JP7093225B2 - Seam inspection device - Google Patents

Description

The present invention relates to a seam inspection device.

In garment factories, sewing machines are used to produce clothing. Patent Document 1 discloses an example of a seam inspection device for inspecting a seam formed by a sewing machine.

Japanese Unexamined Patent Publication No. 11-090077

If the inspection of seams is complicated, the productivity of clothing can be reduced. In order to suppress a decrease in the productivity of clothing, a technique capable of efficiently inspecting seams is required.

An aspect of the present invention is to efficiently carry out inspection of seams.

According to the aspect of the present invention, the tension sensor that detects the tension of the needle thread applied to the sewing machine needle and the abnormality of the seam formed on the sewing object by the sewing machine needle are detected based on the detection value of the tension sensor. A seam inspection device is provided that comprises a processing device.

According to the aspect of the present invention, the inspection of seams can be efficiently performed.

FIG. 1 is a perspective view schematically showing a sewing machine according to an embodiment. FIG. 2 is a diagram showing a motion diagram of the needle bar and the balance according to the embodiment. FIG. 3 is a functional block diagram showing a seam inspection device according to an embodiment. FIG. 4 is a diagram schematically showing a normal seam. FIG. 5 is a diagram schematically showing an abnormal seam. FIG. 6 is a diagram schematically showing an abnormal seam. FIG. 7 is a diagram showing the detected values of the tension sensor. FIG. 8 is a diagram showing the detected values of the tension sensor. FIG. 9 is a diagram showing a cumulative curve. FIG. 10 is a diagram showing a frequency spectrum of tension. FIG. 11 is a flowchart showing a sewing method according to the embodiment. FIG. 12 is a flowchart showing a sewing method according to the embodiment.

Hereinafter, embodiments according to the present invention will be described with reference to the drawings, but the present invention is not limited thereto. The components of the embodiments described below can be combined as appropriate. In addition, some components may not be used.

[First Embodiment]
<Sewing machine>
The sewing machine 1 according to the present embodiment will be described. In this embodiment, the positional relationship of each part will be described based on the local coordinate system defined in the sewing machine 1. The local coordinate system is defined by the XYZ Cartesian coordinate system. The direction parallel to the X-axis in the predetermined plane is defined as the X-axis direction. The direction parallel to the Y-axis in a predetermined plane orthogonal to the X-axis is defined as the Y-axis direction. The direction parallel to the Z axis orthogonal to the predetermined surface is defined as the Z axis direction. The direction of rotation about the X axis is the θX direction.

FIG. 1 is a perspective view schematically showing the sewing machine 1 according to the present embodiment. As shown in FIG. 1, the sewing machine 1 includes a sewing machine head 2, a needle bar 4, a balance 5, a thread tensioner 6, a needle plate 7, a holding member 8, a hook 9, a motor 10, and a seam. It is provided with an inspection device 20.

The needle bar 4 holds the sewing machine needle 3 and reciprocates in the Z-axis direction. The needle bar 4 holds the sewing machine needle 3 so that the sewing machine needle 3 and the Z axis are parallel to each other. The needle bar 4 is supported by the sewing machine head 2. The needle bar 4 is arranged above the needle plate 7 and can face the surface of the sewing object S. The needle thread UT is hung on the sewing machine needle 3. The sewing machine needle 3 has a threading hole through which the needle thread UT passes. The sewing machine needle 3 holds the needle thread UT on the inner surface of the threading hole. When the needle bar 4 reciprocates in the Z-axis direction, the sewing machine needle 3 reciprocates in the Z-axis direction while holding the needle thread UT.

The balance 5 supplies the needle thread UT to the sewing machine needle 3. The balance 5 is supported by the sewing machine head 2. The balance 5 has a balance hole through which the needle thread UT passes. The balance 5 holds the needle thread UT on the inner surface of the balance hole. The balance 5 reciprocates in the Z-axis direction while holding the needle thread UT. The balance 5 reciprocates in conjunction with the needle bar 4. The balance 5 reciprocates in the Z-axis direction to feed and pull the needle thread UT.

The thread tensioner 6 applies tension to the needle thread UT. The needle thread UT is supplied from the thread supply source to the thread tensioner 6. In the path through which the needle thread UT passes, the balance 5 is arranged between the sewing machine needle 3 and the thread tensioner 6. The thread tensioner 6 adjusts the tension of the needle thread UT supplied to the sewing machine needle 3 via the balance 5.

The needle plate 7 supports the sewing object S. The sewing machine needle 3 held by the needle bar 4 and the needle plate 7 face each other. The needle plate 7 has a needle hole through which the sewing machine needle 3 can pass. The sewing machine needle 3 that has penetrated the sewing object S supported by the needle plate 7 passes through the needle hole.

The pressing member 8 presses the sewing object S from above. The pressing member 8 is supported by the sewing machine head 2. The pressing member 8 is arranged above the needle plate 7 and holds the sewing object S between the pressing member 8 and the needle plate 7.

