP is attached to the pallet PL. The jig AP is, for example, ikeru. The work W to be processed is attached to the jig AP by the worker U2.

As shown in FIG. 7, a camera 534 is provided in the work station 500. The camera 534 is installed so as to photograph the work area in the work station 500, and photographs the worker U2 performing the setup work in the work station 500. Only one camera 534 may be arranged in the work station 500, or a plurality of cameras 534 may be arranged. The camera 534 periodically sends the image obtained by photographing the work area to the person detection unit 552 of the image processing device 532.

The person detection unit 552 detects the worker from the image obtained from the camera 534. An arbitrary image processing program is adopted as the image processing algorithm for detecting the worker.

In a certain aspect, the image processing device 532 acquires in advance a background image in which the worker is not shown. When the image processing device 532 acquires the input image obtained by photographing the work area from the same viewpoint as the background image, the image processing device 532 differentials the background image from the input image. As a result, the image processing device 532 can obtain a background subtraction image obtained by removing the background from the input image. The image processing device 532 extracts a region having a pixel value equal to or higher than a predetermined value from the background subtraction image, and detects the region as a person region.

In another aspect, the person detection unit 552 detects the worker from the image using the trained model. The trained model is pre-generated by a training process using a training data set. The training data set contains a plurality of training images showing a person. Each learning image is associated with a label indicating whether or not a person is shown. The internal parameters of the trained model are pre-optimized by the training process using such a training data set.

Various machine learning algorithms can be adopted as the learning method for generating the trained model. As an example, as the machine learning algorithm, deep learning, convolutional neural network (CNN), full-layer convolutional neural network (FCN), support vector machine and the like are adopted.

Preferably, the person detection unit 552 detects the coordinates of each part such as the worker's hand or arm from the image obtained from the camera 534. The above-mentioned machine learning algorithm is adopted for detecting each part of the worker.

The above-mentioned person detection process is sequentially executed on the images obtained from the camera 534. The person detection unit 552 sequentially outputs the detection result of the person to the motion analysis unit 554.

(C3. Motion analysis unit 554)
Next, the function of the motion analysis unit 554 shown in FIG. 3 will be described. The motion analysis unit 554 sequentially receives the person detection results output from the person detection unit 552 and analyzes the motion state of the worker.

The person detection result by the person detection unit 552 is represented by, for example, the coordinate values of the worker in the image. Preferably, the coordinate value represents the position of the worker's face, arm, or hand. The motion analysis unit 554 calculates an index that correlates with the motion amount of the operator based on the coordinate values sequentially obtained from the person detection unit 552. As an example of the index, the motion analysis unit 554 sequentially calculates the variance value (that is, the movement variance) of the coordinate values obtained within a predetermined time.

The motion analysis unit 554 determines that the operator is in operation when the calculated movement variance is larger than a predetermined first threshold value. The operating state means a state in which an operator is performing some work at the work station 500.

Further, when the calculated movement variance is smaller than a predetermined second threshold value (≦ first threshold value), the motion analysis unit 554 determines that the worker is inactive. Stopping the action means that the worker is not operating.

When the person is not detected by the person detection unit 552, the motion analysis unit 554 outputs the person undetected as the motion analysis result of the worker.

As described above, the motion analysis unit 554 outputs the motion analysis result of the worker in the work station 500 as the motion analysis, the action stop, or the person not detected. The motion analysis result by the motion analysis unit 554 is output to the action determination unit 154.

The motion states that can be analyzed by the motion analysis unit 554 are not limited to the three types of motion, motion stoppage, and person undetected. As an example, the motion analysis unit 554 may further classify "in operation" according to the amount of motion of the operator. For example, "in operation" may be classified into "in operation (large amount of operation)" and "in operation (small amount of operation)" according to the amount of operation of the operator.

(C4. Behavior discrimination unit 154)
Next, the function of the behavior determination unit 154 shown in FIG. 3 will be described with reference to FIGS. 7 to 12. FIG. 7 is an oblique view of the inside of the work station 500.

