Judgment device, fastening device, and judgment system

Abstract

To provide a determination device that determines the completion of fastening of a fastener.SOLUTION: A determination device, which determines an operation of a fastening tool for fastening a fastener, comprises a sound detection part for converting a detected sound to an electric signal, and a determination part for determining whether or not fastening of the fastener is completed, on the basis of the electric signal. The determination device can also comprise an operation control part for stopping the operation of the fastening tool, when the determination part determines that the fastening is completed.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a determination device, a fastening device, and a determination system. [Background technology]

[0002] 2. Description of the Related Art Power tools such as impact drivers are known in the art (see, for example, Patent Document 1). Patent Document 1: JP 2021-7999 A Summary of the Invention [Problem to be solved by the invention]

[0003] In a power tool, it is preferable to be able to detect whether or not a task has been completed. [Means for solving the problem]

[0004] In order to solve the above problems, a first aspect of the present invention provides a determination device for determining the operation of a fastening tool for fastening a fastener. The determination device may include a sound detection unit that converts a detected sound into an electrical signal. The determination device may include a determination unit that determines whether or not the fastener has been fastened based on the electrical signal.

[0005] In a second aspect of the present invention, there is provided a fastening device including the determination device according to the first aspect and a fastening tool.

[0006] In a third aspect of the present invention, a judgment system is provided that includes a judgment device relating to the first aspect, a dialogue module that dialogues with a user of the fastening tool, and a dialogue memory unit that stores the judgment result in the judgment unit and the dialogue data of the dialogue module in correspondence with each other.

[0007] The above summary of the invention does not list all of the necessary features of the present invention. Also, subcombinations of these features may also be inventions. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram illustrating an example of a fastening device 200 according to an embodiment of the present invention. [Diagram 2] 2A to 2C are diagrams illustrating an example of a fastener fastened by the fastening device 200. [Diagram 3] FIG. 2 is a diagram illustrating an example of the configuration of a determination device 220. [Figure 4] FIG. 3 is a diagram illustrating a decision model learning device 310 that generates a decision model. [Diagram 5] 13 is a flowchart showing an example of the operation of the determination device 220. [Figure 6] FIG. 13 is a diagram showing an example of a waveform of an electrical signal of a fastening sound. [Figure 7] 13 is a diagram showing an example of a determination model stored in a determination model storage unit 260. FIG. [Figure 8] 13 is a diagram showing another example of a determination model stored in the determination model storage unit 260. FIG. [Figure 9] FIG. 2 is a diagram illustrating an example of the configuration of a determination system 232. [Figure 10] FIG. 13 is a diagram illustrating another exemplary configuration of the determination device 220. [Figure 11] FIG. 13 is a diagram illustrating another exemplary configuration of the determination device 220. [Figure 12] FIG. 2 is a diagram showing another example of the configuration of the recording device 100. [Figure 13] 2 is a circuit diagram showing an example of the configuration of a high-pass filter 110. FIG. [Figure 14] 2 is a diagram showing an example of the frequency spectrum of an analog signal and the frequency characteristics of a high-pass filter 110. FIG. [Figure 15] FIG. 2 is a diagram illustrating an example of a frequency spectrum of vibration noise contained in an analog signal. [Figure 16] 2 is a diagram showing an example of a time waveform of an analog signal input to a high-pass filter 110. FIG. [Figure 17] 2 is a diagram showing an example of a time waveform of an analog signal output by a high-pass filter 110. FIG. [Figure 18]11 is a diagram showing an example of digital noise superimposed by the signal processing unit 130. FIG. [Figure 19] FIG. 2 is a diagram showing an example of a time waveform of a digital signal on which digital noise is superimposed. [Figure 20] 2 is a diagram showing an example of a circuit board 360 on which the circuit of the determination device 220 is mounted. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0010] 1 is a schematic diagram showing an example of a fastening device 200 according to an embodiment of the present invention. The fastening device 200 fastens a fastener such as a screw or a bolt. The fastening device 200 includes a fastening tool 210 and a determination device 220. The fastening tool 210 is, for example, an impact driver, but is not limited to this. The fastening tool 210 rotates the fastener by energy such as electric power, and fastens the fastener.

[0011] The fastening tool 210 of this example includes a housing 211, a connection portion 212, an operation portion 213, a grip portion 214, and a base portion 215. The housing 211 houses each component of the fastening tool 210. The housing 211 houses components such as a motor.

[0012] The connection part 212 is provided on the housing 211 and is directly or indirectly connected to the fastener. An adapter that can be replaced depending on the type of fastener may be connected to the connection part 212. The connection part 212 rotates the fastener by power generated by a motor or the like.

[0013] The operation unit 213 is operated by a user of the fastening device 200. In response to an operation on the operation unit 213, components such as a motor inside the housing 211 operate to fasten the fastener. The operation unit 213 may be a trigger that can be pressed.

[0014] The gripping portion 214 is a portion to be gripped by a user during a fastening operation. The determination device 220 is fixed to the base portion 215. The base portion 215 may have a terminal capable of inputting and outputting an electric signal between the base portion 215 and the determination device 220. The base portion 215 in this example is provided at the tip of the gripping portion 214.

[0015] The determination device 220 may have a case fixed to the base portion 215. A circuit electrically connected to the fastening tool 210 is housed in the case. A power source that supplies power to the fastening tool 210 may be provided in the case.

