JP6742563B1 - Driving sound diagnosis system, driving sound diagnosis method, and machine learning device for driving sound diagnosis system - Google Patents

Abstract

The drive sound diagnosis system (10) includes a drive sound detection unit (11) that detects a drive sound of an actuator or a driven machine, a drive position of an actuator, a drive speed, or a driving state detection that acquires a force generated by driving in time series. A section (12), a sound vibration time-series spectrum acquisition section (15), a feature point extraction section (16), and a factor determination section (18). The sound vibration time series spectrum acquisition unit outputs a time series spectrum in which the power of the frequency spectrum calculated from the time series data of the driving sound is associated with the frequency and the time. The feature point extraction unit outputs feature point data that is a combination of the frequency of the feature point in the time-series spectrum, the time point, the driving position of the actuator at that time point, the driving speed, or the force generated by the driving. The factor determination unit compares the numerical value range and the numerical value of the characteristic point data when the combination of the frequency or time including the characteristic point for each phenomenon and the driving data at that time is made into the multidimensional data, and the driving sound is generated. Determine the factors.

Description

The present invention relates to a drive sound diagnostic system, a drive sound diagnostic method, and a machine learning device for a drive sound diagnostic system for diagnosing a drive sound of an actuator or a driven machine driven by the actuator.

In general, in a device including a power source such as a motor, it is known that the driving sound of a power source or a machine to be driven by the power source includes a lot of information regarding the states of the power source and the driving target. There is. For example, when some abnormality occurs in the power source or the drive target, a sound or vibration different from that in the normal state occurs. Therefore, a diagnostic device is known that diagnoses whether sound or vibration is abnormal. However, when the device is operated for the first time, or when the device is driven immediately after the mechanical configuration and the drive pattern of the device are changed, it is difficult to immediately determine whether the drive sound is normal. For this reason, there is a demand for a technique of acquiring a driving sound, which is a sound or a vibration generated by the device, with a sensor and easily specifying a cause of the driving sound. In particular, there is a demand for a technique for performing diagnosis using drive sound more easily and universally without limiting the mechanical configuration and settings of the device.

Patent Document 1 discloses a technique of measuring the sound or vibration generated by an apparatus including a rotating device and identifying the presence or absence of an abnormality or the cause of the abnormality in the apparatus. According to this technique, first, before the actual operation of the device, a set of characteristics relating to frequency and time is acquired in advance for each abnormality cause with respect to the sound generated by the power source at the time of abnormal noise generation and the driven machine that is a machine driven by the power source. I'll do it. The characteristic relating to the frequency is the frequency at which the peak is generated from the time change of the spectrum obtained by performing the short-time Fourier transform or the like on the time series data of the measured driving sound. The feature regarding time is a time interval at which a vertex is generated for each frequency feature amount. Then, at the time of actual operation of the device, the presence or absence and the cause of the abnormality are identified by comparing the characteristics regarding the frequency and time acquired during the actual operation by the same method with the characteristics regarding the frequency and time acquired in advance. ..

JP, 10-274558, A

However, in the technique described in Patent Document 1, the presence or absence and the cause of the abnormality of the device are specified only from the data obtained by measuring the driving sound generated by the actuator or the driven machine. Therefore, there is a problem that it is difficult to identify the cause of the abnormality that depends on the position or speed of the actuator or the driven machine.

The present invention has been made in view of the above, and an object of the present invention is to obtain a drive sound diagnostic system capable of specifying the cause of an abnormality depending on the position or speed of an actuator or a driven machine.

In order to solve the above-mentioned problems and achieve the object, the driving sound diagnostic system according to the present invention includes a driving sound detection unit, a driving state detection unit, a sound vibration time series spectrum acquisition unit, and a feature point extraction unit. And a factor determination unit. The drive sound detection unit detects a sound generated by an actuator or a driven machine driven by the actuator or a drive sound that is mechanical vibration. The driving state detection unit acquires the driving position, driving speed, or force generated by driving of the actuator in time series. The sound vibration time-series spectrum acquisition unit calculates a frequency spectrum corresponding to each time of the sound vibration data, which is time-series data of the detected driving sound, and associates the calculated frequency spectrum power with the frequency and the time. Output the time series spectrum. The feature point extraction unit extracts, as a feature point, a point at which the waveform of the power of the time-series spectrum with respect to frequency and time is at least one of the apex, peak, ridgeline, and saddle point of the waveform with respect to frequency and time of power of the time-series spectrum. Then, the characteristic point data, which is a set of the frequency of the characteristic point, the time, the waveform of the characteristic point, and the driving position, the driving speed of the actuator at the time of the characteristic point, or the operation data which is the force generated by the driving, is output. The factor determination unit, for each phenomenon that occurs in the actuator or the driven machine that is the cause of the driving sound, at least one of the frequency and time that include the characteristic points that accompany the phenomenon, the drive position of the actuator at that time, It is detected by comparing the numerical value of the characteristic point data with the factor judgment condition that defines the first numerical range when the combination of the driving speed or the driving data that is the force generated by the driving is multidimensional data. Determine the cause of the driving noise.

The drive sound diagnostic system according to the present invention has the effect of being able to identify the cause of an abnormality that depends on the position or speed of the actuator or driven machine.

FIG. 3 is a block diagram showing an example of a functional configuration of the drive sound diagnostic system according to the first embodiment. The figure which shows an example of the hardware constitutions when the drive sound diagnostic system which concerns on Embodiment 1 is applied to an elevator. FIG. 3 is a block diagram showing an example of a hardware configuration of an arithmetic processing unit according to the first embodiment. FIG. 2 is a block diagram schematically showing an example of the functional configuration of the arithmetic processing unit of FIG. 2 according to the first embodiment. 3 is a flowchart showing an example of a processing procedure of the driving sound diagnosis method according to the first embodiment. The figure which shows an example of the sound vibration data by Embodiment 1. The figure which shows an example of the driving data by Embodiment 1. The flowchart which shows an example of the procedure of the synchronous processing of the sound vibration data and operation data by Embodiment 1. FIG. 3 is a diagram for explaining a procedure for synchronizing the sound vibration data and the operation data according to the first embodiment. The figure which shows an example which divided the driving data of FIG. 7 by the driving mode. The figure which shows an example of the time series spectrum data which frequency-converted the sound vibration data of FIG. 6 with the three-dimensional graph by the 3 axes of time, frequency, and power. The figure which shows an example of the vertex of the sound extracted from the time series spectrum data of FIG. 11 in the three-dimensional graph by the 3 axes of time, frequency, and power. The figure which shows an example of the hardware constitutions when the drive sound diagnostic system which concerns on Embodiment 2 is applied to a picking unit. FIG. 3 is a block diagram schematically showing an example of a functional configuration of a server device according to the second embodiment. FIG. 5 is a diagram showing an example of a device data record according to the second embodiment. The block diagram which shows typically an example of a function structure of the user terminal by Embodiment 2. Block diagram showing an example of the hardware configuration of the server device and the user terminal FIG. 3 is a block diagram showing an example of a functional configuration of a factor determination unit in the drive sound diagnostic system according to the third embodiment. Block diagram showing an example of a functional configuration of a machine learning device of the drive sound diagnostic system according to the fourth embodiment The block diagram which shows typically an example of a function structure of the server apparatus by Embodiment 4. The block diagram which shows typically an example of a function structure of the user terminal by Embodiment 4.

Hereinafter, a drive sound diagnostic system, a drive sound diagnostic method, and a machine learning device for a drive sound diagnostic system according to an embodiment of the present invention will be described in detail with reference to the drawings. The present invention is not limited to these embodiments.

Embodiment 1.
FIG. 1 is a block diagram showing an example of the functional configuration of the drive sound diagnostic system according to the first embodiment. The driving sound diagnosis system 10 includes a driving sound detection unit 11, a driving state detection unit 12, a time synchronization unit 13, a driving mode extraction unit 14, a sound vibration time series spectrum acquisition unit 15, and a feature point extraction unit 16. A driving vibration extraction unit 17 and a factor determination unit 18 are provided.

The drive sound detector 11 detects a sound or a vibration generated by an actuator and a driven machine that is a machine driven by the actuator. Hereinafter, the sound or vibration generated by the actuator and the driven machine will be referred to as driving sound. The drive sound detector 11 is a sensor that detects sound or vibration. A vibration sensor such as a microphone that detects sound and an acceleration sensor is an example of the driving sound detection unit 11. The drive sound detector 11 may detect a sound emitted by a drive device that drives the actuator.

The driving state detection unit 12 acquires the driving state of the actuator connected to the driving device in time series. The operating state of the actuator includes a driving position, a driving speed, or a force generated by driving the actuator. A motor is an example of an actuator. Encoder that detects the rotation angle of the motor, linear scale that detects the position of the linear motor, position sensor, displacement meter, distance sensor, speed detector, current detector, acceleration sensor, gyro sensor, force sensor It is an example of the unit 12.

The time synchronization unit 13 includes sound vibration data that is time-series data of the driving sound detected by the driving sound detection unit 11 and operation data that is time-series data of the driving state detected by the driving state detection unit 12. Synchronize the time. In one example, the time synchronization unit 13 obtains a difference between time points that are the reference of the sound vibration data and the operation data, corrects the time point of the sound vibration data or the operation data using this difference, Synchronized sound vibration data and operation data are acquired by extracting the commonly acquired data between the times.

An example of operation data is time series data of current, generated torque, position, and speed. The operation data may be information on the driving device or may be an estimated value based on some detectable data. A motor drive device may store a motor position command, a speed command, a torque command, a current command, and a voltage command, and the drive sound diagnosis system 10 may acquire these from the motor drive device and use them as operation data as they are. The driving data may be obtained by comparison calculation with possible data or estimation calculation including filtering.

Further, the operation data is not limited to the analog signal. The binary data that is turned on when the speed reaches the commanded speed is an example of operation data. In addition, the operation data does not have to be a time/value pair. A function that takes a time representing a speed pattern at each time as an argument is an example of operation data.

The driving mode extraction unit 14 divides the driving state into two or more sections divided by time based on the driving data detected by the driving state detection unit 12. Specifically, the operation mode extraction unit 14 determines the type of the operation state of the actuator by analyzing the operation data, and extracts the time section in which the operation state of the actuator of the specific type is obtained as the operation mode. As for the operation mode, the operation state may be determined from the operation data after being synchronized with the sound and vibration data by the time synchronization unit 13, or the operation mode may be determined from the operation data before being synchronized with the sound and vibration data by the time synchronization unit 13. You may determine a state.