The action determination unit 154 determines the action type of the worker in the work station 500 based on the machine tool state value acquired by the acquisition unit 152 and the operation state of the worker by the motion sensor 530. At that time, the action type of the worker is determined based on the action type definition 124 in which the action type is associated with each combination of the machine tool state value and the operation state.

The action types that can be discriminated by the action discriminating unit 154 include, for example, "setup work", "cleaning work", "incapacity state", and "non-work state". “During setup work” means that the operator is performing work such as attaching the work to be machined to the pallet or removing the machined work from the pallet. “During cleaning work” means that the worker is cleaning the work area. The "incapacitated state" means that the worker is in a state of being unable to move for some reason. The "non-working state" means that the worker is not at the work station 500.

When the action type of the worker is determined to be "incapacitated state", the machine tool 10 outputs an alarm by voice or warning sound to notify the surroundings that the worker is in "incapacitated state". To do.

In the following, the behavior type discrimination methods 1 to 5 based on the behavior type definition 124 will be described in order.

(A) Behavior type discrimination method 1
First, the behavior type discrimination method 1 by the behavior discrimination unit 154 will be described with reference to FIG. FIG. 8 is a diagram showing an action type definition 124 used in the action type determination method 1.

As shown in FIG. 8, in this example, the action type of the operator is determined by the combination of the operation state of the operation panel 430 and the motion analysis result by the motion sensor 530. As described in "(a) Specific example 1 of machine tool state value" described above, the operating state of the operation panel 430 is an example of the machine tool state value, and is represented by "operating" or "non-operating". Is done.

When the operation state of the operation panel 430 indicates "in operation" and the operation analysis result indicates "in operation", the action determination unit 154 determines that the action type of the worker is "in setup work". ..

When the worker U2 shown in FIG. 7 is performing some operation inside the work station 500, and the worker U1 shown in FIG. 4 is operating the operation panel 430 of the processing machine 400 outside the work station 500. There is a high possibility that the worker U2 is performing the setup work. In this way, by considering both the motion analysis result of the motion sensor 530 and the operating state of the operation panel 430, it is possible to reliably detect the setup work.

Further, when the operation state of the operation panel 430 indicates "not in operation" and the operation analysis result indicates "in operation", the action determination unit 154 sets the action type of the operator to "cleaning work" or "cleaning work in progress". It is determined that "setup work is in progress". “During cleaning work” or “during setup work” is distinguished according to, for example, the amount of movement of the operator. As an example, when the operation state indicates "in operation" and the operation analysis result indicates "in operation (large amount of operation)", the action determination unit 154 sets the action type of the worker to "cleaning work in progress". Determine. Further, when the operation state indicates "in operation" and the operation analysis result indicates "in operation (small amount of operation)", the action determination unit 154 indicates that the action type of the worker is "in setup work". To determine.

Further, when the operation state of the operation panel 430 indicates "non-operating" and the motion analysis result indicates "non-operating", the action discriminating unit 154 sets the action type of the worker to "incapacitated state". Determine. More specifically, in the action determination unit 154, the machine tool state value as an operating state does not change by a predetermined value or more within a predetermined time, and the output value by the motion sensor 530 changes by a predetermined value or more within a predetermined time. If not, it is determined that the action type is "incapacitated state".

Further, when the action analysis result indicates "person not detected", the action determination unit 154 determines that the action type of the worker is "non-working state".

(B) Behavior type discrimination method 2
Next, with reference to FIG. 9, the action type discrimination method 2 by the action discrimination unit 154 will be described. FIG. 9 is a diagram showing an action type definition 124 used in the action type determination method 2.

As shown in FIG. 9, in this example, the action type of the worker is determined by the combination of the open / closed state of the door DR that can be detected by the above-mentioned open / close sensor 541 and the motion analysis result by the motion sensor 530. .. As described in "(b) Specific example 2 of the machine tool state value" described above, the open / closed state of the door DR is an example of the machine tool state value, and is represented by "open state" or "closed state".

When the open / closed state indicates "open state" and the operation analysis result indicates "in operation", the action determination unit 154 determines that the action type of the worker is "setup work in progress".

