Screw fastening defect judgment device and learning device

By generating and analyzing the normalized data string of rotation torque, the problem in the prior art is difficult to determine that the self-tapping screw reaches the bottom normally in a soft material, and the accurate determination of the screw solid state is achieved.

CN115397620BActive Publication Date: 2024-11-22OMRON CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202180027740.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2020-05-20
Filing Date
2021-03-02
Publication Date
2024-11-22
Estimated Expiration
2041-03-02

AI Technical Summary

Technical Problem

It is difficult to determine whether the self-tapping screw reaches the bottom normally in a soft material, especially when the torque value varies depending on the workpiece, it is difficult to determine the screw state based solely on the torque value.

Method used

By generating a normalized data string of rotation torque, determining whether the screw is bad based on the torque change amount, the PLC controls data acquisition and processing of rotation servo and reciprocating servo, and generates a normalized torque data string, and according to the threshold value Determine the screw-fixed state.

Benefits of technology

It can accurately determine whether the screw is defective when using self-tapping screws. It is suitable for soft materials and improves the accuracy of the screw state determination.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115397620B_ABST
    Figure CN115397620B_ABST
Patent Text Reader

Abstract

The present invention provides a screw fastening defect determination device and a learning device. Even when a self-tapping screw is used on a soft material, it is possible to determine whether a screw fastening defect has occurred. A PLC (10) includes a determination unit (13), which generates a data string of normalized torque, i.e., a change in the rotational torque relative to the first data point of the data string, for a data string of rotational torque containing a specified number of data points, and determines whether a screw fastening defect has occurred based on the data string of normalized torque.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a device for determining a defective screw fastening and a learning device. Background Art

[0002] Patent document 1 discloses a screw-fastening state detection device for an electric rotary tool, which includes a cylindrical shell for accommodating a spring that elastically supports the steel ball relative to a steel ball engaged with an internal gear (internal gear) of a reduction mechanism in a clutch mechanism, a torque adjustment mechanism having an adjustment screw that can be operated from the outside to adjust the elastic force of the spring in the cylindrical shell, and a torque detection element is provided on the outer side surface of the cylindrical shell.

[0003] The screw fastening state detection device of the electric rotary tool described in Reference 1 converts the detection value of the output signal detected by the torque detection element during the screw fastening operation into a torque value, thereby making a good or bad judgment on the screw fastening state.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Publication No. 2016-147317 Summary of the invention

[0007] Problems to be solved by the invention

[0008] However, for example, when using a self-tapping screw for a soft material (workpiece) such as resin, the front end of the self-tapping screw may move forward from the bottom of the workpiece during the temporary tightening process until the seat surface of the self-tapping screw contacts the workpiece, due to the wrong length of the screw or the poor formation of the workpiece. In this case, for example, the torque value required from the temporary tightening of the self-tapping screw to the process after the seat surface of the self-tapping screw contacts the workpiece, i.e., the formal tightening, is different. However, the torque value varies for each workpiece. Therefore, in the screw fastening state detection device of the electric rotary tool described in Patent Document 1, it is difficult to determine whether the self-tapping screw has reached the bottom normally by simply judging the screw fastening state based on the torque value.

[0009] An object of one embodiment of the present invention is to realize a screw fastening failure determination device that can determine whether a screw fastening failure has occurred even when a self-tapping screw is used on a soft material.

[0010] Technical means of solving problems

[0011] In order to solve the problem, a screw fastening defect judgment device according to an embodiment of the present invention generates, for a data string of rotational torque containing a specified number of data points, a data string of normalized torque, which is the change in the rotational torque relative to the first data point of the data string, and judges whether screw fastening has failed based on the data string of normalized torque. The data string of rotational torque ends with a data point at which the rotational torque becomes above a specified first threshold value among the data points for sampling the rotational torque of the motor at a specified period, and the motor generates a rotational motion around the axis of a screwdriver for tightening the screws.