[0016] The determination device 220 determines the operation of the fastening tool 210. The determination device 220 determines whether or not the fastening of the fastener is completed based on a sound detected during the fastening operation of the fastening tool 210. The determination device 220 may control the operation of the fastening tool 210 based on the determination result. For example, when it is determined that the fastening of the fastener is completed, the determination device 220 may stop the fastening operation by the fastening tool 210. The determination device 220 may control a motor that rotates the fastener.

[0017] FIG. 2 is a diagram for explaining an example of a fastener fastened by the fastening device 200. The fastener may be used to fasten members constituting a building 300 together. The building 300 includes, for example, a foundation 305, a column 301, and a beam 302. The foundation 305 is a member fixed to the ground. The foundation 305 may be made of concrete. The pillar 301 has one end fixed to the ground or the foundation 305. The pillar 301 may have a fixing part 303 fixed to the ground or the foundation 305. The beam 302 is a member having both ends fixed to something other than the ground or the foundation 305. The ends of the beam 302 may be fixed to the pillar 301 or another beam 302. And the beam 302 may be made of iron. The pillar 301 and the beam 302 may be made of wood, or may be made of other materials.

[0018] The respective members are fixed to each other by fasteners 304. The fasteners 304 may be members that are fastened by rotating, such as bolts. The fasteners 304 are used in a plurality of places in the building 300.

[0019] 3 is a diagram showing an example of the configuration of the determination device 220. The determination device 220 includes the recording device 100 and a determination section 240. The determination device 220 may further include at least one of an operation control section 250 and a determination model storage section 260.

[0020] The sound recording device 100 includes a sound detection unit 10 and records the detected sound. The sound detection unit 10 converts the detected sound into an analog electrical signal (sometimes simply referred to as an analog signal) and outputs it. The sound detection unit 10 detects sound pressure, for example, like a microphone, and outputs an analog signal corresponding to the sound pressure waveform.

[0021] The sound recording device 100 preferably records sounds during the fastening operation of the fastening tool 210. The sound recording device 100 may switch whether to record the detected sound depending on whether the operation unit 213 is operated. The sound recording device 100 may record sounds from when the fastening tool 210 starts the fastening operation to when it ends the fastening operation. The sound detection unit 10 may also switch whether to detect a sound depending on the operation of the operation unit 213.

[0022] The determination unit 240 determines whether or not the fastening of the fastener 304 is completed based on the electrical signal output by the sound detection unit 10 and recorded by the recording device 100. The determination unit 240 may determine whether or not the fastening of the fastener 304 is completed using a determination model created in advance. The determination model may be a model created by machine learning, or may be a model in which a determination criterion and a determination algorithm are created by a designer or the like. The determination device 220 of this example has a determination model storage unit 260 that stores one or more determination models.

[0023] The fastening sound generated from the fastener 304 and the fastening tool 210 changes between a state in which the fastening of the fastener 304 is not complete and the fastener 304 is rotating with a small torque and a state in which the fastening of the fastener 304 is complete and the fastener 304 does not rotate even when a large torque is applied to the fastener 304. In this example, it is determined whether or not the fastening of the fastener 304 is complete based on the fastening sound generated from the fastener 304 and the fastening tool 210. This makes it possible to determine the fastening state of the fastener 304 with a simple configuration.

[0024] When the fastening operation of the fastening tool 210 is completed by the operation unit 213 even though the fastening of the fastener 304 is not completed, the determination device 220 may notify the user of the fastening tool 210 of that fact. Furthermore, the determination device 220 may record identification information of the fastener 304 whose fastening is not completed. The identification information of the fastener 304 includes information indicating the position where the fastener 304 is provided within the building 300, for example.

[0025] When the determination unit 240 determines that the fastening is completed, the operation control unit 250 stops the operation of the fastening tool 210. When the determination unit 240 determines that the fastening is completed, the operation control unit 250 stops the fastening operation of the fastening tool 210 regardless of the operation state of the operation unit 213. This allows the fastener 304 to be fastened efficiently.

[0026] 4 is a diagram illustrating a determination model learning device 310 that generates a determination model. The determination model learning device 310 includes a calculation device. The determination model learning device 310 may be included in the determination device 220, or may be a computer provided outside the determination device 220.

[0027] A plurality of pieces of teacher data are input to the judgment model learning device 310, and a judgment model is generated based on the teacher data. A combination of tightening sound data and torque data is input to the judgment model learning device 310 of this example as the teacher data.

[0028] The fastening sound data is data of the fastening sound when the fastening tool 304 is fastened. The fastening sound data may be waveform data of the fastening sound, or may be feature data extracted from the waveform of the fastening sound. The feature may include, for example, the amplitude of the peak, the interval between the peaks, the width of the peak, etc. The torque data is data measuring the tightening torque of the fastener 304 after tightening. The tightening torque may be the torque required to start rotating the fastener 304 in the direction opposite to the tightening direction. The torque data may be data indicating whether the tightening torque is equal to or greater than a certain level.

[0029] The judgment model learning device 310 generates a judgment model that estimates the tightening torque from the fastening sound data based on the teacher data. The judgment model in this example estimates the value of the tightening torque of the fastener 304 from feature amount data of the electrical signal of the tightening sound. For example, the judgment model learning device 310 generates the judgment model by a random forest regression method, but the machine learning method is not limited to this.