The sound vibration time-series spectrum acquisition unit 15 performs frequency conversion on the sound vibration data that has been time-synchronized by the time synchronization unit 13, and acquires the time-series spectrum in which the spectrum of the sound vibration data corresponding to each time is obtained. .. The time-series spectrum is a set in which the power of the calculated frequency spectrum is associated with the frequency and the time. When performing the frequency conversion, the sound vibration time-series spectrum acquisition unit 15 selects the time to perform the frequency conversion by performing the frequency conversion only on the section of the specific operation mode among the extraction results of the operation mode extraction unit 14. May be. As an example, the operation mode in which the actuator in which driving noise is unlikely to be measured is stopped can be excluded from the targets of frequency conversion. In this case, the amount of data to be subjected to frequency conversion processing is reduced, so that it is possible to reduce the memory used during calculation and the processing time.

When the waveform of the power of the time series spectrum obtained by the sound vibration time series spectrum acquisition unit 15 with respect to frequency and time satisfies the predetermined conditions, the feature point extraction unit 16 extracts the point as a feature point. The characteristic point extraction unit 16 sets the frequency, the time, the power of the characteristic point, the waveform of the characteristic point, and the operation data at the time of the characteristic point as a characteristic point data.

The driving vibration extraction unit 17 extracts a vibration component from the time-synchronized driving data, and acquires vibration data including its frequency or amplitude.

The factor determination unit 18 determines a factor determination condition, which is a numerical range defined for each phenomenon that occurs as a factor of the driving sound and that includes a feature point that accompanies the phenomenon, and the feature extracted by the feature point extraction unit 16. The cause of the driving sound is determined by comparing the point data with the point data. At this time, the factor determination condition may include a numerical value range that includes vibration data that is predetermined for each phenomenon that is a factor of the driving sound and that accompanies the phenomenon. In this case, the factor determination unit 18 compares the factor determination condition with the characteristic point data extracted by the characteristic point extraction unit 16 and the vibration data extracted by the driving vibration extraction unit 17 to determine the driving sound. Estimate the cause.

If a numerical range that includes characteristic points is specified for each abnormality of the device, you must obtain the numerical range that includes the characteristic points for each cause of the device abnormality for all types of driven machines. I won't. Also, when the configuration of the driven machine is changed, similarly, it is necessary to obtain a range of numerical values including characteristic points for each cause of abnormality of the device. There are many types of driven machines, and there are many variations of changes in the configurations of driven machines as well. Therefore, it is a reality to find the numerical range that includes the characteristic points for each abnormality cause of the device. Not at all.

However, in the first embodiment, the numerical range in which the characteristic points are included is determined not for each abnormality of the device but for each phenomenon that occurs as a factor of the driving sound. That is, the characteristic amount is not defined by a specific drive pattern such as the value of the rotation speed of the motor, but is expressed by a conditional expression that does not depend on the drive pattern, for example, a conditional expression that uses the rotation speed of the motor as a variable. Therefore, even if the driven machine is different or the configuration of the driven machine is changed, the same phenomenon occurs if the driving noise is the same, regardless of the type or configuration of the driven machine. The same factor determination conditions can be used. As a result, it is possible to shorten the time required for the preparation of the diagnosis as compared with the case where the range of the numerical values including the characteristic points is defined for each abnormality of the device, and the drive sound can be diagnosed universally. You can

The characteristic point data is a set of frequency, time, power of the characteristic point, waveform of the characteristic point, and operation data at the time of the characteristic point. Therefore, not only information about sound or vibration but also information about the position or speed of the actuator or driven machine is included. In other words, the factor determining unit 18 determines the factors that cause the generation of the driving sound, including the position or speed of the actuator or the driven machine. Therefore, it depends on the position or speed of the actuator or the driven machine. It is possible to easily identify the cause of the abnormality.

Further, in FIG. 1, the time synchronization unit 13, the driving mode extraction unit 14, and the driving vibration extraction unit 17 may be appropriately included in the driving sound diagnostic system 10 depending on the performance required for the diagnosis or the device configuration. It may be removed from the sound diagnostic system 10. In one example, when the sound vibration data and the operation data are acquired by the same measuring instrument or device, the AD (Analog to Digital) converter having the same acquisition timing is used to synchronize the acquired data. be able to. That is, the sound vibration data and the operation data can be synchronized without providing the time synchronization unit 13. In this case, by removing the time synchronization unit 13, it is possible to reduce the memory used in the drive sound diagnostic system 10 and the processing time.

FIG. 2 is a diagram illustrating an example of a hardware configuration when the drive sound diagnostic system according to the first embodiment is applied to an elevator. As shown in FIG. 2, the diagnosis target 100 includes a motor 110 that is an actuator, a driven machine 120, and a drive device 130 that drives the motor 110. In addition, the diagnosis target 100 is provided with a driving sound diagnosis system 10A including a driving sound detection unit 11, a driving state detection unit 12, and an arithmetic processing unit 140.

The motor 110 is a servo motor that controls the current in the armature winding based on the difference between the drive command and the rotation information. The motor 110 may be an actuator that generates power by receiving energy or an electric signal from a device that drives the motor 110. In this example, the motor 110 is controlled by the drive device 130. However, the state quantity of the motor 110 controlled by the drive device 130 is not limited to the current. Hydraulic pressure, pneumatic pressure, heat, and ultrasonic waves are examples of state quantities of the motor 110 controlled by the drive device 130. Further, the motor 110 is not limited to one that generates a rotational force, and may be a linear motor that drives in a translational direction.

The driven machine 120 is an elevator that conveys an object to be driven in the vertical direction according to the rotation of the motor 110. The driven machine 120 converts a rotation of the motor 110 into a vertical movement, a bracket 121 for fixing the motor 110 to a pedestal, a gear box 122 for amplifying a rotational force generated by the motor 110 and transmitting the same to a ball screw 123. And a coupling 124 that connects the gear box 122 and the ball screw 123.

In addition, the elevator is vertically driven by the rotation of the ball screw 123, a stage 126 fixed to the slider 125 for mounting a work, and a linear guide for slidably guiding the movement of the slider 125 in the vertical direction. A guide 127 and a bracket 128 that rotatably fixes the ball screw 123 to the linear guide 127 via a bearing are provided.

Here, the case where the driven machine 120 is an elevator having the ball screw 123 is illustrated, but the driven machine 120 may be a machine that generates sound or vibration according to the rotation of the motor 110. Screws, belts, gears, cams, linkages, bearings or seals, or machines that combine these elements are examples of driven machines 120.

The drive device 130 is connected to the motor 110 via a cable 151. The drive device 130 includes a motor drive 131, a motor control device 132, and a display 133. The motor drive 131 supplies power for driving the motor 110 to the motor 110. Further, the motor drive 131 drives the motor 110 according to the drive command transmitted from the motor control device 132.

The motor control device 132 controls the amount and timing of the current supplied to the motor 110 by the motor drive 131 by sending an electric signal such as a command position or command speed to the motor drive 131. The display 133 displays various states of the entire system including the drive sound diagnosis system 10A and the diagnosis target 100, and notifies the user of the status.

In the first embodiment, the motor drive 131 is connected to the driving sound detection unit 11 and the driving state detection unit 12, and relays communication between the driving sound detection unit 11 and the driving state detection unit 12 and the motor control device 132. Have the function to

The motor control device 132 is a controller that gives a drive command including a pattern of the position or speed of the motor 110 to the motor drive 131. The motor control device 132 is a control device including a PLC (Programmable Logic Controller), a motor driving CPU (Central Processing Unit), a DSP (Digital Signal Processor), a pulse generator, and the like.

Further, the display unit 133 obtains the state of the entire system including the drive sound diagnostic system 10A from at least one of the motor drive 131, the motor control device 132, and the arithmetic processing unit 140 by communication, and displays it in a format easy for the user to see. I do. The display 133 may have a built-in liquid crystal display. By including the display unit 133 in the system, after the drive sound is diagnosed by the arithmetic processing unit 140, the result of the drive sound diagnosis is displayed on the display unit 133 via communication to notify the user in an easy-to-understand manner. You can

The drive device 130 may be any device that drives at least one motor 110, and may be configured by combining some or more of the present embodiment.

The arithmetic processing unit 140 is a processing device that can execute a diagnostic process of the drive sound diagnostic system 10A described later as software. In the first embodiment, the CPU of the microcomputer incorporated in the motor control device 132 realizes the function of the arithmetic processing unit 140. FIG. 3 is a block diagram showing an example of the hardware configuration of the arithmetic processing unit according to the first embodiment. The arithmetic processing unit 140 includes a processor 141 and a memory 142. The processor 141 and the memory 142 are connected via a bus line 143. CPU and GPU (Graphics Processing Units) are examples of the processor 141.

FIG. 4 is a block diagram schematically showing an example of the functional configuration of the arithmetic processing unit of FIG. 2 according to the first embodiment. The arithmetic processing unit 140 includes a time synchronization unit 13, a driving mode extraction unit 14, a sound vibration time series spectrum acquisition unit 15, a feature point extraction unit 16, a driving vibration extraction unit 17, and a factor determination unit 18. , As software executed by the CPU of the microcomputer. The same components as those in FIGS. 1 and 2 are designated by the same reference numerals and the description thereof is omitted.

In FIG. 2, the arithmetic processing unit 140 is shown as being built in the motor control device 132, but the embodiment is not limited to this structure. The arithmetic processing unit 140 may be incorporated in the motor drive 131, which is another device of the drive device 130, or may be incorporated in the display 133. Further, another microcomputer may be attached to the motor control device 132 to form the arithmetic processing unit 140. Further, it may be connected as a separate device independent of the driving device 130.

The drive sound detection unit 11 is a microphone that detects a drive sound generated by the diagnosis target 100. The detected driving sound is transmitted to the arithmetic processing unit 140 via the cable 152 and the driving device 130. In the example of FIG. 2, the drive sound detection unit 11 is fixed to the elevator. However, the drive sound detection unit 11 only needs to be able to detect the drive sound of the diagnosis target 100, and the installation method is not limited to being fixed to the driven machine 120. The driving sound detection unit 11 may be fixed to the motor 110, or may be installed separately from the driven machine 120 at a distance such that the driving sound can be detected.

If the sounding location of the phenomenon to be diagnosed is limited, the microphone can be placed adjacent to the sounding location, or a directional microphone can be used. The range may be limited. By limiting the sound collection, it is possible to reduce ambient noise that interferes with diagnosis and reduce false diagnosis.