[0012] Effects of the Invention

[0013] According to the screw fastening defect determination device of one embodiment of the present invention, even when a self-tapping screw is used for a soft material, it is possible to determine whether a screw fastening defect has occurred. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 1 is a block diagram showing an overview of the screw fastening system according to the present embodiment.

[0015] Figure 2 It is a block diagram showing the structure of the PLC according to this embodiment.

[0016] Figure 3 It is a diagram showing an example of the appearance of the screw-fastening system according to the present embodiment.

[0017] Figure 4 It is a diagram showing a data string of normalized torque according to the present embodiment.

[0018] Figure 5 1 is a flowchart showing an example of a screw fastening failure determination process according to the present embodiment.

[0019] Figure 6 It is a block diagram showing the configuration of a PLC and a learning device according to a modification of the present embodiment.

[0020] Figure 7 1 is a flowchart showing an example of a screw fastening failure determination process according to a modification of the present embodiment.

[0021] [Explanation of Symbols]

[0022] 1: Screw-on system

[0023] 10: PLC (device for determining defective screw fastening)

[0024] 30: Rotation servo (first motor)

[0025] 40: Reciprocating servo (second motor)

[0026] 51: Screwdriver

[0027] 70: Learning Department (Learning Device) DETAILED DESCRIPTION

[0028] Hereinafter, an embodiment of one aspect of the present invention (hereinafter also referred to as “the present embodiment”) will be described with reference to the drawings.

[0029] §1 Application examples

[0030] Figure 1 1 is a block diagram showing an overview of the screw fastening system 1 of the present embodiment. Figure 1 As shown in FIG. 1 , the screw fastening system 1 includes a programmable logic controller (PLC) 10 (a screw fastening defect determination device), a coupling 20, a rotation servo 30 (a first motor), and a reciprocating servo 40 (a second motor). The screw fastening system 1 is operated by a screwdriver 51 (see FIG. 1 ) described later. Figure 3 ), the rotational motion around the axis and the reciprocating motion toward the axis direction are used to perform the screw-fastening action. At this time, the PLC 10 controls the screw-fastening action and determines the occurrence of defects in the screw-fastening action.

[0031] In this specification, the so-called defect in screwing operation refers to the top bottom. The so-called top bottom means that the screw reaches the bottom of the screw hole before the screwing is completed due to reasons such as the screw being longer than the screw hole or the workpiece being formed poorly.

[0032] The rotation servo 30 is a motor that generates a rotational motion around the axis of the screwdriver 51. The rotation servo 30 outputs its own rotation speed (deg. / s), rotation amount (deg.), and rotation torque (ratio (%) to the rated torque) to the coupling 20. Specifically, the rotation servo 30 outputs data points of its own rotation speed, rotation amount, and rotation torque sampled at a predetermined period to the coupling 20.

[0033] The reciprocating servo 40 is a motor that generates axial reciprocating motion of the screwdriver 51. The reciprocating servo 40 outputs the moving speed (mm / s), moving position (mm), and moving torque (ratio (%) to the rated torque) of the screwdriver 51 generated by its own rotation to the coupling 20.

[0034] The coupling 20 connects the PLC 10 with the rotating servo 30 and the reciprocating servo 40. Specifically, the coupling 20 transmits the control signal received from the PLC 10 to the rotating servo 30 and the reciprocating servo 40. Furthermore, the coupling 20 transmits the data points received from the rotating servo 30, which are sampled at a predetermined period for the rotation speed, rotation amount, and rotation torque of the rotating servo 30, to the PLC 10. Furthermore, the coupling 20 transmits the moving speed, moving position, and moving torque of the screwdriver 51 generated by the rotation of the reciprocating servo 40, which are received from the reciprocating servo 40, to the PLC 10.

[0035] In the following description, the rotation speed, rotation amount, and rotation torque of the rotation servo 30 and the rotation torque data string, and the movement speed, movement position, and movement torque of the screwdriver 51 generated by the rotation of the reciprocating servo 40 are sometimes collectively referred to as parameters.