[0030] 5 is a flowchart showing an example of the operation of the determination device 220. First, the sound detection unit 10 acquires a fastening sound (S501). The recording device 100 extracts a predetermined frequency component from the electrical signal output by the sound detection unit 10 (S502). The recording device 100 may extract a component of the electrical signal in a frequency band of, for example, 20 kHz or higher.

[0031] The cutoff frequency in the filtering step S502 may be a frequency that can remove human voice. The cutoff frequency is, for example, a frequency of 4 kHz or more. The main component of human voice is approximately 2 kHz or less. By setting the cutoff frequency to a frequency of 4 kHz or more, most of the human voice can be removed. Therefore, it is possible to record sound data from which personal information and confidential information that may be contained in the voice has been removed. In addition, the cutoff frequency is, for example, a frequency of 20 kHz or less. This makes it possible to record the fastening sound generated when the fastening device 200 operates. The fastening sound is, for example, the sound of metal parts such as screws and bolts rubbing or hitting each other. The cutoff frequency may be changeable within a range of 4 kHz or more and 20 kHz or less.

[0032] Next, the recording device 100 converts the analog electrical signal into a digital signal (S503). Next, the determination unit 240 extracts features of the digital signal waveform (S504). Next, the determination unit 240 determines the state of the fastener 304 using the extracted features and a predetermined determination model (S505). In this example, the determination unit 240 determines whether or not the fastening of the fastener 304 has been completed based on the components of the digital signal in a frequency band of 20 kHz or more.

[0033] If it is determined in the determination step S505 that the fastening is completed (Y), the operation control unit 506 outputs a stop signal to the fastening tool 210 to stop the fastening operation (S506). This completes the fastening operation of the fastening tool 210. If it is determined in the determination step S505 that the fastening is not completed (N), the processing from S501 may be repeated. If the fastening operation has already been completed by operating the operation unit 213 despite the fastening not being completed, the determination unit 240 may notify the user that the fastening of this fastener 304 is not completed, or may store this in memory. In this case as well, the determination device 220 ends the processing.

[0034] FIG. 6 is a diagram showing an example of a waveform of an electric signal of a fastening sound. The fastening tool 210 of this example is an impact driver that generates a continuous impact sound when fastening the fastener 304. The electric signal waveform has a plurality of peaks 601 corresponding to the impact sound. The determination unit 240 may extract at least one of the amplitude M, width W, and interval T between the peaks 601 as a feature. The determination unit 240 may also use the power of a predetermined band in the frequency spectrum of the electric signal as a feature. The determination unit 240 may use the power of a plurality of bands as a feature. For example, the determination unit 240 may use the power of the entire band of a predetermined band (e.g., 0 kHz-48 kHz) and the power of a plurality of partial bands (e.g., 20 kHz-34 kHz, 34 kHz-48 kHz) as a feature.

[0035] Furthermore, the determination unit 240 may apply a predetermined window function to the digital signal to generate a frequency spectrum by FFT. The time width of the window indicated by the window function is a period including at least one impact sound. The time width of the window may include multiple peaks 601. The start point t1 of the window may be immediately after the peak 601 or may be a point having a predetermined time interval with respect to the peak 601. Although the window in FIG. 6 is rectangular, windows of other shapes may be used.

[0036] FIG. 7 is a diagram showing an example of a judgment model stored in the judgment model storage unit 260. The judgment model storage unit 260 in this example stores a different judgment model for each type of fastening object. A fastening object is a member fastened by a fastener 304, or a combination of members fastened. For example, in the example of FIG. 2, the fastening objects include a column 301, a beam 302, a foundation 305, and a combination of these. The fastening object may be different for each position of each member. For example, the column base, which is the leg of the column 301 (fixing part 303 in FIG. 2), and the column head, which is the head of the column 301, may be treated as different fastening objects. Even if the use of the members is the same, if the materials of the members are different, they may be treated as different fastening objects.

[0037] The fastening sound generated during the fastening operation may differ depending on the type of fastening object. Therefore, the determination unit 240 can more accurately determine whether the fastening of the fastener 304 is complete by determining whether the fastening of the fastener 304 is complete using a different determination model for each type of fastening object. The determination model storage unit 260 may further store a general-purpose determination model to be used when the type of the fastening object cannot be determined.

[0038] The judgment model storage unit 260 may store a different judgment model for each type of fastener 304. When at least one of the shape, size, and material of the fastener 304 is different, the type of the fastener 304 may be different.

[0039] The type of the fastening object and the type of the fastener 304 may be instructed by the user to the determination device 220. The user may input the instruction by voice, or may input the instruction by other methods such as a selection button. The determination model learning device 310 may generate a determination model for each type of the fastening object and each type of the fastener 304.

[0040] 8 is a diagram showing another example of a judgment model stored in the judgment model storage unit 260. The judgment model storage unit 260 of this example stores a different judgment model for each type of fastening tool 210. Fastening tools 210 that produce different fastening sounds during operation may be treated as different types of fastening tools 210. In addition, at least one of the manufacturer of the fastening tool 210 and the product name of the fastening tool 210 may be used as the type of the fastening tool 210. The judgment model storage unit 260 may further store a general-purpose judgment model to be used when the type of the fastening tool 210 cannot be determined. The judgment model learning device 310 may generate a judgment model for each type of fastening tool 210.