Further, a plurality of microphones can be used as the driving sound detection unit 11. By collecting the same sound or vibration with a plurality of microphones, false diagnosis due to noise can be reduced.

Further, a recorder may be used to record the drive sound generated by the diagnosis target 100 in time series as sound vibration data. A smartphone or a voice recorder is an example of a recorder. Alternatively, a moving image may be taken with a camera or the like, and only the sound part may be extracted as sound vibration data.

Further, the drive sound detection unit 11 may be provided with a storage unit that stores the drive sounds generated in time series as sound vibration data, and the stored sound vibration data may be transmitted to a higher-level arithmetic device as necessary. In this case, when the drive sound diagnosis is not performed, the communication between the drive sound detection unit 11 and the arithmetic processing unit 140 is not performed, and when the drive sound diagnosis is performed, the time series stored by the drive sound detection unit 11 is stored. Sound and vibration data is transmitted together. With such a configuration, it is possible to reduce the processing related to the communication between the drive sound detection unit 11 and the arithmetic processing unit 140.

The operating state detector 12 is an encoder that is attached to the motor 110 and detects the rotation angle of the motor 110. The data of the rotation angle detected by the encoder is transmitted to the arithmetic processing unit 140 via the cable 153 and the driving device 130 as an operating state.

The installation location of the operating state detection unit 12 is not limited to being fixed to the motor 110. The operating state detection unit 12 may be fixed to the drive unit of the driven machine 120 that is a machine driven by the motor 110. Similar to the driving sound detection unit 11, a storage unit that stores the detected time-series operation states as operation data in the operation state detection unit 12 is provided, and the stored operation data is transmitted to a higher-order arithmetic device as necessary. The method may be used.

The arithmetic processing unit 140 receives the driving sound detected by the driving sound detecting unit 11 and the driving state detected by the driving state detecting unit 12 via the cables 152 and 153, and diagnoses the factors of the driving noise.

The arithmetic processing unit 140 is connected to the driving sound detecting unit 11 and the driving condition detecting unit 12 through a high-speed network without data delay in order to exchange appropriate data with the driving sound detecting unit 11 and the driving condition detecting unit 12. Environment is desirable.

Next, the operation of the diagnosis target 100 will be described. The user of the elevator of the driven machine 120 inputs a drive command of the motor 110 to the motor control device 132 in order to convey a work (not shown) by the elevator. The motor control device 132 transmits a drive command to the motor drive 131 based on the information including the drive pattern and the operation timing input by the user. The motor drive 131 controls the motor drive current according to the received drive command to drive the motor 110. In the elevator, when the motor 110 that is a power source rotates, the ball screw 123 rotates, and the slider 125 connected to the ball screw 123 and the stage 126 connected to the slider 125 move up and down.

In one example, the user of the elevator mounts the work on the stage 126 while the position of the stage 126 is moving vertically below the linear guide 127 by the above-described operation. The stage 126 moves vertically above the linear guide 127 as the motor 110 rotates. With this movement, the elevator conveys the work mounted on the stage 126.

The diagnosis target 100 emits a driving sound when being driven by the motor 110. Specifically, the diagnosis target 100 includes the torque pulsation of the motor 110, the translational and torsional rigidity of the ball screw 123, the connection rigidity of the coupling 124, the meshing rigidity of the gear, the movement, deformation or collision of the machine, and the linear guide 127. A drive sound is generated due to sliding friction between the slider and the slider 125. The drive sound generated by the diagnosis target 100 is detected by the drive sound detection unit 11, the rotation angle of the motor 110 is detected by the operating state detection unit 12, and the motor drive 131, the motor control device 132, and the calculation are performed via the cables 152 and 153. It is transmitted to the processing unit 140. However, the transmission method is not necessarily wired, and may be wireless or via a recording medium.

The display unit 133 appropriately communicates with the motor control device 132, and requires a user including the rotation angle of the motor 110 detected by the operation state detection unit 12 and the presence/absence of abnormality of the entire system including the diagnosis target 100. Various information to be displayed is displayed on the display 133.

In the first embodiment, the time synchronization unit 13, the driving mode extraction unit 14, the sound vibration time series spectrum acquisition unit 15, the feature point extraction unit 16, the driving vibration extraction unit 17, and the factor determination unit 18 are one piece of hardware. Although it is configured on the processing unit 140, it may be configured by being divided into separate pieces of hardware. As an example, the time synchronization unit 13 can be separated from the arithmetic processing unit 140 and configured as software on the microcomputer of the motor drive 131. In this case, the motor drive 131, which performs control processing at a higher speed than the motor control device 132, performs the time synchronization process with a strict time requirement, and the arithmetic processing unit 140 of the motor control device 132 has a relatively time constraint. The processes of the small operation mode extraction unit 14, the sound vibration time series spectrum acquisition unit 15, the feature point extraction unit 16, the operation vibration extraction unit 17, and the factor determination unit 18 are performed. As a result, the required performance of the arithmetic processing unit 140 can be reduced, and it is possible to realize the diagnosis of the driving sound factor even with a device having a low arithmetic processing capability.

Further, the realization of each function is not limited to the realization by software on the CPU of the microcomputer, and an electronic circuit such as ASIC (Application Specific Integrated Circuits), FPGA (Field Programmable Gate Array) or CPLD (Complex Programmable Logic Device) is used. May be.

Next, a drive sound diagnosis procedure in the drive sound diagnosis system 10A that targets the sound or vibration generated by the diagnosis target 100 will be described. FIG. 5 is a flowchart showing an example of a processing procedure of the driving sound diagnosis method according to the first embodiment. In the first embodiment, as described above, when the driven machine 120 is driven by the drive of the motor 110, a driving sound is generated due to movement, deformation, collision, rigidity, friction, etc. of the machine. Further, the driving sound varies in magnitude and frequency of sound pressure depending on the driving method of the motor 110. Therefore, in the first embodiment, a method of diagnosing the drive sound generated by the driven machine 120 will be described.

The drive sound detection unit 11 of the drive sound diagnosis system 10A detects the drive sound (step S11), and the operation state detection unit 12 detects the operation state of the motor 110 (step S12).

The time synchronization unit 13 takes in the drive sound from the drive sound detection unit 11 as time-series sound vibration data (step S13). FIG. 6 is a diagram showing an example of sound vibration data according to the first embodiment. In this figure, the horizontal axis represents time and the vertical axis represents amplitude.

In addition, the time synchronization unit 13 takes in the driving state from the driving state detection unit 12 as time-series driving data (step S14). FIG. 7 is a diagram showing an example of operation data according to the first embodiment. In this figure, the horizontal axis represents time and the vertical axis represents rotation angle, rotation speed, and current. In FIG. 7, as the operation data, the rotation angle Po of the motor 110 from the reference position of the ball screw 123, the rotation speed w of the motor 110, and the motor current i are shown.

Here, it is necessary to acquire the data at the same time when the sound vibration data is acquired and the operation data is acquired. However, if the time is the same, the acquisition time of the data to be captured may be different, or the time at which some of the data is acquired may be different from the same time.

Further, in the case where the frequency of the sound or vibration generated by the diagnosis target 100 is predicted by some knowledge, it is desirable to thin out the sampling of the sound vibration data and the operation data up to the target frequency band. The thinning process can reduce the amount of memory used and the processing time. When performing the thinning-out process, since the frequency conversion of the sound vibration data is performed in a process subsequent to the processes of the driving sound detecting unit 11 and the driving state detecting unit 12, it is preferable to perform the filtering process by the noise removal filter. The low pass filter, the high pass filter, the band pass filter, the notch filter, and the band eliminate filter are examples of noise removal filters. Moreover, you may apply the illustrated filter individually or in multiple numbers as a noise removal filter. By doing so, an effect of reducing aliasing noise due to thinning can be expected.

Then, the time synchronization unit 13 performs a synchronization process of the sound vibration data and the operation data (step S15). FIG. 8 is a flowchart showing an example of a procedure of a synchronization process of sound vibration data and operation data according to the first embodiment.

First, the difference between the reference times of the sound vibration data and the operation data is acquired (step S31). Here, the reference time is the time when the time is 0 in each data. When the sound and vibration data and the driving data are not synchronized, the timing for setting the time 0 of each data is set individually, so that the actual acquisition timing may differ even if the data acquisition time is the same. is there. Therefore, the time of each data is corrected by obtaining the difference between the actual time at which the time is 0 in each data.

As a method for obtaining the difference between the reference times, there is a method in which the timing for acquiring the data is designed in advance to be a constant time difference and the constant time difference is used as the reference time difference. Further, there is also a method in which a common master clock is accessed in advance so that each data is acquired at the same timing and the difference between reference times is set to zero. Alternatively, a method in which a time at a common master clock at the timing of starting the acquisition of data is stored as a time stamp and the difference between the time stamps of the sound vibration data and the operation data is set as the difference between the reference times can be used.

FIG. 9 is a diagram for explaining a procedure for synchronizing the sound vibration data and the operation data according to the first embodiment. In the example of FIG. 9, time 0 of the sound vibration data Da is the data acquisition time, and time 0 of the operation data Do is the data acquisition time. It is assumed that the time 0 of the sound vibration data Da is t1 at the reference time, and the time 0 of the operation data Do is t2 at the reference time. In this case, the difference Δt between the reference times is t2-t1.

Then, the acquisition time of each data is corrected based on the obtained difference of the reference times (step S32). Specifically, of the sound and vibration data and the operation data, the difference between the obtained reference times is added as a correction to the acquisition time of each data of the data that has already been acquired.

In the example of FIG. 9, the data whose acquisition has started first is the sound vibration data Da. Therefore, the reference time t2 of the operation data is obtained by adding the difference Δt between the reference times to the acquisition time t1 of the sound vibration data Da.

Returning to FIG. 8, the time interval in which the sound vibration data and the operation data are commonly acquired is calculated (step S33). An example of a specific calculation method is common from the acquisition start time of the data that is acquired later in the above process to the acquisition time of the earliest timing of the last acquisition time of the sound vibration data and the operation data. This is a method of setting the time between the acquired times. In the example of FIG. 9, from the acquisition start time t2 of the operation data Do to the last acquisition time t3 of the sound vibration data Da is the time interval Δtc commonly acquired.

Then, the data of the non-common time that is not the calculated common time acquired is discarded (step S34). In the example of FIG. 9, the sound vibration data Da before time t2 and the operation data Do after time t3 are discarded. As described above, the sound vibration data and the operation data can be synchronized, and the synchronization processing of the sound vibration data and the operation data ends.