Further, when the open / closed state indicates "closed state" and the operation analysis result indicates "in operation", the action determination unit 154 determines that the action type of the worker is "cleaning work in progress".

Further, when the open / closed state indicates "closed state" and the motion analysis result indicates "non-operating", the action determining unit 154 determines the action type of the worker as "incapacitated state". More specifically, when the open / closed state does not change within a predetermined time and the output value by the motion sensor 530 does not change by a predetermined value or more within a predetermined time, the action type is set to "behavior". It is determined that it is in an "impossible state".

Further, when the action analysis result indicates "person not detected", the action determination unit 154 determines that the action type of the worker is "non-working state".

(C) Behavior type discrimination method 3
Next, with reference to FIG. 10, the action type discrimination method 3 by the action discrimination unit 154 will be described. FIG. 10 is a diagram showing an action type definition 124 used in the action type determination method 3.

As shown in FIG. 10, in this example, the action type of the operator is determined by the combination of the state of the clamp strength detected by the clamp sensor 543 and the motion analysis result by the motion sensor 530. Clamp strength is an example of machine tool state value. As described in "(c) Specific example 3 of machine tool state value" described above, the clamp strength detected by the clamp sensor 543 increases as the work of attaching the work to the jig progresses. On the other hand, in the work removal work, the clamp strength detected by the clamp sensor 543 decreases as the removal work progresses.

Focusing on this point, when the clamp strength is increased and the motion analysis result indicates "in motion", the action type of the worker is "in setup work (installation work)". It is determined that it is. On the other hand, when the clamp strength is reduced and the operation analysis result indicates "in operation", it is determined that the action type of the operator is "in setup work (during removal work)".

Whether or not the clamp strength is increased is determined based on, for example, the amount of change in the clamp strength. More specifically, when the moving average value of the clamp strength is larger than the previous value, the behavior determination unit 154 determines that the clamp strength is increasing. On the other hand, when the moving average value of the clamp strength is smaller than the previous value, the behavior determination unit 154 determines that the clamp strength is reduced.

Further, when the clamp strength is not detected and the motion analysis result indicates "in operation", the action determination unit 154 determines that the action type of the worker is "cleaning work in progress". Alternatively, when the clamp strength is less than a predetermined value and the motion analysis result indicates "in operation", the action determination unit 154 determines that the action type of the worker is "cleaning work in progress".

Further, when the clamp strength does not change and the motion analysis result indicates "non-operating", the behavior determining unit 154 determines the behavior type of the worker as "incapacitated state". More specifically, the action determination unit 154 determines the action type when the clamp strength does not change by a predetermined value or more within a predetermined time and the output value by the motion sensor 530 does not change by a predetermined value or more within a predetermined time. Is determined to be in an "incapacitated state".

Further, when the action analysis result indicates "person not detected", the action determination unit 154 determines that the action type of the worker is "non-working state".

(D) Behavior type discrimination method 4
Next, with reference to FIG. 11, the action type discrimination method 4 by the action discrimination unit 154 will be described. FIG. 11 is a diagram showing an action type definition 124 used in the action type determination method 4.

As shown in FIG. 11, in this example, the action type of the worker is determined by the combination of the output value of the area sensor 545 described above and the motion analysis result by the motion sensor 530. As described in "(d) Specific example 4 of machine tool state value" described above, the output value of the area sensor 545 is an example of the machine tool state value, and is represented by "blocked state" or "non-blocked state". Is done.

When the output value of the area sensor 545 indicates "blocking state" and the operation analysis result indicates "in operation", the action determination unit 154 determines that the action type of the worker is "setup work in progress". ..

Further, when the output value of the area sensor 545 indicates "non-blocking state" and the operation analysis result indicates "in operation", the action determination unit 154 determines that the action type of the worker is "cleaning work in progress". To do.

Further, when the output value of the area sensor 545 indicates "non-blocking state" and the motion analysis result indicates "non-operating", the action discrimination unit 154 sets the action type of the worker to "incapacitated state". Determine. More specifically, when the action determination unit 154 does not change the machine tool state value as an operating state within a predetermined time and the output value by the motion sensor 530 does not change by a predetermined value or more within a predetermined time. , It is determined that the action type is "incapacitated state".