[0041] The type of the fastening tool 210 may be detected by the determination device 220. When the fastening tool 210 is connected, the determination device 220 may receive a signal indicating the type of the fastening tool 210. The fastening sound generated during the fastening operation may differ depending on the type of the fastening tool 210. Therefore, the determination unit 240 can more accurately determine whether the fastening of the fastener 304 has been completed by determining whether the fastening of the fastener 304 has been completed using a determination model that differs depending on the type of the fastening tool 210.

[0042] Fig. 9 is a diagram showing a configuration example of the determination system 232. The determination system 232 further includes a dialogue module 350 in addition to the determination device 220 described in Fig. 1 to Fig. 8. The dialogue module 350 is provided outside the case of the determination device 220. The dialogue module 350 is a device carried by a user of the fastening tool 210. The dialogue module 350 may be software incorporated in a communication device such as a telephone carried by the user.

[0043] The dialogue module 350 inputs and outputs information in a dialogue format with a user of the fastening tool 210. The dialogue module 350 may output preset questions and answers in voice in accordance with the user's voice.

[0044] The dialogue module 350 of this example detects the voice of the user indicating the fastening target of the fastener 304. The dialogue module 350 may output a question to the user inquiring about the fastening target of the fastener 304.

[0045] The dialogue module 350 notifies the determination unit 240 of information indicating the fastening target of the fastener 304. The dialogue module 350 may transmit the information to the determination unit 240 by short-range wireless communication. The determination unit 240 may select a determination model based on the information.

[0046] Fig. 10 is a diagram showing another example of the configuration of the determination device 220. The determination device 220 of this example includes a location storage unit 270 in addition to any of the configurations described in Fig. 1 to Fig. 9. The other configurations are similar to the configurations described in Fig. 1 to Fig. 9. Furthermore, the determination device 220 may be capable of communicating with a dialogue module 350.

[0047] The location storage unit 270 stores information about the location of the fastener 304 in the building 300 for which the determination unit 240 has determined that the fastening has been completed. All fasteners 304 included in the building 300 may be registered in advance in the location storage unit 270. The location storage unit 270 stores information about whether or not the fastening has been completed for each fastener 304. The location storage unit 270 may update the state of each fastener 304 according to the determination result of the determination unit 240. The location storage unit 270 may store, for each location of the building 300, the number of fasteners 304 to be fastened and the number of fasteners 304 that have been fastened.

[0048] The determination unit 240 may determine which fastener 304 the fastening sound detected by the sound detection unit 10 is the fastening sound of, based on information from the dialogue module 350. The dialogue module 350 may receive a voice from the user of the fastening tool 210 indicating which fastener 304 is to be fastened. The voice may include, for example, identification information of the fastener 304, or may include identification information of a member to be fastened by the fastener 304. The dialogue module 350 may output a question to the user inquiring about the identification information of the fastener 304 or the member.

[0049] The determination unit 240 may present information indicating the fasteners 304 that have not yet been fully fastened to a user of the fastening tool 210 based on the information stored in the location memory unit 270. The determination unit 240 may present the information via the dialogue module 350, or may present the information by another method. For example, the determination unit 240 may cause the information to be displayed on a display device carried by the user.

[0050] The location storage unit 270 may function as a dialogue storage unit that associates and stores the determination result by the determination unit 240 with the dialogue data of the dialogue module 350. The location storage unit 270 may extract and store information indicating which fastener 304 is to be fastened from the dialogue data.

[0051] Fig. 11 is a diagram showing another example of the configuration of the determination device 220. The determination device 220 of this example includes a posture detection unit 280 in addition to any of the configurations described in Fig. 1 to Fig. 10. The other configurations are similar to the configurations described in Fig. 1 to Fig. 10. Furthermore, the determination device 220 may be capable of communicating with a dialogue module 350.

[0052] The attitude detection unit 280 detects the attitude of the fastening tool 210 when fastening the fastener 304. The attitude of the fastening tool 210 may be three-dimensional information indicating in which direction the connection portion 212 is facing.

[0053] The determination unit 240 may determine whether or not the fastening is completed based on the posture of the fastening tool 210 when fastening the fastener 304. The determination unit 240 may select a determination model to be used based on the posture, and may correct the feature amount.

[0054] The determination unit 240 may estimate a fastening target of the fastener 304 based on the posture of the fastening tool 210. For example, when the connection portion 212 faces downward, the determination unit 240 may determine that the fixing portion 303 is fastened to the foundation 305. The determination unit 240 may select a determination model based on the estimated fastening target.

[0055] Furthermore, the fastening sound generated from the fastening tool 210 or the fastener 304 may change depending on the posture of the fastening tool 210. For example, the weight of the fastening tool 210 applied to the fastener 304 changes between when the fastening tool 210 is connected upward from below the fastener 304 and when the fastening tool 210 is connected downward from above the fastener 304. Therefore, the fastening sound may also change. The determination unit 240 may select a determination model based on the posture of the fastening tool 210 and may correct the feature amount. How the feature amount should be corrected may be determined in advance based on the difference in the feature amount of the fastening sound measured for each posture of the fastening tool 210.

[0056] Fig. 12 is a diagram showing another example of the configuration of the sound recording device 100. In addition to the configuration of the sound recording device 100 described in Fig. 1 to Fig. 11, the sound recording device 100 of this example includes a high-pass filter 110, an AD conversion unit 120, a signal processing unit 130, a control unit 140, a communication unit 150, and a storage medium 20. The storage medium 20 may be a device provided outside the determination device 220. The storage medium 20 may be a memory provided exclusively for sound data, or may be a memory that also stores other data.