[0036] Figure 2 1 is a block diagram showing the structure of the PLC 10. The PLC 10 controls the operation of the screw fastening system 1. Figure 2 As shown, the PLC 10 includes a control unit 11 , a communication unit 12 , and a determination unit 13 .

[0037] The control unit 11 outputs a control signal for controlling the rotating servo 30 and the reciprocating servo 40 to the communication unit 12. The communication unit 12 transmits the control signal input from the control unit 11 to the coupling 20. The control signal is transmitted to the rotating servo 30 and the reciprocating servo 40 via the coupling 20 to control the rotating servo 30 and the reciprocating servo 40. The control unit 11 controls the rotating servo 30 and the reciprocating servo 40 synchronously. Furthermore, the control unit 11 feeds back the parameters of the rotating servo 30 and the reciprocating servo 40 to the control of the rotating servo 30 and the reciprocating servo 40.

[0038] The communication unit 12 receives parameters from the rotation servo 30 and the reciprocation servo 40 via the coupling 20. The control unit 11 and the determination unit 13 acquire parameters from the coupling 20 via the communication unit 12 as needed.

[0039] The determination unit 13 determines whether or not a screw fastening failure has occurred. The content of the determination made by the determination unit 13 will be described later.

[0040] Furthermore, the screw fastening system 1 further includes a notification device (not shown). When the determination unit 13 determines that a screw fastening failure has occurred, it outputs the determination result through the notification device. The notification device is, for example, a speaker that outputs a sound indicating the determination result, or a display that displays an image indicating the determination result.

[0041] §2 Structure Example

[0042] (Structure of screw fastening system 1)

[0043] Figure 3 1 is a diagram showing an example of the appearance of the screw fastening system 1 according to the present embodiment. Figure 3 As shown, the screw fastening system 1 includes a rotation servo 30, a reciprocating servo 40, a screwdriver unit 50, and a support column 60. Figure 3 Although not shown, the screw-fastening system 1 also includes the PLC 10 and the coupling 20 as described above.

[0044] The screwdriver unit 50 is a unit for tightening a screw. The screwdriver unit 50 includes a screwdriver 51 and a screw holding portion 52. The screwdriver 51 performs a screw-fastening operation by rotating around an axis and reciprocating along an axial direction. In the following description, the direction in which the screwdriver 51 moves during the screw-fastening process in the axial direction of the screwdriver 51 is referred to as downward.

[0045] The rotation servo 30 is disposed above the screwdriver 51 to generate a rotational motion around the axis of the screwdriver 51. Furthermore, the screw holding portion 52 is disposed below the screwdriver 51 to hold a screw to be screwed by the screwdriver 51.

[0046] The support 60 supports the screw unit 50 so that it can move up and down. The reciprocating servo 40 is provided on the upper part of the support 60 and is connected to the screw unit 50 via a ball screw (not shown). The rotational motion of the reciprocating servo 40 is converted into a linear motion in the up and down direction by the ball screw. As a result, the screw unit 50 reciprocates up and down.

[0047] (Screw action)

[0048] The screwing action performed by the screw-fastening system 1 is as follows. First, the screw holding portion 52, which holds the screw, lowers the screw toward the portion to be screwed on a workpiece (not shown) that is the object of screwing and contains resin. However, the workpiece is not limited to resin as long as it is a soft material. Next, the screwdriver 51 rotates the screw while pressing against the portion to be screwed until the screw is temporarily seated. Here, the so-called temporary seating refers to the state in which the seat surface of the screw contacts the workpiece.

[0049] The screw-fastening system 1 further rotates the screw while holding it from the state where the screw has been temporarily seated, thereby performing formal tightening. In this embodiment, formal tightening is performed until the rotational torque of the rotation servo 30 reaches a predetermined formal tightening completion value. When the rotational torque reaches the formal tightening completion value, the screw-fastening system 1 stops holding the screw, and maintains the state where the rotational torque is above the formal tightening completion value for 100ms.