Further, when the action analysis result indicates "person not detected", the action determination unit 154 determines that the action type of the worker is "non-working state".

(E) Behavior type discrimination method 5
In the above, the action determination unit 154 has determined the action type of the worker at the work station 500 based on the combination of one type of machine tool state value and the output value of the motion sensor 530. The method of determining the type is not limited to this. For example, the action determination unit 154 may determine the action type of the worker at the work station 500 based on the combination of two or more types of machine tool state values and the output value of the motion sensor 530.

(C5. Work history 126)
In the following, the work history 126 shown in FIG. 3 will be described with reference to FIG. FIG. 12 is a diagram showing an example of the data structure of the work history 126.

The action type determination result by the action determination unit 154 is written in the work history 126. The work history 126 may be stored in a storage device in the machine tool 10 or may be stored in an external device (for example, a server or an external hard disk).

As shown in FIG. 12, the work history 126 is associated with worker identification information (for example, worker ID (Identification)), action type detection time, and detected action type.

By analyzing the work history 126, the designer or the manager can accurately grasp the operating status of the machine tool, and can review the design concept of the machine tool and the production process of the work.

<D. Data sharing method>
A method of sharing data between various devices constituting the machine tool 10 will be described with reference to FIG. FIG. 13 is a diagram schematically showing a cooperative relationship of various devices constituting the machine tool 10.

As described above, the control system 100 and the PLC 151 are connected to a network NW1 such as Ethernet. The remote I / O units 61 to 64 and the PLC 151 are connected to the network NW2 which is a field network.

The frame 72 is transmitted to the network NW2. The frame 72 orbits the network NW2 at predetermined control cycles. The remote I / O units 61 to 64 and the PLC 151 share various data via the frame 72.

The frame 72 is, for example, a data area 71A for the PLC 151, a data area 71B for the transfer device 300 connected to the remote I / O unit 61, and data for the processing machine 400 connected to the remote I / O unit 62. It has a region 71C, a data region 71D for the human sensor 530 connected to the remote I / O unit 63, and a data region 71E for various sensors 550 connected to the remote I / O unit 64.

The data area 71A of the frame 72 is an area in which the PLC 151 writes various data. In the data area 71A, a transfer instruction of the pallet PL and the like are written. The transport instruction includes the transport destination of the pallet PL. The transport destination is, for example, an identification number indicating a storage location in the storage unit 200 (for example, an ID (Identification) indicating the storage location) or an identification number for identifying the processing machine 400 (for example, an ID of a machine tool). It is represented by. The various data written in the data area 71A by the PLC 151 can be referred to by various devices connected to the network NW2.

The data area 71B of the frame 72 is an area in which the remote I / O unit 61 writes various data related to the transfer device 300. Various data written in the data area 71B are referred to by various devices connected to the network NW2.

The data area 71C of the frame 72 is an area in which the remote I / O unit 62 writes various data related to the processing machine 400. The various data written in the data area 71C are referred to by various devices connected to the network NW2.

The data area 71D of the frame 72 is an area in which the remote I / O unit 63 writes the output value of the motion sensor 530. As an example, the above-mentioned motion analysis result detected by the motion sensor 530 is written in the data area 71D of the frame 72. The various data written in the data area 71D are referred to by various devices connected to the network NW2. The above-mentioned action determination unit 154 (see FIG. 3) acquires the motion analysis result by the motion sensor 530 by referring to the data area 71D of the frame 72.

The data area 71E of the frame 72 is an area in which the remote I / O unit 64 writes the output values of the various sensors 550. As an example, the above-mentioned machine tool state value is written in the data area 71E of the frame 72. The various data written in the data area 71E are referred to by various devices connected to the network NW2. The acquisition unit 152 (see FIG. 3) described above acquires various machine tool state values by referring to the data area 71E of the frame 72.