[0057] The high-pass filter 110 attenuates components below a predetermined cutoff frequency for the analog signal output by the sound detection unit 10 and outputs the signal. The cutoff frequency may be a frequency that can remove human voice. The cutoff frequency is, for example, 4 kHz or higher. Human voice is generally 1 kHz to 4 kHz. By setting the cutoff frequency to a frequency of 4 kHz or higher, most of the human voice can be removed. Therefore, sound data from which personal information and confidential information that may be included in the voice has been removed can be recorded. In addition, the cutoff frequency is a frequency of 20 kHz or lower. This makes it possible to record the fastening sound generated when the fastening tool 210 operates. The fastening sound is, for example, the sound of metal parts such as screws and bolts rubbing or hitting each other. The cutoff frequency may be changeable within a range of 4 kHz or higher and 20 kHz or lower.

[0058] The AD conversion unit 120 converts the analog signal output by the high-pass filter 110 into a digital signal with a predetermined number of bits. The AD conversion unit 120 samples the analog signal at a predetermined cycle and outputs a time-series digital signal. In this example, the high-pass filter 110 is disposed before the AD conversion unit 120. This makes it possible to reduce the amplitude of the analog signal input to the AD conversion unit 120. This makes it possible to allocate the range of digital values ​​in the digital signal to a relatively small amplitude, thereby improving the amplitude resolution of the digital signal. This makes it possible to record the target signal with high accuracy.

[0059] The signal processing unit 130 performs a predetermined process on the digital signal output by the AD conversion unit 120. The signal processing unit 130 may perform a predetermined calculation on the digital signal and perform digital filter processing, for example. The signal processing unit 130 may reduce frequency components of the digital signal that are equal to or lower than the cutoff frequency of the high-pass filter 110. This makes it possible to more reliably remove human voices.

[0060] The signal processing unit 130 may output the digital signal that has been subjected to the predetermined processing to the determination unit 240. The signal processing unit 130 may store the digital signal that has been subjected to the predetermined processing in the storage medium 20. In addition, the signal processing unit 130 may transmit the digital signal that has been subjected to the predetermined processing to the outside of the determination device 220 via the communication unit 150.

[0061] The control unit 140 controls the operation of the signal processing unit 130. The control unit 140 may adjust a cutoff frequency in the digital filter processing of the signal processing unit 130. The control unit 140 may control the signal processing unit 130 to store a digital signal in the storage medium 20, or to transmit the digital signal to the outside. The control unit 140 may control the operation of the signal processing unit 130 in response to an instruction input by a user or the like.

[0062] The communication unit 150 transmits a signal specified by the signal processing unit 130 to the outside. The communication unit 150 may transmit a digital signal processed by the signal processing unit 130 to the outside. The communication unit 150 may transmit the digital signal to an external server. The server may analyze sound information contained in the digital signal. The server may function as the determination model learning device 310 described in FIG. 4. According to this example, the digital signal transmitted to the outside by the communication unit 150 contains almost no human voice information. This makes it possible to prevent leakage of personal information or confidential information.

[0063] The characteristics of the high-pass filter 110, such as the order and the cutoff frequency, may be variable. The control unit 140 may control the characteristics of the high-pass filter 110.

[0064] For example, the control unit 140 may control the cutoff frequency of the high-pass filter 110 according to the amplitude of the analog signal output by the sound detection unit 10. The control unit 140 may control the cutoff frequency to be higher as the amplitude of the analog signal is larger. The control unit 140 may control the order of the high-pass filter 110 to be higher as the amplitude of the analog signal is larger. This increases the components removed from the analog signal, so that the amplitude of the analog signal input to the AD conversion unit 120 can be suppressed. The control unit 140 may control the cutoff frequency or the order of the high-pass filter 110 according to the digital signal output by the AD conversion unit 120. When the value of the digital signal is saturated (i.e., the digital signal has reached a maximum value), the control unit 140 may set the cutoff frequency of the high-pass filter 110 to a higher value or set the order to a higher order. This makes it possible to suppress the value of the digital signal from being saturated.

[0065] 13 is a circuit diagram showing an example of the configuration of high-pass filter 110. High-pass filter 110 of this example includes input unit 11, first capacitor 111, second capacitor 112, coil 113, resistor 114, and output unit 121. Input unit 11 is a terminal to which an analog signal is input from sound detection unit 10. Output unit 121 is a terminal that outputs an analog signal to AD conversion unit 120.

[0066] The first capacitor 111 and the second capacitor 112 are provided in series between the input section 11 and the output section 121. The coil 113 is provided between a connection node between the second capacitor 112 and the output section 121 and a reference potential. The reference potential is, for example, a ground potential. The resistor 114 is provided between a connection node between the second capacitor 112 and the output section 121 and the reference potential. The coil 113 and the resistor 114 are provided in parallel with each other. With this configuration, the high-pass filter 110 passes high-frequency components to the output section 121 and outputs low-frequency components to the reference potential via the coil 113 and the resistor 114.

[0067] High-pass filter 110 may include at least one of switch 115, switch 116, switch 117, and switch 118. Switch 115 is provided in parallel with first capacitor 111, and switches between connecting and not connecting both ends of first capacitor 111. In other words, switch 115 switches between passing an analog signal transmitted from input unit 11 to first capacitor 111 or bypassing it to switch 115.

