Interference noise detection device

Abstract

To improve the workability of fitting work and to accurately detect fitting sounds. [Solution] The interference sound detection device comprises a microphone, a holding member for holding a interference member provided at an end of a wire harness, a sensor for detecting the wire harness with the interference member held by the holding member, and a controller for controlling the execution of a judgment process for determining whether or not the sound collected by the microphone contains an interference sound caused by the interference member based on sound data based on the sound collected by the microphone, wherein the controller executes the judgment process while the sensor detects the wire harness and does not execute the judgment process while the sensor does not detect the wire harness.

Description

[Technical field]

[0001] The present disclosure relates to a fitting noise detection device that detects fitting noise generated when fitting members are fitted together. [Background technology]

[0002] In the manufacture of products that include electrically operated components, such as automobiles, communication devices, and medical devices, wire harnesses are used to connect the components together. A wire harness is a device in which one or more cables that transmit power, electrical signals, etc. are attached to the ends of the cables with a connecting member, such as a connector, for connecting the one or more cables together to other components.

[0003] In the manufacturing process of products using wire harnesses, workers need to perform a joining operation in which a joining member provided at the end of the wire harness is joined to another joining member. If the components are not electrically connected properly due to an improper joining operation, it may cause manufacturing defects in the final product.

[0004] For this reason, Patent Document 1 and Patent Document 2 disclose a method for judging the quality of a fitting operation by detecting a "fitting sound" that occurs when fitting parts. In Patent Documents 1 and 2, the fitting sound is detected by collecting sound data using a wristwatch-type device worn by the worker during the fitting operation. The fitting sound is a "predetermined sound" that occurs when the fitting parts are properly fitted together, and is also called a "click sound" or the like. For example, the fitting parts have a locking mechanism, and are configured so that when the fitting parts are properly fitted together, the locking mechanism maintains the fitting state. The fitting sound occurs when two fitting parts are properly locked together by the locking mechanism. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2023-112729 A [Patent Document 2] Patent Publication No. 2022-108326 Summary of the Invention [Problem to be solved by the invention]

[0006] In order to reduce manufacturing defects in products that require fitting operations in the manufacturing process, it is necessary to improve the workability of the fitting operation and to accurately detect fitting noise.

[0007] The present disclosure provides a technique for improving the workability of fitting work and for accurately detecting fitting sounds. [Means for solving the problem]

[0008] According to one aspect of the present disclosure, a mating sound detection device includes a microphone, a holding member for holding a mating member provided at an end of a wire harness, a sensor for detecting the wire harness with the mating member held by the holding member, and a controller for controlling execution of a determination process for determining whether or not a sound collected by the microphone includes a mating sound caused by the mating member based on sound data based on the sound collected by the microphone, wherein the controller executes the determination process while the sensor detects the wire harness and does not execute the determination process while the sensor does not detect the wire harness. Effect of the Invention

[0009] According to the present disclosure, the workability of the fitting work can be improved and fitting sounds can be detected with high accuracy. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing a schematic configuration example of an interference sound detection system including an interference sound detection device. [Diagram 2] FIG. 1 is a schematic perspective view showing an example of an interference noise detection device. [Diagram 3] FIG. 13 is a diagram showing an example of a state in which a wire harness is held by the mating noise detection device. [Figure 4] FIG. 2 is a diagram showing an example of a schematic external appearance of a head of the interference sound detection device. [Diagram 5] FIG. 2 is a diagram showing an example of the functional configuration of a mixed sound detection device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the invention according to the claims, and not all combinations of features described in the embodiments are essential to the invention. Two or more features among the multiple features described in the embodiments may be arbitrarily combined. In addition, the same reference numbers are used for the same or similar configurations, and duplicated descriptions are omitted.

[0012] 1 shows an example of a joint sound detection system including a joint sound detection device 100. The joint sound detection device 100 is used during joint work in a factory. The joint sound detection device 100 can be configured to be wirelessly accessible to a local area network (LAN) 200 provided in the factory. A manufacturing system 600 that manages the manufacturing process in the factory is connected to the LAN 200. The LAN 200 is also connected to the Internet 300, and a learning server 400 and a database 500 are connected to the Internet 300.