[0050] Then, the screw-fastening system 1 makes the rotation torque of the rotation servo 30 become less than 0% and releases the screw. Then, the screw-fastening system 1 moves the screwdriver 51 upward to restore it to its original position, thereby completing the screw-fastening operation. However, the rotation torque and holding time described above are examples and vary depending on the type of screw and the type of fastener / fastened object.

[0051] (Defective screw fastening judgment action)

[0052] Specifically, the determination unit 13 obtains the data points of the rotational torque from the connector 20 via the communication unit 12. Next, the determination unit 13 generates a data string of normalized torque for a data string of rotational torque containing a specified number of data points, with the data point at the end of the obtained data point where the rotational torque becomes above the specified first threshold. Here, the so-called data string of normalized torque refers to the amount of change in the rotational torque of each data point of the data string of rotational torque relative to the rotational torque of the first data point. Moreover, the first threshold is a specified value of the rotational torque of the rotation servo 30 when the screw-fastening system 1 completes the temporary tightening of the screw and starts the formal tightening.

[0053] The determination unit 13 acquires the second threshold value from a storage device (not shown). Here, the second threshold value is a predetermined threshold value for determining whether a screw failure has occurred with respect to the value of the normalized torque at a data point at a predetermined position in the data string of the normalized torque.

[0054] The determination unit 13 determines that the screw fastener is defective when the normalized torque of the data point at the specified position in the data string of the normalized torque is greater than the specified second threshold value. Thus, the determination unit 13 can determine that the screw fastener is defective by determining whether the normalized torque of the data point at the specified position in the data string of the normalized torque is greater than the second threshold value.

[0055] The determination unit 13 may also obtain a third threshold value from a storage device (not shown). Here, the third threshold value is a predetermined threshold value for determining whether a screw failure has occurred with respect to the total value of the normalized torque of data points within a predetermined range in the normalized torque data string.

[0056] At this time, the determination unit 13 determines that the screw fastener is defective when the sum of the normalized torque of the data points in the specified range in the data string of the normalized torque is greater than the third threshold value. Thus, the determination unit 13 can determine that the screw fastener is defective by determining whether the sum of the normalized torque of the data points in the specified range in the data string of the normalized torque is greater than the third threshold value.

[0057] Figure 4 It is a diagram showing a data string of normalized torque according to the present embodiment. Figure 4The horizontal axis represents the data points (sampling time), and the vertical axis represents the normalized torque value. Figure 4 Th2 in the vertical axis represents the second threshold value. Figure 4 In the example shown, the number of data points included in the normalized torque data string is set to 51, and the predetermined position is set to the 43rd position from the head of the data string. Therefore, when the normalized torque of the 43rd data point is greater than Th2, the determination unit 13 determines that a screw failure has occurred. Figure 4 In the figure, the data of 50 screws with normal screw fastening are represented in black, and the data of 32 screws with abnormal screw fastening are represented in gray. In the data of normal screws, the normalized torque of the 43rd data point is less than Th2. On the other hand, in the data of abnormal screws, the torque increase caused by the screw exceeding the bottom of the screw hole and advancing is generated, so the normalized torque of the 43rd data point is above Th2. Therefore, according to the judgment, the defect in screw fastening can be appropriately judged. In addition, in the non-normalized torque (raw data) before making the starting point consistent, the deviation of the torque of each workpiece is large, so it is impossible to use a single threshold to distinguish between normal and abnormal.

[0058] The specific value of the second threshold value can be appropriately set to a value that can determine whether the screw is normal or defective. Moreover, the number of data points contained in the data string of the normalized torque is not limited to 51, and can be appropriately set. Moreover, the specified position is not limited to the 43rd position, and can be appropriately set to a position that can determine whether the screw is normal or defective by the second threshold value. Moreover, the specific value of the third threshold value when the determination unit 13 uses the third threshold value for determination and the specific range of data points used to calculate the total value of the normalized torque are also the same.