[0068] The switch 116 is provided in parallel with the second capacitor 112, and switches between connecting and disconnecting both ends of the second capacitor 112. In other words, the switch 116 switches between passing the analog signal transmitted from the input unit 11 to the second capacitor 112 or diverting the signal to the switch 116.

[0069] Switch 117 is provided in series with coil 113, and switches whether or not the component of the analog signal transmitted from input unit 11 is output to the reference potential via coil 113. Switch 118 is provided in series with resistor 114, and switches whether or not the component of the analog signal transmitted from input unit 11 is output to the reference potential via resistor 114.

[0070] The control unit 140 may control each switch. By controlling each switch, the order and cutoff frequency of the high-pass filter 110 can be adjusted. The high-pass filter 110 in the example of Fig. 13 includes two sets of combinations of a capacitor and a switch in series. In another example, the high-pass filter 110 may include three or more sets of combinations of a capacitor and a switch in series.

[0071] The capacitance of the first capacitor 111 is C1 [F], the capacitance of the second capacitor 112 is C2 [F], the capacitance of the coil 113 is L [H], and the resistance value of the resistor 114 is R [Ω]. The on-resistance of each switch and the parasitic components in the wiring and the like are assumed to be negligibly small.

[0072] When the switches 115 and 116 are on and the switches 117 and 118 are off, the high-pass filter 110 is in bypass mode, and the transfer function from the input port 11 to the output port 121 is 1. Therefore, the frequency characteristics of the analog signal do not change.

[0073] When switch 115 is off, switch 116 is on, switch 117 is off, and switch 118 is on, high-pass filter 110 functions as a first-order filter, and the cutoff frequency fc is expressed by the following formula. fc=1 / (2π×(C1×R))

[0074] When switch 115 is off, switch 116 is on, switch 117 is on, and switch 118 is off, high-pass filter 110 functions as a secondary filter, and the cutoff frequency fc is expressed by the following equation. fc=1 / (2π×(C1×L) 0.5 )

[0075] When switch 115 is on, switch 116 is off, switch 117 is off, and switch 118 is on, high-pass filter 110 functions as a first-order filter, and the cutoff frequency fc is expressed by the following formula. fc=1 / (2π×(C2×R))

[0076] When switch 115 is on, switch 116 is off, switch 117 is on, and switch 118 is off, high-pass filter 110 functions as a secondary filter, and the cutoff frequency fc is expressed by the following equation. fc=1 / (2π×(C2×L) 0.5 )

[0077] When switch 115 is off, switch 116 is off, switch 117 is off, and switch 118 is on, high-pass filter 110 functions as a first-order filter, and the cutoff frequency fc is expressed by the following formula: where the series combined capacitance of C1 and C2 is C3. fc=1 / (2π×(C3×R))

[0078] When switch 115 is off, switch 116 is off, switch 117 is on, and switch 118 is off, high-pass filter 110 functions as a secondary filter, and the cutoff frequency fc is expressed by the following formula. fc=1 / (2π×(C3×L) 0.5 )

[0079] In this way, by controlling each switch, it is possible to control the order and the cutoff frequency of the high-pass filter 110. In this example, the high-pass filter 110 is a single-ended circuit, but the high-pass filter 110 may be a fully differential circuit. The specific circuit of the high-pass filter 110 is not limited to this example.

[0080] 13, it is preferable that the high-pass filter 110 is composed of passive elements and does not include active elements such as an amplifier. By configuring the high-pass filter 110 with only passive elements, it is possible to prevent the amplitude of the analog signal output by the high-pass filter 110 from being amplified. As a result, it is possible to suppress the amplitude of the analog signal input to the AD conversion unit 120.

[0081] Fig. 14 is a diagram showing an example of the frequency spectrum of an analog signal and the frequency characteristics of high-pass filter 110. In Fig. 14, the horizontal axis indicates frequency, and the vertical axis indicates spectrum intensity. High-pass filter 110 in this example functions as a secondary filter. The cutoff frequency of high-pass filter 110 is denoted as fc. Cutoff frequency fc is the frequency at which the gain is -6 dB.

[0082] The analog signal in this example includes frequency components of a target signal to be recorded and frequency components of speech noise. The target signal in this example is a fastening sound generated by the fastening tool 210 or the fastener 304. The peak frequency of the spectrum of the target signal in this example is greater than 20 kHz. The speech noise is noise caused by human voice. The spectrum of the speech noise is mainly distributed in the band of 1 kHz to 4 kHz. The peak frequency of the spectrum of the speech noise is less than 4 kHz.

[0083] The cutoff frequency fc is preferably higher than the peak frequency of the spectrum of the speech noise. The cutoff frequency fc is 4 kHz or higher. The cutoff frequency fc may be higher than the upper end frequency of the spectrum of the speech noise. For example, the cutoff frequency fc may be 10 kHz or higher. However, the cutoff frequency fc is preferably lower than the peak frequency of the target signal. For example, the cutoff frequency fc is 20 kHz or lower. The peak frequency of the target signal is f1, and the peak frequency of the dialogue noise is f2. The cutoff frequency fc may be set to an intermediate frequency between the peak frequency f1 and the peak frequency f2, may be set within a range of the intermediate frequency ±5 kHz, may be set within a range of the intermediate frequency ±3 kHz, or may be set within a range of the intermediate frequency ±1 kHz. This makes it easier to both leave the components of the target signal and remove the components of the speech noise. The control unit 140 may set the cutoff frequency fc of the high-pass filter 110 based on the peak frequency of the noise components, such as the speech noise, included in the analog signal and the peak frequency of the target signal. The control section 140 may input an analog signal to the AD conversion section 120 with the high-pass filter 110 set to the bypass mode, and cause the signal processing section 130 to analyze the frequency spectrum.