Returning to FIG. 5, the operation mode extraction unit 14 estimates the operation state of the driven machine 120 based on the operation data that has been time-synchronized, and extracts the operation mode (step S16). In the first embodiment, the operation mode of the driven machine 120 is divided into three modes, that is, during stop, during constant speed operation or during acceleration/deceleration.

<Stopped>
A section where the rotation of the motor 110 is stopped is defined as being stopped. Here, the rotation of the motor 110 is stopped means that the sum of the amounts of change in the data of the rotation angle of the motor 110 detected by the operating state detection unit 12 falls within a specific threshold for a certain period of time. At this time, the section in which the sum of the changes in the rotation angle data is within a specific threshold is defined as the section in which the position is stopped. The fixed time included in the condition may be determined according to the average value of the detection cycle of the sound vibration data and the operation data.

<During constant speed operation>
A section in which the rotation speed of the motor 110 is constant and which is not stopped is defined as being in constant speed operation. Here, that the speed is constant means that the sum of the amounts of change in the speed data stays within a specific threshold value for a certain period of time, as in the stop state. At this time, a section in which the sum of the variation amounts of the speed data is within a specific threshold value is set as a section in which the speed is constant and longer than a predetermined time.

<During acceleration/deceleration>
A section that is neither in stop nor in constant speed operation is defined as being in acceleration/deceleration. With respect to the driving direction, it may be distinguished that the acceleration is positive when the acceleration is being performed and the acceleration is negative when the deceleration is being performed. FIG. 10 is a diagram showing an example in which the operation data of FIG. 7 is divided in operation modes. In this example, the operation mode is in acceleration/deceleration from time 0 to t11, in constant speed operation from time t11 to t12, in acceleration/deceleration from time t12 to t13, and after time t13. Is stopped.

Returning to FIG. 5, the sound vibration time series spectrum acquisition unit 15 performs frequency conversion on the sound vibration data synchronized by the time synchronization unit 13 to calculate the spectrum of the sound vibration data at each time (step S17). ). The spectrum of the sound vibration data is time-series spectrum data in which the power of the calculated frequency spectrum is associated with the frequency and the time.

The frequency conversion is preferably performed by short-time Fourier transform (STFT) or wavelet transform. Since the time-series spectrum is obtained by these methods, the labor and processing such as filter design can be reduced.

Here, if the band of the frequency of the drive sound emitted by the diagnosis target 100 is predicted by some knowledge, a filter for extracting frequency components within the band predicted before frequency conversion is applied to the sound vibration data. May be. By applying the filter, the drive sound can be diagnosed more accurately.

In the first embodiment, the sound vibration time-series spectrum acquisition unit 15 frequency-tunes only the sound vibration data corresponding to the period during constant speed operation extracted by the operation mode extraction unit 14 among the sound vibration data that has been time-synchronized. Convert and discard data for other periods.

FIG. 11 is a diagram showing an example of time-series spectrum data obtained by frequency-converting the sound vibration data of FIG. 6 in a three-dimensional graph with three axes of time, frequency, and power. In this figure, the vertical axis represents power, and the two orthogonal axes in the plane perpendicular to the vertical axis represent time and frequency.

Returning to FIG. 5, with respect to the spectrum of the sound vibration data represented by the time series data obtained by the sound vibration time series spectrum acquisition unit 15, the feature point extraction unit 16 determines the frequency and time of the power of the spectrum. The characteristic points that satisfy the above conditions are extracted (step S18). In addition, the feature point extraction unit 16 generates feature point data for the extracted feature points (step S19). The feature point data is a set of frequency, time, power, waveform of the feature point and operation data at the time of the feature point.

An example of conditions used when the feature point extraction unit 16 extracts the feature points is a vertex, a peak, a ridgeline, and a saddle point. The case of acquiring vertices as feature points will be described.

First, since the spectrum of time series sound vibration data contains noise, a low pass filter is applied to the time axis and the frequency axis. The time constant of the low pass filter is determined by the sampling period of the sound vibration data and the frequency conversion resolution. Further, instead of applying the low pass filter, the Hilbert transform may be applied to the time series spectrum.

Next, with respect to the time-series spectrum after the low-pass filter is applied, a power threshold value is determined, and it is divided into an area having a power larger than the threshold and an area having a power smaller than the threshold. The median value of the time-series spectrum is an example of a power threshold.

Then, the following four points are acquired from the points x=(t _x , f _x , p _x ) whose power is larger than the threshold value. Here, t _x , f _x , and p _x respectively indicate the time, frequency, and power at the point x.
(1) frequency in the f _x, a point x1 at the next time t _{x + 1} of the acquisition time _{t x (t x + 1,} f x, p 1)
(2) at a frequency f _x, the previous one acquisition time t _x the time t _x-1 of the point _{x2 (t x-1, f} x, p 2)
(3) at the acquisition time t _x, the next frequency f _{x + 1} of point x3 frequencies _{f x (t x, f x} + 1, p 3)
(4) at the acquisition time t _x, the frequency of the previous one f _x frequency f _x-1 of the point _{x4 (t x, f x-} 1, p 4)

Next, the powers of five points in total, which is obtained by adding the original point x to the above four points x1, x2, x3, and x4, are compared. When the power of the point x is larger than the other four points among the five points, that is, the point x surrounded by the other four points x1, x2, x3 and x4 among the five points is the point of the maximum power. Then, the point x is set as a vertex candidate. In this example, when a point having the maximum power is extracted using the point x and two points adjacent to each other in the time axis direction and the frequency axis direction with the point x as the center. However, the embodiment is not limited to this. That is, when a plurality of points surrounding the point x on the plane formed by the time axis and the frequency axis and the point x are used, and the power of the point x surrounded by the plurality of points becomes maximum, the point x May be extracted as a point having the maximum power.

Finally, the vertex candidates are arranged in descending order of power, and a certain number of points from the largest one are extracted as maxima.

Here, the candidate points may be arranged in descending order of power, and a certain number obtained from the larger one may be used as the apex, or all candidate points whose power exceeds a predetermined threshold may be used as the apex. Good. Moreover, you may combine these methods.

In this way, by acquiring the vertices of the waveform with respect to the frequency and time of the power of the time-series spectrum as the feature points, it is possible to reduce the calculation amount by the factor diagnosis described later by a method with a small processing amount.

If the driving data is not acquired at the time of the characteristic point, the driving data at the time closest to the time of the characteristic point is used, or the characteristic point is calculated based on the driving data at a plurality of times before and after the time of the characteristic point. By interpolating the driving data at the time of, the driving data at the time of the characteristic point can be determined.

FIG. 12 is a diagram showing an example of vertices of sounds extracted from the time-series spectrum data of FIG. 11 in a three-dimensional graph with three axes of time, frequency, and power. In this figure, the vertices 1, 2, 3 extracted by the method described above are shown.

Returning to FIG. 5, the driving vibration extraction unit 17 extracts the vibration component from the time-synchronized driving data, and acquires the vibration data (step S20). The frequency, amplitude or phase of the vibration component is an example of vibration data. This process may be performed independently of the sound vibration time series spectrum acquisition process of step S17.

An example of the method of extracting the vibration component is a method of obtaining the time from the peak of the wave peak of the operation data during constant speed operation to the peak of the next peak.

Next, the factor determination unit 18 compares the feature point data generated in step S19 and the vibration data acquired in step S20 with the factor determination condition registered for each drive sound factor to generate the drive sound. The factor is determined (step S21). Here, each factor determination condition registered for each factor of the driving sound is, for the feature point data, a characteristic that occurs with each phenomenon that occurs in the motor 110 or the driven machine 120 that is the factor of the driving noise. Numerical value range when a combination of at least one of the frequency and the time including the point and the driving position, the driving speed, or the operation data that is the force generated by the driving of the motor 110 that is the actuator at the time is multidimensional data. Is defined. With respect to the vibration data, for each phenomenon that occurs in the motor 110 or the driven machine 120 as a cause of the driving sound, a numerical range that includes a vibration component that accompanies this phenomenon is determined.

For the characteristic point data, the factor determination unit 18 determines the generation factor of the sound vibration data by comparing the acquired characteristic point data with the numerical range for each factor. For the vibration data, the factor determination unit 18 compares the acquired vibration data with the numerical range for each factor, that is, compares the vibration component of the operation data with the peak of the sound to generate the vibration data. Determine the factors.

As an example, when dirt adheres to the linear guide 127 and friction between the slider 125 and the linear guide 127 increases to generate a rubbing sound, the rubbing sound is generated when the slider 125 falls within a specific position section. Occurs only when. Therefore, when the position of the motor 110 at the time when the characteristic point is generated is concentrated at a specific position or within a section P having a constant width, the diagnosis target 100 determines that the sound is generated in the section P. 18 makes a decision. Here, the width of the section P can be determined by the ratio to the difference between the maximum value and the minimum value of the position data in the time-series operation data. Further, this factor determination condition may be any condition that allows inspection that the distribution of the position of the motor 110 at the time of the characteristic point is concentrated on a specific position. For example, the number or the ratio of the characteristic points deviating from the section P having a constant width, the average and variance of the positions of the characteristic points at time, or the correlation coefficient between the frequency and the position of the characteristic points is calculated, and the calculated value is set in advance. It may be inspected to be within the specified range.

Further, as another example, it is known that when the centers of the two axes connected by the coupling 124 are deviated, a characteristic sound is generated at a frequency twice the number of rotations of the coupling 124. .. Therefore, the rotational speed of the coupling 124 is calculated by multiplying the speed of the motor 110 of the operation data at the time when the characteristic point occurs by the conversion ratio of the gearbox 122, and the calculated rotational speed and the frequency of the characteristic point are 2 The factor determining unit 18 determines that the centers of the two axes connected by the coupling 124 are deviated when they are in a directly proportional relationship. At this time, instead of the speed of the motor 110, the current of the motor 110 may be acquired as operation data and the values may be accumulated to substitute for the speed.

As another example of another condition, when the machine resonates by driving the motor 110, a resonance sound having a particular resonance frequency f is generated at a particular speed v that excites the machine resonance. Therefore, the rotation speed of the motor 110 at the time when the characteristic point is generated is concentrated on a specific speed or a section V having a constant width, and the frequency of the characteristic point is concentrated on a specific frequency or a section F having a constant width. At this time, the diagnosis unit 100 determines that the factor determination unit 18 determines that the sound of the frequency f is generated due to the mechanical resonance at the rotation speed v.