<E. Hardware configuration of control system 100>
The hardware configuration of the control system 100 will be described with reference to FIG. FIG. 14 is a schematic diagram showing an example of the hardware configuration of the control system 100.

The control system 100 includes a processor 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a communication interface 104, a display interface 105, an input interface 107, and a storage device 120. These components are connected to bus 110.

The processor 101 is composed of, for example, at least one integrated circuit. The integrated circuit is, for example, at least one CPU (Central Processing Unit), at least one GPU (Graphics Processing Unit), at least one ASIC (Application Specific Integrated Circuit), at least one FPGA (Field Programmable Gate Array), or them. It may be composed of a combination of.

The processor 101 controls the operation of the control system 100 by executing various programs such as the behavior discrimination program 122 and the operating system. The processor 101 reads the action determination program 122 from the storage device 120 or the ROM 102 into the RAM 103 based on the reception of the execution instruction of the action determination program 122. The RAM 103 functions as a working memory and temporarily stores various data necessary for executing the action determination program 122.

A LAN (Local Area Network), an antenna, or the like is connected to the communication interface 104. The control system 100 is connected to the network NW1 via the communication interface 104. As a result, the control system 100 exchanges data with an external device connected to the network NW1. The external device includes, for example, a control panel 150, a server (not shown), and the like. The control system 100 may be configured so that the behavior determination program 122 can be downloaded from the external device.

A display 106 is connected to the display interface 105. The display interface 105 sends an image signal for displaying an image to the display 106 in accordance with a command from the processor 101 or the like. The display 106 is, for example, a liquid crystal display, an organic EL (Electro Luminescence) display, or other display device. The display 106 may be integrally configured with the control system 100, or may be configured separately from the control system 100.

An input device 108 is connected to the input interface 107. The input device 108 is, for example, a mouse, keyboard, touch panel, or other device capable of accepting user operations. The input device 108 may be integrally configured with the control system 100, or may be configured separately from the control system 100.

The storage device 120 is, for example, a storage medium such as a hard disk or a flash memory. The storage device 120 stores the action discrimination program 122, the above-mentioned action type definition 124, the above-mentioned work history 126, and the like. These storage locations are not limited to the storage device 120, and may be stored in a storage area of the processor 101 (for example, a cache memory), a ROM 102, a RAM 103, an external device (for example, a server), or the like.

The behavior discrimination program 122 may be provided by being incorporated into a part of an arbitrary program, not as a single program. In this case, the action discrimination process by the action discrimination program 122 is realized in cooperation with an arbitrary program. Even a program that does not include such a part of the module does not deviate from the purpose of the behavior discrimination program 122 according to the present embodiment. Further, some or all of the functions provided by the behavioral determination program 122 may be realized by dedicated hardware. Further, the control system 100 may be configured in the form of a so-called cloud service in which at least one server executes a part of the processing of the behavior determination program 122.

<F. Hardware configuration of PLC151>
An example of the hardware configuration of the PLC 151 will be described with reference to FIG. FIG. 15 is a block diagram showing a main hardware configuration of PLC 151.

The PLC 151 includes a processor 161, a ROM (Read Only Memory) 162, a RAM (Random Access Memory) 163, communication interfaces 164 and 165, and a storage device 170.

The processor 161 is composed of at least one integrated circuit. An integrated circuit is composed of, for example, at least one CPU, at least one MPU (Micro Processing Unit), at least one ASIC, at least one FPGA, or a combination thereof.

The processor 161 controls the operation of the transfer device 300 and the processing machine 400 by executing various programs such as the control program 172. The processor 161 reads the control program 172 from the storage device 170 into the ROM 162 based on the reception of the execution instruction of the control program 172. The RAM 163 functions as a working memory and temporarily stores various data necessary for executing the control program 172.

A LAN, an antenna, or the like is connected to the communication interface 164. The PLC 151 is connected to the network NW1 via the communication interface 164. As a result, the PLC 151 exchanges data with an external device connected to the network NW1. The external device includes, for example, a control system 100, a server (not shown), and the like.