[0084] The speech noise includes the conversation of the user, etc. The conversation of the user may include personal information of the user or others, and confidential business information. According to the recording device 100 of this example, it is possible to record a signal from which the speech noise including such personal information and confidential information has been removed.

[0085] Fig. 15 is a diagram showing an example of a frequency spectrum of vibration noise contained in an analog signal. In addition to the vibration noise component, the analog signal may contain the speech noise component and the target signal component shown in Fig. 14. The speech noise component is omitted in Fig. 15.

[0086] Vibration noise is a sound generated by, for example, vibration of a tool. The spectrum of vibration noise is mainly distributed between 1 kHz and 3 kHz. By setting the cutoff frequency fc of the high-pass filter 110 to 4 kHz or more, the vibration noise component can also be removed.

[0087] 16 is a diagram showing an example of a time waveform of an analog signal input to the high-pass filter 110. The analog signal contains a target signal component and a noise component such as speech noise. The signal amplitude is the sum of these components, so the signal amplitude is large.

[0088] 17 is a diagram showing an example of a time waveform of an analog signal output by the high-pass filter 110. Noise components such as speech noise have been removed from the analog signal. As a result, the target signal components are observed periodically and the overall amplitude is reduced. The analog signal is input to the AD conversion unit 120, so that each bit of the AD conversion unit 120 can be efficiently used to improve the resolution in the amplitude direction.

[0089] The signal processing unit 130 performs a predetermined process on the digital signal output by the AD conversion unit 120. The signal processing unit 130 may perform digital filter processing on the digital signal. The digital filter may have a characteristic that the gain changes linearly from a minimum value to a maximum value in a transition region between the pass band and the stop band. The boundary frequency fb of the digital filter may be equal to the cutoff frequency fc of the high-pass filter 110, or may be smaller or larger than the cutoff frequency fc.

[0090] As an example, the transfer function gA(f) of the high-pass filter 110 is expressed by the following equation. gA(f)=f 2 ×(1+(2π×(f / fc)) 2 ) The transfer function gD(f) of the digital filter is expressed by the following formula: The band of the transient region is fb1 to fb2. f <fb1において、 gD(f)=1 / A where A is a constant that is set. For f ≥ fb2, gd(f)=(1+(2π×(f / fc)) 2 ) / f 2

[0091] Furthermore, the signal processing unit 130 may superimpose digital noise on the digital signal output by the AD conversion unit 120. It is preferable that the signal processing unit 130 superimposes the digital noise on at least a part of the frequency band of the speech noise component so that the speech noise component cannot be analyzed.

[0092] Fig. 18 is a diagram showing an example of digital noise superimposed by the signal processing unit 130. Fig. 18 shows the frequency spectrum of the digital signal superimposed with digital noise and the frequency characteristics of the high-pass filter 110. The digital signal includes a digital noise component and a target signal component.

[0093] The signal processing unit 130 superimposes digital noise on at least a part of a frequency band equal to or lower than the cutoff frequency fc of the high-pass filter 110. The signal processing unit 130 may superimpose digital noise on the entire frequency band equal to or lower than the cutoff frequency fc. The signal processing unit 130 may also superimpose digital noise on a frequency band higher than the cutoff frequency fc. For example, the signal processing unit 130 may superimpose digital noise on at least a part of a band between the cutoff frequency fc and the peak frequency of the spectrum of the target signal.

[0094] The signal processor 130 may superimpose the digital noise on a band including a peak frequency of the spectrum of the speech noise. The signal processor 130 may superimpose the digital noise on a band equal to or lower than a lower limit frequency fb1 of the transition region of the digital filter, or may superimpose the digital noise on a band equal to or lower than an upper limit frequency fb2.

[0095] The signal processing unit 130 may superimpose digital noise on a band of 1 kHz or more. This allows the digital noise to be superimposed over almost the entire band of speech noise. The signal processing unit 130 may superimpose digital noise on a band of 0.5 kHz or more, or may superimpose digital noise on a band of 0 Hz or more.

[0096] By superimposing digital noise, it becomes difficult to analyze the contents of the speech noise from the recorded digital signal. The digital noise may be so-called white noise. In other words, the digital noise may be noise whose spectral intensity is almost constant over the entire band to be superimposed. For example, the digital noise may have a fluctuation width of the spectral intensity within a range of ±3 dB of the average value of the spectral intensity. The signal processing unit 130 may output the digital signal before superimposing the digital noise to the determination unit 240. The signal processing unit 130 may output the digital signal after superimposing the digital noise to the communication unit 150 or the storage medium 20.

[0097] Fig. 19 is a diagram showing an example of a time waveform of a digital signal on which digital noise is superimposed. In this example, a digital noise component is superimposed on the waveform shown in Fig. 17. The amplitude of the digital noise component may be smaller or larger than the amplitude of the target signal component.