[0013] The indentation sound detection device 100 according to this embodiment uses a learning model to detect indentation sounds during indentation work. The learning server 400 collects sound data (sound data) during indentation work from multiple indentation sound detection devices 100, and performs machine learning based on the collected sound data to generate a learning model.

[0014] Since the fitting sound may differ depending on the type of fitting part, a learning model may be generated for each type of fitting part. That is, the learning model may be associated with the type of fitting part. The type of fitting part may be distinguished by the shape or material of the fitting part. If the same learning model can be applied to different types of fitting parts, the same learning model may be used. That is, one learning model may be used to detect fitting sounds of multiple types of fitting parts. For example, if multiple types of fitting parts that can use the same learning model are considered as one component group, the learning model may be generated in association with the component group.

[0015] In addition, since the background noise of a factory may differ from factory to factory, a learning model may be generated for each factory (location) in which the interference sound detection device 100 is used. That is, the learning model may be associated with the location in which the learning model is used. Note that, even if the locations in which the learning model is used are different, if the same learning model can be applied, the same learning model may be used. That is, one learning model may be commonly used in multiple locations. For example, if multiple locations in which the same learning model can be used are considered as one location group, the learning model may be generated in association with the location group. Furthermore, a learning model may be generated for each combination of the type of interference component and the factory (location) in which the interference sound detection device 100 is used. Furthermore, a learning model may be generated for each combination of a component group and a location group.

[0016] The database 500 is a database that stores one or more learning models generated by the learning server 400. Before starting a merging operation, the merging sound detection device 100 downloads and stores the learning model to be used in the merging operation from the database 500. The learning server 400 and the database 500 may be the same server. Furthermore, the database 500 may be connected to the LAN 200, and the database 500 may be configured to store only the learning models to be used in the factory where the LAN 200 is installed.

[0017] Fig. 2 is a schematic perspective view showing an example of the interference sound detection device 100, Fig. 3 shows a state in which the interference sound detection device 100 holds the interference member 31 of the wire harness 3, and Fig. 4 shows the interference sound detection device 100 as viewed in the -X direction of Fig. 2. Note that Figs. 2 to 4 are schematic views for understanding an example of the interference sound detection device 100, and do not limit the configuration of the interference sound detection device 100. In Fig. 3, reference numeral 310 denotes a lock mechanism provided on the interference member 31, and reference numeral 32 denotes a cable of the wire harness 3.

[0018] The mating sound detection device 100 includes a head 1 and a main body 2. A plurality of types of heads 1 are provided according to the shape and size of the mating member 31 of the wire harness 3 to be worked on, and are configured to be detachable from the main body 2. A worker performs mating work by attaching the head 1 to the main body 2 in accordance with the mating member 31 of the wire harness 3 to be worked on. Various parts are stored inside the housing of the main body 2.

[0019] The head 1 is a holding member that holds the mating member 31 of the wire harness 3, and is equipped with a handle member 11 and a handle member 12. With the mating member 31 of the wire harness 3 between the handle member 11 and the handle member 12, the worker holds the mating member 31 of the wire harness 3 by grasping (gripping) the handle member 11 and the handle member 12 so that the handle member 11 and the handle member 12 approach each other.

[0020] As shown in FIG. 3, rather than holding the entire mating member 31 with the head 1, the head 1 can be configured so that only a specified area of ​​the mating member 31 on the cable 32 side is gripped by the head 1, and the remaining area of ​​the mating member 31 on the side to be joined with another mating member protrudes from the head 1.

[0021] 4, a hole 13 is provided on the side of the head 1 facing the main body 2 to transmit light emitted by an optical sensor 25 (FIG. 5) provided on the main body 2 and the reflected light. The optical sensor 25 is configured to optically detect the cable 32 of the wire harness 3 when the worker holds the mating member 31 of the wire harness 3 with the head 1.