The kettle 9 holds the bobbin housed in the bobbin case. The hook 9 is arranged below the needle plate 7. The kettle 9 rotates in the θX direction. The hook 9 rotates in conjunction with the needle bar 4. The hook 9 supplies the bobbin thread LT. The hook 9 penetrates the sewing object S supported by the needle plate 7 and scoops the needle thread UT from the sewing machine needle 3 that has passed through the needle hole of the needle plate 7.

The motor 10 generates power. The motor 10 has a stator supported by the sewing machine head 2 and a rotor rotatably supported by the stator. As the rotor rotates, the motor 10 generates power. The power generated by the motor 10 is transmitted to each of the needle bar 4, the balance 5, and the hook 9 via a power transmission mechanism (not shown). The needle bar 4, the balance 5, and the hook 9 are interlocked with each other. By transmitting the power generated by the motor 10 to the needle bar 4, the needle bar 4 and the sewing machine needle 3 held by the needle bar 4 reciprocate in the Z-axis direction. By transmitting the power generated by the motor 10 to the balance 5, the balance 5 reciprocates in the Z-axis direction in conjunction with the needle bar 4. By transmitting the power generated by the motor 10 to the hook 9, the hook 9 rotates in the θX direction in conjunction with the needle bar 4 and the balance 5. The sewing machine 1 sews the sewing object S in cooperation with the sewing machine needle 3 held by the needle bar 4 and the hook 9.

In the following description, the rotation of the rotor means the rotation of the motor 10. Further, the rotation angle of the rotor is referred to as the rotation angle of the motor 10. The sewing machine needle 3 reciprocates due to the rotation of the motor 10. The balance 5 reciprocates in conjunction with the sewing machine needle 3 by the rotation of the motor 10. The hook 9 rotates in conjunction with the sewing machine needle 3 and the balance 5 by the rotation of the motor 10.

The needle thread UT from the thread supply source is hung on the thread tensioner 6 and then hung on the sewing machine needle 3 via the balance 5. When the motor 10 rotates and the needle bar 4 descends, the sewing machine needle 3 held by the needle bar 4 penetrates the sewing object S and passes through the needle hole provided in the needle plate 7. When the sewing machine needle 3 passes through the needle hole of the needle plate 7, the bobbin thread LT supplied from the kettle 9 is hung on the needle thread UT hung on the sewing machine needle 3. With the bobbin thread LT hung on the needle thread UT, the sewing machine needle 3 rises and moves out of the sewing object S. When the sewing machine needle 3 penetrates the sewing object S, the sewing machine 1 stops the sewing object S. When the sewing machine needle 3 moves out of the sewing object S, the sewing machine 1 moves the sewing object S in the + Y direction. The sewing machine 1 reciprocates the sewing machine needle 3 while repeatedly moving and stopping the sewing object S in the + Y direction to form a seam SE on the sewing object S. The seam SE formed on the sewing object S extends in the Y-axis direction.

<Motion diagram>
FIG. 2 is a diagram showing a motion diagram of the needle bar 4 and the balance 5 according to the present embodiment. In FIG. 2, the horizontal axis indicates the rotation angle [°] of the motor 10 with respect to the top dead center of the needle bar. The vertical axis shows the needle bar stroke and the balance stroke. The motion diagram shown in FIG. 2 shows a needle bar motion curve and a balance thread supply curve.

The needle bar top dead center refers to the position of the needle bar 4 on the most + Z side in the movable range of the needle bar 4 in the Z-axis direction. The needle bar bottom dead center refers to the position of the needle bar 4 on the most −Z side in the movable range of the needle bar 4 in the Z-axis direction. The top dead center of the balance means the position of the balance 5 on the most + Z side in the movable range of the balance 5 in the Z-axis direction. The bottom dead center of the balance means the position of the balance 5 on the most −Z side in the movable range of the balance 5 in the Z-axis direction.

The needle bar stroke refers to the position of the needle bar 4 in the Z-axis direction. The balance stroke refers to the position of the balance 5 in the Z-axis direction. The balance thread supply amount means the amount of needle thread UT supplied by the balance 5 to the sewing machine needle 3.

Each of the needle bar 4 and the balance 5 reciprocates in the Z-axis direction in conjunction with the rotation of the motor 10. When the rotation angle of the motor 10 is 0 [°], the needle bar 4 is arranged at the top dead center of the needle bar. When the rotation angle of the motor 10 is about 70 [°], the balance 5 is arranged at the top dead center of the balance. When the rotation angle of the motor 10 is about 180 [°], the needle bar 4 is arranged at the bottom dead center of the needle bar. When the rotation angle of the motor 10 is about 320 [°], the balance 5 is arranged at the bottom dead center of the balance. The tension of the needle thread UT changes based on the difference between the position of the needle bar 4 and the position of the balance 5 in the Z-axis direction.

<Seam inspection device>
The seam inspection device 20 inspects the seam SE formed on the sewing object S. The seam inspection device 20 inspects the seam SE formed on the sewing object S while the sewing object S is supported by the needle plate 7. The seam inspection device 20 inspects the seam SE in parallel with the formation of the seam SE by the sewing machine 1. The seam inspection device 20 detects the presence or absence of an abnormality in the seam SE formed on the sewing object S. Further, the seam inspection device 20 detects an abnormal pattern of the seam SE.