The communication interface 165 is an interface for connecting to the network NW2 which is a field network. The PLC 151 exchanges data with various devices connected to the network NW2 via the communication interface 165.

The storage device 170 is, for example, a storage medium such as a hard disk or a flash memory. The storage device 170 stores the control program 172 and the like. The storage location of the control program 172 is not limited to the storage device 170, and may be stored in a storage area of the processor 161 (for example, a cache area), a ROM 162, a RAM 163, an external device (for example, a server), or the like.

<G. Hardware configuration of processing machine 400>
An example of the hardware configuration of the processing machine 400 will be described with reference to FIG. FIG. 16 is a block diagram showing a main hardware configuration of the processing machine 400.

The processing machine 400 attaches CNC401, ROM402, RAM403, fieldbus controller 404, servo drivers 411A to 411D, servomotors 412A to 412D, encoders 413A to 413D, ball screws 414A and 414B, and tools. Includes a spindle 415 for the purpose and an operation panel 430. These devices are connected via a bus (not shown).

The CNC 401 is composed of at least one integrated circuit. An integrated circuit is composed of, for example, at least one CPU, at least one MPU, at least one ASIC, at least one FPGA, or a combination thereof.

The CNC 401 controls the operation of the CNC 400 by executing various programs such as the machining program 422. The CNC 401 reads the machining program 422 from the storage device 420 into the ROM 402 based on the reception of the execution command of the machining program 422. The RAM 403 functions as a working memory and temporarily stores various data necessary for executing the machining program 422.

The fieldbus controller 404 is an interface for realizing communication with the PLC 151 via the remote I / O unit 62. The CNC 400 exchanges data with the PLC 151 via the fieldbus controller 404.

The operation panel 430 accepts various operations on the processing machine 400. Further, the operation panel 430 includes a display (not shown) and displays various information. The display is, for example, a liquid crystal display, an organic EL display, or other display device.

The CNC 400 controls the servo driver 411A according to the machining program 422. The servo driver 411A sequentially receives input of the target rotation speed (or target position) from the CNC 401, controls the servo motor 412A so that the servo motor 412A rotates at the target rotation speed, and sets the work installation table (not shown). Drive in the X-axis direction. More specifically, the servo driver 411A calculates the actual rotation speed (or actual position) of the servo motor 412A from the feedback signal of the encoder 413A, and when the actual rotation speed is smaller than the target rotation speed, the servo motor 412A If the actual rotation speed is larger than the target rotation speed, the rotation speed of the servomotor 412A is decreased. In this way, the servo driver 411A brings the rotation speed of the servomotor 412A closer to the target rotation speed while sequentially receiving feedback of the rotation speed of the servomotor 412A. The servo driver 411A moves the work setting table connected to the ball screw 414A in the X-axis direction, and moves the work setting table to an arbitrary position in the X-axis direction.

By the same motor control, the servo driver 411B moves the work setting table connected to the ball screw 414B in the Y-axis direction according to a control command from the CNC 400, and moves the work setting table to an arbitrary position in the Y-axis direction. By performing the same motor control, the servo driver 411C moves the spindle 415 in the Z-axis direction and moves the spindle 415 to an arbitrary position in the Z-axis direction according to a control command from the CNC 400. By performing the same motor control, the servo driver 411D controls the rotation speed of the spindle 415 according to the control command from the CNC 400.

The storage device 420 is a storage medium such as a hard disk or a flash memory, for example. The storage device 420 stores the machining program 422 and the like. The storage location of the processing program 422 is not limited to the storage device 420, and may be stored in the storage area of the CNC 401 (for example, a cache area), the ROM 402, the RAM 403, an external device (for example, a server), or the like.

<H. Hardware configuration of image processing device 532>
The hardware configuration of the image processing apparatus 532 will be described in order with reference to FIG. FIG. 17 is a diagram showing an example of the hardware configuration of the image processing device 532.

The image processing device 532 includes a processor 501, a ROM 502, a RAM 503, a communication interface 504, 505, a camera interface 506, and a storage device 520. These components are connected to bus 510.