[0022] The handle member 11 and the handle member 12 are configured to be movable or deformable in a direction approaching each other so that an operator can hold the mating member 31. As an example, the handle member 11 and the handle member 12 can be configured to be elastically deformable. Note that only one of the handle member 11 and the handle member 12 may be configured to be movable or deformable so as to approach the other. Since the head 1 is configured so that an operator holds the mating member 31 by gripping the mating member 31 via the handle member 11 and the handle member 12, the shape of the surface of the head 1 that contacts the mating member 31 does not need to be the same as the shape of the surface of the mating member 31 that contacts the head 1. Therefore, the same head 1 can be used in common for multiple types of mating members 31.

[0023] 3, if the direction in which the head 1 and the main body 2 are aligned when the head 1 is attached to the main body 2 is the X direction, the handle members 11 and 12 are provided along the Y direction when the head 1 is attached to the main body 2, but the head 1 can also be configured so that the handle members 11 and 12 are provided along the X direction. In other words, the head 1 can also be configured to be attached to the main body 2 in a state in which it is rotated by 90 degrees from the state in FIG. 2 with the Z axis as the rotation axis.

[0024] Furthermore, in the configuration example of FIG. 3, if the direction in which the head 1 and the main body 2 are aligned when the head 1 is attached to the main body 2 is the X direction, the longitudinal direction of the wire harness 3 held by the head 1 is approximately the Z direction. This is because the head 1 shown in the configuration example of FIG. 3 is configured to hold the mating member 31 of the wire harness 3 at one end in the Z direction. However, for example, when the direction in which the head 1 and the main body 2 are aligned is the X direction, the head 1 can be configured to hold the mating member 31 of the wire harness 3 at the end opposite to the main body 2, out of the two ends in the X direction. In other words, the head 1 can be configured to be attached to the main body 2 in a state rotated 90 degrees from the state of FIG. 2 with the Y axis as the rotation axis. In this case, the cable 32 of the wire harness 3 held by the head 1 extends toward the main body 2 (X direction), but does not interfere with the main body 2 by drawing the cable 32 out from between the handle member 11 and the handle member 12.

[0025] Fig. 5 shows an example of the functional configuration of the interference sound detection device 100. The hardware for realizing the functional blocks of Fig. 5 is housed in the housing of the main body 2. The controller 26 includes, for example, one or more processors, and is configured to control the interference sound detection device 100 as a whole.

[0026] As described above, the optical sensor 25 detects whether or not the mating sound detection device 100 is holding the wire harness 3. For example, the optical sensor 25 emits light through the hole 13 provided in the head 1 and receives the reflected light. When the head 1 is not holding the wire harness 3, the light emitted by the optical sensor 25 passes between the handle members 11 and 12, and the optical sensor 25 does not receive the reflected light. On the other hand, when the head 1 is holding the wire harness 3, the optical sensor 25 receives the light reflected by the cable 32 of the wire harness 3. Therefore, it is possible to detect whether or not the head 1 is holding the wire harness 3 depending on whether or not the optical sensor 25 receives the reflected light.

[0027] Furthermore, a TOF (Time of Flight) sensor can be used as the optical sensor 25. The TOF sensor is an optical sensor that measures the distance to an object. The approximate distance between the TOF sensor and the cable 32 when the head 1 is holding the wire harness 3 can be determined in advance. Therefore, by using the TOF sensor, even if the head 1 receives reflected light when it is not holding the wire harness 3, it is possible to accurately detect whether the head 1 is holding the wire harness 3 or not.

[0028] In this example, the optical sensor 25 detects the cable 32 of the wire harness 3 in a state in which the worker holds the mating member 31 of the wire harness 3 with the head 1, but it may also detect the mating member 31 of the wire harness 3. In other words, the optical sensor 25 may be configured to detect whether or not the worker is holding the mating member 31 of the wire harness 3 with the head 1 by detecting the wire harness 3 in a state in which the mating member 31 is held by the head 1.

[0029] The microphone 21 is, for example, a MEMS (microelectromechanical system) microphone, which converts sound into an analog sound signal and outputs it to the pre-processing unit 22. The microphone 21 may be disposed on the head 1 side within the main body 2 in order to accurately detect the interference sound. Furthermore, although not shown in Fig. 4, a hole may be provided on the side surface of the head 1 on the main body 2 side to facilitate the microphone 21 to collect sound.