[0059] In addition, the example of the screwing operation is that the screwing system 1 screws a workpiece in a state where the screwing part is not tapped with a female thread (tapped (self-tapping)). However, the screwing system 1 can also screw a workpiece in a state where the screwing part is pre-tapped with a female thread (tapped).

[0060] §3 Action Examples

[0061] Figure 5 FIG. 2 is a flowchart showing an example of a screw fastening failure determination process according to the present embodiment. Figure 5 The determination of the occurrence of a malfunction in the screw-fastening operation performed by the determination unit 13 will be described.

[0062] like Figure 5As shown, the determination unit 13 obtains a data string of rotational torque from the connector 20 via the communication unit 12 (S1). Next, the determination unit 13 generates a data string of normalized torque (S2). Next, the determination unit 13 obtains a second threshold value from the storage device, and determines whether the normalized torque of the data point at a specified position in the data string of normalized torque is above the second threshold value (S3). If the normalized torque is above the second threshold value (Yes in S3), the determination unit 13 outputs a notification signal indicating poor screw fastening to the notification device (S4). If the normalized torque is not above the second threshold value (No in S3), the determination unit 13 does not execute step S4 and ends the processing.

[0063] Furthermore, the determination unit 13 may acquire the third threshold value from the storage device in step S3 and determine whether the sum of the normalized torques of the data points in a predetermined range in the normalized torque data string is equal to or greater than the third threshold value.

[0064] §4 Variations

[0065] Above, the embodiments of the present invention have been described in detail, but the descriptions up to the foregoing are merely illustrative of the present invention in all aspects. Various improvements or modifications can be made without departing from the scope of the present invention. For example, the following changes can be made. In addition, the same symbols are used for the same components as the embodiments, and the descriptions are appropriately omitted for the same points as the embodiments. The following modifications can be appropriately combined.

[0066] The screw-fastening system of this modification includes a learning unit 70 (learning device) in addition to the configuration of the screw-fastening system 1. The learning unit 70 is configured to be able to perform machine learning, and is, for example, a personal computer, a smartphone, a mobile information terminal, or a server.

[0067] Figure 6 1 is a block diagram showing the structure of the PLC 10 and the learning device of this modification. Figure 6 As shown, in this modification, the learning unit 70 is connected to the determination unit 13 .

[0068] The learning unit 70 determines one or more of the prescribed number, prescribed position, and second threshold value in the PLC 10 by learning based on the learning data including the data string of normalized torque and the normal or bad judgment result of the data string of normalized torque. However, the learning unit 70 may also determine one or more of the prescribed number, prescribed range, and third threshold value in the PLC 10 by learning based on the learning data including the data string of normalized torque and the normal or bad judgment result of the data string of normalized torque. In the present embodiment, the learning unit 70 determines all of the prescribed number, prescribed position, and second threshold value in the PLC 10 by learning based on the learning data including the data string of normalized torque and the normal or bad judgment result of the data string of normalized torque.

[0069] Here, learning refers to machine learning and learning with instruction. As algorithms for learning with instruction, for example, neural networks, isolation forests, and support vector machines are used. In addition, the learning unit 70 may also use a probability density function and a kernelized probability model to calculate an abnormality score. The probability density function is, for example, a normal distribution, but is not limited thereto.

[0070] The learning unit 70 outputs the determined specified number, specified position or second threshold value to the determination unit 13 included in the PLC 10. Thus, the determination unit 13 can determine that the screw fastener is defective based on the determined specified number, specified position or second threshold value. However, the learning unit 70 can also output the determined specified number, specified range or third threshold value to the determination unit 13 included in the PLC 10. In the present embodiment, the learning unit 70 outputs the determined specified number, specified position and second threshold value to the determination unit 13 included in the PLC 10. Thus, the determination unit 13 can determine that the screw fastener is defective based on the specified number, specified position and second threshold value learned and determined by the learning unit 70. In the case where the learning unit 70 does not determine one or more of the specified number, specified position and second threshold value through learning, the undetermined value can be pre-stored in the storage device.