Further, when the frequency of the vibration acquired by the driving vibration extraction unit 17 and the time period of the characteristic points at which the frequency f due to mechanical resonance is generated are the same, the rotation of the motor 110 causes the motor 110 to rotate at regular intervals. The factor determination unit 18 determines that the vibration component excites mechanical resonance. That is, by comparing the vibration component of the operation data with the apex of the sound, the mechanical resonance is periodically excited by the vibration component of the drive, and the phenomenon that the resonance is excited is determined by the factor determination unit 18.

As described above, the factor determining unit 18 uses the registered factor determining condition for the feature point data extracted by the feature point extracting unit 16 or for the feature point data and the vibration data extracted by the driving vibration extracting unit 17. On the other hand, an inspection is performed to determine the cause of the driving sound that depends on the position or speed of the actuator or the driven machine 120. The factor determination condition to be registered may be checked as a binary tree search by organizing similar conditions in advance. By doing so, the number of conditions to be inspected for discriminating the factors can be reduced, and the discrimination time can be shortened. This is the end of the processing of the drive sound diagnosis method.

The drive sound diagnosis system 10 or 10A according to the first embodiment synchronizes time-series sound vibration data regarding the drive sound generated by the actuator or the driven machine 120 with time-series operation data regarding the operating state of the actuator. , Extract the operation mode. Also, feature points were extracted from the spectrum of the time-series sound and vibration data obtained by time-frequency analysis of the sound and vibration data, and the operation data at the feature point frequency, time, power, and waveform and time of the feature point were set. Generate feature point data. Then, by comparing the feature point data with a factor determination condition prepared in advance, the cause of the driving sound was determined. In this way, the cause of the drive sound is diagnosed based on the sound vibration data and the operation data, so that the location where the drive sound is generated due to foreign matter adhering to the driven machine 120 can be specified, and the actuator or the driven machine can be identified. The cause of the abnormality depending on the position or speed of 120 can be easily determined. Further, the cause of the change in the frequency of the sound generated according to the speed of the actuator or the driven machine 120 can be determined. Further, even if the entire device is vibrating, it is possible to determine whether the sound vibration is due to driving.

Further, the drive sound diagnosis systems 10 and 10A diagnose the cause of the sound or vibration based on the sound vibration data of the characteristic points, the operation data, and the generation time thereof. Therefore, even if there is a device that emits a large operating noise next to the diagnosis target, it is possible to suppress erroneous diagnosis from the causal relationship between the occurrence time and the operation data.

Further, since the driving sound diagnostic systems 10 and 10A diagnose the sound generation factor by combining the frequency spectrum of the sound vibration data and the operation data, when the change of the spectrum of the sound vibration data is determined, the change of the operation pattern is performed. It is possible to eliminate the influence of the change in the spectrum of the sound vibration data due to. In particular, even if the operation pattern changes depending on the condition of the work, the influence of the sound vibration data on the spectrum can be removed by the operation data, so that the drive sound diagnostic systems 10 and 10A perform appropriate diagnosis. be able to.

Further, the drive sound diagnosis systems 10 and 10A diagnose the drive sound generation factor by substituting the characteristic amount obtained by time-frequency analysis of the sound vibration data into the conditional expression that does not depend on the drive pattern. Therefore, it is not necessary to prepare in advance operation data for normal or abnormal conditions. Therefore, even when the configuration of the driving device or the machine is changed, the driving sound can be universally and immediately diagnosed.

A case where the centers of the two axes connected by the coupling 124 are deviated will be described as an example. It is known that this sound produces a characteristic sound at a frequency twice that of the rotational speed of the coupling 124. It is assumed that the drive pattern is changed from the rotation speed of the motor 110 of 10 rotations per second to the rotation speed of the motor 110 of 20 rotations per second due to the change in the usage method of the machine. In the technique described in Patent Document 1, the threshold value of the peak frequency of sound when detecting an abnormality must be set for each drive pattern. An example of the threshold value of the peak frequency is represented by the following equation (1) before the drive pattern is changed, and is represented by the following equation (2) after the drive pattern is changed.
Peak frequency before change=10×conversion ratio of gearbox 122×2±error [Hz] (1)
Peak frequency after change=20×conversion ratio of gearbox 122×2±error [Hz] (2)

On the other hand, in the present embodiment, the peak frequency, which is the characteristic amount of the sound generated due to the displacement of the coupling 124, is expressed by the following equation (3).
Peak frequency=frequency of rotation speed×conversion ratio of gearbox 122×2±error [Hz] (3)

That is, the peak frequency of the sound generated by the displacement of the coupling 124, which includes the expressions (1) and (2), is expressed by a conditional expression in which the rotation speed of the motor 110 is a variable. It is not necessary to prepare a conditional expression for each rotation speed of the motor 110 in advance. Since the frequency of the rotation speed can be obtained from the acquired operation data, it is possible to determine the deviation of the coupling 124 by using the formula (3) in any operation pattern. .. That is, the frequency, which is the feature amount of the sound, is substituted into the conditional expression that does not depend on the drive pattern, and the determination is performed. In addition, here, the sound generated when the centers of the two axes connected by the coupling 124 are deviated has been described. However, regarding other factors, similarly, the characteristic amount obtained by time-frequency analysis of the vibration data is calculated. , By substituting into a conditional expression that does not depend on the drive pattern, it is possible to diagnose the cause of the drive sound.

Further, the cause is diagnosed based on the drive sound generated by the driven machine 120. By making a diagnosis using the driving sound, it is possible to make a diagnosis regardless of the machine, even when the machine rigidity is low.

Further, the drive sound diagnostic systems 10 and 10A diagnose the cause of sound or vibration using the result of time-frequency analysis of sound vibration data. By performing the time-frequency analysis, it is possible to reduce erroneous factor diagnosis due to sensor erroneous detection or noise.

Further, the drive sound diagnosis system 10 or 10A diagnoses the cause of the drive sound based on the feature amount obtained by time-frequency analysis of the sound vibration data. As a result, the data to be diagnosed can be reduced and the processing time can be reduced. Further, by using the frequency, it is possible to estimate the cause of the driving sound.

In the drive sound diagnostic systems 10 and 10A, the operation mode extraction unit 14 estimates the operation state of the device based on the operation data and extracts the operation mode. Then, frequency conversion is performed only on the sound and vibration data corresponding to the period during constant speed operation, and the sound and vibration data during acceleration/deceleration in which the driving of the actuator is difficult to stabilize can be discarded. Therefore, compared with the case where the sound vibration data during acceleration/deceleration is also used, the accuracy of the diagnosis is improved, and the sound vibration data that is not suitable for the diagnosis is discarded, so that the amount of memory and the processing time used in the arithmetic processing are reduced. Can be reduced.

Further, the drive sound diagnosis system 10 or 10A determines a period in which the driven machine 120 is not operating based on the operation data, and omits sound vibration data in the period in which the driven machine 120 is not operating. It is possible to prevent false detection due to. Further, the processing cost can be reduced by omitting the frequency conversion when the driven machine 120 is not operating.

Furthermore, when investigating the cause of the driving sound, the influence of the driving sound due to another phenomenon can be eliminated by specifying the operation mode including the driving sound to be investigated. In particular, when a plurality of actuators are provided, it is possible to estimate the actuator that causes the driving sound.

Further, the drive sound diagnostic systems 10 and 10A determine that the operation mode extraction unit 14 is in constant speed operation for a certain period of time when the sum of changes in speed data, which is operation data, falls within a specific threshold value. By doing so, when the speed of the actuator is within a certain range, the driving sound generated by the driven machine 120 is stable and tends to be in a homogeneous state, so that the factor of the sound can be determined more accurately. .. Further, since the sound in a stable state can be extracted without specifying the speed, the same factor diagnosis can be performed during the constant speed operation even if the drive pattern is different. Further, it is possible to extract the sound when the actuator or the driven machine 120 stabilizes at a plurality of speeds, which is desirable for factor estimation.

Further, since the driving sound diagnosis systems 10 and 10A include the driving vibration extracting unit 17 that extracts the vibration component from the driving data, the factor determining unit 18 can compare the vibration component with the occurrence time of the characteristic point. This makes it possible to determine a phenomenon in which the mechanical resonance is periodically excited by the vibration component of the drive and the resonance is excited.

Further, the drive sound diagnostic systems 10 and 10A detect that the characteristic points and the distribution of the positions of the motor 110 at the time of the characteristic points are concentrated at a specific position. By doing so, it is possible to determine whether or not the detected feature point is a feature point generated due to a factor depending on the driving data.

In addition, the drive sound diagnostic systems 10 and 10A extract feature points as feature points at which the power of the time-series spectrum becomes the apex of the waveform with respect to frequency and time. By reducing the number of points to be diagnosed by extraction, the processing performed by the factor determining unit 18 can be reduced. By calculating the correlation coefficient between the apex of the spectrum and the operation data, it is possible to determine whether or not the detected apex is caused by a factor depending on the operation data.

In addition, the drive sound diagnostic systems 10 and 10A determine the cause of the drive sound generated by the driven machine 120 and notify the user of the elevator through the display 133. By doing so, the user of the elevator can detect that there is a problem in the driving sound of the driven machine 120 and take appropriate action based on the diagnosis result.

Embodiment 2.
FIG. 13 is a diagram showing an example of a hardware configuration when the drive sound diagnostic system according to the second embodiment is applied to a picking unit. In this example, the diagnosis target 200 is a picking unit that transfers the work 291 flowing on the belt conveyor 225 to another belt conveyor 226.

As shown in FIG. 13, the diagnosis target 200 includes a plurality of motors 211, 212, 213, 214 and an actuator 215, a driven machine 220, and a drive device 230. The drive sound diagnosis system 10B is provided for the diagnosis target 200. The driving sound diagnosis system 10B includes a driving sound detection unit 11, a driving state detection unit 12, a wireless network device 240, a server device 250, a user terminal 260, and a network device 270. The server device 250 and the user terminal 260 are connected via a communication line 280. In the driven machine 220, the vertical direction is the Z direction, the extending direction of the belt conveyors 225 and 226 is the Y direction, and the direction perpendicular to the Y direction and the Z direction is the X direction in a plane perpendicular to the Z direction. And

The driven machine 220 is a picking unit. The driven machine 220 includes a linear rail 221, a ball screw 222, a linear guide 223, a head 224, and two belt conveyors 225 and 226.