Processor 501 is configured by, for example, at least one integrated circuit. An integrated circuit may consist of, for example, at least one CPU, at least one GPU, at least one ASIC, at least one FPGA, or a combination thereof.

The processor 501 controls the operation of the image processing device 532 by executing various programs such as the image processing program 522 having a person detection function. The processor 501 reads the program to be executed into the RAM 503 from the storage device 520 or the ROM 502 based on the reception of the execution instructions of the various programs. The RAM 503 functions as a working memory and temporarily stores various data necessary for executing the program.

A LAN, an antenna, or the like is connected to the communication interface 504. The image processing device 532 exchanges data with an external device such as a server via the communication interface 504.

The communication interface 505 is an interface for connecting to the network NW2 which is a field network. The image processing device 532 exchanges data with various devices connected to the network NW2 via the communication interface 505.

The camera interface 506 is an interface for connecting the camera 534 and the image processing device 532 by wire or wirelessly. The camera 534 may be a CCD (Charge Coupled Device) camera, an infrared camera (thermography), or another type of camera. The camera 534 is installed so as to photograph the work area in the work station 500, and photographs the worker performing the setup work in the work station 500.

The storage device 520 is, for example, a storage medium such as a hard disk or a flash memory. The storage device 520 stores, for example, an image processing program 522. The storage location of the image processing program 522 is not limited to the storage device 520, and may be stored in a storage area of the processor 501 (for example, a cache memory), a ROM 502, a RAM 503, an external device (for example, a server), or the like.

<I. Control flow>
The control flow of the control device 50 will be described with reference to FIG. FIG. 18 is a flowchart showing a part of the processing executed by the control device 50.

In step S110, the control device 50 determines whether or not the execution command of the action determination program 122 has been accepted. When the control device 50 determines that the execution command of the action determination program 122 has been received (YES in step S110), the control device 50 switches the control to step S112. If not (NO in step S110), the control device 50 re-executes the process of step S110.

In step S112, the control device 50 functions as the acquisition unit 152 (see FIG. 3) described above, and acquires machine tool state values from various sensors 550. Since the machine tool state value is as described above, the explanation will not be repeated.

In step S114, the control device 50 functions as the above-mentioned action determination unit 154 (see FIG. 3), and acquires the operating state of the worker at the work station 500 from the motion sensor 530. Since the operating state is as described above, the description thereof will not be repeated.

In step S116, the control device 50 functions as the above-mentioned action determination unit 154 (see FIG. 3), and is based on the combination of the machine tool state value acquired in step S112 and the operating state of the operator acquired in step S114. The action type of the worker is determined. More specifically, the control device 50 refers to the action type definition 124 in which the action type of the worker is associated with each combination of the machine tool state value and the operation state, and the machine tool state value acquired in step S112. , The action type corresponding to the combination with the operating state of the worker acquired in step S114 is specified.

In step S118, the control device 50 associates the action type determination result in step S116 with the worker identification information (for example, the worker ID) and the current time, and then associates the above-mentioned work history 126 (FIG. FIG. 12). The worker identification information is identified, for example, from the worker login information at the terminal of the work station 500. The current time is received from, for example, an external device.

In step S120, the control device 50 determines whether or not to end the action determination program 122. The end instruction of the action determination program 122 is issued, for example, based on the end operation by the user. When the control device 50 determines that the action determination program 122 is terminated (YES in step S120), the control device 50 terminates the process shown in FIG. If not (NO in step S120), the controller 50 returns control to step S112.

<J. Summary>
As described above, the machine tool 10 determines the action type of the worker by the combination of the operating state of the worker detected by the motion sensor 530 and the machine tool state. By using the two pieces of information of the worker's operating state and the machine tool state value by the motion sensor 530, it is possible to classify the worker's action type in more detail than when one piece of information is used.