FIG. 3 is a functional block diagram showing a seam inspection device 20 according to the present embodiment. As shown in FIGS. 1 and 3, the seam inspection device 20 includes a tension sensor 21 for detecting the tension of the needle thread UT hung on the sewing machine needle 3, an angle sensor 22 for detecting the rotation angle of the motor 10, and a tension sensor. Based on the detection value of 21, the processing device 30 for detecting the abnormality of the seam SE formed on the sewing object S by the sewing machine needle 3, the output device 23 for outputting the detection result of the processing device 30, and the operator are operated. The input device 24 is provided.

The processing device 30 includes a computer system. The processing device 30 includes a computing device 30A including a processor such as a CPU (Central Processing Unit), a non-volatile memory such as ROM (Read Only Memory) or storage, and a volatile memory such as RAM (Random Access Memory). It has a storage device 30B including the storage device 30B and an input / output interface 30C including an input / output circuit capable of inputting / outputting signals and data.

The tension sensor 21 detects the tension of the needle thread UT supplied to the sewing machine needle 3. The tension sensor 21 includes, for example, a strain gauge and a piezoelectric element. As shown in FIG. 1, the tension sensor 21 is arranged between the balance 5 and the sewing needle 3 in the path through which the needle thread UT passes. The tension sensor 21 detects the tension of the needle thread UT between the balance 5 and the sewing machine needle 3. The tension sensor 21 is connected to the input / output interface 30C. The tension sensor 21 outputs the detected value of the tension of the needle thread UT to the processing device 30.

The angle sensor 22 detects the rotation angle of the motor 10. The angle sensor 22 includes, for example, an encoder. The angle sensor 22 detects the rotation angle of the motor 10 with the rotation angle of the motor 10 when the needle rod 4 is arranged at the top dead point of the needle rod as 0 [°]. The angle sensor 22 is connected to the input / output interface 30C. The angle sensor 22 outputs the detected value of the rotation angle of the motor 10 to the processing device 30.

The output device 23 outputs the detection result of the processing device 30. The output device 23 is connected to the input / output interface 30C. As the output device 23, at least one of a display device and a printing device is exemplified. Display devices include flat panel displays such as liquid crystal displays (LCDs) or organic electroluminescence displays (OELDs).

The input device 24 generates input data by being operated by an operator. The input device 24 is connected to the input / output interface 30C. The input device 24 outputs the generated input data to the processing device 30. As the input device 24, at least one of an operation button, a touch panel, and a computer keyboard is exemplified.

The arithmetic unit 30A includes a detection value acquisition unit 31, a detection feature amount analysis unit 32, a determination unit 33, an output unit 34, and a reference feature amount generation unit 35. The storage device 30B has a reference feature amount storage unit 36.

The detection value acquisition unit 31 acquires the detection value of the tension sensor 21. Further, the detection value acquisition unit 31 acquires the detection value of the angle sensor 22.

The detection feature amount analysis unit 32 analyzes the detection value of the tension sensor 21 acquired by the detection value acquisition unit 31, and calculates the detection value feature amount indicating the feature amount of the detection value of the tension sensor 21. The detected feature amount indicates the actual feature amount of the tension of the needle thread UT.

The determination unit 33 determines whether or not there is an abnormality in the seam SE based on the analysis result of the detection feature amount analysis unit 32. Further, the determination unit 33 determines an abnormality pattern of the seam SE based on the analysis result of the detection feature amount analysis unit 32.

The output unit 34 outputs output data including at least one of the detection value acquired by the detection value acquisition unit 31, the analysis result of the detection feature amount analysis unit 32, and the determination result of the determination unit 33 to the output device 23. The output device 23 outputs the output data from the output unit 34.

The reference feature amount generation unit 35 indicates the feature amount of the tension of the needle thread UT when the normal seam SE is formed based on the detection value of the tension sensor 21 when the normal seam SE is formed. Calculate the amount. That is, in the present embodiment, the reference feature amount includes the normal feature amount indicating the feature amount of the tension of the needle thread UT when the normal seam SE is formed.

The reference feature amount storage unit 36 stores the reference feature amount of the tension generated by the reference feature amount generation unit 35.

The determination unit 33 collates the detected feature amount calculated by the detection feature amount analysis unit 32 with the reference feature amount stored in the reference feature amount storage unit 36, and determines the abnormality of the seam SE. The determination of the abnormality of the seam SE includes the determination of the presence or absence of the abnormality of the seam SE and the determination of the pattern of the abnormality of the seam SE.

<Abnormal seams>
FIG. 4 is a diagram schematically showing a normal seam SE. 5 and 6 are diagrams schematically showing the abnormal seam SE.

In the present embodiment, the sewing machine 1 is a lockstitch sewing machine that performs lockstitch. As shown in FIG. 4, the normal seam SE in the lockstitch is formed linearly in the Y-axis direction. One normal seam SE is formed with a normal length Pn. Each of the plurality of seams SE is formed with a normal length Pn.