The linear rail 221 is a rail that fixes the driving direction of the motor 212 that is a linear motor. In this example, the linear rail 221 is arranged to extend in the Y direction above the two belt conveyors 225 and 226 arranged in parallel. A head 224 is connected to the linear rail 221 via a motor 212, a ball screw 222 and a linear guide 223. The movable direction of the motor 212 when the motor 212 is driven is limited to the extending direction of the linear rail 221. In the example of FIG. 13, the movable direction of the motor 212 is limited to the X direction.

The ball screw 222 is connected to the motor 211 and drives the head 224 in the Z direction by the rotation of the motor 211. The linear guide 223 is a guide that limits the driving direction of the ball screw 222 to the Z direction. The linear guide 223 is fastened to the motor 211 and the ball screw 222, and is fixed to the movable portion of the motor 212. As a result, the ball screw 222 is driven along the linear rail 221 by the drive of the motor 212.

The head 224 is a stage that is driven in the Z direction by driving the ball screw 222. The head 224 has a shape extending in the Y direction, and has an actuator 215 having a mechanism for holding the work 291 in the lower part. The actuator 215 is a vacuum pad that holds the work 291 by a vacuum suction mechanism. The work 291 held by the actuator 215 can be moved up and down by the ball screw 222. The work 291 is a picking target of the picking unit.

The belt conveyor 225 is a feeder that supplies the work 291 from the positive side to the negative side in the Y direction. A motor 213 is connected to the belt conveyor 225. The work 291 on the belt is conveyed by driving the built-in belt by the rotation of the motor 213.

The belt conveyor 226 is an unloader that conveys the work 291 from the positive side to the negative side in the Y direction. The motor 214 is connected to the belt conveyor 226. The work 291 on the belt is conveyed by driving the built-in belt by the rotation of the motor 214.

The motor 211 is connected to the ball screw 222. The motor 211 is a servo motor that receives a current controlled by the drive device 230 and rotates a shaft.

The motor 212 is connected to the linear rail 221. The motor 212 is a linear servo motor that receives a current controlled by the drive device 230 and drives the motor 212 in the X direction.

The motor 213 is connected to the belt conveyor 225, and the motor 214 is connected to the belt conveyor 226. The motors 213 and 214 are stepping motors that receive pulsed electric signals from the drive device 230 and rotate the shafts.

The actuator 215 is a plurality of vacuum pads that receive an electric signal from the driving device 230 and adsorb or desorb the work 291. The work 291 to be picked is held or released by the suction or desorption operation.

The drive device 230 includes a plurality of motor drives 231, 232, 233 and a motor control device 234.

The motor drive 231 is connected to the motor 211 by a cable, and supplies the driving power to the motor 211 while referring to the rotation angle of the motor 211. The motor drive 232 is connected to the motor 212 by a cable, and supplies the driving power to the motor 212 while referring to the position of the motor 212. The motor drive 233 is connected to the motors 213 and 214 by a cable, and sends a pulsed command to the motors 213 and 214.

The motor control device 234 controls the motor drives 231, 232, 233 and controls the driving of the motors 211, 212, 213, 214. The motor drives 231, 232, 233 and the motor control device 234 are connected by a cable and can exchange information with each other by communication. Further, the motor control device 234 is connected to the actuator 215 by a cable (not shown), and controls adsorption and desorption of the work 291 by the actuator 215 by an electric signal. The vacuum pump is an example of the actuator 215 because it sucks or desorbs the work 291. When the vacuum pump operates, the work 291 is adsorbed, and when the vacuum pump does not operate, the work 291 is detached.

The drive sound detection unit 11 is a microphone that is disposed adjacent to the driven machine 220 and that detects a sound emitted by the diagnosis target 200. The drive sound detection unit 11 is provided with a communication unit 241A. An example of the communication unit 241A is a wireless communication device. The driving sound detection unit 11 sets the detected driving sound in combination with a time stamp that is the time when the sound is detected, and transmits the driving sound to the server device 250 via the communication unit 241A.

The driving state detection unit 12 is a logger that is connected to the driving device 230 via a cable and acquires information on the driving device 230 as a driving state. The driving state detection unit 12 appropriately communicates with the driving device 230 to acquire and record various data including the driving state. The operation state detection unit 12 acquires the speed command of the motors 211, 212, 213, 214 and the suction state of the actuator 215 as the operation state of the diagnosis target 200, and outputs it to the time synchronization unit 13. The binary data of adsorption or desorption is an example of the adsorption state.

The driving state detection unit 12 is provided with a communication unit 241B. An example of the communication unit 241B is a wireless communication device. The driving state detection unit 12 pairs the acquired driving state with a time stamp, which is the time when the driving state is acquired, and transmits it to the server device 250 via the communication unit 241B.

Although FIG. 13 shows a case in which one driving sound detecting section 11 and one operating state detecting section 12 are provided for the plural-axis motors 211, 212, 213, 214 and the actuator 215, A plurality of driving sound detection units 11 or a plurality of driving state detection units 12 may be provided. In particular, in the case of the driven machine 220 having a configuration of eliminating the interference due to the drive sound of other motors by shielding or the like, the drive sound detection unit 11 is provided for the respective motors 211, 212, 213, 214 and the actuator 215. By providing this, more accurate diagnosis can be expected.

The wireless network device 240 is a device that performs wireless communication with the communication units 241A and 241B. The wireless network device 240 has a communication unit 241C. A wireless LAN (Local Area Network) is constructed by the wireless network device 240 and the communication units 241A, 241B, 241C, and the wireless network device 240 becomes an access point of the communication units 241A, 241B, 241C. The wireless network device 240 also has a role of a router at the same time, and relays communication between each terminal and the network via the communication line 280. The communication units 241A, 241B, 241C and the wireless network device 240 perform time synchronization between the wireless equipment including the communication units 241A, 241B, 241C and the wireless network device 240, as necessary. This is to make the time used by the drive sound detection unit 11 and the driving state detection unit 12 accurate.

In the second embodiment, the function processing unit that performs the factor determination using the sound vibration data and the operation data is provided separately in the server device 250 and the user terminal 260. The server device 250 and the user terminal 260 are connected via a communication line 280.

When the server device 250 is instructed by the user terminal 260 to execute the process of determining the cause of the driving sound with respect to the driven machine 220, the sound vibration data and the driving which are time-series data of the driving sound acquired from the driven machine 220. A process of generating device data including feature point data is performed using operation data that is time-series data of the state.

FIG. 14 is a block diagram schematically showing an example of the functional configuration of the server device according to the second embodiment. The server device 250 is an information processing device installed on the network through the communication line 280. The server device 250 has the functions of the time synchronization unit 13, the operation mode extraction unit 14, the sound vibration time series spectrum acquisition unit 15, and the feature point extraction unit 16. That is, the server device 250 includes the time synchronization unit 13, the operation mode extraction unit 14, the sound vibration time series spectrum acquisition unit 15, and the feature point extraction unit 16 as the applications on the server device 250. In addition, in the second embodiment, a configuration in which the driving vibration extraction unit 17 is omitted is illustrated.

The server device 250 also includes a communication unit 251 that communicates between the driving sound detection unit 11 and the driving state detection unit 12 and with the user terminal 260.

Furthermore, the server device 250 includes a device data storage unit 252. The device data storage unit 252 is a database such as RDBMS (Relational Database Management System) or Not only SQL. The server device 250 collects device data including the driving sound and the driving condition sent from the driving sound detector 11 and the driving condition detector 12 to the network in the database, processes the data as necessary, and stores the data. As an example, as described in the first embodiment, the sound vibration data and the operation data are synchronized, time-series spectrum data is acquired for the sound vibration data, feature points are extracted from this spectrum data, and Device data including feature point data that is a set of frequency, time, power, waveform, and operation data at feature point time is stored in the device data storage unit 252.

FIG. 15 is a diagram showing an example of a record of device data according to the second embodiment. One record of the device data includes a registration time, a driving mode, feature point data, and driving data. It should be noted that by analyzing the data collected by the server device 250 by deep learning or the like, it is possible to more accurately determine the factor.

The user terminal 260 instructs the server device 250 to determine a factor regarding the driving sound of the driven machine 220, performs a factor determination process using the device data received from the server device 250, and displays the result. The user terminal 260 is an information processing device possessed by the user of the driven machine 220. An example of the user terminal 260 is a laptop or desktop personal computer.

FIG. 16 is a block diagram schematically showing an example of the functional configuration of the user terminal according to the second embodiment. The user terminal 260 has the function of the factor determining unit 18 described in the first embodiment. That is, the user terminal 260 includes the factor determination unit 18 as an application on the user terminal 260.

The user terminal 260 also includes a communication unit 261, an input unit 262, and a display unit 263. The communication unit 261 communicates with the server device 250 via the communication line 280. As an example, an instruction to execute the process for determining the factor input by the user through the input unit 262 is transmitted to the server device 250, and various information including device data is received from the server device 250. The communication unit 261 can also be connected to the driving sound detection unit 11 and the driving state detection unit 12 to acquire sound vibration data in which driving sound is time-series data and driving data in which driving state is time-series data. ..

The input unit 262 is an input interface with the user. The keyboard or mouse is an example of the input unit 262. From the input unit 262, an instruction to execute the process of determining the factor of the driven machine 220 is input.

The display unit 263 displays information necessary for executing the process of determining the factor of the driven machine 220. The liquid crystal display is an example of the display unit 263. The display unit 263 displays the result of factor determination, device data acquired via the network, and the like.

The network device 270 is a communication device that relays communication among the driving sound detection unit 11 and the driving state detection unit 12 provided in the driven machine 220, the server device 250, and the user terminal 260. The router is an example of the network device 270.

As shown in FIG. 13, by configuring the driving sound diagnostic system 10B via a network, it is possible to diagnose the driving sound even in a remote place different from the factory where the driven machine 220 is installed. ..

The server device 250 and the user terminal 260 that diagnose the driving sound are realized by the information processing device as described above. FIG. 17 is a block diagram showing an example of the hardware configuration of the server device and the user terminal. The server device 250 and the user terminal 260 include an arithmetic device 401, a memory 402, a storage device 403, a communication device 404, an input device 405, and a display device 406. The arithmetic device 401, the memory 402, the storage device 403, the communication device 404, the input device 405, and the display device 406 are connected via a bus line 407.