[0030] The pre-processing unit 22 has an analog-to-digital converter (ADC) that converts the analog sound signal output by the microphone 21 into digital sound data, and outputs the digital sound data to the determination unit 23 .

[0031] The determination unit 23 stores a learning model acquired from the database 500, and by inputting sound data from the preprocessing unit 22 to the learning model, determines whether or not the sound indicated by the sound data contains a joint sound caused by the joint member 31. The determination unit 23 then notifies the controller 26 of the determination result as to whether or not the sound indicated by the sound data contains a joint sound caused by the joint member 31, that is, the detection result as to whether or not a joint sound has been detected. The function of the determination unit 23 may be realized by the processor of the controller 26.

[0032] The controller 26 presents the detection result of whether or not the interlocking sound has been detected to the worker via the user interface (UI) 27 based on the determination result from the determination unit 23. As an example, the UI 27 has, for example, an LED that lights up in at least two colors. When the controller detects the interlocking sound, the controller controls the LED to light up in a first color, and when the controller does not detect the interlocking sound, the controller controls the LED to light up in a second color different from the first color. Alternatively, the UI 27 has, for example, an LED that lights up in a single color. The controller 26 turns off the LED until the interlocking sound is detected, and when the controller detects the interlocking sound, turns on the LED until a predetermined condition is satisfied. The predetermined condition may be satisfied, for example, when the user performs a confirmation input via the UI 27. Alternatively, the predetermined condition may be satisfied when the optical sensor 25 no longer detects the wire harness 3. Furthermore, the predetermined condition may be satisfied when a predetermined period has elapsed since the optical sensor 25 no longer detects the wire harness 3. Furthermore, the UI 27 may have a plurality of LEDs. The controller 26 changes the lighting / extinguishing state of the plurality of LEDs depending on whether or not an interference sound is detected. The UI 27 may be provided with a display, and may be configured to display whether or not an interference sound is detected on the display. Furthermore, the UI 27 may have one or more operation buttons for switching on / off the power supply of the interference sound detection device 100 and for switching the operation mode of the interference sound detection device 100, which will be described later.

[0033] The communication unit 24 has a function of wirelessly accessing the LAN 200 and communicating with devices on the LAN 200 or the Internet 300 such as the manufacturing system 600, the learning server 400, and the database 500.

[0034] The interleaved sound detection device 100 can be configured to operate in either an operation mode, a "work mode" or a "learning mode." An operator can set the operation mode of the interleaved sound detection device 100 via the UI 27. The work mode is a mode used when performing interleaving work, and the learning mode is a mode used when transmitting sound data to the learning server 400 for machine learning.

[0035] The operation of the fitting sound detection device 100 during the fitting work will be described below. For the fitting work, the fitting sound detection device 100 is set to a work mode. In addition, the determination unit 23 stores in advance a learning model corresponding to the wire harness 3 to be used in the fitting work. Since the communication unit 24 is not necessary in the fitting work, the controller 26 can set the operation state of the communication unit 24 to a "power saving state" instead of a "normal state". Note that the normal state is a state in which the communication unit 24 can operate normally, that is, a state in which the communication unit 24 can communicate. In addition, the power saving state is a state in which less power is consumed than in the normal state. For example, a state in which the power supply to the communication unit 24 is cut off is one aspect of the power saving state. In addition, a state in which the power supply to some circuits of the communication unit 24 is continued and the power supply to the remaining circuits of the communication unit 24 is cut off in order to quickly transition to the normal state is also one aspect of the power saving state.

[0036] As with the communication unit 24, the microphone 21 and pre-processing unit 22 are also defined as operating states into a normal state and a power-saving state. In the normal state, the microphone 21 collects sound and outputs a sound signal. On the other hand, in the power-saving state, the microphone 21 does not collect sound and therefore does not output a sound signal. Also, in the normal state, the pre-processing unit 22 outputs sound data when a sound signal is input. On the other hand, in the power-saving state, the pre-processing unit 22 does not output sound data even if a sound signal is input.

[0037] Furthermore, the determination unit 23 can be configured to define a normal state and a power saving state, similar to the communication unit 24. In the normal state, when sound data is input, the determination unit 23 uses a learning model to determine whether or not an interfering sound has been detected. On the other hand, in the power saving state, the determination unit 23 does not perform a determination using the learning model.