There are a plurality of abnormal patterns of seam SE. The abnormal patterns of the seam SE include the abnormality of the first pattern in which at least one of the seam SE is lengthened, the abnormality of the second pattern in which at least a part of the seam SE is lost, and the needle thread UT and the lower thread in the sewing object S. An abnormality of the third pattern in which at least one of the thread LTs is loosened is exemplified. The abnormality of the first pattern is called "eye skipping". The abnormality of the second pattern is called "thread breakage". The abnormality of the third pattern is called "lantern".

FIG. 5 is a diagram showing an example of “eye skipping” which is an abnormality of the first pattern. The “seam skipping” is a phenomenon in which a seam SE is not formed at a constant normal length Pn, but a seam SE is formed at an abnormal length Pu longer than the normal length Pn. As the pattern of "eye skipping", the "single stitch jump" in which the seam SE of the abnormal length Pu1 as shown in FIG. 5 (A) occurs sporadically, and the abnormal length Pu1 as shown in FIG. 5 (B). Examples thereof include "continuous stitch skipping" in which seam SE occurs continuously and "long stitch skipping" in which stitch SE having an abnormal length Pu2 longer than the abnormal length Pu1 as shown in FIG. 5C is generated. To.

FIG. 6 is a diagram showing an example of a “lantern” which is an abnormality of the third pattern. The "lantern" is a phenomenon in which the needle thread UT and the bobbin thread LT are hung, but the needle thread UT is loosened on the front surface of the sewing object S and the bobbin thread LT is loosened on the back surface of the sewing object S. .. FIG. 6 shows an example in which the bobbin thread LT is loosened on the back surface of the sewing object S.

<First method of detecting seam abnormalities>
The first method of detecting the abnormality of the seam SE will be described. In the first method, the determination unit 33 determines the abnormality of the seam SE based on the detection value of the tension sensor 21 and the detection value of the angle sensor 22.

The tension sensor 21 outputs the detected value of the tension of the needle thread UT at a predetermined cycle (for example, every 0.1 [ms]) in the rotation of the motor 10. That is, when the motor 10 rotates at each of the plurality of rotation angles, the tension sensor 21 outputs a detected value at each of the plurality of rotation angles.

The reference feature amount is output from the tension sensor 21 at each of the plurality of rotation angles when the motor 10 rotates at each of the plurality of rotation angles when the normal seam SE as shown in FIG. 4 is formed. Includes detected values of tension applied. The reference feature amount is derived based on a preliminary experiment (including a simulation experiment) and is stored in advance in the reference feature amount storage unit 36.

The detection feature amount is the detection of the actual tension output from the tension sensor 21 at each of the plurality of rotation angles when the motor 10 rotates at each of the plurality of rotation angles when the seam SE is actually formed. Includes a value.

In the present embodiment, the determination unit 33 collates the detected feature amount derived when the rotation angle of the motor 10 is a specific angle with the reference feature amount, and determines the abnormality of the seam SE.

When determining whether or not "jumping" has occurred, the determination unit 33 detects the tension sensor 21 acquired when the rotation angle of the motor 10 is a specific angle of 270 [°] or more and 360 [°] or less. The detected feature amount derived from the value is compared with the reference feature amount stored in the reference feature amount storage unit 36, and it is determined whether or not "skipping" has occurred.

FIG. 7 is a diagram showing the detected values of the tension sensor 21. In FIG. 7, the horizontal axis represents the rotation angle of the motor 10, and the vertical axis represents the detected value of the tension sensor 21. In FIG. 7, the range Sa and the range Sn indicate a range in which the rotation angle of the motor 10 is a specific angle of 270 [°] or more and 360 [°] or less. The determination unit 33 collates the detected feature amount derived when the rotation angle of the motor 10 is 270 [°] or more and 360 [°] or less with the reference feature amount, and determines whether or not “eye skipping” has occurred. To judge.

When a normal seam SE is formed, the tension sensor 21 outputs a detection value as shown in the range Sn. When "jumping" occurs, the tension sensor 21 outputs a detected value as shown in the range Sa. As shown in FIG. 7, the detected value of the tension sensor 21 in the range Sn and the detected value of the tension sensor 21 in the range Sa are different. In the range where the rotation angle of the motor 10 is 270 [°] or more and 360 [°] or less, the tension of the needle thread UT when "skipping" occurs is the tension of the needle thread UT when the normal stitch SE is formed. It also becomes smaller due to tension.

In the present embodiment, the detected value as shown in the range Sn is stored in the reference feature amount storage unit 36 as the reference feature amount. The detection feature amount analysis unit 32 extracts the detection value in the range where the rotation angle of the motor 10 is 270 [°] or more and 360 [°] or less from the detection value of the tension sensor 21 acquired by the detection value acquisition unit 31. Derivation of the detected feature amount for determining "skipping". The determination unit 33 collates the detected feature amount calculated by the detection feature amount analysis unit 32 with the reference feature amount stored in the reference feature amount storage unit 36, and determines whether or not "skipping" has occurred. Is determined. When the detected feature amount includes the detected value as shown in the range Sa, the determination unit 33 may determine that "skipping" has occurred based on the collation result between the detected feature amount and the reference feature amount. can. When the detected feature amount includes the detected value as shown in the range Sn, the determination unit 33 may determine that "skipping" has not occurred based on the collation result between the detected feature amount and the reference feature amount. can.