The arithmetic unit 401 is a processor including a CPU that performs arithmetic processing. The memory 402 functions as a work area for storing data used by the arithmetic unit 401 during arithmetic processing. The storage device 403 stores computer programs, information, and the like. The communication device 404 has a communication function with another device connected to the network. The input device 405 receives input from the operator. The input device 405 is a keyboard, a mouse, or the like. The display device 406 outputs a display screen. The display device 406 is a monitor, a display, or the like. A touch panel in which the input device 405 and the display device 406 are integrated may be used.

The functions of the time synchronization unit 13, the operation mode extraction unit 14, the sound vibration time series spectrum acquisition unit 15, and the feature point extraction unit 16 shown in FIG. 14 are obtained by the arithmetic device 401 reading a computer program stored in the storage device 403. It is realized by executing.

The function of the factor determining unit 18 illustrated in FIG. 16 is realized by the arithmetic device 401 reading and executing the computer program stored in the storage device 403.

Next, the operation of the diagnosis target 200 will be described. The user of the picking unit inputs drive commands for the motors 211, 212, 213, 214 and the actuator 215 to the motor control device 234 in order to convey the work 291 by the picking unit. As an example, the user inputs a command to the motor control device 234 from the user terminal 260. Then, a command is transmitted to the motor control device 234 via the network device 270, the communication line 280, the server device 250, the wireless network device 240, the communication unit 241C, and the communication unit 241B. The motor control device 234 generates and transmits a drive command to the motor drives 231, 232, 233 according to the input command.

The motor drives 231, 232, 233 control the motor drive current according to the received drive command to drive the motors 211, 212, 213, 214 and the actuator 215.

By driving the motor 211, the ball screw 222 connected to the motor 211 rotates, and the head 224 and the actuator 215 connected to the ball screw 222 move in the Z direction.

By driving the motor 212, the linear guide 223 connected to the motor 212, the motor 211, and the device connected to the motor 211 move in the X direction.

By driving the motor 213, the belt conveyor 225 rotates, and the work 291 on the belt conveyor 225 moves from the positive side to the negative side in the Y direction. Similarly, when the motor 214 is driven, the belt conveyor 226 rotates and the work 291 on the belt conveyor 226 moves from the positive side to the negative side in the Y direction.

The actuator 215 holds the work 291 by adsorbing the work 291 moving on the belt conveyor 225 at the timing when the work 291 is contacted directly below the actuator 215. Accordingly, even when the actuator 215 moves upward due to the driving of the motor 211 after suction, the state in which the work 291 is in contact with the actuator 215 can be maintained.

Then, the motor 211 rotates to move the actuator 215 upward. At this time, since the work 291 is adsorbed by the actuator 215, the work 291 also rises as the actuator 215 rises, and is separated from the belt conveyor 225.

Next, the work 291 is moved directly above the belt conveyor 226 by driving the motor 212 to the positive side in the Y direction. After that, the work 291 is placed on the belt conveyor 226 by rotating the motor 211 again. The actuator 215 places the work 291 on the belt conveyor 226 by releasing the work 291 at the timing when the held work 291 contacts the belt conveyor 226. After releasing the actuator 215, the motor 211 and the motor 212 are driven to return the actuator 215 to the starting position. Finally, by rotating the motor 214, the work 291 is carried out toward the Y direction negative side of the belt conveyor 226.

In the process of the operation described above, the diagnosis target 200 emits a driving sound when it is driven. The drive sound generated by the diagnosis target 200 and the rotation angles of the motors 211, 212, 213, and 214 are recorded and acquired by the drive sound detection unit 11 and the operation state detection unit 12, and are recorded in the server device 250 by wireless communication. Sent.

The server device 250 communicates with the driving sound detection unit 11 and the driving state detection unit 12 through the wireless network device 240 as needed, acquires various information about the diagnosis target 200 including the driving sound and the driving state, and the device data storage unit 252. Store the information in. As preprocessing to be stored in the device data storage unit 252, the time synchronization unit 13, the operation mode extraction unit 14, the sound vibration time series spectrum acquisition unit 15, and the feature point extraction unit 16 are the sound vibration data and the driving of the acquired time series data. The processing is executed on the data to calculate the operation mode and the characteristic point data. The device data storage unit 252 includes the feature point data calculated by the time synchronization unit 13, the operation mode extraction unit 14, the sound vibration time series spectrum acquisition unit 15, and the feature point extraction unit 16, and the operation data in which the time of the feature point is synchronized. And other necessary information regarding the diagnosis target 200 is stored.

The user terminal 260 acquires various kinds of system information required by the user, such as the presence or absence of a system abnormality, through the server device 250 and displays the information on the display unit 263 of the user terminal 260 in response to the user's request. Further, the user can use the database stored in the device data storage unit 252 of the server device 250 to perform the analysis necessary for the maintenance and operation of the diagnosis target 200 and the drive sound diagnosis system 10B.

Next, a drive sound diagnosis procedure in the drive sound diagnosis system 10B according to the second embodiment will be described. The basic drive sound diagnosis procedure is almost the same as that of the first embodiment, but the following description will focus on the differences from the first embodiment.

In the second embodiment, the time synchronization unit 13 of the server device 250 synchronizes the sound vibration data and the operation data by using the time stamps set by the driving sound detection unit 11 and the operation state detection unit 12. This makes it possible to synchronize the sound vibration data and the driving data even when the real-time property of communication cannot be ensured due to poor communication quality.

Further, when the operation mode extraction unit 14 of the server device 250 or the like requires data for a specific time, it is assumed that data having a time stamp specified by the time stamp is extracted. By extracting with this method, it is possible to perform analysis as synchronized data even when the acquisition periods of the sound vibration data and the operation data are different.

As another method when the detection cycle of the sound vibration data and the operation data is different, a method of thinning out the data after performing the filter processing so that the same cycle is used, or a method such as linear interpolation of the data between A method of interpolation is conceivable.

Further, the operation mode extraction unit 14 sets the operation mode by dividing the process depending on which of the plurality of motors 211, 212, 213, 214 and the actuator 215 mainly operates. Specifically, the operation mode extraction unit 14 determines which motor 211, 212, 213, 214 or, based on the operation data, from the speed command of the motors 211, 212, 213, 214 and the data of the crimping state of the actuator 215. The operation mode is determined by determining whether the actuator 215 is operating. In one example, the motor 213 mainly operates during work loading, the motors 211 and 212 mainly operate during work lifting, the motor 214 mainly operates during work unloading, and the actuator 215 mainly operates during pump operation. To work. Therefore, in one example, the operation mode extraction unit 14 divides the operation mode into the loading of the workpiece, the lifting of the workpiece, the unloading of the workpiece, and the pump operation.

The factor determination unit 18 of the user terminal 260 compares the feature point data with the numerical range generated by the server device 250, which is the factor determination condition, and determines the factor of the driving sound. As a method of generating the numerical range in the server device 250, the numerical range may be generated based on the parameter estimated to be a factor based on the knowledge, or the numerical range may be calculated by machine learning based on the operation data and the sound vibration data. It may be generated. The server device 250 may dynamically generate the factor determination condition immediately before the factor determination unit 18 determines the factor determination condition. In this case, since the factor diagnosis can be performed based on the more urgent case, the diagnosis can be performed with higher accuracy.

In addition, in the second embodiment, as shown in FIG. 1, the driving vibration extracting unit 17 is not provided. Therefore, the factor determination unit 18 determines the factor using the feature point data instead of using the vibration data.

The drive sound diagnostic system 10B according to the second embodiment compares the characteristic point data obtained by time-frequency analysis of the sound vibration data and the operation data with the numerical range generated by the server device 250 for each operation mode, thereby driving Diagnose the cause of sound. For this reason, it is not necessary to prepare in advance operation data for normal or abnormal conditions, and general-purpose and immediate diagnosis of drive sound can be performed even when the configuration of the drive device or machine is changed.

Further, according to the drive sound diagnosis system 10B of the second embodiment, it is possible to immediately determine the cause of the drive sound generated by the driven machine 220 driven by the plurality of motors 211, 212, 213, 214 and the actuator 215. it can. In particular, it becomes easy to determine which motor is driven by which motor. Accordingly, when there is a problem with the driving sound of the driven machine 220, the user can take an appropriate measure from that factor, and can shorten the time required for the measure.

Embodiment 3.
FIG. 18 is a block diagram showing an example of the functional configuration of the factor determination unit in the drive sound diagnostic system according to the third embodiment. The drive sound diagnostic system according to the third embodiment uses the factor determination unit 18 of the arithmetic processing unit 140 according to the first embodiment to determine the cause of the drive sound by using the learning device that has already learned about the drive sound factor determination. It is replaced with the section 18A. In the following, the same components as those in the first embodiment will be designated by the same reference numerals and the description thereof will be omitted, and only the parts different from the first embodiment will be described.

The factor determination unit 18A includes a learning result storage unit 31 and a factor inference unit 32. The learning result storage unit 31 stores a learning result obtained by performing machine learning in advance for estimating a factor of driving sound with respect to the feature point data extracted by the feature point extraction unit 16. The factor inference unit 32 executes arithmetic processing based on the learning result of the learning result storage unit 31.

The factor determination unit 18A receives the feature point data extracted by the feature point extraction unit 16 as an input, and causes the factor inference unit 32 to perform an arithmetic process based on the learning result of the learning result storage unit 31, thereby causing the cause of the driving sound. Make a distinction.

At this time, the learning result stored in the learning result storage unit 31 may be the result of machine learning using all the feature point data, or the result of machine learning using a part of the feature point data. May be. Further, the factor inference unit 32 extracts input data according to the feature point data used by the learning result storage unit 31 at the time of learning and performs arithmetic processing.

Further, as the learning model of machine learning for guiding the learning result stored in the learning result storage unit 31, there are a K-nearest neighbor method, a decision tree, a support vector machine, and a kernel approximation. Further, deep learning may be used as the learning model.

The factor determination unit 18A in the third embodiment determines the factor determination of the driving sound by using the learned learning device. With this, it is possible to provide more accurate determination of the driving sound factor. Further, since the factor determining unit 18A uses a learning device that performs machine learning using the same data as the factor determining unit 18, it is possible to perform determination that does not depend on the drive pattern. Therefore, the learning result stored in the learning result storage unit 31 can be applied to various driving devices.

Fourth Embodiment
FIG. 19 is a block diagram showing an example of the functional configuration of the machine learning device of the drive sound diagnostic system according to the fourth embodiment. In the machine learning device 50, the server device 250 and the user terminal 260, which have the function processing unit for performing the factor determination using the sound vibration data and the operation data in the second embodiment, are provided with the machine learning function. In addition, below, the same components as those of the first and second embodiments will be denoted by the same reference numerals, and the description thereof will be omitted.