[0038] In this embodiment, the controller 26 controls the interference sound detection device 100 to execute the determination process for determining the interference sound only while the optical sensor 25 detects the wire harness 3, and not to perform the determination process during other periods. For this reason, the controller 26 sets both the microphone 21 and the pre-processing unit 22 to a power-saving state while the optical sensor 25 does not detect the wire harness 3. In other words, the controller 26 controls the interference sound detection device 100 to not collect sound while the optical sensor 25 does not detect the wire harness 3. Therefore, sound data is not input to the determination unit 23, and therefore the determination process is not performed. Note that, instead of setting both the microphone 21 and the pre-processing unit 22 to a power-saving state while the optical sensor 25 does not detect the wire harness 3, it is also possible to configure the interference sound detection device 100 not to collect sound by setting only one of the microphone 21 and the pre-processing unit 22 to a power-saving state and setting the other to a normal state.

[0039] In addition, when the operating state of the determination unit 23 is configured to be configurable, the determination unit 23 can also be set to a power saving state while the optical sensor 25 is not detecting the wire harness 3.

[0040] When the optical sensor 25 detects the wire harness 3, the controller 26 transitions the functional blocks that were set to the power saving state while the optical sensor 25 was not detecting the wire harness 3 to the normal state. In other words, while the optical sensor 25 is detecting the wire harness 3, the controller 26 sets all of the microphone 21, the preprocessing unit 22, and the determination unit 23 to the normal state.

[0041] Therefore, during one determination period from when the interference sound detection device 100 holds the wire harness 3 to when it no longer holds the wire harness 3, the microphone 21 and the pre-processing unit 22 collect sounds and output sound data. Then, the determination unit 23 determines whether or not the sound indicated by the sound data input from the pre-processing unit 22 includes an interference sound, and notifies the controller 26 of the determination result. In other words, the determination unit 23 notifies the controller 26 of the detection result of whether or not an interference sound has been detected during one determination period.

[0042] The controller 26 presents the result of the determination by the determination unit 23 to the worker via the UI 27. A determination result indicating that a fitting sound has been detected indicates that the fitting work was good, and a determination result indicating that a fitting sound has not been detected indicates that the fitting work was not good.

[0043] Furthermore, if no interference sound is detected in the determination process, the controller 26 may be configured to notify the manufacturing system 600 of an error via the communication unit 24. In response to the notification of the error, the manufacturing system 600 may start necessary processing such as stopping the production line. In this case, the controller 26 sets the communication unit 24 to the normal state at least while the determination process is being performed.

[0044] Next, the operation of the fitting sound detection device 100 when the learning mode is set will be described. The only difference from the work mode is that the communication unit 24 transmits sound data to the learning server 400 via the LAN 200 and the Internet 300. Therefore, in the learning mode, the controller 26 sets the communication unit 24 to the normal state while the fitting sound detection device 100 holds the wire harness 3. When the fitting work is performed, the worker individually checks whether the fitting work is good or bad, separately from the judgment result by the learning model, and the result confirmed by the worker via the UI 27 is transmitted to the learning server 400. For example, the worker can check whether the fitting work is good or bad by checking whether the fitting members are locked together by the locking mechanism. The result confirmed by the worker becomes the correct label of the sound data transmitted immediately before. In the learning mode, the judgment result by the judgment unit 23 is not necessary, so in the learning mode, the controller 26 can set the judgment unit 23 to a power saving state.

[0045] As described above, according to this embodiment, the fitting sound detection device 100 has a head 1 for an operator to hold the fitting member 31 of the wire harness 3. When an operator holds the fitting member 31 directly with his / her hand to perform the fitting work, the operator may not be able to hold the fitting member 31 stably due to the size, shape, position of the fitting member 31 in the product, etc., of the fitting member 31, and therefore it may be difficult to perform the fitting work correctly. On the other hand, in the fitting sound detection device 100 according to this embodiment, the operator holds the fitting member 31 via the head 1, so that the fitting member 31 can be held stably, and therefore the workability of the fitting work can be improved compared to when the operator holds the fitting member 31 directly with his / her hand to perform the fitting work.