When determining whether or not "thread breakage" has occurred, the determination unit 33 detects the tension sensor 21 acquired when the rotation angle of the motor 10 is a specific angle of 0 [°] or more and 90 [°] or less. It is determined whether or not "thread breakage" has occurred by collating the detected feature amount derived from the value with the reference feature amount stored in the reference feature amount storage unit 36.

FIG. 8 is a diagram showing the detected values of the tension sensor 21. In FIG. 8, the horizontal axis represents the rotation angle of the motor 10, and the vertical axis represents the detected value of the tension sensor 21. In FIG. 8, the range Sa and the range Sn indicate a range in which the rotation angle of the motor 10 is a specific angle of 0 [°] or more and 90 [°] or less. The determination unit 33 collates the detected feature amount derived when the rotation angle of the motor 10 is 0 [°] or more and 90 [°] or less with the reference feature amount, and determines whether or not "thread breakage" has occurred. To judge.

When a normal seam SE is formed, the tension sensor 21 outputs a detection value as shown in the range Sn. When "thread breakage" occurs, the tension sensor 21 outputs a detection value as shown in the range Sa. As shown in FIG. 8, the detected value of the tension sensor 21 in the range Sn and the detected value of the tension sensor 21 in the range Sa are different. In the range where the rotation angle of the motor 10 is 0 [°] or more and 90 [°] or less, the tension of the needle thread UT when "thread breakage" occurs is the tension of the needle thread UT when a normal seam SE is formed. It is smaller than the tension.

In the present embodiment, the detected value as shown in the range Sn is stored in the reference feature amount storage unit 36 as the reference feature amount. The detection feature amount analysis unit 32 extracts the detection value in the range where the rotation angle of the motor 10 is 0 [°] or more and 90 [°] or less from the detection value of the tension sensor 21 acquired by the detection value acquisition unit 31. The detection feature amount for determining "thread breakage" is derived. The determination unit 33 collates the detected feature amount calculated by the detection feature amount analysis unit 32 with the reference feature amount stored in the reference feature amount storage unit 36, and determines whether or not "thread breakage" has occurred. Is determined. When the detected feature amount includes the detected value as shown in the range Sa, the determination unit 33 may determine that "thread breakage" has occurred based on the collation result between the detected feature amount and the reference feature amount. can. When the detected feature amount includes the detected value as shown in the range Sn, the determination unit 33 may determine that "thread breakage" has not occurred based on the collation result between the detected feature amount and the reference feature amount. can.

<Second method for detecting seam abnormalities>
A second method for detecting an abnormality in the seam SE will be described. Also in the second method, the determination unit 33 determines the abnormality of the seam SE based on the detection value of the tension sensor 21 and the detection value of the angle sensor 22.

In the second method, the detected feature amount includes a detected cumulative curve showing the cumulative value of the detected values of the tension sensor 21 in the rotation of the motor 10. The reference feature amount includes a reference cumulative curve showing the cumulative value of tension when the seam SE is normal.

The determination unit 93 has a detected cumulative value curve showing the cumulative value of the detected value of the tension sensor 21 in the rotation of the motor 10 and a reference cumulative curve showing the cumulative value of the tension of the needle thread UT when the seam SE is normal. By collating, it is determined that the seam SE is abnormal. In the present embodiment, the determination unit 93 collates the detected cumulative curve with the reference cumulative curve, and determines whether or not the "lantern" has occurred.

As described above, the tension sensor 21 outputs the detected value of the tension of the needle thread UT at a predetermined cycle in the rotation of the motor 10. That is, when the motor 10 rotates at each of the plurality of rotation angles, the tension sensor 21 outputs a detected value at each of the plurality of rotation angles.

The cumulative value means the cumulative value of the detected value of the tension detected by the tension sensor 21 at each of the plurality of rotation angles of the motor 10. The longer the detection time of the tension sensor 21, the larger the cumulative value. The cumulative curve refers to a curve showing the relationship between a plurality of rotation angles of the motor 10 and a cumulative value of tension at each of the plurality of rotation angles.

The reference cumulative curve is a cumulative curve showing the cumulative value of tension when a normal seam SE is formed, and is stored in advance in the reference feature amount storage unit 36.

The detection cumulative curve is a cumulative curve showing the cumulative value of the actual detected value, and is calculated by the detection feature amount analysis unit 32.

The determination unit 93 collates the detected cumulative curve with the reference cumulative curve, and determines the abnormality of the seam SE.