[0071] The learning unit 70 updates one or more of the specified number, specified position, and the second threshold value by learning based on the data string of the normalized torque in the screw and the determination result made by the determination unit when the determination unit 13 has made a specified number of determinations, a specified period of time has passed, or there is an instruction from the outside. Thus, the determination unit 13 can determine that the screw is defective based on the updated specified number, specified position, or second threshold. However, the learning unit 70 can also update one or more of the specified number, specified range, and the third threshold value by learning based on the data string of the normalized torque in the screw and the determination result made by the determination unit when the determination unit 13 has made a specified number of determinations, a specified period of time has passed, or there is an instruction from the outside. In this embodiment, the learning unit 70 updates all of the specified number, specified position, and the second threshold value by learning based on the data string of the normalized torque in the screw and the determination result made by the determination unit when the conditions for starting learning are met. Thus, the determination unit 13 can determine that the screw is defective based on the updated specified number, specified position, and the second threshold.

[0072] Figure 7 FIG. 1 is a flowchart showing an example of a screw fastening failure determination process according to this modification. Figure 7 The determination of the occurrence of a defect in the screwing operation performed by the determination unit 13 and the learning unit 70 will be described below. Figure 7 As shown, the determination unit 13 performs the processing from S1 to S5. The processing of the determination unit 13 from S1 to S4 is the same as described above, so the description is omitted. When the normalized torque is not above the second threshold value (No in S3), or after outputting the notification signal indicating poor screw fastening to the notification device (S4), the determination unit 13 outputs the data of the determination result to the learning unit 70 (S5). Specifically, the determination unit 13 outputs the learning data of the normalized torque data string and the normal or poor determination result of the normalized torque data string to the learning unit 70. Then, the determination unit 13 ends the determination processing of the occurrence of the defect.

[0073] The learning unit 70 determines whether the conditions for starting learning are met (S11). The conditions for starting learning are, for example:

[0074] (i) immediately after the processing of the learning unit 70 has started;

[0075] (ii) the determination unit 13 performs determination a predetermined number of times;

[0076] (iii) a prescribed period has elapsed since the conditions for commencing study were last met; and

[0077] (iv) An instruction to start learning is received from outside.

[0078] When any one of these conditions is satisfied, the learning unit 70 determines that the condition for starting learning is satisfied. However, the conditions for starting learning are not limited to these. Furthermore, one or more of these conditions may not be set as the condition for starting learning.

[0079] If the condition for starting learning has not been met (No in S11), the learning unit 70 repeats step S11 until the condition for starting learning is met. If the condition for starting learning has been met (Yes in S11), the learning unit 70 obtains learning data (S12). In the case where the processing of the learning unit 70 has just started, the learning data is the teaching data stored in the storage device. In other cases, the learning data is the learning data stored in the storage device from the determination unit 13 in step S5. Next, the learning unit 70 determines the specified number in the PLC 10 through learning based on the learning data, and outputs the specified number to the determination unit 13 (S13). Next, the determination unit 13 determines the specified position and the second threshold in the PLC 10 through learning based on the learning data, and outputs the specified position and the second threshold to the determination unit 13 (S14). Then, the learning unit 70 ends the learning process.

[0080] In addition, if the determination unit 13 determines the third threshold as the reference in S3 , the determination unit 13 may determine the prescribed range and the third threshold in the PLC 10 by learning based on the learning data in S14 , and output the prescribed range and the third threshold to the determination unit 13 .