[0046] Furthermore, in this embodiment, the sound generated during the fitting operation is collected by the microphone 21 provided on the main body 2 of the fitting sound detection device 100. By using the fitting sound detection device 100 of this embodiment, it is possible to collect sounds at a position closer to the fitting member 31 than in the conventional wristwatch-type device, and therefore it is possible to improve the accuracy of the fitting sound determination by the learning model.

[0047] Furthermore, the components of the fitting sound detection device 100 are controlled so that sound is collected while the worker is holding the wire harness 3 with the head 1, that is, while the worker is performing the fitting work, and sound is not collected while the worker is not holding the wire harness 3 with the head 1, that is, while the worker is not performing the fitting work. With this configuration, the power consumption of the fitting sound detection device 100 can be reduced.

[0048] Second Embodiment Next, the second embodiment will be described, focusing on the differences from the first embodiment. In the first embodiment, a configuration was described in which a learning model is generated for each location (factory) or location group in which the interfering sound detection device 100 is used. This is because background noise may differ from factory to factory. In this embodiment, noise information indicating the background noise of the location (factory) in which the interfering sound detection device 100 is used is stored in the database 500. The noise information may be digital data generated by collecting background noise for each location (factory) in which the interfering sound detection device 100 is used or for each location group.

[0049] The controller 26 obtains noise information of the location where the interference sound detection device 100 is used from the database 500 via the communication unit 24, and stores the information in the pre-processing unit 22. The pre-processing unit 22 outputs sound data indicating a sound obtained by subtracting background noise indicated by the noise information from the sound indicated by the sound signal. Therefore, the sound data with the background noise reduced is input to the determination unit 23, and the interference sound can be detected with high accuracy.

[0050] <Third embodiment> Next, the third embodiment will be described, focusing on the differences from the second embodiment. In the second embodiment, the noise information is generated in advance and stored in the database 500. In this embodiment, the interference sound detection device 100 generates and updates the noise information during the interference work.

[0051] The controller 26 starts the determination process when the optical sensor 25 detects the wire harness 3, and stops the determination process when the optical sensor 25 no longer detects the wire harness 3. In this embodiment, when the controller 26 stops the determination process, it starts a measurement process of background noise. The period during which the measurement process is performed may be set in the controller 26 in advance. In this case, the controller 26 ends the measurement process when a predetermined period has elapsed since the start of the measurement process. Alternatively, the measurement process may be performed until the optical sensor 25 detects the wire harness 3. In this case, the controller 26 starts the measurement process when the determination process ends, and performs the measurement process until the start of the next determination process is triggered. The controller 26 sets at least one of the microphone 21 and the pre-processing unit 22 to a power saving state while neither the determination process nor the measurement process is being performed.

[0052] During the measurement process, the controller 26 sets the microphone 21 and the pre-processing unit 22 to a normal state. Then, the pre-processing unit 22 determines background noise based on the sound signal input from the microphone 21 during the measurement process to generate noise information. Alternatively, the pre-processing unit 22 updates the noise information already generated based on the sound signal input from the microphone 21 during the measurement process.

[0053] As described above, by measuring the background noise during the fitting operation, the influence of background noise that may vary depending on the time and date, etc., can be suppressed, and therefore the fitting sound can be determined with high accuracy.

[0054] <Other forms> 1, the learning server 400 and the database 500 are connected to the Internet 300, but the learning server 400 and the database 500 can also be configured to be connected to the LAN 200. In this case, the LAN 200 can also be a closed network within a factory that is not connected to the Internet 300.

[0055] In addition, a configuration can be adopted in which a joint sound detection device used only for joint work, i.e., a joint sound detection device that operates only in the work mode described above, and a joint sound detection device used only for collecting learning data, i.e., a joint sound detection device that operates only in the learning mode described above, are separately provided.

[0056] Furthermore, the above-mentioned intrusive sound detection device 100 has a communication unit 24, and acquires the learning model, noise information, etc. via a network. However, it is also possible to configure the intrusive sound detection device 100 so that the learning model, noise information, etc. are stored in the intrusive sound detection device 100 via a universal serial bus (USB) memory device or the like, and instead omit the communication unit 24. Furthermore, the communication unit 24 may be a wired communication interface such as a USB interface.