FIG. 9 is a diagram showing a cumulative curve. In FIG. 9, the horizontal axis represents the rotation angle of the motor 10, and the vertical axis represents the cumulative value of tension. FIG. 9 shows a cumulative curve when the motor 10 is, for example, 1000 rpm. For example, the detection value of the tension when the rotation angle of the motor 10 is 180 [°] is acquired, then the detection value of the tension when the rotation angle of the motor 10 is 181 [°] is acquired, and the value is added to the detection value of 180 [°]. .. Similarly, the cumulative value is calculated by sequentially adding 182 [°], 183 [°], ..., 0 [°], ..., 359 [°].

When a normal seam SE is formed, a cumulative curve as shown by the curve Ln is generated. When a "lantern" occurs, a cumulative curve as shown by the curve La is generated. As shown in FIG. 9, the slope of the curve Ln and the slope of the curve La are different. The slope of the cumulative curve (curve La) when the "lantern" occurs is larger than the slope of the cumulative curve (curve Ln) when the normal seam SE is formed.

In the present embodiment, the cumulative curve as shown by the curve Ln is stored in the reference feature amount storage unit 36 as the reference cumulative curve. The detection feature amount analysis unit 32 calculates a detection cumulative curve for determining "lantern" based on the detection value of the tension sensor 21 acquired by the detection value acquisition unit 31. The determination unit 33 collates the detection cumulative curve calculated by the detection feature amount analysis unit 32 with the reference cumulative curve stored in the reference feature amount storage unit 36, and determines whether or not "lantern" is generated. judge. When the detected cumulative curve is a cumulative curve as shown by the curve La, the determination unit 33 can determine that "lantern" has occurred based on the collation result between the detected cumulative curve and the reference cumulative curve. .. When the detected cumulative curve is a cumulative curve as shown by the curve Ln, the determination unit 33 can determine that "lantern" has not occurred based on the collation result between the detected cumulative curve and the reference cumulative curve. ..

<Third method of detecting seam abnormalities>
A third method for detecting an abnormality in the seam SE will be described. In the third method, the detection feature amount includes the detection frequency spectrum calculated by Fourier transforming the detection value of the tension sensor 21 in the rotation of the motor 10. The reference feature quantity includes the reference frequency spectrum calculated by Fourier transforming the tension when the seam SE is normal.

The determination unit 93 calculates the detection frequency spectrum calculated by Fourier transforming the detected value of the tension sensor 21 in the rotation of the motor 10 and the tension of the needle thread UT when the seam SE is normal by Fourier transforming. The abnormality of the seam SE is determined by collating with the reference frequency spectrum. The determination unit 93 can collate the detected frequency spectrum with the reference frequency spectrum and determine, for example, whether or not a "lantern" has occurred.

FIG. 10 is a diagram showing a frequency spectrum of tension. In FIG. 10, the horizontal axis indicates the frequency of the detected value of tension, and the vertical axis indicates the amplitude of the detected value of tension. FIG. 10 shows the result of performing a fast Fourier transform (FFT) of the detected value of the tension detected when the motor 10 is operated at, for example, 1000 rpm.

When a normal seam SE is formed, a frequency spectrum as shown in FIG. 10 (A) is generated. When a "lantern" occurs, a frequency spectrum as shown in FIG. 10 (B) is generated. As shown in FIG. 10, when a "lantern" is generated, a peak PK is formed at a specific frequency. When "lantern" occurs, the tension of the needle thread UT slightly vibrates, so that a peak PK is formed.

In the present embodiment, the frequency spectrum as shown in FIG. 10A is stored in the reference feature amount storage unit 36 as the reference frequency spectrum. The detection feature amount analysis unit 32 calculates a detection frequency spectrum for determining "lantern" based on the detection value of the tension sensor 21 acquired by the detection value acquisition unit 31. The determination unit 33 collates the detection frequency spectrum calculated by the detection feature amount analysis unit 32 with the reference frequency spectrum stored in the reference feature amount storage unit 36, and determines whether or not "lantern" is generated. judge. When the detected frequency spectrum is a frequency spectrum as shown in FIG. 10 (B), the determination unit 33 determines that "lantern" is generated based on the collation result between the detected frequency spectrum and the reference frequency spectrum. be able to. When the detected frequency spectrum is a frequency spectrum as shown in FIG. 10 (A), the determination unit 33 determines that "lantern" has not occurred based on the collation result between the detected frequency spectrum and the reference frequency spectrum. be able to.

<Sewing method>
Next, the sewing method according to this embodiment will be described. FIG. 11 is a flowchart showing a sewing method according to the present embodiment. As shown in FIG. 11, the sewing method according to the present embodiment includes a reference feature amount calculation process and a seam inspection process.

The reference feature amount calculation process will be described. The sewing object S is installed on the needle plate 7 of the sewing machine 1. The sewing machine 1 starts sewing the sewing object S. The tension sensor 21 detects the tension of the needle thread UT in parallel with the sewing of the sewing object S. The tension sensor 21 outputs the detected value of the tension of the needle thread UT to the processing device 30. The reference feature amount generation unit 35 acquires the detected value of the tension sensor 21 via the detected value acquisition unit 31 (step SA1).