It should be considered that the embodiments disclosed this time are exemplary in all respects and not restrictive. The scope of the present invention is shown not by the above description but by the scope of claims, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

10 machine tools, 50 controllers, 61-64 remote I / O units, 71A-71E data areas, 72 frames, 100 control systems, 101,161,501 processors, 102,162,402,502 ROM, 103,163 403,503 RAM, 104,164,165,504,505 communication interface, 105 display interface, 106 display, 107 input interface, 108 input device, 110,510 bus, 120,170,420,520 storage device, 122 behavior discrimination Program, 124 action type definition, 126 work history, 150 control panel, 151 PLC, 152 acquisition unit, 154 action discrimination unit, 172 control program, 200 storage unit, 300 transport device, 330 rails, 331 trolley, 333 fork unit, 334 , 411, 411A to 411D servo driver, 335, 421, 412A to 412D servo motor, 400 processing machine, 404 field bus controller, 413A to 413D encoder, 414A, 414B ball screw, 415 spindle, 422 processing program, 430 operation panel, 500 work station, 506 camera interface, 522 image processing program, 530 human sensor, 532 image processing device, 534 camera, 541 open / close sensor, 543 clamp sensor, 545 area sensor, 545A floodlight unit, 545B light receiving unit, 550 various sensors , 552 Person detection unit, 554 Motion analysis unit.

Claims (9)

A machine tool for processing workpieces
A work area for a person to work on the work, and
A motion sensor for detecting the movement of a person in the work area,
A control device for controlling the machine tool is provided.
The control device is
An acquisition unit for acquiring a state value indicating the state of the machine tool, and
A machine tool including a discriminating unit for discriminating an action type of a person in the work area based on an output value of the motion sensor and a state value acquired by the acquisition unit. The machine tool according to claim 1, wherein the action type that can be discriminated by the discriminating unit includes a setup work indicating that a person in the work area is working on the work. The machine tool further includes an operation unit for receiving an operation on the machine tool.
The state value includes the operation state of the operation unit.
When the motion sensor detects the movement of a person in the work area and indicates that the operation state is in operation, the determination unit determines that the action type is in the setup work. The machine tool according to claim 2. The action type that can be discriminated by the discriminating unit includes during cleaning work indicating that a person in the work area is cleaning.
When the motion of the person in the work area is detected by the motion sensor and the operation state indicates that the operation state is not being operated, the acquisition unit determines that the action type is the cleaning operation. The machine tool according to claim 3, which is determined. The machine tool
An openable door that separates the work installation location from the work area,
Including an open / close sensor for detecting the open / closed state of the door.
The state value includes the open / close state detected by the open / close sensor.
When the movement of a person in the work area is detected by the motion sensor and the open / closed state indicates the open state of the door, the discriminating unit determines that the action type is in the setup work. The machine tool according to claim 2. The action type that can be discriminated by the discriminating unit includes during cleaning work indicating that a person in the work area is cleaning.
When the movement of a person in the work area is detected by the motion sensor and the open / closed state indicates the closed state of the door, the discriminating unit determines that the action type is the cleaning operation. The machine tool according to claim 5. The action type that can be discriminated by the discriminating unit includes an incapacitating state indicating that the person cannot act in the work area.
When the output value by the motion sensor does not change by a predetermined value or more within a predetermined time and the state value acquired by the acquisition unit does not change by a predetermined value or more within a predetermined time, the discriminating unit is described. The machine tool according to any one of claims 1 to 6, which determines that the action type is the incapacitated state. It is a method of determining the behavior type of a person in a machine tool.
The machine tool
A work area for the person to work on the work to be processed, and
It is equipped with a motion sensor for detecting the movement of the person in the work area.
The discrimination method is
The step of acquiring the output value of the motion sensor and
A step of acquiring a state value indicating the state of the machine tool, and
A method for determining an action type, which comprises a step of determining an action type of a person in the work area based on an output value of the motion sensor and the state value. It is a program to determine the behavior type of a person in a machine tool.
The machine tool
A work area for the person to work on the work to be processed, and
It is equipped with a motion sensor for detecting the movement of the person in the work area.
The discrimination program is applied to the machine tool.
The step of acquiring the output value of the motion sensor and
A step of acquiring a state value indicating the state of the machine tool, and
An action type determination program that executes a step of determining an action type of a person in the work area based on the output value of the motion sensor and the state value.

Images