[0057] In the above embodiment, the optical sensor 25 detects whether the head 1 holds the mating member 31 of the wire harness 3, but a sensor of a type different from the optical sensor may be used to detect whether the head 1 holds the mating member 31 of the wire harness 3. For example, a flag whose position changes depending on whether the head 1 holds the mating member 31 of the wire harness 3 can be provided in the head 1, and a mechanical sensor can be used to detect whether the head 1 holds the mating member 31 of the wire harness 3 based on the position of the flag. Furthermore, an ultrasonic sensor or the like having a frequency that does not interfere with sounds in the place of use may be used to detect whether the head 1 holds the mating member 31 of the wire harness 3.

[0058] The above configuration improves the workability of the joining work and enables accurate detection of joining sounds. This makes it possible to contribute to Goal 9 of the United Nations' Sustainable Development Goals (SDGs), which states, "Build resilient infrastructure, promote sustainable industrialization and foster innovation."

[0059] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention. [Explanation of symbols]

[0060] 21: microphone, 1: head, 25: optical sensor, 26: controller

Claims

1. A microphone and A holding member for holding a mating member provided at an end of the wire harness; a sensor that detects the wire harness in which the mating member is held by the holding member; A controller controls execution of a determination process for determining whether or not the sound collected by the microphone includes an interference sound caused by the interference member, based on sound data based on the sound collected by the microphone; Equipped with The controller executes the determination process while the sensor detects the wire harness, and does not execute the determination process while the sensor does not detect the wire harness.

2. The interference noise detection device according to claim 1 , wherein the controller does not execute the determination process by not collecting sound with the microphone while the sensor is not detecting the wire harness.

3. The interference noise detection device according to claim 1 , wherein the holding member is configured to be detachable from a housing that houses the microphone, the sensor, and the controller.

4. The mating noise detection device according to claim 3 , wherein the sensor detects the wire harness by emitting light through a hole provided in the holding member.

5. The interference sound detection device according to claim 1, further comprising a pre-processing unit that stores noise information indicating background noise, and outputs the sound data indicating a sound obtained by subtracting the background noise from the sound collected by the microphone based on the sound collected by the microphone and the noise information.

6. The interference sound detection device according to claim 5, wherein the controller controls an operating state of at least one of the microphone and the pre-processing unit so that power consumption of at least one of the microphone and the pre-processing unit when the determination process is not being performed is smaller than power consumption when the determination process is being performed.

7. The interference noise detection device according to claim 5, wherein the controller, in response to the sensor no longer detecting the wire harness, starts a measurement process for measuring the background noise based on the sound collected by the microphone and generating or updating the noise information.

8. The interference sound detection device according to claim 7, wherein the controller controls the operating state of at least one of the microphone and the pre-processing unit so that the power consumption of at least one of the microphone and the pre-processing unit when neither the determination process nor the measurement process is being performed is smaller than the power consumption when the determination process is being performed.

9. The incoherent sound detection device according to any one of claims 1 to 8, further comprising a judgment means for using a learning model to judge whether or not the incoherent sound is included in the sound represented by the sound data from the start of the judgment process to the end of the judgment process.

10. The apparatus for detecting intermittent sounds according to claim 9 , further comprising a communication means for communicating with a server device storing one or more learning models to acquire the learning models.

11. The apparatus of claim 9 , wherein the learning model is associated with a location where the apparatus is used.

12. The interference noise detection device according to claim 9 , wherein the learning model is associated with a type of the interference member.

13. 9. The interference noise detection device according to claim 1, further comprising a communication means for transmitting the sound data while the sensor is detecting the wire harness to a network when operating in a first mode, and not transmitting the sound data while the sensor is detecting the wire harness to the network when operating in a second mode.

14. The incoherent sound detection device according to any one of claims 1 to 8, further comprising a communication means for wirelessly notifying a specified device of an error when the determination process determines that the incoherent sound is not included in the sound collected by the microphone.

Images