The seam SE formed on the sewing object S is confirmed. When the normal seam SE is formed, the input device 24 is operated by the operator so as to generate input data indicating that the normal seam SE is formed. The reference feature amount generation unit 35 acquires input data indicating that a normal seam SE has been formed (step SA2).

The reference feature amount generation unit 35 calculates a reference feature amount indicating the tension feature amount of the needle thread UT when a normal stitch SE is formed based on the detected value of the tension sensor 21 and the input data (step). SA3).

The reference feature amount generation unit 35 stores the calculated reference feature amount in the reference feature amount storage unit 36 (step SA4).

Next, the seam inspection process will be described. The sewing object S is installed on the needle plate 7 of the sewing machine 1. The sewing machine 1 starts sewing the sewing object S. The tension sensor 21 detects the tension of the needle thread UT in parallel with the sewing of the sewing object S. The tension sensor 21 outputs the detected value of the tension of the needle thread UT to the processing device 30. The detection feature amount analysis unit 32 acquires the detection value of the tension sensor 21 via the detection value acquisition unit 31 (step SB1).

The detected feature amount analysis unit 32 analyzes the detected value of the tension sensor 21 and calculates the detected feature amount of the detected value (step SB2).

The determination unit 33 collates the detected feature amount calculated by the detection feature amount analysis unit 32 with the reference feature amount stored in the reference feature amount storage unit 36, and determines the abnormality of the seam SE (step SB3). ).

The determination unit 33 determines the abnormality of the seam SE based on at least one of the first method, the second method, and the third method of detecting the abnormality of the seam SE. The output unit 34 outputs the determination result of the determination unit 33 to the output device 23 (step SB4).

<Effect>
As described above, according to the present embodiment, the tension of the needle thread UT is detected by the tension sensor 21. An abnormality in the seam SE can be easily detected based on the detected value of the tension of the needle thread UT. Therefore, the inspection of the seam SE can be efficiently performed.

In the present embodiment, the reference feature amount is derived in advance based on the detected value of the tension when the normal seam SE is formed. Thereby, the abnormality of the seam SE can be efficiently determined only by collating the reference feature amount and the detected feature amount.

As in the first method and the second method of detecting the abnormality of the seam SE, not only the detection value of the tension sensor 21 but also the detection value of the angle sensor 22 is acquired, so that the detection value and the angle of the tension sensor 21 are acquired. Based on the detection value of the sensor 22, the abnormality of the seam SE can be determined with high accuracy.

Further, as in the second method of detecting the abnormality of the seam SE, the cumulative curve is generated based on the cumulative value of the tension, so that even if the detection value of the tension sensor 21 contains noise, the influence of the noise. Is reduced. Therefore, the abnormality of the seam SE can be determined with high accuracy.

Further, as in the third method of detecting the abnormality of the seam SE, the frequency spectrum of the detected value of the tension is generated, so that the abnormality of the seam SE can be detected with high accuracy without using the detected value of the angle sensor 22. It can be determined.

<Modification example>
In the above-described embodiment, the detected feature amount and the reference feature amount are collated to detect the abnormality of the seam SE. An abnormality of the seam SE may be detected by setting a threshold value related to the detected value of tension and based on the comparison result between the detected value and the threshold value.

[Second Embodiment]
The second embodiment will be described. In the following description, the same or equivalent components as those in the above-described embodiment are designated by the same reference numerals, and the description thereof will be simplified or omitted.

FIG. 12 is a flowchart showing a sewing method according to the present embodiment. As shown in FIG. 12, the sewing method according to the present embodiment includes a learning process and an identification process.

The learning process will be described. The sewing object S is installed on the needle plate 7 of the sewing machine 1. The sewing machine 1 starts sewing the sewing object S. The tension sensor 21 detects the tension of the needle thread UT in parallel with the sewing of the sewing object S. The tension sensor 21 outputs the detected value of the tension of the needle thread UT to the processing device 30. The reference feature amount generation unit 35 acquires the detected value of the tension sensor 21 via the detected value acquisition unit 31 (step SC1).

The reference feature amount generation unit 35 assigns a label to the detected value of the tension sensor 21 (step SC2). The label is a correct label indicating that a normal seam SE has been formed, a first abnormal label indicating that an abnormality of the first pattern "skipping" has occurred, and an abnormality of the second pattern "thread breakage". Includes a second anomaly label indicating that an anomaly has occurred, and a third anomaly label indicating that a "lantern", which is an anomaly of the third pattern, has occurred. The reference feature amount generation unit 35 assigns a correct label to the detected value of the tension sensor 21 acquired when the normal seam SE is formed. The reference feature amount generation unit 35 assigns the first abnormality label to the detected value of the tension sensor 21 acquired when the abnormality of the first pattern occurs. The reference feature amount generation unit 35 assigns a second abnormality label to the detected value of the tension sensor 21 acquired when the abnormality of the second pattern occurs. The reference feature amount generation unit 35 assigns a third abnormality label to the detected value of the tension sensor 21 acquired when the abnormality of the third pattern occurs.