The machine learning device 50 includes a driving sound detection unit 11, a driving state detection unit 12, a sound vibration time series spectrum acquisition unit 15, a feature point extraction unit 16, a factor acquisition unit 51, a factor learning unit 52, and learning. And a result storage unit 53.

The factor acquisition unit 51 acquires data relating to the driving sound generation factor. The factor acquisition unit 51 may be, for example, a unit that acquires data regarding the generation factor of the measured driving sound input by the operation of the designer or the user. Alternatively, the factor acquisition unit 51 may acquire the diagnosis result of the drive sound generation factor according to the first embodiment or the second embodiment, or may be the diagnosis result of the drive sound generation factor in another drive sound diagnosis system. May be obtained.

The factor learning unit 52, according to the training data set created based on the combination of the feature point data extracted by the feature point extraction unit 16 and the data regarding the driving sound generation factor acquired by the factor acquisition unit 51, Learn the driving sound generation factors. The learning model used in the factor learning unit 52 may be the learning model described in the third embodiment. The diagnostic data used for the training data set may be from a plurality of driven machines 220. In one example, a more accurate diagnosis can be made by connecting to a plurality of driven machines 220 via a communication line 280 or the like and collecting diagnostic data. The learning result storage unit 53 stores the learning result by the factor learning unit 52.

FIG. 20 is a block diagram schematically showing an example of the functional configuration of the server device according to the fourth embodiment. The server device 250A is an information processing device installed on the network through the communication line 280. The server device 250A includes a time synchronization unit 13, a driving mode extraction unit 14, a sound vibration time series spectrum acquisition unit 15, a feature point extraction unit 16, a factor learning unit 52, a learning result storage unit 53, and a communication unit. 251 is provided.

The server device 250A processes the device data including the driving sound and the driving state sent from the driving sound detecting unit 11 and the driving state detecting unit 12 to the communication line 280, if necessary, and thereafter learns and stores the device data. As an example, first, as in the second embodiment, all or part of feature point data that is a set of frequency, time, power, waveform of a feature point and operation data at the time of a feature point is input to the factor learning unit 52. To be done. Next, the driving sound generation factors are acquired from the user terminal 260 via the communication line 280 and the communication unit 251, and combined to form a training data set. Finally, the factor learning unit 52 learns the driving sound generation factor using the training data set, and stores the result in the learning result storage unit 53.

FIG. 21 is a block diagram schematically showing an example of the functional configuration of the user terminal according to the fourth embodiment. The user terminal 260A includes a communication unit 261, an input unit 262A, a display unit 263, a factor determination unit 18, and a factor acquisition unit 51.

The factor acquisition unit 51 acquires, for example, the user regarding the data regarding the driving sound generation factor. The acquired data regarding the cause of the driving sound is transmitted to the server device 250A via the communication unit 261.

The input unit 262A is an input interface with the user. The input unit 262A is an interface when the user inputs an instruction to execute the process of determining the factor of the driven machine 220, and when the user inputs the data regarding the drive sound generation factor acquired by the factor acquisition unit 51. Becomes

The drive sound diagnosis system according to the fourth embodiment has both a machine learning function of a drive sound factor and a factor determination function using the result of the machine learning function. As a result, the accuracy of the factor diagnosis can be increased by proceeding with the learning while utilizing the factor diagnosis of the driving sound.

Further, by connecting to the plurality of driven machines 220 or the user terminal 260A via the communication line 280, more accurate factor diagnosis can be used at a plurality of places regardless of the installation location of the driven machines 220. .. As a result, it becomes possible to learn a highly versatile diagnosis.

The drive sound diagnosis system according to the fourth embodiment has both a machine learning function of a drive sound factor and a factor determination function using the result of the machine learning function, but the machine learning device 50 of the drive sound diagnosis system is configured independently. The factor determination using the learning result may be a function of another device. An example of the factor discriminating apparatus using the learning result has the configuration shown in FIG. 18 of the third embodiment.

The configurations described in the above embodiments are examples of the content of the present invention, and can be combined with another known technique, and the configurations of the configurations are not deviated from the scope not departing from the gist of the present invention. It is also possible to omit or change parts.

10, 10A, 10B driving sound diagnostic system, 11 driving sound detection unit, 12 driving state detection unit, 13 time synchronization unit, 14 driving mode extraction unit, 15 sound vibration time series spectrum acquisition unit, 16 feature point extraction unit, 17 driving Vibration extraction unit, 18, 18A factor determination unit, 31, 53 learning result storage unit, 32 factor reasoning unit, 50 machine learning device, 51 factor acquisition unit, 52 factor learning unit, 100,200 diagnosis target, 110, 211, 212 , 213, 214 motor, 120, 220 driven machine, 130, 230 drive device, 131, 231, 232, 233 motor drive, 132, 234 motor control device, 133 display unit, 140 arithmetic processing unit, 215 actuator, 250, 250A server device, 251,261 communication unit, 252 device data storage unit, 260,260A user terminal, 270 network device, 280 communication line.

Claims (7)

A drive sound detection unit that detects a drive sound that is a sound or mechanical vibration generated in an actuator or a driven machine driven by the actuator,
A driving position of the actuator, a driving speed or a driving state detection unit for acquiring a force generated by driving in time series,
The frequency spectrum corresponding to each time of the sound vibration data, which is the time series data of the detected driving sound, is calculated, and the power of the calculated frequency spectrum is associated with the frequency and the time to form a time series spectrum. Sound vibration time series spectrum acquisition unit to output,
The characteristic point is that the waveform of the power of the time-series spectrum with respect to the frequency and the time is at least one of a vertex, a peak, a ridgeline, and a saddle point of the waveform of the power of the time-series spectrum with respect to the frequency and the time. And the driving frequency of the characteristic point, the time, the waveform of the characteristic point, the driving position of the actuator at the time of the characteristic point, the driving speed, or the operation data that is the force generated by the driving is set as a set. A feature point extraction unit that outputs feature point data,
For each phenomenon that occurs in the actuator or the driven machine that is a factor of the driving sound, at least one of the frequency and the time that include the characteristic point that accompanies the phenomenon, and the actuator at the time. A factor determination condition that defines a first numerical range when the combination of the driving position, the driving speed, or the driving data that is the force generated by the driving is set as multidimensional data, and the numerical values of the characteristic point data are compared. A factor determining unit that determines a factor that causes the driving sound detected by
A drive sound diagnostic system comprising: Further comprising an operation mode extraction unit that divides the operating state of the driven machine into two or more sections divided by time based on the operation data,
2. The sound vibration time series spectrum acquisition unit calculates the frequency spectrum using at least one point of the sound vibration data detected between the start time and the end time of the section. Drive sound diagnostic system. The driving sound diagnostic system according to claim 2, wherein the operation mode extraction unit extracts a section in which the speed of the actuator is within a certain width for a time longer than a predetermined time. Further comprising a driving vibration extraction unit for extracting a vibration component from the driving data,
In addition to comparing the numerical value of the characteristic point data with the first numerical value range, the factor determination unit includes a second numerical value that includes the vibration component and the vibration component generated for each phenomenon for each phenomenon. The drive sound diagnostic system according to any one of claims 1 to 3, wherein a cause of the detected drive sound is determined by comparing a range with the drive sound. The factor determination unit,
A learning result storage unit that stores a learning result of machine learning for estimating the feature point data and a sound factor for the driving data,
A factor inference unit that receives the multidimensional data, executes a calculation process based on the learning result stored in the learning result storage unit, and determines a factor that causes the driving sound,
The drive sound diagnostic system according to any one of claims 1 to 4 , further comprising: Detecting a drive sound that is a sound or a mechanical vibration generated in an actuator or a driven machine driven by the actuator;
A step of acquiring the drive position of the actuator, the drive speed or the force generated by the drive in time series,
The frequency spectrum corresponding to each time of the sound vibration data, which is the time series data of the detected driving sound, is calculated, and the power of the calculated frequency spectrum is associated with the frequency and the time to form a time series spectrum. Output process,
The characteristic point is that the waveform of the power of the time-series spectrum with respect to the frequency and the time is at least one of a vertex, a peak, a ridgeline, and a saddle point of the waveform of the power of the time-series spectrum with respect to the frequency and the time. And the driving frequency of the characteristic point, the time, the waveform of the characteristic point, the driving position of the actuator at the time of the characteristic point, the driving speed, or the operation data that is the force generated by the driving is set as a set. A step of outputting feature point data,
For each phenomenon that occurs in the actuator or the driven machine that is a factor of the driving sound, at least one of the frequency and the time that include the characteristic point that accompanies the phenomenon, and the actuator at the time. Comparing the numerical value of the characteristic point data with a factor determination condition that defines a numerical range when a combination of the driving position, the driving speed, or the driving data that is a force generated by driving is set as multidimensional data. And a step of determining a cause of the driving sound detected in
A driving sound diagnosis method comprising: A drive sound detection unit that detects a drive sound that is a sound or mechanical vibration generated in an actuator or a driven machine driven by the actuator,
A driving position of the actuator, a driving speed, or a driving state detection unit that acquires a force generated by driving in time series,
The frequency spectrum corresponding to each time of the sound vibration data, which is the time series data of the detected driving sound, is calculated, and the power of the calculated frequency spectrum is associated with the frequency and the time to form a time series spectrum. Sound vibration time series spectrum acquisition unit to output,
The characteristic point is that the waveform of the power of the time-series spectrum with respect to the frequency and the time is at least one of a vertex, a peak, a ridgeline, and a saddle point of the waveform of the power of the time-series spectrum with respect to the frequency and the time. And the driving frequency of the characteristic point, the time, the waveform of the characteristic point, and the driving position of the actuator at the time of the characteristic point, the driving speed, or the operation data that is a force generated by driving as a set. A feature point extraction unit that outputs the feature point data,
For each phenomenon that occurs in the actuator or the driven machine that is a factor of the driving sound, at least one of the frequency and the time that include the characteristic point that accompanies the phenomenon, and the actuator at the time. A driving position, a driving speed, or a combination of the driving data, which is a force generated by driving, as multidimensional data, and a factor learning unit that learns a generation factor of the driving sound based on the multidimensional data,
A learning result storage unit for storing the learning result learned by the factor learning unit;
A machine learning device for a drive sound diagnostic system, comprising: a factor acquisition unit that acquires a drive sound generation factor given to the factor learning unit.