[0081] 〔Example of implementation using software〕

[0082] The control block (particularly the determination unit 13 ) and the learning unit 70 of the PLC 10 may be realized by a logic circuit (hardware) formed on an integrated circuit (IC (Integrated Circuit) chip) or the like, or may be realized by software.

[0083] In the latter case, the PLC 10 includes a computer that executes commands of software, i.e., a program, that implements each function. The computer includes, for example, one or more processors, and includes a computer-readable recording medium that stores the program. In addition, in the computer, the program is read and executed from the recording medium by the processor, thereby achieving the purpose of the present invention. As the processor, for example, a central processing unit (CPU) can be used. As the recording medium, a "non-temporary tangible medium" can be used, for example, in addition to a read-only memory (ROM), a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, etc. can also be used. Moreover, a random access memory (RAM) that expands the program may also be included. Moreover, the program may also be provided to the computer via any transmission medium (communication network or broadcast wave, etc.) that can transmit the program. In addition, an embodiment of the present invention can also be implemented in an embodiment of a data signal embedded in a carrier wave that materializes the program through electronic transmission.

[0084] 〔Summarize〕

[0085] In order to solve the problem, a screw fastening defect judgment device according to an embodiment of the present invention generates, for a data string of rotational torque containing a specified number of data points, a data string of normalized torque, which is the change in the rotational torque relative to the first data point of the data string, and judges whether screw fastening has failed based on the data string of normalized torque. The data string of rotational torque ends with a data point at which the rotational torque becomes above a specified first threshold value among the data points for sampling the rotational torque of the motor at a specified period, and the motor generates a rotational motion around the axis of a screwdriver for tightening the screws.

[0086] According to the structure, the data string of the normalized torque can be compared with the data string of the abnormal torque, so as to determine whether the screw fastening is defective. Therefore, for example, when a self-tapping screw is used for a soft material, even if the torque value varies according to each workpiece, it is possible to determine whether the screw fastening is defective.

[0087] Moreover, in a screw fastening failure determination device according to an embodiment of the present invention, it is preferred that the determination unit determines that a screw fastening failure has occurred when the normalized torque of a data point at a specified position in the data string of the normalized torque is greater than a specified second threshold value.

[0088] According to the above configuration, by determining whether the normalized torque at a data point at a predetermined position in the normalized torque data string is equal to or greater than the second threshold value, it is possible to determine that a screw fastener failure has occurred.

[0089] Moreover, a learning device of one embodiment of the present invention determines one or more of the specified number, the specified position and the specified second threshold in the poor screw fastening judgment device through learning based on learning data including the data string of the normalized torque and the normal or poor judgment result of the data string of the normalized torque, and outputs the determined specified number, the specified position or the specified second threshold to the poor screw fastening judgment device.

[0090] According to the above configuration, it is possible to appropriately determine that a screw fastening failure has occurred based on the predetermined number, predetermined position, or second threshold value determined through learning.

[0091] Moreover, the learning device of one embodiment of the present invention is preferably configured to update one or more of the specified number, the specified position and the specified second threshold through learning based on the data string of the normalized torque in the screw and the judgment result made by the judgment unit when the judgment unit has made a specified number of judgments, a specified period has passed, or there is an instruction from the outside.

[0092] According to the above configuration, it is possible to more appropriately determine that a screw fastening failure has occurred based on the updated predetermined number, predetermined position, or second threshold value.

[0093] Moreover, in a screw fastening defect determination device according to an embodiment of the present invention, it is preferred that the determination unit determines that a screw fastening defect has occurred when the sum of the normalized torques of data points within a specified range in the data string of the normalized torque is greater than a specified third threshold value.

[0094] According to the above configuration, by determining whether the sum of the normalized torques of the data points in the predetermined range in the normalized torque data string is equal to or greater than the third threshold value, it is possible to determine that a screw fastener failure has occurred.