The reference feature amount generation unit 35 machine-learns the detected value with the label by a specified machine learning algorithm (step SC3). As a machine learning algorithm, at least one of a decision tree, a random forest, and a neural network is exemplified.

A learning model is generated by machine learning the labeled detection values (step SC4). The generated learning model is stored in the reference feature amount storage unit 36.

Next, the identification process will be described. The sewing object S is installed on the needle plate 7 of the sewing machine 1. The sewing machine 1 starts sewing the sewing object S. The tension sensor 21 detects the tension of the needle thread UT in parallel with the sewing of the sewing object S. The tension sensor 21 outputs the detected value of the tension of the needle thread UT to the processing device 30. The detection feature amount analysis unit 32 acquires the detection value of the tension sensor 21 via the detection value acquisition unit 31 (step SD1).

The detected feature amount analysis unit 32 analyzes the detected value of the tension sensor 21 and calculates the detected feature amount of the detected value. The determination unit 33 identifies the abnormal pattern of the seam SE based on the detected feature amount calculated by the detection feature amount analysis unit 32 and the learning model stored in the reference feature amount storage unit 36 (step SD2). ).

The output unit 34 outputs the identification result of the determination unit 33 to the output device 23 (step SD3). For example, when the abnormal pattern of the seam SE is identified as the first pattern, the output unit 34 outputs output data indicating that the abnormal “separation” of the first pattern has occurred to the output device 23. Let me. When the abnormal pattern of the seam SE is identified as the second pattern, the output unit 34 causes the output device 23 to output output data indicating that the abnormal "thread break" of the second pattern has occurred. When the pattern of abnormality of the seam SE is identified as the third pattern, the output unit 34 causes the output device 23 to output output data indicating that the "lantern" which is an abnormality of the third pattern has occurred. When it is identified as a normal seam SE, the output unit 34 causes the output device 23 to output output data indicating that the seam SE is normal.

As described above, machine learning (supervised learning) may be performed based on the detected value of the tension sensor 21, and an abnormality in the seam SE may be detected based on the generated model.

1 ... sewing machine, 2 ... sewing machine head, 3 ... sewing machine needle, 4 ... needle bar, 5 ... balance, 6 ... thread tensioner, 7 ... needle plate, 8 ... holding member, 9 ... kettle, 10 ... motor, 20 ... seam Inspection device, 21 ... Tension sensor, 22 ... Angle sensor, 23 ... Output device, 24 ... Input device, 30 ... Processing device, 30A ... Calculation device, 30B ... Storage device, 30C ... Input / output interface, 31 ... Detection value acquisition unit , 32 ... detection feature amount analysis unit, 33 ... judgment unit, 34 ... output unit, 35 ... reference feature amount generation unit, 36 ... reference feature amount storage unit, LT ... bobbin thread, S ... sewing object, SE ... seam, UT ... Needle thread.

Claims (3)

A tension sensor that detects the tension of the needle thread applied to the sewing machine needle that reciprocates due to the rotation of the motor ,
A processing device that detects an abnormality in the seam formed on the sewing object by the sewing machine needle based on the detection value of the tension sensor, and a processing device.
It is equipped with an angle sensor that detects the rotation angle of the motor .
The processing device is
A detection feature amount analysis unit that analyzes the detection value of the tension sensor and calculates a detection feature amount indicating the feature amount of the detection value, and a detection feature amount analysis unit.
A reference feature amount storage unit for storing the reference feature amount of the tension, and a reference feature amount storage unit.
A determination unit for determining the abnormality by collating the detected feature amount with the reference feature amount,
Have,
The tension sensor outputs the detection value at a specified cycle in the rotation of the motor, and outputs the detection value.
The determination unit determines the abnormality based on the detection value of the tension sensor and the detection value of the angle sensor.
The detected feature amount includes a detected cumulative curve showing the cumulative value of the detected value in the rotation of the motor.
The reference feature amount includes a reference cumulative curve showing the cumulative value of the tension when the seam is normal.
Seam inspection device. The determination unit determines the abnormality by collating the detected feature amount derived when the rotation angle of the motor is a specific angle with the reference feature amount.
The seam inspection device according to claim 1 . A tension sensor that detects the tension of the needle thread applied to the sewing machine needle that reciprocates due to the rotation of the motor,
A processing device for detecting an abnormality in a seam formed on an object to be sewn by the sewing machine needle based on a detection value of the tension sensor is provided.
The processing device is
A detection feature amount analysis unit that analyzes the detection value of the tension sensor and calculates a detection feature amount indicating the feature amount of the detection value, and a detection feature amount analysis unit.
A reference feature amount storage unit for storing the reference feature amount of the tension, and a reference feature amount storage unit.
It has a determination unit for collating the detected feature amount with the reference feature amount and determining the abnormality.
The tension sensor outputs the detection value at a specified cycle in the rotation of the motor, and outputs the detection value.
The detected feature amount includes a detection frequency spectrum calculated by Fourier transforming the detected value in the rotation of the motor.
The reference feature amount includes a reference frequency spectrum calculated by Fourier transforming the tension when the seam is normal.
Seam inspection device.

Images