[0098] According to this example, since digital noise is superimposed at a stage subsequent to the AD conversion unit 120, the amplitude of the analog signal input to the AD conversion unit 120 does not increase. By superimposing digital noise, the audio information can be concealed. The communication unit 150 can transmit the signal with the concealed audio information to the outside. Furthermore, the storage medium 20 can record the signal with the concealed audio information.

[0099] 20 is a diagram showing an example of a circuit board 360 on which the circuit of the determination device 220 is mounted. Circuits other than the determination device 220 may also be provided on the circuit board 360.

[0100] The circuit board 360 is provided with a vibration-proof material 380. The vibration-proof material 380 is made of a material having a lower elastic modulus than the circuit board 360. For example, the vibration-proof material 380 is made of a silicon gel. The vibration-proof material 380 is disposed between the circuit board 360 and a wall of a housing in which the circuit board 360 is housed. The vibration-proof material 380 in this example is provided so as to surround a portion of the circuit board 360. This makes it possible to suppress vibrations of the sound detection unit 10 and suppress vibration components in the analog signal.

[0101] A plurality of vibration-proof materials 380 may be provided for the circuit board 360. Also, the vibration-proof material 380 may be provided in common for the plurality of circuit boards 360. In this example, the plurality of circuit boards 360 are provided in a stacked manner. A support portion 370 is disposed between the two circuit boards 360. The support portion 370 defines the distance between the two circuit boards 360. The support portion 370 may function as a heat sink that releases heat from the circuit board 360 to the outside. The vibration-proof material 380 may be provided so as to go around the plurality of circuit boards 360 and the support portion 370.

[0102] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is clear to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the description of the claims that such modifications and improvements can also be included in the technical scope of the present invention.

[0103] It should be noted that the order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and may be realized in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is explained using "first," "next," etc. for convenience, it does not mean that it is essential to perform the process in this order. [Explanation of symbols]

[0104] REFERENCE SIGNS LIST 10 sound detection unit, 11 input unit, 20 storage medium, 100 recording device, 110 high-pass filter, 111 first capacitor, 112 second capacitor, 113 coil, 114 resistor, 115 switch, 116 switch, 117 switch, 118 switch, 120 AD conversion unit, 121 output unit, 130 signal processing unit, 140 control unit, 150 communication unit, 200 fastening device, 210 fastening tool, 211 housing, 212 connection unit , 213... operation unit, 214... gripping unit, 215... base unit, 220... determination device, 232... determination system, 240... determination unit, 250... motion control unit, 260... determination model storage unit, 270... location storage unit, 280... attitude detection unit, 300... building, 301... column, 302... beam, 303... fixing unit, 304... fastener, 305... foundation, 310... determination model learning device, 350... dialogue module, 360... circuit board, 370... support unit, 380... vibration isolation material, 601... peak

Claims

1. A determination device for determining an operation of a fastening tool for fastening a fastener, A sound detection unit that converts detected sound into an electrical signal; a determination unit that determines whether or not fastening of the fastener has been completed based on the electrical signal; Equipped with The determination unit determines whether or not the fastener has been tightened using a determination model generated by machine learning, The judgment model estimates a value of a tightening torque of the fastener from feature amount data of the electrical signal, The determination unit inputs a frequency spectrum of the electrical signal to the determination model as feature data of the electrical signal. Judgment device.

2. an operation control unit that stops the operation of the fastening tool when the determination unit determines that the fastening is completed; The determination device according to claim 1 .

3. The determination unit determines whether the fastening is completed based on a component of the electrical signal in a frequency band of 20 kHz or more. The determination device according to claim 1 or 2.

4. The fastening tool generates a continuous impact sound when the fastener is fastened, The determination unit determines whether the fastening has been completed based on the electrical signal during a period including at least one of the impact sounds. The determination device according to any one of claims 1 to 3.

5. The determination unit determines whether the fastening is completed based on a type of a fastening object to be fastened by the fastener. The determination device according to claim 1 .

6. The determination unit determines whether or not the fastening of the fastener is completed by using the determination model that differs for each type of fastening object to be fastened by the fastener. The determination device according to claim 4.

7. The determination unit determines whether the fastening is completed based on the type of the fastening tool. The determination device according to claim 1 .

8. Further comprising a judgment model storage unit that stores a plurality of the judgment models, The determination unit selects the determination model to be used based on the attitude of the fastening tool when the fastener is fastened. The determination device according to claim 1 .

9. The fastener further includes a location memory unit that stores information about the location of the fastener in the building where the fastener has been completed. The determination device according to claim 1 .

10. The sound detection unit converts the detected sound into an analog signal, The determination device includes: a high-pass filter that attenuates components of the analog signal equal to or lower than a cutoff frequency; an AD conversion unit that converts the analog signal that has passed through the high-pass filter into a digital signal and inputs the digital signal to the determination unit; The determination device according to claim 1 , further comprising:

11. The cutoff frequency is 4 kHz or more and 20 kHz or less. The determination device according to claim 10.

12. A determination device described in any one of claims 1 to 11, wherein the determination unit generates the frequency spectrum by performing an FFT on the electrical signal.

13. The determination device according to any one of claims 1 to 12, The fastening tool and A fastening device comprising:

14. The determination device according to any one of claims 1 to 12, a dialogue module for dialogue with a user of the fastening tool; a dialogue storage unit that stores the determination result of the determination unit and the dialogue data of the dialogue module in association with each other; A determination system comprising:

Images