[0095] Moreover, a learning device of one embodiment of the present invention determines one or more of the specified number, the specified range and the specified third threshold in the poor screw fastening judgment device through learning based on learning data including the data string of the normalized torque and the normal or poor judgment result of the data string of the normalized torque, and outputs the determined specified number, the specified range or the specified third threshold to the poor screw fastening judgment device.

[0096] According to the above configuration, it is possible to appropriately determine that a screw fastening failure has occurred based on the predetermined number, the predetermined range, or the third threshold value determined through learning.

[0097] Moreover, the learning device of one embodiment of the present invention may also be configured to update one or more of the specified number, the specified range and the specified third threshold through learning based on the data string of the normalized torque in the screw and the judgment result made by the judgment unit when the judgment unit has made a specified number of judgments, a specified period has passed, or there is an instruction from the outside.

[0098] According to the above configuration, it is possible to more appropriately determine that a screw fastening failure has occurred based on the updated predetermined number, predetermined range, or third threshold value.

[0099] The present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims. Embodiments obtained by appropriately combining technical components disclosed in different embodiments are also included in the technical scope of the present invention.

Claims

1. A device for determining a screw fastening failure, comprising a determination unit, wherein the determination unit generates, for a data string of rotational torque containing a specified number of data points, a data string of normalized torque, which is a change amount of the rotational torque of each data point relative to the rotational torque of the first data point of the data string, wherein the data string of rotational torque ends with a data point at which the rotational torque becomes greater than a specified first threshold value among data points for sampling the rotational torque of a motor at a specified period, wherein the motor generates a rotational motion of a screwdriver for tightening a screw around an axis, and The determination unit determines whether a screw failure occurs based on the normalized torque data string. The first threshold value is a predetermined value of the rotation torque when temporary tightening of the screw is completed and formal tightening is started.

2. The screw fastening defect determination device according to claim 1, wherein the determination unit determines that the screw fastening is defective when the normalized torque of a data point at a specified position in the data string of the normalized torque is greater than a specified second threshold value.

3. A learning device, which determines one or more of the specified number, the specified position and the specified second threshold value in the screw fastening defect determination device according to claim 2 by learning based on learning data including the data string of the normalized torque and the normal or bad determination result of the data string of the normalized torque, The determined prescribed number, the prescribed position or the prescribed second threshold value is output to the screw fastening failure determination device.

4. A learning device according to claim 3, wherein when the determination unit has made a predetermined number of determinations, a predetermined period has passed, or there is an instruction from the outside, the predetermined number, the predetermined position, and one or more of the predetermined second threshold values ​​are updated through learning based on the data string of the normalized torque in the screw and the determination result made by the determination unit.

5. A device for determining a screw fastening failure, comprising a determination unit, wherein the determination unit generates, for a data string of rotational torque containing a specified number of data points, a data string of normalized torque, which is a change amount of the rotational torque relative to the first data point of the data string, wherein the data string of rotational torque ends with a data point at which the rotational torque becomes greater than a specified first threshold value among data points for sampling the rotational torque of a motor at a specified period, wherein the motor generates a rotational motion of a screwdriver for tightening a screw around an axis, and The determination unit determines whether a screw failure occurs based on the normalized torque data string. The determination unit determines that a failure has occurred in the screw when a total of the normalized torques at data points within a predetermined range in the data string of the normalized torque is equal to or greater than a predetermined third threshold value.

6. A learning device, which determines one or more of the specified number, the specified range, and the specified third threshold value in the screw fastening defect determination device according to claim 5 by learning based on learning data including the data string of the normalized torque and the normal or poor determination result of the data string of the normalized torque, The determined prescribed number, the prescribed range or the prescribed third threshold value is output to the screw fastening failure determination device.

7. The learning device according to claim 6, wherein When the determination unit has made a predetermined number of determinations, a predetermined period has passed, or there is an instruction from the outside, the predetermined number, the predetermined range, and one or more of the predetermined third threshold values ​​are updated through learning based on the data string of the normalized torque in the screw and the determination result made by the determination unit.